rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2025-12-27 20:42:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: rust:issue/681
Branches Tags
rust:main rust:stuhood.upstream-erased-sort-computer rust:trinity.pointard/ff-query rust:bucket_id_agg rust:paradedb/fix-agg-validation rust:flatheadmill-geo rust:paradedb-paradedb/fix-overflow-issue rust:low_card_optimization rust:paul.masurel/clippy rust:fix_size_hint rust:qw-airmail-20250916 rust:unit-test-aggregation-sum-other rust:clippy-and-cleanups rust:trinity.pointard/opti-sstable-sorted-ords-to-term rust:release_0.24 rust:dependabot/cargo/rand-0.9.1 rust:dependabot/cargo/lru-0.14.0 rust:dependabot/cargo/fs4-0.13.1 rust:tagged-user-input-ast rust:1686a/parse-agg-res rust:dependabot/cargo/rand_distr-0.5.1 rust:issue/2411-adding-panic-handler-to-rayon-merge-thread-pool rust:dependabot/cargo/nom-8 rust:upgrade_deps rust:test_parser rust:dependabot/github_actions/codecov/codecov-action-5 rust:binggan-0.12.0 rust:agg_format rust:path_collector rust:test_order_bug rust:test_columnar_multi rust:columnar_optionalmask_in_multivalues rust:prefix-phrase-query-optim rust:tantivy-with-oneshot rust:update_example rust:store-reader-enumerate rust:document-deserialize-seed rust:check_doc_mem rust:experimental-do-not-merge rust:expdonotmerge rust:cherry-pick-vec-instead-of-btreemap rust:validate_length rust:raphael_bench_avx_filter rust:raphael_optim_memset2 rust:query-field-name-avoid-alloc rust:check_bug rust:missing_test rust:list_fields rust:block-cache-control rust:trinity--multilayer-sstable rust:tracing-tantivy2 rust:tracing-tantivy rust:index_writer_err rust:default_fast_field_tokenizer rust:fmassot/add-preserve-original-ascii-folding rust:numeric_with_str_col rust:straightforward-simplify rust:fmassot/fake-test-branch rust:fmassot/dynamic-tokenizer-poc-follow-up rust:fmassot/add-box-token-filter-and-refactor rust:dynamic-tokenizer-proof-of-concept rust:fmassot/add-box-tokenizer-and-token-filter rust:tokenizer-api-0.1.1 rust:addconversion rust:removed-extra-enum-alternative-for-datetime-precision rust:issue/1981-reproduce-bm25-bug rust:tokenizer_docs rust:merge-proptests rust:columnar-todo rust:quickwit-0.5 rust:remove-byteorder rust:remove_dyn rust:pr/alexcole/1855-inject-bm25-statistics rust:evance-expose-build-query-from-user-input-ast rust:missing-specialized-method-arcdyncolumn rust:fast-u64-range-query rust:0.19.2 rust:columnar-cli2 rust:trinity--pub-term-as-slice rust:typed-column3 rust:columnar-merge3 rust:columnar-merge-exploring-fn rust:use_columnar rust:typed-column2 rust:term_agg_bucket_limit rust:range rust:typed-column rust:columnar-main rust:forced-types rust:u128-columnar rust:use_stats rust:truncation_comment rust:0.19.1 rust:trinity/yoke-documents rust:column-handle rust:columnar-cli rust:columnar rust:revert-1711-sparse_dense_index rust:commit-changes rust:sparse_dense_index_headroom rust:optional_column rust:no-column-for-multivalued rust:fmassot--bench-hdfs-with-array rust:bugfix-position-broken rust:float rust:simplify rust:debug_time rust:sparse_codecs rust:fix_estimate rust:column-reader rust:column-reader-b rust:columnreader-simple rust:col-trait-refact rust:ip_fastfield rust:column-trait-2 rust:refact-dyn-column rust:column-trait rust:refact-codec-trait rust:pr/PSeitz/1485-1 rust:fastfieldcodec rust:termmap_per_field rust:fastfield-codecs-tests rust:rayon-indexing-writers rust:issue/1251 rust:index-bench rust:fix_open_bytes_index rust:warming rust:revert-1222-issue/1195 rust:add-random-bench-for-fast-field rust:wasm-friendly-exploratory rust:revert-1159-patch-1 rust:debug-position-panic-0.15.3 rust:fix-issue-1111 rust:remove_rand rust:unused-deps rust:hfb/phrase_match_slop rust:0.15.3 rust:expose-min-max-on-multi-fast-field-reader rust:revert-1094-expose-min-max-on-multi-fast-field-reader rust:hotfix-1088 rust:owned-bytes-instead-of-rawdoc rust:rihardsk-date-ranges rust:issue/997 rust:0.13.3 rust:fail-fast-store-checkpoint rust:debugging-store rust:issue/reproduce-897 rust:issue/969-reproduce rust:troublescooter-static rust:intermediate-mergeable-troublescooter rust:barrotsteindev-filter-collector-tpredicatevalue rust:issue/938b rust:issue/938 rust:barrotsteindev-filter-collector rust:issue/922 rust:issue/896 rust:quickfix-explain rust:slog rust:limit-random-seeks rust:0.13.1 rust:issue/866b rust:bugfix-unittest-macos rust:githubactions rust:fieldnorm_readers rust:blockwand rust:nodeffeatfails rust:removedaliveiterator rust:robyoung-introduce-offset-to-top-docs rust:specialization-of-foreach-for-union-scorer rust:elshize-bmw rust:cutt rust:nrt rust:storewriter-out rust:segment_writer_in_ram2 rust:polling rust:audunhalland-query-boost rust:poll-meta rust:segment_writer_in_ram rust:bundle rust:petr-tik-n662_footer_is_incompatible_impl rust:race-condition-in-tests rust:hotfix-0.10.3-issue681 rust:remove-tru rust:kkoziara-pre-tokenized-text rust:issue/681 rust:issue/680 rust:refactoring/field rust:updating/uuid rust:fix-bench rust:hotfix-656 rust:readd-macos-ci rust:incremental-search rust:crate-division rust:streamer-with-state rust:criterion rust:python-binding-changes rust:bump-version rust:gh-pages rust:issue/554 rust:perf/experimental-union-for_each rust:issue/526b rust:softcommits rust:0.9.1-hotfix rust:revert-521-fix-non-english-stemmers rust:issue/500-hotfix rust:hotfix/0.8.2 rust:issue/483 rust:bug/merge-deted rust:issue/407 rust:issue/457 rust:segment_fruits rust:doc rust:dds/lenient rust:issue/webasm rust:issue/396 rust:broken_collector_with_result rust:dss/automaton-weight-suggestion rust:wasm rust:common-crawl rust:tantivy-imhotep
rust:0.25.0 rust:0.22.1 rust:0.24.2 rust:0.24.1 rust:tantivy-query-grammar-v0.24.0 rust:tantivy-columnar-v0.5.0 rust:tantivy-bitpacker-v0.8.0 rust:ownedbytes-v0.9.0 rust:tantivy-stacker-v0.5.0 rust:tantivy-sstable-v0.5.0 rust:tantivy-common-v0.9.0 rust:tantivy-tokenizer-api-v0.5.0 rust:0.24 rust:qw-airmail-20250224-hotfix-merge-panic rust:qw-airmail-20250219-hotfix-merge-panic rust:qw-airmail-202406 rust:qw-airmail-20240611 rust:qw-airmail-20240606 rust:quickwit-rev rust:0.22.0 rust:tantivy-stacker-v0.3.0 rust:ownedbytes-v0.7.0 rust:tantivy-tokenizer-api-v0.3.0 rust:tantivy-columnar-v0.3.0 rust:tantivy-common-v0.7.0 rust:tantivy-query-grammar-v0.22.0 rust:tantivy-sstable-v0.3.0 rust:tantivy-bitpacker-v0.6.0 rust:0.21.1 rust:0.21 rust:0.20.2 rust:0.20.1 rust:0.20 rust:quickwit-0.5-rev rust:0.19.2 rust:0.19.1 rust:0.19 rust:0.18.1 rust:0.18 rust:0.17 rust:0.16.1 rust:0.15.3 rust:0.15.2 rust:0.15.1 rust:0.15 rust:0.14 rust:0.13.3 rust:0.13.2 rust:0.13.1 rust:0.13 rust:0.12 rust:0.11.3 rust:0.11.1 rust:0.11 rust:0.10.3 rust:0.1 rust:0.10.2 rust:0.10.1 rust:0.10.0 rust:0.9.1 rust:0.9 rust:0.8.2 rust:0.8.2b rust:0.8.1 rust:0.8.0 rust:0.7.2 rust:0.7.1 rust:0.7.0 rust:0.6.1 rust:0.6.0 rust:0.5.2 rust:0.5.1 rust:0.5.0 rust:0.4.3 rust:0.4.2 rust:0.4.0 rust:0.3.1 rust:0.3.0 rust:0.2.0
...
compare: rust:0.14
Branches Tags
rust:stuhood.upstream-erased-sort-computer rust:main rust:trinity.pointard/ff-query rust:bucket_id_agg rust:paradedb/fix-agg-validation rust:flatheadmill-geo rust:paradedb-paradedb/fix-overflow-issue rust:low_card_optimization rust:paul.masurel/clippy rust:fix_size_hint rust:qw-airmail-20250916 rust:unit-test-aggregation-sum-other rust:clippy-and-cleanups rust:trinity.pointard/opti-sstable-sorted-ords-to-term rust:release_0.24 rust:dependabot/cargo/rand-0.9.1 rust:dependabot/cargo/lru-0.14.0 rust:dependabot/cargo/fs4-0.13.1 rust:tagged-user-input-ast rust:1686a/parse-agg-res rust:dependabot/cargo/rand_distr-0.5.1 rust:issue/2411-adding-panic-handler-to-rayon-merge-thread-pool rust:dependabot/cargo/nom-8 rust:upgrade_deps rust:test_parser rust:dependabot/github_actions/codecov/codecov-action-5 rust:binggan-0.12.0 rust:agg_format rust:path_collector rust:test_order_bug rust:test_columnar_multi rust:columnar_optionalmask_in_multivalues rust:prefix-phrase-query-optim rust:tantivy-with-oneshot rust:update_example rust:store-reader-enumerate rust:document-deserialize-seed rust:check_doc_mem rust:experimental-do-not-merge rust:expdonotmerge rust:cherry-pick-vec-instead-of-btreemap rust:validate_length rust:raphael_bench_avx_filter rust:raphael_optim_memset2 rust:query-field-name-avoid-alloc rust:check_bug rust:missing_test rust:list_fields rust:block-cache-control rust:trinity--multilayer-sstable rust:tracing-tantivy2 rust:tracing-tantivy rust:index_writer_err rust:default_fast_field_tokenizer rust:fmassot/add-preserve-original-ascii-folding rust:numeric_with_str_col rust:straightforward-simplify rust:fmassot/fake-test-branch rust:fmassot/dynamic-tokenizer-poc-follow-up rust:fmassot/add-box-token-filter-and-refactor rust:dynamic-tokenizer-proof-of-concept rust:fmassot/add-box-tokenizer-and-token-filter rust:tokenizer-api-0.1.1 rust:addconversion rust:removed-extra-enum-alternative-for-datetime-precision rust:issue/1981-reproduce-bm25-bug rust:tokenizer_docs rust:merge-proptests rust:columnar-todo rust:quickwit-0.5 rust:remove-byteorder rust:remove_dyn rust:pr/alexcole/1855-inject-bm25-statistics rust:evance-expose-build-query-from-user-input-ast rust:missing-specialized-method-arcdyncolumn rust:fast-u64-range-query rust:0.19.2 rust:columnar-cli2 rust:trinity--pub-term-as-slice rust:typed-column3 rust:columnar-merge3 rust:columnar-merge-exploring-fn rust:use_columnar rust:typed-column2 rust:term_agg_bucket_limit rust:range rust:typed-column rust:columnar-main rust:forced-types rust:u128-columnar rust:use_stats rust:truncation_comment rust:0.19.1 rust:trinity/yoke-documents rust:column-handle rust:columnar-cli rust:columnar rust:revert-1711-sparse_dense_index rust:commit-changes rust:sparse_dense_index_headroom rust:optional_column rust:no-column-for-multivalued rust:fmassot--bench-hdfs-with-array rust:bugfix-position-broken rust:float rust:simplify rust:debug_time rust:sparse_codecs rust:fix_estimate rust:column-reader rust:column-reader-b rust:columnreader-simple rust:col-trait-refact rust:ip_fastfield rust:column-trait-2 rust:refact-dyn-column rust:column-trait rust:refact-codec-trait rust:pr/PSeitz/1485-1 rust:fastfieldcodec rust:termmap_per_field rust:fastfield-codecs-tests rust:rayon-indexing-writers rust:issue/1251 rust:index-bench rust:fix_open_bytes_index rust:warming rust:revert-1222-issue/1195 rust:add-random-bench-for-fast-field rust:wasm-friendly-exploratory rust:revert-1159-patch-1 rust:debug-position-panic-0.15.3 rust:fix-issue-1111 rust:remove_rand rust:unused-deps rust:hfb/phrase_match_slop rust:0.15.3 rust:expose-min-max-on-multi-fast-field-reader rust:revert-1094-expose-min-max-on-multi-fast-field-reader rust:hotfix-1088 rust:owned-bytes-instead-of-rawdoc rust:rihardsk-date-ranges rust:issue/997 rust:0.13.3 rust:fail-fast-store-checkpoint rust:debugging-store rust:issue/reproduce-897 rust:issue/969-reproduce rust:troublescooter-static rust:intermediate-mergeable-troublescooter rust:barrotsteindev-filter-collector-tpredicatevalue rust:issue/938b rust:issue/938 rust:barrotsteindev-filter-collector rust:issue/922 rust:issue/896 rust:quickfix-explain rust:slog rust:limit-random-seeks rust:0.13.1 rust:issue/866b rust:bugfix-unittest-macos rust:githubactions rust:fieldnorm_readers rust:blockwand rust:nodeffeatfails rust:removedaliveiterator rust:robyoung-introduce-offset-to-top-docs rust:specialization-of-foreach-for-union-scorer rust:elshize-bmw rust:cutt rust:nrt rust:storewriter-out rust:segment_writer_in_ram2 rust:polling rust:audunhalland-query-boost rust:poll-meta rust:segment_writer_in_ram rust:bundle rust:petr-tik-n662_footer_is_incompatible_impl rust:race-condition-in-tests rust:hotfix-0.10.3-issue681 rust:remove-tru rust:kkoziara-pre-tokenized-text rust:issue/681 rust:issue/680 rust:refactoring/field rust:updating/uuid rust:fix-bench rust:hotfix-656 rust:readd-macos-ci rust:incremental-search rust:crate-division rust:streamer-with-state rust:criterion rust:python-binding-changes rust:bump-version rust:gh-pages rust:issue/554 rust:perf/experimental-union-for_each rust:issue/526b rust:softcommits rust:0.9.1-hotfix rust:revert-521-fix-non-english-stemmers rust:issue/500-hotfix rust:hotfix/0.8.2 rust:issue/483 rust:bug/merge-deted rust:issue/407 rust:issue/457 rust:segment_fruits rust:doc rust:dds/lenient rust:issue/webasm rust:issue/396 rust:broken_collector_with_result rust:dss/automaton-weight-suggestion rust:wasm rust:common-crawl rust:tantivy-imhotep
rust:0.25.0 rust:0.22.1 rust:0.24.2 rust:0.24.1 rust:tantivy-query-grammar-v0.24.0 rust:tantivy-columnar-v0.5.0 rust:tantivy-bitpacker-v0.8.0 rust:ownedbytes-v0.9.0 rust:tantivy-stacker-v0.5.0 rust:tantivy-sstable-v0.5.0 rust:tantivy-common-v0.9.0 rust:tantivy-tokenizer-api-v0.5.0 rust:0.24 rust:qw-airmail-20250224-hotfix-merge-panic rust:qw-airmail-20250219-hotfix-merge-panic rust:qw-airmail-202406 rust:qw-airmail-20240611 rust:qw-airmail-20240606 rust:quickwit-rev rust:0.22.0 rust:tantivy-stacker-v0.3.0 rust:ownedbytes-v0.7.0 rust:tantivy-tokenizer-api-v0.3.0 rust:tantivy-columnar-v0.3.0 rust:tantivy-common-v0.7.0 rust:tantivy-query-grammar-v0.22.0 rust:tantivy-sstable-v0.3.0 rust:tantivy-bitpacker-v0.6.0 rust:0.21.1 rust:0.21 rust:0.20.2 rust:0.20.1 rust:0.20 rust:quickwit-0.5-rev rust:0.19.2 rust:0.19.1 rust:0.19 rust:0.18.1 rust:0.18 rust:0.17 rust:0.16.1 rust:0.15.3 rust:0.15.2 rust:0.15.1 rust:0.15 rust:0.14 rust:0.13.3 rust:0.13.2 rust:0.13.1 rust:0.13 rust:0.12 rust:0.11.3 rust:0.11.1 rust:0.11 rust:0.10.3 rust:0.1 rust:0.10.2 rust:0.10.1 rust:0.10.0 rust:0.9.1 rust:0.9 rust:0.8.2 rust:0.8.2b rust:0.8.1 rust:0.8.0 rust:0.7.2 rust:0.7.1 rust:0.7.0 rust:0.6.1 rust:0.6.0 rust:0.5.2 rust:0.5.1 rust:0.5.0 rust:0.4.3 rust:0.4.2 rust:0.4.0 rust:0.3.1 rust:0.3.0 rust:0.2.0

290 Commits
issue/681 ... 0.14

Author SHA1 Message Date
Paul Masurel
784717749f Removing unused imports. 2021-02-05 23:04:17 +09:00
Paul Masurel
945bcc5bd3 Bump tantivy-grammar version 2021-02-05 22:58:21 +09:00
Paul Masurel
51aa9c319e Bumped version to 0.14 2021-02-05 22:55:26 +09:00
Paul Masurel
74d8d2946b Merge pull request #980 from lengyijun/patch-8 
Update segment_postings.rs
 2021-02-05 22:52:29 +09:00
lyj
0a160cc16e Update segment_postings.rs 2021-02-05 21:32:25 +08:00
Paul Masurel
f099f97daa Merge pull request #979 from slckl/main 
FacetCounts are now pub use in tantivy::collector (Closes #978)
 2021-02-05 17:05:20 +09:00
alif
769e9ba14d added simple docs to FacetCounts now-public API 2021-02-05 09:18:20 +02:00
alif
a482c0e966 pub use FacetCounts in tantivy::collector module 2021-02-05 09:00:48 +02:00
Paul Masurel
86d92a72e7 Renaming MultiValueIntFastField* to MultiValuedIntFastField* 2021-01-21 22:47:00 +09:00
Paul Masurel
ef618a5999 Made fast field reader clonable. 2021-01-21 22:15:24 +09:00
Paul Masurel
94d3d7a89a Rename FastFieldReaders::load_all 2021-01-21 18:38:48 +09:00
Paul Masurel
aa9e79f957 Clippy warnings. 2021-01-21 18:23:20 +09:00
Paul Masurel
84a2f534db Merge pull request #976 from tantivy-search/issue/fastfield_no_load 
Fast field are not loaded on the opening of a segment.
 2021-01-21 18:14:55 +09:00
Paul Masurel
1b4be24dca Fast field are not loaded on the opening of a segment. 
They are instead loaded lazily when they are request.
 2021-01-21 18:13:08 +09:00
Paul Masurel
824ccc37ae Merge pull request #975 from jamescorbett/patch-1 
Change from serde::export to std::marker
 2021-01-12 10:04:23 +09:00
Paul Masurel
5231651020 Closes #974 2021-01-12 10:03:37 +09:00
James Corbett
fa2c6f80c7 Change from serde::export to std::marker 
For some reason under a docker build I get a build error under docker only saying that `serde::export` is private. This fixes it for me.

```
error[E0603]: module `export` is private
   --> /usr/local/cargo/registry/src/github.com-1ecc6299db9ec823/tantivy-0.13.2/src/collector/top_collector.rs:5:12
    |
5   | use serde::export::PhantomData;
    |            ^^^^^^ private module
    |
note: the module `export` is defined here
   --> /usr/local/cargo/registry/src/github.com-1ecc6299db9ec823/serde-1.0.119/src/lib.rs:275:5
    |
275 | use self::__private as export;
    |     ^^^^^^^^^^^^^^^^^^^^^^^^^
```
 2021-01-12 00:25:54 +00:00
Paul Masurel
43c7b3bfec Bugfix in the RAMDirectory. 
There was a state where the meta.json was empty.
 2021-01-11 14:11:42 +09:00
Paul Masurel
b17a10546a Minor change in unit test. 2021-01-11 11:33:59 +09:00
Paul Masurel
bf6e6e8a7c Merge pull request #972 from tantivy-search/issue/969 
Issue/969
 2021-01-07 22:49:31 +09:00
Paul Masurel
203b0256a3 Minor renaming 2021-01-07 22:47:57 +09:00
Paul Masurel
caf2a38b7e Closes #969. 
The segment stacking optimization is not updating "first_doc_in_block".
 2021-01-07 22:43:56 +09:00
Paul Masurel
96f24b078e Added failing unit test. 2021-01-07 22:43:28 +09:00
Paul Masurel
332b50a4eb Merge pull request #970 from tantivy-search/functional-test-store 
Added a functional long running test to test store merging.
 2021-01-07 14:27:08 +09:00
Paul Masurel
8ca0954b3b Added a functional long running test to test store merging. 2021-01-07 14:07:15 +09:00
Paul Masurel
36343e2de8 Merge pull request #968 from tantivy-search/add-bench-analyzer 
added a simple bench for the default analyzer
 2021-01-06 21:33:39 +09:00
Paul Masurel
2f14a892ca added a simple bench for the default analyzer 2021-01-06 19:11:26 +09:00
Paul Masurel
9c3cabce40 Updated version of the rand crate. 2021-01-06 18:09:00 +09:00
Paul Masurel
f8d71c2b10 Merge pull request #964 from mosuka/deserializable 
Make NamedFieldDocument deserializable
 2021-01-06 17:43:53 +09:00
Paul Masurel
394dfb24f1 Merge pull request #965 from lewisdiamond/patch-1 
Fix spelling
 2021-01-06 13:38:31 +09:00
Lewis Diamond
b0549a229d Fix spelling 2021-01-05 22:34:56 -05:00
Minoru Osuka
670b6eaff6 Make NamedFieldDocument deserializable 2020-12-21 16:51:31 +09:00
Paul Masurel
a4f33d3823 Added comment to f64 conversion to u64. 
- Added proptest
- Added comment to Lemire blog post.
 2020-12-15 13:40:31 +09:00
Paul Masurel
c7841e3da5 Merge pull request #953 from barrotsteindev/filter-collector-tpredicatevalue 
Generic filter collector
 2020-12-14 10:35:46 +09:00
barrotsteindev
e7b4a12bba cargo fmt 2020-12-10 14:10:55 +02:00
barrotsteindev
0aaa929d6e Merge branch 'main' into filter-collector-tpredicatevalue 2020-12-10 11:27:19 +02:00
barrotsteindev
1112797c18 added a line to CHANGELOG.md 2020-12-10 11:25:08 +02:00
barrotsteindev
920481e1c1 change unit test 2020-12-10 11:24:53 +02:00
Paul Masurel
55f7b84966 Merge pull request #952 from tantivy-search/bm25-on-onebyte 
Encode blockwand on a single byte.
 2020-12-10 18:09:31 +09:00
Paul Masurel
09ab4df1fe Encode blockwand on a single byte. 2020-12-10 18:08:52 +09:00
barrotsteindev
0c2cf81b37 cargo fmt 2020-12-10 11:08:35 +02:00
barrotsteindev
d864430bda final edits 2020-12-10 11:08:15 +02:00
Paul Masurel
de60540e06 fixing compilation 2020-12-10 10:36:21 +02:00
Paul Masurel
c3e311e6b8 Removed 'static in compression_lz4. 2020-12-09 15:30:52 +09:00
barrotsteindev
ac704f2f22 WIP generic filter collector 2020-12-08 14:36:52 +02:00
Paul Masurel
be626083a0 Reorganized and added termdict unit tests. 2020-12-07 12:50:36 +09:00
Paul Masurel
b68fcca1e0 Minor changes 
- Open{Write,Read}Error::wrap_io_error made public
- Arc<PathBuf> -> Arc<Path> in file_watcher.
 2020-12-03 23:31:50 +09:00
Paul Masurel
af6dfa1856 Small refactoring 2020-12-03 14:27:05 +09:00
Paul Masurel
654c400a0b TermDictionary.finish does not flush 2020-12-03 13:36:25 +09:00
Paul Masurel
80a99539ce Several TermDict operation now returns an io::Result 2020-12-03 13:13:11 +09:00
Paul Masurel
4b1c770e5e Simplified counting writer and removed flush 2020-12-03 11:24:39 +09:00
Paul Masurel
3491645e69 Moved the term merger 2020-12-03 10:24:04 +09:00
Paul Masurel
e72c8287f8 Merge pull request #951 from tantivy-search/fst-isolated 
Fst isolated
 2020-12-03 10:11:39 +09:00
Paul Masurel
b4b3bc7acd Cargo fmt 2020-12-03 10:08:38 +09:00
Paul Masurel
521c7b271b Isolated fst impl of termdictionary in a specific module. 2020-12-02 21:18:33 +09:00
Paul Masurel
acd888c999 Merge pull request #950 from tantivy-search/guilload--fix-clippy-warning 
Fix clippy warning
 2020-12-02 08:09:31 +09:00
Adrien Guillo
3ab1ba0b2f Fix clippy warning 2020-12-01 12:07:53 -08:00
Paul Masurel
b344c0ac05 Merge pull request #949 from tantivy-search/docset_is_send 
DocSet is send
 2020-12-01 19:12:51 +09:00
Paul Masurel
1741619c7f DocSet is send 2020-12-01 19:11:21 +09:00
Paul Masurel
067ba3dff0 Merge pull request #946 from tantivy-search/issue/test-bugfix-atomicwrite 
Attempt to fix bug surfacing sometimes in test.
 2020-12-01 15:29:51 +09:00
Paul Masurel
f79250f665 Fix perf regression in the benchmark for the Count collector. 
In order to reduce IO, we introduced a way to instanciate a dummy
constant FieldnormReader which worked by allocating a buffer with
as many bytes as there are docs in the segments.

This allocation is not a negligible by any mean.

This PR works by offering two implementation for the
FieldnormReader.
The const field norm reader simply returns the same value all of the
time, while the array based one does the same as the current one.
 2020-12-01 08:51:32 +09:00
Paul Masurel
5a33b8d533 Merge pull request #942 from barrotsteindev/filter-collector 
added initial implementation for filter_collector
 2020-11-30 11:26:28 +09:00
Paul Masurel
d165655fb1 Added specialized implementation for count/count_including... in &mut DocSet 2020-11-30 11:24:13 +09:00
barrotsteindev
c805871b92 better test 2020-11-25 14:25:49 +02:00
barrotsteindev
f288e32634 rebaes on origin/main 2020-11-25 14:08:43 +02:00
barrotsteindev
bc44543d8f added TPredicate generic param and updated tests 2020-11-25 14:08:24 +02:00
Paul Masurel
db514208a7 Removed the SegmentCollector type from the Generics of the 
FilterCollector
 2020-11-25 14:08:24 +02:00
barrotsteindev
b6ff29e020 simplified FilterCollector#for_segment 2020-11-25 14:08:24 +02:00
barrotsteindev
7c94dfdc15 fmt 2020-11-25 14:08:24 +02:00
barrotsteindev
8782c0eada updated docs 2020-11-25 14:08:24 +02:00
barrotsteindev
fea0ba1042 removed unnecessary static liftimes 2020-11-25 14:08:24 +02:00
barrotsteindev
027555c75f added initial implementation for filter_collector 2020-11-25 14:08:24 +02:00
Paul Masurel
b478ed747a Attempt to fix bug surfacing sometimes in test. 
Recently, `test_index_manual_policy_mmap` has been failing on Windows.

The idea addressed by this patch is that we forget to sync the parent
directory with the current implementation of atomic writes.
This was done correctly when we were relying the atomicwrites crate.

*crossing fingers*
 2020-11-25 18:00:05 +09:00
Paul Masurel
e9aa27dace Avoid computing the BM25 weight if scoring is disabled 2020-11-25 14:35:49 +09:00
Paul Masurel
c079133f3a Merge pull request #945 from tantivy-search/guilload--replace-arc-box-with-arc 
Replace some `Arc<Box<dyn...` with `Arc<dyn...`
 2020-11-25 13:57:22 +09:00
Paul Masurel
30c5f7c5f0 Applied CR comments 2020-11-25 13:56:05 +09:00
Adrien Guillo
6f26871c0f Replace some Arc<Box<dyn... with Arc<dyn... 2020-11-24 19:54:53 -08:00
Paul Masurel
f93cc5b5e3 Merge pull request #944 from tantivy-search/no-file-len-problem 
No filelen problem.
 2020-11-25 11:54:44 +09:00
Paul Masurel
5a25c8dfd3 No filelen problem. 2020-11-25 11:51:58 +09:00
Paul Masurel
f5c079159d Merge pull request #943 from tantivy-search/guilload--ownedbytes-helper-methods 
Add helper methods for reading u8 and u64 to `OwnedBytes`
 2020-11-25 09:04:40 +09:00
Adrien Guillo
1cfdce3437 Add helper methods for reading u8 and u64 to OwnedBytes 2020-11-23 10:45:46 -08:00
Paul Masurel
e9e6d141e9 Merge pull request #941 from tantivy-search/revert-940-guilload--move-list-files-to-index 
Revert "Move `SegmentUpdater::list_files()` to `Index`"
 2020-11-20 13:54:05 +09:00
Paul Masurel
8d0e049261 Revert "Move SegmentUpdater::list_files() to Index" 2020-11-20 13:53:50 +09:00
Paul Masurel
0335c7353d Merge pull request #940 from tantivy-search/guilload--move-list-files-to-index 
Move `SegmentUpdater::list_files()` to `Index`
 2020-11-18 11:08:20 +09:00
Adrien Guillo
267e920a80 Move SegmentUpdater::list_files() to Index 
... and make the method public
 2020-11-17 17:54:18 -08:00
Paul Masurel
d8a3a47e3e Refactoring of the skip index. 
Merge pull request #927 from tantivy-search/compact-store-index
    
The skip index now identifies both the start and the end offset of blocks. Checkpoints are compressed in blocks, reaching better compression.
 2020-11-17 16:13:45 +09:00
Paul Masurel
7f0e61b173 Refactoring of the skip index. 
The skip index now identifies both the start and the end offset
of blocks. Checkpoints are compressed in blocks, reaching better
compression.
 2020-11-17 16:05:11 +09:00
Paul Masurel
ce4c50446b Merge pull request #937 from tantivy-search/guilload--cache-store-reader-blocks 
Cache store reader blocks in an LRU fashion
 2020-11-17 13:45:10 +09:00
Adrien Guillo
9ab25d2575 Cache store reader blocks in an LRU fashion 2020-11-16 19:09:10 -08:00
Paul Masurel
6d4b982417 Marked blockwand test as ignored. 
- Using impl trait for iterating `matching_segments` in the termdict
merger
 2020-11-16 13:44:14 +09:00
Paul Masurel
650eca271f Merge pull request #932 from tantivy-search/fix-unit-test-file-watcher 
Fixing unit test.
 2020-11-13 11:47:15 +09:00
Paul Masurel
8ee55aef6d Fixing unit test. 2020-11-13 09:01:45 +09:00
Paul Masurel
40d41c7dcb Merge pull request #929 from tantivy-search/api-public-term-merger 
Make field TermMerger API public
 2020-11-12 14:11:53 +09:00
Paul Masurel
c780a889a7 Merge pull request #931 from tantivy-search/issue/930 
Closes #930 Minor bug.
 2020-11-12 13:22:34 +09:00
Paul Masurel
eef348004e Closes #930 Minor bug. 
Watch callback could be callback if the last watch handle was dropped
shortly before meta.json is called.
 2020-11-11 15:51:23 +09:00
Paul Masurel
e784bbc40f Update src/core/searcher.rs 
Co-authored-by: Adrien Guillo <adrien.guillo@gmail.com>
 2020-11-11 12:37:52 +09:00
Paul Masurel
b8118d439f Make field TermMerger API public 2020-11-11 11:59:09 +09:00
Paul Masurel
a49e59053c Making block wand test more robusts 2020-11-10 18:01:38 +09:00
Paul Masurel
41bb2bd58b Merge pull request #926 from tantivy-search/guilload--directory-exists 
Modified `Directory::exists` API to return `Result<bool, OpenReadError>`
 2020-11-10 17:59:45 +09:00
Adrien Guillo
7fd6054145 Modified Directory::exists API to return Result<bool, OpenReadError> 2020-11-09 18:00:14 -08:00
Paul Masurel
6abf4e97b5 Merge pull request #925 from tantivy-search/postings-end-offset 
Adding post stop offset to TermInfo.
 2020-11-09 15:58:04 +09:00
Paul Masurel
d23aee76c9 Avoid loading fieldnorms when not necessary 2020-11-09 15:50:16 +09:00
Adrien Guillo
58a1595792 Updated CHANGELOG 2020-11-06 11:13:44 -08:00
Paul Masurel
726d32eac5 Merge pull request #924 from tantivy-search/guilload--implement-poll-watcher 
Implement FileWatcher
 2020-11-06 22:41:26 +09:00
Paul Masurel
b5f3dcdc8b TermInfo contain the end_offset of the postings. 
We slice the ReadOnlySource tightly.
 2020-11-06 15:18:51 +09:00
Adrien Guillo
2875deb4b1 Implement FileWatcher 2020-11-05 20:08:15 -08:00
Paul Masurel
b2dfacdc70 Fixed bench and removed unnecessary public symbols. 2020-11-05 16:12:03 +09:00
Paul Masurel
36a0520a48 Added failing proptest and fixed it. 2020-11-05 15:40:00 +09:00
Paul Masurel
6b5a5ac1d0 Merge pull request #923 from tantivy-search/refact-param-serialize 
Minor refactoring postings serializers options.
 2020-11-03 15:49:34 +09:00
Paul Masurel
581c2bb718 Minor refactoring postings serializers options. 2020-11-03 15:47:25 +09:00
Paul Masurel
3d192c0f57 Merge pull request #921 from tantivy-search/more-pub-for-hot-directory 
Exposing API for the hot directory
 2020-10-29 13:04:37 +09:00
Paul Masurel
9dc36f4431 Exposing API for the hot directory 2020-10-29 13:04:13 +09:00
Paul Masurel
730ccefffb Fixes a bug in TermQuery::explain. 
Closes #915
 2020-10-28 22:29:15 +09:00
Paul Masurel
2c56f4b583 Updated CHANGELOG 2020-10-28 17:39:01 +09:00
Paul Masurel
9e27da8b4e Added CR comments. 
Added Unit tests.
 2020-10-28 17:35:34 +09:00
Adrien Guillo
7f373f232a Add helper methods for BooleanQuery 2020-10-28 17:35:34 +09:00
Stephen Becker IV
6f0487979c Removing Inoperable 'Say Thanks' Links (#919) 
Dearest Maintainer,

The say thanks project moved to email https://github.com/BlitzKraft/saythanks.io/issues/60.  I removed the links. You might want to use your email but at that point people could just email you thanks?

Anyway, Thanks for the hard work on the project. I am enjoying it.

Dictated but not reviewed,
Becker
 2020-10-28 15:08:47 +09:00
Pasha Podolsky
71c66a5405 [tantivy] Run clippy linter (#914) 2020-10-27 14:36:02 +09:00
Paul Masurel
2eb5326aa4 Fixing compilation 2020-10-27 14:00:14 +09:00
Paul Masurel
91e92fa8a3 Made public. 2020-10-20 14:59:41 +09:00
Paul Masurel
9cc1661ce2 Updating crossbeam (#909) 2020-10-13 10:55:50 +09:00
Paul Masurel
c3f44d38f3 Moving HasLen (#910) 2020-10-13 10:19:30 +09:00
Paul Masurel
01b4aa9adc Refactoring dir (#905) 2020-10-11 22:22:56 +09:00
Paul Masurel
7a78b1cba3 Fix unit test on windows 2020-10-09 14:57:39 +09:00
Paul Masurel
4d011cc648 Updated changelog 2020-10-09 14:54:07 +09:00
Pasha Podolsky
80cbe889ba [tantivy] Add brotli codec for row storage (#885) 
* [tantivy] Add brotli codec for row storage

* [tantivy] Fix not actual comments for code

* [CR] Fixes for comment and cursor
 2020-10-09 14:51:42 +09:00
Paul Masurel
c23a03ad81 Large API Change in the Directory API. (#901) 
Tantivy used to assume that all files could be somehow memory mapped. After this change, Directory return a `FileSlice` that can be reduced and eventually read into an `OwnedBytes` object. Long and blocking io operation are still required by they do not span over the entire file.
 2020-10-08 16:36:51 +09:00
Paul Masurel
579e3d1ed8 Removed dev-deps to serde_yaml 2020-10-06 10:04:06 +09:00
Pasha Podolsky
687a36a49c [tantivy] Fix for schema deserialization error (#902) 
Co-authored-by: Pasha <pasha@izihawa.net>
 2020-10-05 11:24:48 +09:00
Paul Masurel
ad82b455a3 Minor change 2020-10-01 20:45:07 +09:00
Paul Masurel
848afa43ee Merge branch 'issue/896' into main 2020-10-01 20:43:42 +09:00
Paul Masurel
7720d21265 Closes #896 - Facet reader related 
Bugfix. Acquiring a facet reader on a segment that does not contain any
doc with this facet returns `None`.
 2020-10-01 20:25:28 +09:00
Paul Masurel
96f946d4c3 Raultang master (#879) 
* add support for indexed bytes fast field

* remove backup code file

* refine test cases

* Simplified unit test. Renamed it as it is testing the storable part. Not the indexed part.

* Small refactoring and added unit test. If multivalued we only retain the first FAST value.

Co-authored-by: Raul <raul.tang.lc@gmail.com>
 2020-10-01 18:03:18 +09:00
dependabot-preview[bot]
3432149759 Update base64 requirement from 0.12 to 0.13 (#895) 
Updates the requirements on [base64](https://github.com/marshallpierce/rust-base64) to permit the latest version.
- [Release notes](https://github.com/marshallpierce/rust-base64/releases)
- [Changelog](https://github.com/marshallpierce/rust-base64/blob/master/RELEASE-NOTES.md)
- [Commits](https://github.com/marshallpierce/rust-base64/compare/v0.12.0...v0.13.0)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>

Co-authored-by: dependabot-preview[bot] <27856297+dependabot-preview[bot]@users.noreply.github.com>
 2020-10-01 11:37:36 +09:00
Paul Masurel
392221e36a Removing dead file 2020-10-01 11:36:55 +09:00
Paul Masurel
674cae8ee2 Issue/822 TopDocs sorted by i64, and date fastfield (in addition to u64) (#890) 
* Unsatisfactory implementation.

The fastfield are hit. But for performance, we want the comparison to happen on u64,
and the conversion to the FastType to be done only on the selected TopK
elements.

For i64, the current approach might be ok.
For DateTime, it is most likely catastrophic.

Closes #822

* Decoupled SegmentCollector Fruit from Collector Fruit.

Deferred conversion from u64 to the proper FastField type to after the overall collection.
(tantivy guarantees that u64 encoding is consistent with the original
ordering of the fastfield)

Closes #882
 2020-09-30 17:51:11 +09:00
Paul Masurel
838c476733 Hirevo move to thiserror (#889) 
* Migrated from `failure` to `thiserror`

* Refactoring

Co-authored-by: Nicolas Polomack <nicolas@polomack.eu>
 2020-09-30 16:34:10 +09:00
Paul Masurel
5f574348d1 Syntactic change. 2020-09-26 21:33:00 +09:00
Paul Masurel
19a02b2c30 Merge tag '0.13.1' 
0.13.1 was published as a hotfix to accomodate tantivy-py.
 2020-09-19 21:20:27 +09:00
Paul Masurel
c339b05789 Bumped version and edited changelog 2020-09-19 21:13:19 +09:00
Paul Masurel
2d3c657f9d Added Send Sync to collectors. 2020-09-19 21:04:44 +09:00
Paul Masurel
07f9b828ae Added Send and Sync to the Query trait. 2020-09-19 21:04:29 +09:00
Paul Masurel
70bae7ce4c Removing Term Vec allocation (#881) 2020-09-08 23:11:00 +09:00
Paul Masurel
ac2a7273e6 Re-added comment to Score. 2020-09-08 21:41:34 +09:00
Paul Masurel
4ce9517a82 fix unit test for bench. remove scoref64 feature. fixed test for lz4 feature. 2020-09-08 07:35:00 +09:00
Paul Masurel
73024a8af3 Fixing compilation of bench and doctests. 2020-09-08 07:18:43 +09:00
Paul Masurel
e70e605fc3 fix unit test (at least on linux) 2020-09-07 23:35:04 +09:00
Paul Masurel
439d6956a9 Returning Result in some of the API (#880) 
* Returning Result in some of the API

* Introducing `.writer_for_test(..)`
 2020-09-07 15:52:34 +09:00
Paul Masurel
6530bf0eae Make field types less strict when populating documents. 2020-09-06 10:24:03 +09:00
Paul Masurel
151498cbe7 Creating the tempfile for atomicwrites in the same directory as the MmapDirectory. (#878) 2020-09-05 23:06:29 +09:00
Paul Masurel
3a72b1cb98 Accept dash within field names. (#874) 
Accept dash in field names and enforce field names constraint at the
creation of the schema.

Closes #796
 2020-09-01 13:38:52 +09:00
Paul Masurel
2737822620 Fixing unit tests. (#868) 
There was a unit test failing when notify was sending more
than one event on atomicwrites.

It was observed on MacOS CI.
 2020-08-27 16:43:39 +09:00
b8591340
06c12ae221 Filter meta.json from validate_checksum (#872) 2020-08-27 07:54:37 +09:00
Paul Masurel
4e4400af7f Added cargo timing report to .gitignore 2020-08-23 16:15:28 +09:00
Paul Masurel
3f1ecf53ab Merge branch 'master' of github.com:tantivy-search/tantivy 2020-08-22 21:30:47 +09:00
Paul Masurel
0b583b8130 Plastic changes 2020-08-22 21:29:12 +09:00
Paul Masurel
31d18dca1c Removing dependency to atomicwrites (#866) 2020-08-21 21:37:05 +09:00
stephenlagree
5e06e7de5a Update basic_search.rs (#865) 
Remove duplicated document entry.
 2020-08-21 11:23:09 +09:00
Paul Masurel
8af53cbd36 Merge branch 'master' of github.com:tantivy-search/tantivy 2020-08-21 08:57:42 +09:00
Paul Masurel
4914076e8f Fixing release build 2020-08-21 08:57:27 +09:00
Paul Masurel
e04f47e922 Using block wand for term queries too. 2020-08-20 15:51:21 +09:00
Paul Masurel
f355695581 Code clean up 2020-08-20 15:42:50 +09:00
Paul Masurel
cbacdf0de8 Edited README. 2020-08-20 14:28:24 +09:00
Paul Masurel
3dd0322f4c Bumped version 2020-08-19 22:41:48 +09:00
Paul Masurel
2481c87be8 Block wand (#856) 2020-08-19 22:36:36 +09:00
Paul Masurel
b6a664b5f8 cargo fmt 2020-08-16 12:40:50 +09:00
lyj
25b666a7c9 Update occur.rs (#862) 2020-08-16 10:49:55 +09:00
Paul Masurel
9b41912e66 Bugfix (#861) 2020-08-12 16:06:24 +09:00
Paul Masurel
8e74bb98b5 Added field norm readers (#854) 2020-07-20 13:05:05 +09:00
Paul Masurel
6db8bb49d6 Assert nearly equals macro (#853) 
* Assert nearly equals macro

* Renamed specialized_scorer in TermScorer
 2020-07-17 16:40:41 +09:00
lyj
410aed0176 Update segment_updater.rs (#848) 2020-07-16 12:33:11 +09:00
aptend
00a239a712 fix typo in index_meta.rs (#851) 2020-07-16 12:32:45 +09:00
Paul Masurel
68fe406924 Removed asserts (#850) 2020-07-16 12:24:55 +09:00
Paul Masurel
f71b04acb0 Bugfix. (#849) 
go_to_first_doc was typically calling seek with a target smaller than
doc.

Since SegmentPostings typically do a linear search on the full block,
regardless of the current position, it could have our segment postings
go backward.
 2020-07-16 10:57:51 +09:00
lyj
1ab7f660a4 Update index.rs (#846) 2020-07-02 15:11:38 +09:00
Sean Stangl
0ebbc4cb5a Fix incorrect SimpleTokenizer link in documentation (#844) 2020-07-01 10:26:36 +09:00
lyj
5300cb5da0 Update mod.rs (#845) 2020-07-01 10:25:26 +09:00
Ype Kingma
7d773abc92 Boolean query: do not combine excluded scores. (#840) 
* Do nothing when combining score values of excluded scores.

* Add test case for two excluded.

* Test score for two excluded terms.

* Use TopDocs in test_boolean_query_two_excluded
 2020-06-08 20:01:19 +09:00
Paul Masurel
c34541ccce Alive doc iterator. (#837) 2020-06-05 19:42:51 +09:00
Paul Masurel
1cc5bd706c Fixes build for no-default-features (#839) 2020-06-05 19:41:55 +09:00
Paul Masurel
4026d183bc Small readability change 2020-06-03 09:04:57 +09:00
Paul Masurel
c0f5645cd9 Move for_each functions from Scorer to Weight. (#836) 
* Move for_each functions from Scorer to Weight.

* Specialized foreach / foreach_pruning for union of termscorer.
 2020-06-01 11:31:18 +09:00
Paul Masurel
cbff874e43 Change the loading of blocks. 2020-05-27 16:36:50 +09:00
Paul Masurel
baf015fc57 Simplification of the segment postings seek implementation. (#834) 2020-05-27 08:49:47 +09:00
Paul Masurel
7275ebdf3c Skiprefactoring skipabsolute (#831) 
Simplification of the way we handle positions.
 2020-05-25 09:51:23 +09:00
Paul Masurel
b974e7ce34 Closes #828. (#829) 
There was a bug in the LogMergePolicy that was surfacing when there were
segments, but all of the segments were larger than the max limit.

After filtering, the list of segments candidate for merge was 0, and
the code was indexing the first element of an empty Vec.
 2020-05-22 16:24:07 +09:00
Paul Masurel
8f8f34499f Updated CHANGELOG with the TopCollector offset information and cargo fmt. 2020-05-20 22:26:54 +09:00
Rob Young
6ea6f4bfcd Add offset to TopDocsCollector (#826) 
* Add offset to TopDocsCollector

Add an offset to TopDocsCollector and TopDocs to make it clearer how to
handle pagination.

Closes #822

* Address review comments

- Make Debug formatting of TopDocs clearer.
- Add unit tests for limit and offset on TopCollector.
- Change API for using offset to a fluent interface.
- Add some context to the docstring to clarify what limit and offset are
  equivalent to in other projects.

* Changes required by rebase on e25284

- Pass Collector into TweakedScoreTopCollector and
  CustomScoreTopCollector.
- Add std:: qualifier to f32, i32 etc. Not sure why this was not failing
  already.
- Add unit tests for TopDocs with offset including for tweaked and
  custom score collectors.

In order to convert a TopCollector<Score> to a TopCollector<TScore> I
had to add a `into_tscore` method to `TopCollector`. This is a hack but
I don't know how to avoid it.
 2020-05-20 22:25:24 +09:00
Paul Masurel
e25284bafe Major change in the DocSet/Scorer API (#824) 
- Change in the DocSet and Scorer API. (@fulmicoton). 
A freshly created DocSet point directly to their first doc. A sentinel value called TERMINATED marks the end of a DocSet.
`.advance()` returns the new DocId. `Scorer::skip(target)` has been replaced by `Scorer::seek(target)` and returns the resulting DocId.
As a result, iterating through DocSet now looks as follows
```rust
let mut doc = docset.doc();
while doc != TERMINATED {
   // ...
   doc = docset.advance();
}
```
The change made it possible to greatly simplify a lot of the docset's code.
- Misc internal optimization and introduction of the `Scorer::for_each_pruning` function. (@fulmicoton)
 2020-05-16 16:33:36 +09:00
Fisher Darling
8b67877cd5 Made field methods const fns (#823) 2020-05-16 10:59:50 +09:00
Rob Young
9de1360538 Minor doc and test improvements around fuzzy querying (#825) 2020-05-16 10:59:24 +09:00
Paul Masurel
c55db83609 Closes #805 (#820) 
Added TryInto implementation for IndexReaderBuilder
 2020-04-27 12:01:17 +09:00
Paul Masurel
1e5ebdbf3c Format and remove useless import (#819) 2020-04-27 11:56:49 +09:00
Paul Masurel
9a2090ab21 Create the MMapDirectory does not return a Directory. (#818) 2020-04-27 11:42:20 +09:00
Paul Masurel
e4aaacdb86 Minor change in README.md 2020-04-21 21:30:34 +09:00
Paul Masurel
29acf1104d Update README's claim on performance. 2020-04-21 14:44:26 +09:00
Paul Masurel
3d34fa0b69 Fixed changelog 2020-04-19 15:55:54 +09:00
Rob Young
77f363987a Make TweakScore and CustomScore mutable at the segment level (#807) 
* Make TweakScore and CustomScore mutable

Make TweakScore and CustomScore mutable at the segment level.

Addresses issue #806

* Add example to show tweak_score working for facets
 2020-04-19 15:54:00 +09:00
Paul Masurel
c0be461191 Removing tantivy-fst conf and removing warning. (#813) 2020-04-18 20:19:23 +09:00
dependabot-preview[bot]
1fb562f44a Update fail requirement from 0.3 to 0.4 (#810) 
Updates the requirements on [fail](https://github.com/tikv/fail-rs) to permit the latest version.
- [Release notes](https://github.com/tikv/fail-rs/releases)
- [Changelog](https://github.com/tikv/fail-rs/blob/master/CHANGELOG.md)
- [Commits](https://github.com/tikv/fail-rs/compare/v0.3.0...v0.4.0)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>

Co-authored-by: dependabot-preview[bot] <27856297+dependabot-preview[bot]@users.noreply.github.com>
 2020-04-17 07:14:19 +09:00
Rob Young
c591d0e591 Switch fst dependency to git (#808) 
Closes #803

This allows the package to be built without first cloning the
tantivy-search/fst repo into the expected place. This should fix CI.
 2020-04-16 23:05:12 +09:00
Paul Masurel
186d7fc20e Fix build 2020-04-01 09:32:45 +09:00
Paul Masurel
cfbdef5186 Using tantivy-fst version 0.3. 2020-03-31 23:24:54 +09:00
Paul Masurel
d04368b1d4 Closes #788. OR not working when using conjunction by default. (#802) 2020-03-31 21:13:50 +09:00
Chen Xu
b167058028 Fix prefix option for FuzzyTermQuery (#797) 
* Fix prefix option for FuzzyTermQuery

* Update changelog
 2020-03-19 20:19:32 +09:00
Paul Masurel
262957717b unit test fix and use of matches 2020-03-15 00:20:17 +09:00
Paul Masurel
873a808321 Removed itertools (#792) 2020-03-11 18:41:04 +09:00
dependabot-preview[bot]
6fa8f9330e Update base64 requirement from 0.11.0 to 0.12.0 (#791) 
Updates the requirements on [base64](https://github.com/marshallpierce/rust-base64) to permit the latest version.
- [Release notes](https://github.com/marshallpierce/rust-base64/releases)
- [Changelog](https://github.com/marshallpierce/rust-base64/blob/master/RELEASE-NOTES.md)
- [Commits](https://github.com/marshallpierce/rust-base64/compare/v0.11.0...v0.12.0)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>

Co-authored-by: dependabot-preview[bot] <27856297+dependabot-preview[bot]@users.noreply.github.com>
 2020-03-11 17:51:22 +09:00
Paul Masurel
b3f0ef0878 Avoid writing a new delete file if there was no actual deletes. (#787) 
When applying the delete operations in the delete queue, it is possible
that there was no new deleted document.

In this case, avoid creating a new delete file, and updating the delete
opstamp.
 2020-03-08 13:04:21 +09:00
Paul Masurel
04304262ba cargo fmt 2020-03-08 09:58:42 +09:00
Paul Masurel
920ced364a Added a method to persist the RAMDirectory into a different directory. 2020-03-07 17:00:50 +09:00
Paul Masurel
e0499118e2 Minor refactoring 2020-03-07 15:56:03 +09:00
Paul Masurel
50b5efae46 Added derive feature to serde crate 2020-03-06 23:46:29 +09:00
Paul Masurel
486b8fa9c5 Removing serde-derive dependency (#786) 2020-03-06 23:33:58 +09:00
Minoru Osuka
b2baed9bdd Add Lindera to README.md (#785) 
* Add Lindera to README.md

* Put lindera in first place
 2020-03-03 20:23:59 +09:00
Paul Masurel
b591542c0b Removing err.description() before deprecation. 2020-03-03 09:58:49 +09:00
Paul Masurel
a83fa00ac4 Faster compilation of query-grammar. (#784) 2020-03-02 22:12:42 +09:00
Paul Masurel
7ff5c7c797 Removing the fst feature in the levenshtein_automata crate. 2020-03-02 21:47:05 +09:00
Paul Masurel
1748602691 ignore -> compile_fail 2020-03-02 09:59:48 +09:00
Paul Masurel
6542dd5337 Removing parenthesis. 2020-03-01 09:41:53 +09:00
Nicholas Connor
c64a44b9e1 Slight re-organization to increase contrast of "Getting Started" (#783) 2020-02-28 08:42:38 +09:00
Paul Masurel
fccc5b3bed Closes #758 2020-02-27 17:58:43 +09:00
Paul Masurel
98b9d5c6c4 Closes #780. Will be fixed on the next published release. 2020-02-21 09:41:52 +09:00
Paul Masurel
afd2c1a8ad Merge branch 'master' of github.com:tantivy-search/tantivy 2020-02-19 22:08:44 +09:00
Paul Masurel
81f35a3ceb Bumped tantivy-grammar version 2020-02-19 22:08:31 +09:00
Paul Masurel
7e2e765f4a Bumped tantivy-grammar version 2020-02-19 22:07:54 +09:00
Paul Masurel
7d6cfa58e1 [WIP] Alternative take on boosted queries (#772) 
* Alternative take on boosted queries

* Fixing unit test

* Added boosting to the query grammar.

* Made BoostQuery public.

* Added support for boosting field in QueryParser

Closes #547
 2020-02-19 11:04:38 +09:00
Paul Masurel
14735ce3aa Update snap version to 1. (#781) 2020-02-17 10:41:44 +09:00
Paul Masurel
72f7cc1569 Closes #777 (#779) 2020-02-17 09:53:38 +09:00
Paul Masurel
abef5c4e74 Updating combine to version 4 (#775) 2020-02-06 23:02:48 +09:00
Paul Masurel
ae14022bf0 Removed use::Result. (#771) 2020-01-31 18:47:02 +09:00
Alexander
55f5658d40 Make Executor public so Searcher::search_in_executor method now can be used (#769) 
* Make Executor public so Searcher::search_in_executor method now can be used

* Fixed cargo fmt
 2020-01-31 15:50:26 +09:00
Paul Masurel
3ae6363462 Updated CHANGELOG 2020-01-30 10:16:56 +09:00
Halvor Fladsrud Bø
9e20d7f8a5 Maximum size of segment to be considered for merge (#765) 
* Replicated changes from dead PR

* Ran formatter.
 2020-01-30 10:14:34 +09:00
Halvor Fladsrud Bø
ab13ffe377 Facet path string (#759) 
* Added to_path_string

* Fixed logic. Found strange behavior with string comparisons.

* ran formatter

* Fixed test

* Fixed format

* Fixed comment
 2020-01-30 10:11:29 +09:00
Paul Masurel
039138ed50 Added the empty dictionary item in the CHANGELOG 2020-01-30 10:10:34 +09:00
Paul Masurel
6227a0555a Added unit test for empty dictionaries. 2020-01-30 10:08:27 +09:00
Audun Halland
f85d0a522a Optimize TermDictionary::empty by precomputed data source (#767) 2020-01-30 10:04:58 +09:00
Halvor Fladsrud Bø
5795488ba7 Backward iteration for termdict range (#757) 
* Added backwards iteration to termdict

* Ran formatter

* Updated fst dependency

* Updated dependency

* Changelog and version

* Fixed version

* Made it part of 12.0
 2020-01-30 09:59:21 +09:00
Paul Masurel
c3045dfb5c Remove time dev-deps by relying on chrono::Duration reexport. 2020-01-29 23:25:03 +09:00
Paul Masurel
811fd0cb9e Dynamic analyzer (#755) 
* Removed generics in tokenizers

* lowercaser

* Added TokenizerExt

* Introducing BoxedTokenizer

* Introducing BoxXXXXX helper struct

* Closes #762.

* Introducing a TextAnalyzer
 2020-01-29 18:23:37 +09:00
dependabot-preview[bot]
f6847c46d7 Update tantivy-fst requirement from 0.1 to 0.2 (#750) 
Updates the requirements on [tantivy-fst](https://github.com/tantivy-search/fst) to permit the latest version.
- [Release notes](https://github.com/tantivy-search/fst/releases)
- [Commits](https://github.com/tantivy-search/fst/compare/0.1.1...0.2.0)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>
 2020-01-21 07:57:39 +09:00
Paul Masurel
92dac7af5c Return an error instead of panicking when sorting by a non fast field. (#748) 
Closes #747
 2020-01-08 13:41:02 +09:00
Paul Masurel
801905d77f Davide romanini arm atomic mutex (#746) 
* Add atomic mutex implementation for ARM.

* Applied rustfmt.

* rustfmt

Co-authored-by: davide-romanini <davide.romanini@gmail.com>
 2019-12-30 23:42:11 +09:00
Paul Horn
8f5ac86f30 Expose UserOperation as a public type. (#744) 
In order to make `IndexWriter::run` callable from outside of the create,
the `UserOperation` type needs to be publicly available.
Since the `indexer` module is private, we just export the `UserOperation`
type directly.
 2019-12-29 22:37:13 +09:00
Paul Masurel
d12a06b65b Tiny code simplification. 2019-12-26 09:33:17 +09:00
Minoru Osuka
749432f949 Make SchemaBuilder::add_field() public (#742) 
* Make add_field() to public

* cargo format
 2019-12-25 20:37:34 +09:00
Paul Masurel
c1400f25a7 Handle facet search in the QueryParser. (#741) 
Closes #738
 2019-12-25 17:43:33 +09:00
Paul Masurel
87120acf7c Bump version 2019-12-20 21:22:43 +09:00
Paul Masurel
401f74f7ae Implement fast field for DateTime. (#736) 2019-12-20 21:20:15 +09:00
Paul Masurel
03d31f6713 Update CHANGELOG 2019-12-19 10:07:43 +09:00
Paul Masurel
a57faf07f6 Added a constructor for WatchHandle (#734) 
Closes #731
 2019-12-19 10:06:02 +09:00
Paul Masurel
562ea9a839 Merge branch 'master' of github.com:tantivy-search/tantivy 2019-12-19 09:32:50 +09:00
Paul Masurel
cf92cc1ada Closes #732 (#733) 
The future returned by `IndexWriter::merge` does not borrow `&mut self`
 2019-12-18 23:25:22 +09:00
Paul Masurel
f6000aece7 Closes #732 
The future returned by `IndexWriter::merge` does not borrow `&mut self`
 2019-12-18 21:48:51 +09:00
Paul Masurel
2b3fe3a2b5 Bumped version for hotfix 2019-12-17 21:10:50 +09:00
Paul Masurel
0fde90faac Closes #729 (#730) 
Bug related with merge and deletes...
 2019-12-17 21:09:08 +09:00
Paul Masurel
5838644b03 Added README in tantivy-query-grammar 2019-12-16 08:41:21 +09:00
Paul Masurel
c0011edd05 Added version for tantivy-grammar before publish 2019-12-16 08:35:17 +09:00
petr-tik
431c187a60 Make error handling richer in Footer::is_compatible (#724) 
* WIP implemented is_compatible

hide Footer::from_bytes from public consumption - only found Footer::extract
used outside the module

Add a new error type for IncompatibleIndex
add a prototypical call to footer.is_compatible() in ManagedDirectory::open_read
to make sure we error before reading it further

* Make error handling more ergonomic

Add an error subtype for OpenReadError and converters to TantivyError

* Remove an unnecessary assert

it's follower by the same check that Errors instead of panicking

* Correct the compatibility check logic

Leave a defensive versioned footer check to make sure we add new logic handling
when we add possible footer versions

Restricted VersionedFooter::from_bytes to be used inside the crate only

remove a half-baked test

* WIP.

* Return an error if index incompatible - closes #662

Enrich the error type with incompatibility

Change return type to Result<bool, TantivyError>, instead of bool

Add an Incompatibility enum that enriches the IncompatibleIndex error variant
with information, which then allows us to generate a developer-friendly hint how
to upgrade library version or switch feature flags for a different compression
algorithm

Updated changelog

Change the signature of is_compatible

Added documentation to the Incompatibility
Added a conditional test on a Footer with lz4 erroring
 2019-12-14 09:14:33 +09:00
Caio Romão
392abec420 Make u64_lenient() handle f64 fast fields too (#726) 
* Make u64_lenient() handle f64 fast fields too

Without this, we get a panic during merge since the merger will
get a `None` where it expects something.

Prior to this patch, you can reproduce the panic with:

    use tantivy::{
        self,
        schema::{SchemaBuilder, FAST},
        Document, Index, Result,
    };

    #[test]
    fn pass() -> Result<()> {
        let mut builder = SchemaBuilder::new();
        let field = builder.add_f64_field("f64", FAST);
        let index = Index::create_in_ram(builder.build());

        let mut writer = index.writer_with_num_threads(1, 50_000_000)?;

        for i in 0..1000 {
            let mut doc = Document::new();
            doc.add_f64(field, 0.42);
            writer.add_document(doc);

            if i % 5 == 0 {
                writer.commit()?;
            }
        }

        writer.commit()?;

        Ok(())
    }

* Add test to verify that f64 fields are merged

* Ensure multi-valued fast fields can be merged too
 2019-12-13 23:41:22 +09:00
Paul Masurel
dfbe337fe2 Optimize deletes (#723) 
Closes #710
 2019-12-13 09:50:00 +09:00
Paul Masurel
b9896c4962 Cleanup 2019-12-10 23:01:07 +09:00
Paul Masurel
afa5715e56 Added unit test. 2019-12-10 22:49:32 +09:00
Paul Masurel
79474288d0 Some clippy minor fixes (#722) 2019-12-09 13:40:04 +09:00
Paul Masurel
daf64487b4 Fixing JSON se/deserialization of dates. (#721) 
Closes #719
 2019-12-09 13:31:35 +09:00
Ximo Guanter
00816f5529 Fix outdated reference in documentation (#720) 2019-12-08 18:10:50 +09:00
Paul Masurel
f73787e6e5 Merge branch 'master' of github.com:tantivy-search/tantivy 2019-12-06 10:06:09 +09:00
Paul Masurel
5cffa71467 Using census 0.4 2019-12-06 10:04:01 +09:00
Christian Hunstad
02af28b3b7 add norwegian stemmer (#717) 2019-11-27 21:08:59 +09:00
Paul Masurel
afe0134d0f Kkoziara remove tokens from doc store (#715) 
* Prevent tokens from being stored in the document store.

Commit adds prepare_for_store method to Document, which changes all
PreTokenizedString values into String values. The method is called
before adding document to the document store to prevent tokens from
being saved there. Commit also adds small changes to comments in
pre_tokenized_text example.

* Avoid storing the pretokenized text.
 2019-11-25 22:39:12 +09:00
Christian Hunstad
db9e81d0f9 Updated rust-stemmers version to 1.2 (#716) 
* Updated rust-stemmers version to 1.2

* 1.2.0 -> 1.2
 2019-11-25 22:38:48 +09:00
Paul Masurel
3821f57ecc Closes #712 (#714) 
Fixing the memory leak in the DeleteQueue.
 2019-11-25 15:57:29 +09:00
Paul Masurel
d379f98b22 Waiting for indexing threads when dropping IndexWriter 2019-11-23 15:00:27 +09:00
Paul Masurel
ef3eddf3da clippy first stab (#711) 2019-11-22 13:09:35 +09:00
Paul Masurel
08a2368845 Closes #708 (#709) 
Fixes a race condition in the test.
 2019-11-21 11:41:59 +09:00
Paul Masurel
1868fc1e2c Text fix 2019-11-20 23:00:39 +09:00
Paul Masurel
451a0252ab thread pool merge (#704) 2019-11-20 21:18:05 +09:00
Paul Masurel
42756c7474 Removing futures-cpupool and upgrading to futures-0.3 2019-11-15 18:35:31 +09:00
Paul Masurel
598b076240 Making some of the IndexWriter's method public. 2019-11-11 12:41:45 +09:00
Paul Masurel
f1f96fc417 Updating some doc. 2019-11-11 10:04:12 +09:00
Paul Masurel
9c941603f5 Petr tik n662 errror incompatible footer version (#696) 
* code tidy-up

Replace `20` magic constant with COMMON_FOOTER_SIZE

Add a docstring showing how footer is serialised
Add a test for footer length checking

* Add more tests for VersionedFooter

successful and panicking .to_bytes() calls

* Minor changes in footer.rs
 2019-11-10 14:40:06 +09:00
Paul Masurel
fb3d6fa332 Adding Value::From<PretokenizedText> (#697) 2019-11-10 14:39:44 +09:00
Paul Masurel
88fd7f091a SegmentUpdater.add_segment does not need to return true (#693) 2019-11-09 21:18:51 +09:00
Jacob Brown
6e4fdfd4bf replace scoped_pool (#685) 2019-11-07 10:26:08 +09:00
kkoziara
0519056bd8 Added handling of pre-tokenized text fields (#642). (#669) 
* Added handling of pre-tokenized text fields (#642).

* * Updated changelog and examples concerning #642.
* Added tokenized_text method to Value implementation.
* Implemented From<TokenizedString> for TokenizedStream.

* * Removed tokenized flag from TextOptions and code reliance on the flag.
* Changed naming to use word "pre-tokenized" instead of "tokenized".
* Updated example code.
* Fixed comments.

* Minor code refactoring. Test improvements.
 2019-11-07 10:10:56 +09:00
dependabot-preview[bot]
7305ad575e Update smallvec requirement from 0.6 to 1.0 (#686) 
Updates the requirements on [smallvec](https://github.com/servo/rust-smallvec) to permit the latest version.
- [Release notes](https://github.com/servo/rust-smallvec/releases)
- [Commits](https://github.com/servo/rust-smallvec/compare/v0.6.0...v1.0.0)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>
 2019-11-07 09:55:33 +09:00
Paul Masurel
79f64ac2f4 Create FUNDING.yml 2019-11-05 16:26:12 +09:00
Paul Masurel
67bce6cbf2 Fixing the construction of the DeleteBitset. (#683) 
Closes #681
 2019-11-04 15:39:11 +09:00
xiaoniu-578fa6bff964d005
e5316a4388 Reduce unnecessary clone. (#684) 2019-11-04 13:57:59 +09:00
203 changed files with 18526 additions and 8268 deletions
Expand all files Collapse all files

12
.github/FUNDING.yml vendored Normal file
View File

@@ -0,0 +1,12 @@
# These are supported funding model platforms
github: fulmicoton
patreon: # Replace with a single Patreon username
open_collective: # Replace with a single Open Collective username
ko_fi: # Replace with a single Ko-fi username
tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
liberapay: # Replace with a single Liberapay username
issuehunt: # Replace with a single IssueHunt username
otechie: # Replace with a single Otechie username
custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

2
.gitignore vendored
View File

@@ -1,4 +1,5 @@
tantivy.iml
proptest-regressions
*.swp
target
target/debug
@@ -11,3 +12,4 @@ cpp/simdcomp/bitpackingbenchmark
*.bk
.idea
trace.dat
cargo-timing*

152
CHANGELOG.md
View File

@@ -1,3 +1,88 @@
Tantivy 0.14.0
=========================
- Remove dependency to atomicwrites #833 .Implemented by @fulmicoton upon suggestion and research from @asafigan).
- Migrated tantivy error from the now deprecated `failure` crate to `thiserror` #760. (@hirevo)
- API Change. Accessing the typed value off a `Schema::Value` now returns an Option instead of panicking if the type does not match.
- Large API Change in the Directory API. Tantivy used to assume that all files could be somehow memory mapped. After this change, Directory return a `FileSlice` that can be reduced and eventually read into an `OwnedBytes` object. Long and blocking io operation are still required by they do not span over the entire file.
- Added support for Brotli compression in the DocStore. (@ppodolsky)
- Added helper for building intersections and unions in BooleanQuery (@guilload)
- Bugfix in `Query::explain`
- Removed dependency on `notify` #924. Replaced with `FileWatcher` struct that polls meta file every 500ms in background thread. (@halvorboe @guilload)
- Added `FilterCollector`, which wraps another collector and filters docs using a predicate over a fast field (@barrotsteindev)
- Simplified the encoding of the skip reader struct. BlockWAND max tf is now encoded over a single byte. (@fulmicoton)
- `FilterCollector` now supports all Fast Field value types (@barrotsteindev)
- FastField are not all loaded when opening the segment reader. (@fulmicoton)
This version breaks compatibility and requires users to reindex everything.
Tantivy 0.13.2
===================
Bugfix. Acquiring a facet reader on a segment that does not contain any
doc with this facet returns `None`. (#896)
Tantivy 0.13.1
===================
Made `Query` and `Collector` `Send + Sync`.
Updated misc dependency versions.
Tantivy 0.13.0
======================
Tantivy 0.13 introduce a change in the index format that will require
you to reindex your index (BlockWAND information are added in the skiplist).
The index size increase is minor as this information is only added for
full blocks.
If you have a massive index for which reindexing is not an option, please contact me
so that we can discuss possible solutions.
- Bugfix in `FuzzyTermQuery` not matching terms by prefix when it should (@Peachball)
- Relaxed constraints on the custom/tweak score functions. At the segment level, they can be mut, and they are not required to be Sync + Send.
- `MMapDirectory::open` does not return a `Result` anymore.
- Change in the DocSet and Scorer API. (@fulmicoton).
A freshly created DocSet point directly to their first doc. A sentinel value called TERMINATED marks the end of a DocSet.
`.advance()` returns the new DocId. `Scorer::skip(target)` has been replaced by `Scorer::seek(target)` and returns the resulting DocId.
As a result, iterating through DocSet now looks as follows
```rust
let mut doc = docset.doc();
while doc != TERMINATED {
// ...
doc = docset.advance();
}
```
The change made it possible to greatly simplify a lot of the docset's code.
- Misc internal optimization and introduction of the `Scorer::for_each_pruning` function. (@fulmicoton)
- Added an offset option to the Top(.*)Collectors. (@robyoung)
- Added Block WAND. Performance on TOP-K on term-unions should be greatly increased. (@fulmicoton, and special thanks
to the PISA team for answering all my questions!)
Tantivy 0.12.0
======================
- Removing static dispatch in tokenizers for simplicity. (#762)
- Added backward iteration for `TermDictionary` stream. (@halvorboe)
- Fixed a performance issue when searching for the posting lists of a missing term (@audunhalland)
- Added a configurable maximum number of docs (10M by default) for a segment to be considered for merge (@hntd187, landed by @halvorboe #713)
- Important Bugfix #777, causing tantivy to retain memory mapping. (diagnosed by @poljar)
- Added support for field boosting. (#547, @fulmicoton)
## How to update?
Crates relying on custom tokenizer, or registering tokenizer in the manager will require some
minor changes. Check https://github.com/tantivy-search/tantivy/blob/main/examples/custom_tokenizer.rs
to check for some code sample.
Tantivy 0.11.3
=======================
- Fixed DateTime as a fast field (#735)
Tantivy 0.11.2
=======================
- The future returned by `IndexWriter::merge` does not borrow `self` mutably anymore (#732)
- Exposing a constructor for `WatchHandle` (#731)
Tantivy 0.11.1
=====================
- Bug fix #729
Tantivy 0.11.0
=====================
@@ -9,14 +94,19 @@ Tantivy 0.11.0
- API change around `Box<BoxableTokenizer>`. See detail in #629
- Avoid rebuilding Regex automaton whenever a regex query is reused. #639 (@brainlock)
- Add footer with some metadata to index files. #605 (@fdb-hiroshima)
- Add a method to check the compatibility of the footer in the index with the running version of tantivy (@petr-tik)
- TopDocs collector: ensure stable sorting on equal score. #671 (@brainlock)
- Added handling of pre-tokenized text fields (#642), which will enable users to
load tokens created outside tantivy. See usage in examples/pre_tokenized_text. (@kkoziara)
- Fix crash when committing multiple times with deleted documents. #681 (@brainlock)
## How to update?
- The index format is changed. You are required to reindex your data to use tantivy 0.11.
- `Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
- Regex are now compiled when the `RegexQuery` instance is built. As a result, it can now return
an error and handling the `Result` is required.
- `tantivy::version()` now returns a `Version` object. This object implements `ToString()`
Tantivy 0.10.2
=====================
@@ -36,26 +126,26 @@ Tantivy 0.10.0
*Tantivy 0.10.0 index format is compatible with the index format in 0.9.0.*
- Added an API to easily tweak or entirely replace the
default score. See `TopDocs::tweak_score`and `TopScore::custom_score` (@pmasurel)
- Added an API to easily tweak or entirely replace the
default score. See `TopDocs::tweak_score`and `TopScore::custom_score` (@fulmicoton)
- Added an ASCII folding filter (@drusellers)
- Bugfix in `query.count` in presence of deletes (@pmasurel)
- Added `.explain(...)` in `Query` and `Weight` to (@pmasurel)
- Added an efficient way to `delete_all_documents` in `IndexWriter` (@petr-tik).
- Bugfix in `query.count` in presence of deletes (@fulmicoton)
- Added `.explain(...)` in `Query` and `Weight` to (@fulmicoton)
- Added an efficient way to `delete_all_documents` in `IndexWriter` (@petr-tik).
All segments are simply removed.
Minor
---------
- Switched to Rust 2018 (@uvd)
- Small simplification of the code.
- Small simplification of the code.
Calling .freq() or .doc() when .advance() has never been called
on segment postings should panic from now on.
- Tokens exceeding `u16::max_value() - 4` chars are discarded silently instead of panicking.
- Fast fields are now preloaded when the `SegmentReader` is created.
- `IndexMeta` is now public. (@hntd187)
- `IndexWriter` `add_document`, `delete_term`. `IndexWriter` is `Sync`, making it possible to use it with a `
Arc<RwLock<IndexWriter>>`. `add_document` and `delete_term` can
only require a read lock. (@pmasurel)
Arc<RwLock<IndexWriter>>`. `add_document` and `delete_term` can
only require a read lock. (@fulmicoton)
- Introducing `Opstamp` as an expressive type alias for `u64`. (@petr-tik)
- Stamper now relies on `AtomicU64` on all platforms (@petr-tik)
- Bugfix - Files get deleted slightly earlier
@@ -69,7 +159,7 @@ Your program should be usable as is.
Fast fields used to be accessed directly from the `SegmentReader`.
The API changed, you are now required to acquire your fast field reader via the
`segment_reader.fast_fields()`, and use one of the typed method:
`segment_reader.fast_fields()`, and use one of the typed method:
- `.u64()`, `.i64()` if your field is single-valued ;
- `.u64s()`, `.i64s()` if your field is multi-valued ;
- `.bytes()` if your field is bytes fast field.
@@ -78,16 +168,16 @@ The API changed, you are now required to acquire your fast field reader via the
Tantivy 0.9.0
=====================
*0.9.0 index format is not compatible with the
*0.9.0 index format is not compatible with the
previous index format.*
- MAJOR BUGFIX :
- MAJOR BUGFIX :
Some `Mmap` objects were being leaked, and would never get released. (@fulmicoton)
- Removed most unsafe (@fulmicoton)
- Indexer memory footprint improved. (VInt comp, inlining the first block. (@fulmicoton)
- Stemming in other language possible (@pentlander)
- Segments with no docs are deleted earlier (@barrotsteindev)
- Added grouped add and delete operations.
They are guaranteed to happen together (i.e. they cannot be split by a commit).
- Added grouped add and delete operations.
They are guaranteed to happen together (i.e. they cannot be split by a commit).
In addition, adds are guaranteed to happen on the same segment. (@elbow-jason)
- Removed `INT_STORED` and `INT_INDEXED`. It is now possible to use `STORED` and `INDEXED`
for int fields. (@fulmicoton)
@@ -101,26 +191,26 @@ tantivy 0.9 brought some API breaking change.
To update from tantivy 0.8, you will need to go through the following steps.
- `schema::INT_INDEXED` and `schema::INT_STORED` should be replaced by `schema::INDEXED` and `schema::INT_STORED`.
- The index now does not hold the pool of searcher anymore. You are required to create an intermediary object called
`IndexReader` for this.
- The index now does not hold the pool of searcher anymore. You are required to create an intermediary object called
`IndexReader` for this.
```rust
// create the reader. You typically need to create 1 reader for the entire
// lifetime of you program.
let reader = index.reader()?;
// Acquire a searcher (previously `index.searcher()`) is now written:
let searcher = reader.searcher();
// With the default setting of the reader, you are not required to
// With the default setting of the reader, you are not required to
// call `index.load_searchers()` anymore.
//
// The IndexReader will pick up that change automatically, regardless
// of whether the update was done in a different process or not.
// If this behavior is not wanted, you can create your reader with
// If this behavior is not wanted, you can create your reader with
// the `ReloadPolicy::Manual`, and manually decide when to reload the index
// by calling `reader.reload()?`.
```
@@ -135,7 +225,7 @@ Tantivy 0.8.1
=====================
Hotfix of #476.
Merge was reflecting deletes before commit was passed.
Merge was reflecting deletes before commit was passed.
Thanks @barrotsteindev for reporting the bug.
@@ -143,7 +233,7 @@ Tantivy 0.8.0
=====================
*No change in the index format*
- API Breaking change in the collector API. (@jwolfe, @fulmicoton)
- Multithreaded search (@jwolfe, @fulmicoton)
- Multithreaded search (@jwolfe, @fulmicoton)
Tantivy 0.7.1
@@ -171,7 +261,7 @@ Tantivy 0.6.1
- Exclusive `field:{startExcl to endExcl}`
- Mixed `field:[startIncl to endExcl}` and vice versa
- Unbounded `field:[start to *]`, `field:[* to end]`
Tantivy 0.6
==========================
@@ -179,10 +269,10 @@ Tantivy 0.6
Special thanks to @drusellers and @jason-wolfe for their contributions
to this release!
- Removed C code. Tantivy is now pure Rust. (@pmasurel)
- BM25 (@pmasurel)
- Approximate field norms encoded over 1 byte. (@pmasurel)
- Compiles on stable rust (@pmasurel)
- Removed C code. Tantivy is now pure Rust. (@fulmicoton)
- BM25 (@fulmicoton)
- Approximate field norms encoded over 1 byte. (@fulmicoton)
- Compiles on stable rust (@fulmicoton)
- Add &[u8] fastfield for associating arbitrary bytes to each document (@jason-wolfe) (#270)
- Completely uncompressed
- Internally: One u64 fast field for indexes, one fast field for the bytes themselves.
@@ -190,7 +280,7 @@ to this release!
- Add Stopword Filter support (@drusellers)
- Add a FuzzyTermQuery (@drusellers)
- Add a RegexQuery (@drusellers)
- Various performance improvements (@pmasurel)_
- Various performance improvements (@fulmicoton)_
Tantivy 0.5.2

86
Cargo.toml
View File

@@ -1,11 +1,11 @@
[package]
name = "tantivy"
version = "0.11.0"
version = "0.14.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
documentation = "https://docs.rs/tantivy/"
homepage = "https://github.com/tantivy-search/tantivy"
repository = "https://github.com/tantivy-search/tantivy"
readme = "README.md"
@@ -13,56 +13,55 @@ keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
base64 = "0.11.0"
byteorder = "1.0"
crc32fast = "1.2.0"
once_cell = "1.0"
regex ={version = "1.3.0", default-features = false, features = ["std"]}
tantivy-fst = "0.1"
base64 = "0.13"
byteorder = "1"
crc32fast = "1"
once_cell = "1"
regex ={version = "1", default-features = false, features = ["std"]}
tantivy-fst = "0.3"
memmap = {version = "0.7", optional=true}
lz4 = {version="1.20", optional=true}
snap = {version="0.2"}
atomicwrites = {version="0.2.2", optional=true}
tempfile = "3.0"
lz4 = {version="1", optional=true}
brotli = {version="3.3.0", optional=true}
snap = "1"
tempfile = {version="3", optional=true}
log = "0.4"
serde = "1.0"
serde_derive = "1.0"
serde_json = "1.0"
num_cpus = "1.2"
serde = {version="1", features=["derive"]}
serde_json = "1"
num_cpus = "1"
fs2={version="0.4", optional=true}
itertools = "0.8"
levenshtein_automata = {version="0.1", features=["fst_automaton"]}
notify = {version="4", optional=true}
bit-set = "0.5"
levenshtein_automata = "0.2"
uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.7"
futures = "0.1"
futures-cpupool = "0.1"
owning_ref = "0.4"
stable_deref_trait = "1.0.0"
rust-stemmers = "1.1"
downcast-rs = { version="1.0" }
tantivy-query-grammar = { path="./query-grammar" }
crossbeam = "0.8"
futures = {version = "0.3", features=["thread-pool"] }
tantivy-query-grammar = { version="0.14.0", path="./query-grammar" }
stable_deref_trait = "1"
rust-stemmers = "1"
downcast-rs = "1"
bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
census = "0.2"
fnv = "1.0.6"
owned-read = "0.4"
failure = "0.1"
htmlescape = "0.3.1"
fail = "0.3"
scoped-pool = "1.0"
census = "0.4"
fnv = "1"
thiserror = "1.0"
htmlescape = "0.3"
fail = "0.4"
murmurhash32 = "0.2"
chrono = "0.4"
smallvec = "0.6"
smallvec = "1"
rayon = "1"
lru = "0.6"
[target.'cfg(windows)'.dependencies]
winapi = "0.3"
[dev-dependencies]
rand = "0.7"
rand = "0.8"
maplit = "1"
matches = "0.1.8"
time = "0.1.42"
proptest = "0.10"
criterion = "0.3"
[dev-dependencies.fail]
version = "0.4"
features = ["failpoints"]
[profile.release]
opt-level = 3
@@ -75,7 +74,8 @@ overflow-checks = true
[features]
default = ["mmap"]
mmap = ["atomicwrites", "fs2", "memmap", "notify"]
mmap = ["fs2", "tempfile", "memmap"]
brotli-compression = ["brotli"]
lz4-compression = ["lz4"]
failpoints = ["fail/failpoints"]
unstable = [] # useful for benches.
@@ -87,10 +87,6 @@ members = ["query-grammar"]
[badges]
travis-ci = { repository = "tantivy-search/tantivy" }
[dev-dependencies.fail]
version = "0.3"
features = ["failpoints"]
# Following the "fail" crate best practises, we isolate
# tests that define specific behavior in fail check points
# in a different binary.
@@ -102,3 +98,7 @@ features = ["failpoints"]
name = "failpoints"
path = "tests/failpoints/mod.rs"
required-features = ["fail/failpoints"]
[[bench]]
name = "analyzer"
harness = false

23
README.md
View File

@@ -1,11 +1,10 @@
[![Build Status](https://travis-ci.org/tantivy-search/tantivy.svg?branch=master)](https://travis-ci.org/tantivy-search/tantivy)
[![codecov](https://codecov.io/gh/tantivy-search/tantivy/branch/master/graph/badge.svg)](https://codecov.io/gh/tantivy-search/tantivy)
[![Build Status](https://travis-ci.org/tantivy-search/tantivy.svg?branch=main)](https://travis-ci.org/tantivy-search/tantivy)
[![codecov](https://codecov.io/gh/tantivy-search/tantivy/branch/main/graph/badge.svg)](https://codecov.io/gh/tantivy-search/tantivy)
[![Join the chat at https://gitter.im/tantivy-search/tantivy](https://badges.gitter.im/tantivy-search/tantivy.svg)](https://gitter.im/tantivy-search/tantivy?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj/branch/master?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy/branch/master)
[![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj/branch/main?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy/branch/main)
[![Crates.io](https://img.shields.io/crates/v/tantivy.svg)](https://crates.io/crates/tantivy)
[![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton)
![Tantivy](https://tantivy-search.github.io/logo/tantivy-logo.png)
@@ -31,16 +30,15 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark
Tantivy is typically faster than Lucene, but the results depend on
the nature of the queries in your workload.
The following [benchmark](https://tantivy-search.github.io/bench/) break downs
performance for different type of queries / collection.
Your mileage WILL vary depending on the nature of queries and their load.
# Features
- Full-text search
- Configurable tokenizer (stemming available for 17 Latin languages with third party support for Chinese ([tantivy-jieba](https://crates.io/crates/tantivy-jieba) and [cang-jie](https://crates.io/crates/cang-jie)) and [Japanese](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter))
- Configurable tokenizer (stemming available for 17 Latin languages with third party support for Chinese ([tantivy-jieba](https://crates.io/crates/tantivy-jieba) and [cang-jie](https://crates.io/crates/cang-jie)), Japanese ([lindera](https://github.com/lindera-morphology/lindera-tantivy) and [tantivy-tokenizer-tiny-segmente](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter)) and Korean ([lindera](https://github.com/lindera-morphology/lindera-tantivy) + [lindera-ko-dic-builder](https://github.com/lindera-morphology/lindera-ko-dic-builder))
- Fast (check out the :racehorse: :sparkles: [benchmark](https://tantivy-search.github.io/bench/) :sparkles: :racehorse:)
- Tiny startup time (<10ms), perfect for command line tools
- BM25 scoring (the same as Lucene)
@@ -59,18 +57,17 @@ performance for different type of queries / collection.
- Configurable indexing (optional term frequency and position indexing)
- Cheesy logo with a horse
# Non-features
## Non-features
- Distributed search is out of the scope of Tantivy. That being said, Tantivy is a
library upon which one could build a distributed search. Serializable/mergeable collector state for instance,
are within the scope of Tantivy.
# Supported OS and compiler
Tantivy works on stable Rust (>= 1.27) and supports Linux, MacOS, and Windows.
# Getting started
Tantivy works on stable Rust (>= 1.27) and supports Linux, MacOS, and Windows.
- [Tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html)
- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli) - `tantivy-cli` is an actual command line interface that makes it easy for you to create a search engine,
index documents, and search via the CLI or a small server with a REST API.
@@ -87,7 +84,7 @@ There are many ways to support this project.
- Help with documentation by asking questions or submitting PRs
- Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy))
- Talk about Tantivy around you
- Drop a word on on [![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton) or even [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
- [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
# Contributing code

2
appveyor.yml
View File

@@ -18,5 +18,5 @@ install:
build: false
test_script:
- REM SET RUST_LOG=tantivy,test & cargo test --verbose --no-default-features --features mmap
- REM SET RUST_LOG=tantivy,test & cargo test --all --verbose --no-default-features --features mmap
- REM SET RUST_BACKTRACE=1 & cargo build --examples

3774
benches/alice.txt Normal file
View File

File diff suppressed because it is too large Load Diff

22
benches/analyzer.rs Normal file
View File

@@ -0,0 +1,22 @@
use criterion::{criterion_group, criterion_main, Criterion};
use tantivy::tokenizer::TokenizerManager;
const ALICE_TXT: &'static str = include_str!("alice.txt");
pub fn criterion_benchmark(c: &mut Criterion) {
let tokenizer_manager = TokenizerManager::default();
let tokenizer = tokenizer_manager.get("default").unwrap();
c.bench_function("default-tokenize-alice", |b| {
b.iter(|| {
let mut word_count = 0;
let mut token_stream = tokenizer.token_stream(ALICE_TXT);
while token_stream.advance() {
word_count += 1;
}
assert_eq!(word_count, 30_731);
})
});
}
criterion_group!(benches, criterion_benchmark);
criterion_main!(benches);

12
examples/basic_search.rs
View File

@@ -112,18 +112,6 @@ fn main() -> tantivy::Result<()> {
limbs and branches that arch over the pool"
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
// Multivalued field just need to be repeated.
index_writer.add_document(doc!(
title => "Frankenstein",

15
examples/custom_collector.rs
View File

@@ -14,7 +14,7 @@ use tantivy::fastfield::FastFieldReader;
use tantivy::query::QueryParser;
use tantivy::schema::Field;
use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
use tantivy::{doc, Index, SegmentReader, TantivyError};
use tantivy::{doc, Index, Score, SegmentReader};
#[derive(Default)]
struct Stats {
@@ -72,16 +72,7 @@ impl Collector for StatsCollector {
_segment_local_id: u32,
segment_reader: &SegmentReader,
) -> tantivy::Result<StatsSegmentCollector> {
let fast_field_reader = segment_reader
.fast_fields()
.u64(self.field)
.ok_or_else(|| {
let field_name = segment_reader.schema().get_field_name(self.field);
TantivyError::SchemaError(format!(
"Field {:?} is not a u64 fast field.",
field_name
))
})?;
let fast_field_reader = segment_reader.fast_fields().u64(self.field)?;
Ok(StatsSegmentCollector {
fast_field_reader,
stats: Stats::default(),
@@ -114,7 +105,7 @@ struct StatsSegmentCollector {
impl SegmentCollector for StatsSegmentCollector {
type Fruit = Option<Stats>;
fn collect(&mut self, doc: u32, _score: f32) {
fn collect(&mut self, doc: u32, _score: Score) {
let value = self.fast_field_reader.get(doc) as f64;
self.stats.count += 1;
self.stats.sum += value;

107
examples/faceted_search.rs
View File

@@ -13,63 +13,100 @@
// ---
// Importing tantivy...
use tantivy::collector::FacetCollector;
use tantivy::query::AllQuery;
use tantivy::query::{AllQuery, TermQuery};
use tantivy::schema::*;
use tantivy::{doc, Index};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new()?;
// Let's create a temporary directory for the sake of this example
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("name", TEXT | STORED);
// this is our faceted field
schema_builder.add_facet_field("tags");
let name = schema_builder.add_text_field("felin_name", TEXT | STORED);
// this is our faceted field: its scientific classification
let classification = schema_builder.add_facet_field("classification");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let index = Index::create_in_dir(&index_path, schema.clone())?;
let mut index_writer = index.writer(50_000_000)?;
let name = schema.get_field("name").unwrap();
let tags = schema.get_field("tags").unwrap();
let mut index_writer = index.writer(30_000_000)?;
// For convenience, tantivy also comes with a macro to
// reduce the boilerplate above.
index_writer.add_document(doc!(
name => "the ditch",
tags => Facet::from("/pools/north")
name => "Cat",
classification => Facet::from("/Felidae/Felinae/Felis")
));
index_writer.add_document(doc!(
name => "little stacey",
tags => Facet::from("/pools/south")
name => "Canada lynx",
classification => Facet::from("/Felidae/Felinae/Lynx")
));
index_writer.add_document(doc!(
name => "Cheetah",
classification => Facet::from("/Felidae/Felinae/Acinonyx")
));
index_writer.add_document(doc!(
name => "Tiger",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Lion",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Jaguar",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Sunda clouded leopard",
classification => Facet::from("/Felidae/Pantherinae/Neofelis")
));
index_writer.add_document(doc!(
name => "Fossa",
classification => Facet::from("/Eupleridae/Cryptoprocta")
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
{
let mut facet_collector = FacetCollector::for_field(classification);
facet_collector.add_facet("/Felidae");
let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
// This lists all of the facet counts, right below "/Felidae".
let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/Felidae/Felinae"), 3),
(&Facet::from("/Felidae/Pantherinae"), 4),
]
);
}
let mut facet_collector = FacetCollector::for_field(tags);
facet_collector.add_facet("/pools");
// Facets are also searchable.
//
// For instance a common UI pattern is to allow the user someone to click on a facet link
// (e.g: `Pantherinae`) to drill down and filter the current result set with this subfacet.
//
// The search would then look as follows.
let facet_counts = searcher.search(&AllQuery, &facet_collector).unwrap();
// This lists all of the facet counts
let facets: Vec<(&Facet, u64)> = facet_counts.get("/pools").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/pools/north"), 1),
(&Facet::from("/pools/south"), 1),
]
);
// Check the reference doc for different ways to create a `Facet` object.
{
let facet = Facet::from_text("/Felidae/Pantherinae");
let facet_term = Term::from_facet(classification, &facet);
let facet_term_query = TermQuery::new(facet_term, IndexRecordOption::Basic);
let mut facet_collector = FacetCollector::for_field(classification);
facet_collector.add_facet("/Felidae/Pantherinae");
let facet_counts = searcher.search(&facet_term_query, &facet_collector)?;
let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae/Pantherinae").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/Felidae/Pantherinae/Neofelis"), 1),
(&Facet::from("/Felidae/Pantherinae/Panthera"), 3),
]
);
}
Ok(())
}

98
examples/faceted_search_with_tweaked_score.rs Normal file
View File

@@ -0,0 +1,98 @@
use std::collections::HashSet;
use tantivy::collector::TopDocs;
use tantivy::doc;
use tantivy::query::BooleanQuery;
use tantivy::schema::*;
use tantivy::{DocId, Index, Score, SegmentReader};
fn main() -> tantivy::Result<()> {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field("title", STORED);
let ingredient = schema_builder.add_facet_field("ingredient");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let mut index_writer = index.writer(30_000_000)?;
index_writer.add_document(doc!(
title => "Fried egg",
ingredient => Facet::from("/ingredient/egg"),
ingredient => Facet::from("/ingredient/oil"),
));
index_writer.add_document(doc!(
title => "Scrambled egg",
ingredient => Facet::from("/ingredient/egg"),
ingredient => Facet::from("/ingredient/butter"),
ingredient => Facet::from("/ingredient/milk"),
ingredient => Facet::from("/ingredient/salt"),
));
index_writer.add_document(doc!(
title => "Egg rolls",
ingredient => Facet::from("/ingredient/egg"),
ingredient => Facet::from("/ingredient/garlic"),
ingredient => Facet::from("/ingredient/salt"),
ingredient => Facet::from("/ingredient/oil"),
ingredient => Facet::from("/ingredient/tortilla-wrap"),
ingredient => Facet::from("/ingredient/mushroom"),
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
{
let facets = vec![
Facet::from("/ingredient/egg"),
Facet::from("/ingredient/oil"),
Facet::from("/ingredient/garlic"),
Facet::from("/ingredient/mushroom"),
];
let query = BooleanQuery::new_multiterms_query(
facets
.iter()
.map(|key| Term::from_facet(ingredient, &key))
.collect(),
);
let top_docs_by_custom_score =
TopDocs::with_limit(2).tweak_score(move |segment_reader: &SegmentReader| {
let ingredient_reader = segment_reader.facet_reader(ingredient).unwrap();
let facet_dict = ingredient_reader.facet_dict();
let query_ords: HashSet<u64> = facets
.iter()
.filter_map(|key| facet_dict.term_ord(key.encoded_str()).unwrap())
.collect();
let mut facet_ords_buffer: Vec<u64> = Vec::with_capacity(20);
move |doc: DocId, original_score: Score| {
ingredient_reader.facet_ords(doc, &mut facet_ords_buffer);
let missing_ingredients = facet_ords_buffer
.iter()
.filter(|ord| !query_ords.contains(ord))
.count();
let tweak = 1.0 / 4_f32.powi(missing_ingredients as i32);
original_score * tweak
}
});
let top_docs = searcher.search(&query, &top_docs_by_custom_score)?;
let titles: Vec<String> = top_docs
.iter()
.map(|(_, doc_id)| {
searcher
.doc(*doc_id)
.unwrap()
.get_first(title)
.unwrap()
.text()
.unwrap()
.to_owned()
})
.collect();
assert_eq!(titles, vec!["Fried egg", "Egg rolls"]);
}
Ok(())
}

25
examples/iterating_docs_and_positions.rs
View File

@@ -10,7 +10,7 @@
// ---
// Importing tantivy...
use tantivy::schema::*;
use tantivy::{doc, DocId, DocSet, Index, Postings};
use tantivy::{doc, DocSet, Index, Postings, TERMINATED};
fn main() -> tantivy::Result<()> {
// We first create a schema for the sake of the
@@ -45,7 +45,7 @@ fn main() -> tantivy::Result<()> {
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title);
let inverted_index = segment_reader.inverted_index(title)?;
// A `Term` is a text token associated with a field.
// Let's go through all docs containing the term `title:the` and access their position
@@ -58,16 +58,15 @@ fn main() -> tantivy::Result<()> {
// If you don't need all this information, you may get better performance by decompressing less
// information.
if let Some(mut segment_postings) =
inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)
inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)?
{
// this buffer will be used to request for positions
let mut positions: Vec<u32> = Vec::with_capacity(100);
while segment_postings.advance() {
// the number of time the term appears in the document.
let doc_id: DocId = segment_postings.doc(); //< do not try to access this before calling advance once.
let mut doc_id = segment_postings.doc();
while doc_id != TERMINATED {
// This MAY contains deleted documents as well.
if segment_reader.is_deleted(doc_id) {
doc_id = segment_postings.advance();
continue;
}
@@ -86,6 +85,7 @@ fn main() -> tantivy::Result<()> {
// Doc 2: TermFreq 1: [0]
// ```
println!("Doc {}: TermFreq {}: {:?}", doc_id, term_freq, positions);
doc_id = segment_postings.advance();
}
}
}
@@ -106,7 +106,7 @@ fn main() -> tantivy::Result<()> {
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title);
let inverted_index = segment_reader.inverted_index(title)?;
// This segment posting object is like a cursor over the documents matching the term.
// The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
@@ -115,13 +115,18 @@ fn main() -> tantivy::Result<()> {
// If you don't need all this information, you may get better performance by decompressing less
// information.
if let Some(mut block_segment_postings) =
inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)
inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)?
{
while block_segment_postings.advance() {
loop {
let docs = block_segment_postings.docs();
if docs.is_empty() {
break;
}
// Once again these docs MAY contains deleted documents as well.
let docs = block_segment_postings.docs();
// Prints `Docs [0, 2].`
println!("Docs {:?}", docs);
block_segment_postings.advance();
}
}
}

139
examples/pre_tokenized_text.rs Normal file
View File

@@ -0,0 +1,139 @@
// # Pre-tokenized text example
//
// This example shows how to use pre-tokenized text. Sometimes yout might
// want to index and search through text which is already split into
// tokens by some external tool.
//
// In this example we will:
// - use tantivy tokenizer to create tokens and load them directly into tantivy,
// - import tokenized text straight from json,
// - perform a search on documents with pre-tokenized text
use tantivy::collector::{Count, TopDocs};
use tantivy::query::TermQuery;
use tantivy::schema::*;
use tantivy::tokenizer::{PreTokenizedString, SimpleTokenizer, Token, Tokenizer};
use tantivy::{doc, Index, ReloadPolicy};
use tempfile::TempDir;
fn pre_tokenize_text(text: &str) -> Vec<Token> {
let mut token_stream = SimpleTokenizer.token_stream(text);
let mut tokens = vec![];
while token_stream.advance() {
tokens.push(token_stream.token().clone());
}
tokens
}
fn main() -> tantivy::Result<()> {
let index_path = TempDir::new()?;
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("title", TEXT | STORED);
schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_dir(&index_path, schema.clone())?;
let mut index_writer = index.writer(50_000_000)?;
// We can create a document manually, by setting the fields
// one by one in a Document object.
let title = schema.get_field("title").unwrap();
let body = schema.get_field("body").unwrap();
let title_text = "The Old Man and the Sea";
let body_text = "He was an old man who fished alone in a skiff in the Gulf Stream";
// Content of our first document
// We create `PreTokenizedString` which contains original text and vector of tokens
let title_tok = PreTokenizedString {
text: String::from(title_text),
tokens: pre_tokenize_text(title_text),
};
println!(
"Original text: \"{}\" and tokens: {:?}",
title_tok.text, title_tok.tokens
);
let body_tok = PreTokenizedString {
text: String::from(body_text),
tokens: pre_tokenize_text(body_text),
};
// Now lets create a document and add our `PreTokenizedString`
let old_man_doc = doc!(title => title_tok, body => body_tok);
// ... now let's just add it to the IndexWriter
index_writer.add_document(old_man_doc);
// Pretokenized text can also be fed as JSON
let short_man_json = r#"{
"title":[{
"text":"The Old Man",
"tokens":[
{"offset_from":0,"offset_to":3,"position":0,"text":"The","position_length":1},
{"offset_from":4,"offset_to":7,"position":1,"text":"Old","position_length":1},
{"offset_from":8,"offset_to":11,"position":2,"text":"Man","position_length":1}
]
}]
}"#;
let short_man_doc = schema.parse_document(&short_man_json)?;
index_writer.add_document(short_man_doc);
// Let's commit changes
index_writer.commit()?;
// ... and now is the time to query our index
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()?;
let searcher = reader.searcher();
// We want to get documents with token "Man", we will use TermQuery to do it
// Using PreTokenizedString means the tokens are stored as is avoiding stemming
// and lowercasing, which preserves full words in their original form
let query = TermQuery::new(
Term::from_field_text(title, "Man"),
IndexRecordOption::Basic,
);
let (top_docs, count) = searcher
.search(&query, &(TopDocs::with_limit(2), Count))
.unwrap();
assert_eq!(count, 2);
// Now let's print out the results.
// Note that the tokens are not stored along with the original text
// in the document store
for (_score, doc_address) in top_docs {
let retrieved_doc = searcher.doc(doc_address)?;
println!("Document: {}", schema.to_json(&retrieved_doc));
}
// In contrary to the previous query, when we search for the "man" term we
// should get no results, as it's not one of the indexed tokens. SimpleTokenizer
// only splits text on whitespace / punctuation.
let query = TermQuery::new(
Term::from_field_text(title, "man"),
IndexRecordOption::Basic,
);
let (_top_docs, count) = searcher
.search(&query, &(TopDocs::with_limit(2), Count))
.unwrap();
assert_eq!(count, 0);
Ok(())
}

2
examples/stop_words.rs
View File

@@ -50,7 +50,7 @@ fn main() -> tantivy::Result<()> {
// This tokenizer lowers all of the text (to help with stop word matching)
// then removes all instances of `the` and `and` from the corpus
let tokenizer = SimpleTokenizer
let tokenizer = TextAnalyzer::from(SimpleTokenizer)
.filter(LowerCaser)
.filter(StopWordFilter::remove(vec![
"the".to_string(),

4
query-grammar/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-query-grammar"
version = "0.11.0"
version = "0.14.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
@@ -13,4 +13,4 @@ keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
combine = ">=3.6.0,<4.0.0"
combine = {version="4", default-features=false, features=[] }

3
query-grammar/README.md Normal file
View File

@@ -0,0 +1,3 @@
# Tantivy Query Grammar
This crate is used by tantivy to parse queries.

2
query-grammar/src/lib.rs
View File

@@ -1,5 +1,3 @@
#![recursion_limit = "100"]
mod occur;
mod query_grammar;
mod user_input_ast;

46
query-grammar/src/occur.rs
View File

@@ -31,22 +31,12 @@ impl Occur {
/// Compose two occur values.
pub fn compose(left: Occur, right: Occur) -> Occur {
match left {
Occur::Should => right,
Occur::Must => {
if right == Occur::MustNot {
Occur::MustNot
} else {
Occur::Must
}
}
Occur::MustNot => {
if right == Occur::MustNot {
Occur::Must
} else {
Occur::MustNot
}
}
match (left, right) {
(Occur::Should, _) => right,
(Occur::Must, Occur::MustNot) => Occur::MustNot,
(Occur::Must, _) => Occur::Must,
(Occur::MustNot, Occur::MustNot) => Occur::Must,
(Occur::MustNot, _) => Occur::MustNot,
}
}
}
@@ -56,3 +46,27 @@ impl fmt::Display for Occur {
f.write_char(self.to_char())
}
}
#[cfg(test)]
mod test {
use crate::Occur;
#[test]
fn test_occur_compose() {
assert_eq!(Occur::compose(Occur::Should, Occur::Should), Occur::Should);
assert_eq!(Occur::compose(Occur::Should, Occur::Must), Occur::Must);
assert_eq!(
Occur::compose(Occur::Should, Occur::MustNot),
Occur::MustNot
);
assert_eq!(Occur::compose(Occur::Must, Occur::Should), Occur::Must);
assert_eq!(Occur::compose(Occur::Must, Occur::Must), Occur::Must);
assert_eq!(Occur::compose(Occur::Must, Occur::MustNot), Occur::MustNot);
assert_eq!(
Occur::compose(Occur::MustNot, Occur::Should),
Occur::MustNot
);
assert_eq!(Occur::compose(Occur::MustNot, Occur::Must), Occur::MustNot);
assert_eq!(Occur::compose(Occur::MustNot, Occur::MustNot), Occur::Must);
}
}

568
query-grammar/src/query_grammar.rs
View File

@@ -1,171 +1,211 @@
use super::user_input_ast::*;
use super::user_input_ast::{UserInputAST, UserInputBound, UserInputLeaf, UserInputLiteral};
use crate::Occur;
use combine::char::*;
use combine::error::StreamError;
use combine::stream::StreamErrorFor;
use combine::*;
use combine::error::StringStreamError;
use combine::parser::char::{char, digit, letter, space, spaces, string};
use combine::parser::Parser;
use combine::{
attempt, choice, eof, many, many1, one_of, optional, parser, satisfy, skip_many1, value,
};
parser! {
fn field[I]()(I) -> String
where [I: Stream<Item = char>] {
(
letter(),
many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
).skip(char(':')).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
}
parser! {
fn word[I]()(I) -> String
where [I: Stream<Item = char>] {
(
satisfy(|c: char| !c.is_whitespace() && !['-', '`', ':', '{', '}', '"', '[', ']', '(',')'].contains(&c) ),
many(satisfy(|c: char| !c.is_whitespace() && ![':', '{', '}', '"', '[', ']', '(',')'].contains(&c)))
)
fn field<'a>() -> impl Parser<&'a str, Output = String> {
(
(letter().or(char('_'))),
many(satisfy(|c: char| {
c.is_alphanumeric() || c == '_' || c == '-'
})),
)
.skip(char(':'))
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
.and_then(|s: String|
match s.as_str() {
"OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
"AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
"NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
_ => Ok(s)
})
}
}
parser! {
fn literal[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>]
{
let term_val = || {
let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
phrase.or(word())
};
let term_val_with_field = negative_number().or(term_val());
let term_query =
(field(), term_val_with_field)
.map(|(field_name, phrase)| UserInputLiteral {
field_name: Some(field_name),
phrase,
});
let term_default_field = term_val().map(|phrase| UserInputLiteral {
field_name: None,
phrase,
});
attempt(term_query)
.or(term_default_field)
.map(UserInputLeaf::from)
}
}
parser! {
fn negative_number[I]()(I) -> String
where [I: Stream<Item = char>]
{
(char('-'), many1(satisfy(char::is_numeric)),
optional((char('.'), many1(satisfy(char::is_numeric)))))
.map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
if let Some(('.', s3)) = s3 {
format!("{}{}.{}", s1, s2, s3)
} else {
format!("{}{}", s1, s2)
}
})
}
}
parser! {
fn spaces1[I]()(I) -> ()
where [I: Stream<Item = char>] {
skip_many1(space())
}
}
parser! {
/// Function that parses a range out of a Stream
/// Supports ranges like:
/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
/// [a TO *], [a TO c], [abc TO bcd}
fn range[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>] {
let range_term_val = || {
word().or(negative_number()).or(char('*').with(value("*".to_string())))
};
// check for unbounded range in the form of <5, <=10, >5, >=5
let elastic_unbounded_range = (choice([attempt(string(">=")),
attempt(string("<=")),
attempt(string("<")),
attempt(string(">"))])
.skip(spaces()),
range_term_val()).
map(|(comparison_sign, bound): (&str, String)|
match comparison_sign {
">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
"<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
"<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
// default case
_ => (UserInputBound::Unbounded, UserInputBound::Unbounded)
});
let lower_bound = (one_of("{[".chars()), range_term_val())
.map(|(boundary_char, lower_bound): (char, String)|
if lower_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '{' {
UserInputBound::Exclusive(lower_bound)
} else {
UserInputBound::Inclusive(lower_bound)
});
let upper_bound = (range_term_val(), one_of("}]".chars()))
.map(|(higher_bound, boundary_char): (String, char)|
if higher_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '}' {
UserInputBound::Exclusive(higher_bound)
} else {
UserInputBound::Inclusive(higher_bound)
});
// return only lower and upper
let lower_to_upper = (lower_bound.
skip((spaces(),
string("TO"),
spaces())),
upper_bound);
(optional(field()).skip(spaces()),
// try elastic first, if it matches, the range is unbounded
attempt(elastic_unbounded_range).or(lower_to_upper))
.map(|(field, (lower, upper))|
// Construct the leaf from extracted field (optional)
// and bounds
UserInputLeaf::Range {
field,
lower,
upper
fn word<'a>() -> impl Parser<&'a str, Output = String> {
(
satisfy(|c: char| {
!c.is_whitespace()
&& !['-', '^', '`', ':', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
}),
many(satisfy(|c: char| {
!c.is_whitespace() && ![':', '^', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
})),
)
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
.and_then(|s: String| match s.as_str() {
"OR" | "AND " | "NOT" => Err(StringStreamError::UnexpectedParse),
_ => Ok(s),
})
}
}
fn term_val<'a>() -> impl Parser<&'a str, Output = String> {
let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
phrase.or(word())
}
fn term_query<'a>() -> impl Parser<&'a str, Output = UserInputLiteral> {
let term_val_with_field = negative_number().or(term_val());
(field(), term_val_with_field).map(|(field_name, phrase)| UserInputLiteral {
field_name: Some(field_name),
phrase,
})
}
fn literal<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let term_default_field = term_val().map(|phrase| UserInputLiteral {
field_name: None,
phrase,
});
attempt(term_query())
.or(term_default_field)
.map(UserInputLeaf::from)
}
fn negative_number<'a>() -> impl Parser<&'a str, Output = String> {
(
char('-'),
many1(digit()),
optional((char('.'), many1(digit()))),
)
.map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
if let Some(('.', s3)) = s3 {
format!("{}{}.{}", s1, s2, s3)
} else {
format!("{}{}", s1, s2)
}
})
}
fn spaces1<'a>() -> impl Parser<&'a str, Output = ()> {
skip_many1(space())
}
/// Function that parses a range out of a Stream
/// Supports ranges like:
/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
/// [a TO *], [a TO c], [abc TO bcd}
fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let range_term_val = || {
word()
.or(negative_number())
.or(char('*').with(value("*".to_string())))
};
// check for unbounded range in the form of <5, <=10, >5, >=5
let elastic_unbounded_range = (
choice([
attempt(string(">=")),
attempt(string("<=")),
attempt(string("<")),
attempt(string(">")),
])
.skip(spaces()),
range_term_val(),
)
.map(
|(comparison_sign, bound): (&str, String)| match comparison_sign {
">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
"<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
"<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
// default case
_ => (UserInputBound::Unbounded, UserInputBound::Unbounded),
},
);
let lower_bound = (one_of("{[".chars()), range_term_val()).map(
|(boundary_char, lower_bound): (char, String)| {
if lower_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '{' {
UserInputBound::Exclusive(lower_bound)
} else {
UserInputBound::Inclusive(lower_bound)
}
},
);
let upper_bound = (range_term_val(), one_of("}]".chars())).map(
|(higher_bound, boundary_char): (String, char)| {
if higher_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '}' {
UserInputBound::Exclusive(higher_bound)
} else {
UserInputBound::Inclusive(higher_bound)
}
},
);
// return only lower and upper
let lower_to_upper = (
lower_bound.skip((spaces(), string("TO"), spaces())),
upper_bound,
);
(
optional(field()).skip(spaces()),
// try elastic first, if it matches, the range is unbounded
attempt(elastic_unbounded_range).or(lower_to_upper),
)
.map(|(field, (lower, upper))|
// Construct the leaf from extracted field (optional)
// and bounds
UserInputLeaf::Range {
field,
lower,
upper
})
}
fn negate(expr: UserInputAST) -> UserInputAST {
expr.unary(Occur::MustNot)
}
fn must(expr: UserInputAST) -> UserInputAST {
expr.unary(Occur::Must)
fn leaf<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
parser(|input| {
char('(')
.with(ast())
.skip(char(')'))
.or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
.or(attempt(
string("NOT").skip(spaces1()).with(leaf()).map(negate),
))
.or(attempt(range().map(UserInputAST::from)))
.or(literal().map(UserInputAST::from))
.parse_stream(input)
.into_result()
})
}
parser! {
fn leaf[I]()(I) -> UserInputAST
where [I: Stream<Item = char>] {
char('-').with(leaf()).map(negate)
.or(char('+').with(leaf()).map(must))
.or(char('(').with(ast()).skip(char(')')))
.or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
.or(attempt(string("NOT").skip(spaces1()).with(leaf()).map(negate)))
.or(attempt(range().map(UserInputAST::from)))
.or(literal().map(UserInputAST::from))
}
fn occur_symbol<'a>() -> impl Parser<&'a str, Output = Occur> {
char('-')
.map(|_| Occur::MustNot)
.or(char('+').map(|_| Occur::Must))
}
fn occur_leaf<'a>() -> impl Parser<&'a str, Output = (Option<Occur>, UserInputAST)> {
(optional(occur_symbol()), boosted_leaf())
}
fn positive_float_number<'a>() -> impl Parser<&'a str, Output = f64> {
(many1(digit()), optional((char('.'), many1(digit())))).map(
|(int_part, decimal_part_opt): (String, Option<(char, String)>)| {
let mut float_str = int_part;
if let Some((chr, decimal_str)) = decimal_part_opt {
float_str.push(chr);
float_str.push_str(&decimal_str);
}
float_str.parse::<f64>().unwrap()
},
)
}
fn boost<'a>() -> impl Parser<&'a str, Output = f64> {
(char('^'), positive_float_number()).map(|(_, boost)| boost)
}
fn boosted_leaf<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
(leaf(), optional(boost())).map(|(leaf, boost_opt)| match boost_opt {
Some(boost) if (boost - 1.0).abs() > std::f64::EPSILON => {
UserInputAST::Boost(Box::new(leaf), boost)
}
_ => leaf,
})
}
#[derive(Clone, Copy)]
@@ -174,13 +214,10 @@ enum BinaryOperand {
And,
}
parser! {
fn binary_operand[I]()(I) -> BinaryOperand
where [I: Stream<Item = char>]
{
string("AND").with(value(BinaryOperand::And))
.or(string("OR").with(value(BinaryOperand::Or)))
}
fn binary_operand<'a>() -> impl Parser<&'a str, Output = BinaryOperand> {
string("AND")
.with(value(BinaryOperand::And))
.or(string("OR").with(value(BinaryOperand::Or)))
}
fn aggregate_binary_expressions(
@@ -208,37 +245,84 @@ fn aggregate_binary_expressions(
}
}
parser! {
pub fn ast[I]()(I) -> UserInputAST
where [I: Stream<Item = char>]
{
let operand_leaf = (binary_operand().skip(spaces()), leaf().skip(spaces()));
let boolean_expr = (leaf().skip(spaces().silent()), many1(operand_leaf)).map(
|(left, right)| aggregate_binary_expressions(left,right));
let whitespace_separated_leaves = many1(leaf().skip(spaces().silent()))
.map(|subqueries: Vec<UserInputAST>|
if subqueries.len() == 1 {
subqueries.into_iter().next().unwrap()
} else {
UserInputAST::Clause(subqueries.into_iter().collect())
});
let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
spaces().with(expr).skip(spaces())
}
fn operand_leaf<'a>() -> impl Parser<&'a str, Output = (BinaryOperand, UserInputAST)> {
(
binary_operand().skip(spaces()),
boosted_leaf().skip(spaces()),
)
}
parser! {
pub fn parse_to_ast[I]()(I) -> UserInputAST
where [I: Stream<Item = char>]
{
spaces().with(optional(ast()).skip(eof())).map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
}
pub fn ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
let boolean_expr = (boosted_leaf().skip(spaces()), many1(operand_leaf()))
.map(|(left, right)| aggregate_binary_expressions(left, right));
let whitespace_separated_leaves = many1(occur_leaf().skip(spaces().silent())).map(
|subqueries: Vec<(Option<Occur>, UserInputAST)>| {
if subqueries.len() == 1 {
let (occur_opt, ast) = subqueries.into_iter().next().unwrap();
match occur_opt.unwrap_or(Occur::Should) {
Occur::Must | Occur::Should => ast,
Occur::MustNot => UserInputAST::Clause(vec![(Some(Occur::MustNot), ast)]),
}
} else {
UserInputAST::Clause(subqueries.into_iter().collect())
}
},
);
let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
spaces().with(expr).skip(spaces())
}
pub fn parse_to_ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
spaces()
.with(optional(ast()).skip(eof()))
.map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
}
#[cfg(test)]
mod test {
type TestParseResult = Result<(), StringStreamError>;
use super::*;
use combine::parser::Parser;
pub fn nearly_equals(a: f64, b: f64) -> bool {
(a - b).abs() < 0.0005 * (a + b).abs()
}
fn assert_nearly_equals(expected: f64, val: f64) {
assert!(
nearly_equals(val, expected),
"Got {}, expected {}.",
val,
expected
);
}
#[test]
fn test_occur_symbol() -> TestParseResult {
assert_eq!(super::occur_symbol().parse("-")?, (Occur::MustNot, ""));
assert_eq!(super::occur_symbol().parse("+")?, (Occur::Must, ""));
Ok(())
}
#[test]
fn test_positive_float_number() {
fn valid_parse(float_str: &str, expected_val: f64, expected_remaining: &str) {
let (val, remaining) = positive_float_number().parse(float_str).unwrap();
assert_eq!(remaining, expected_remaining);
assert_nearly_equals(val, expected_val);
}
fn error_parse(float_str: &str) {
assert!(positive_float_number().parse(float_str).is_err());
}
valid_parse("1.0", 1.0, "");
valid_parse("1", 1.0, "");
valid_parse("0.234234 aaa", 0.234234f64, " aaa");
error_parse(".3332");
error_parse("1.");
error_parse("-1.");
}
fn test_parse_query_to_ast_helper(query: &str, expected: &str) {
let query = parse_to_ast().parse(query).unwrap().0;
@@ -269,15 +353,24 @@ mod test {
"Err(UnexpectedParse)"
);
test_parse_query_to_ast_helper("NOTa", "\"NOTa\"");
test_parse_query_to_ast_helper("NOT a", "-(\"a\")");
test_parse_query_to_ast_helper("NOT a", "(-\"a\")");
}
#[test]
fn test_boosting() {
assert!(parse_to_ast().parse("a^2^3").is_err());
assert!(parse_to_ast().parse("a^2^").is_err());
test_parse_query_to_ast_helper("a^3", "(\"a\")^3");
test_parse_query_to_ast_helper("a^3 b^2", "(*(\"a\")^3 *(\"b\")^2)");
test_parse_query_to_ast_helper("a^1", "\"a\"");
}
#[test]
fn test_parse_query_to_ast_binary_op() {
test_parse_query_to_ast_helper("a AND b", "(+(\"a\") +(\"b\"))");
test_parse_query_to_ast_helper("a OR b", "(?(\"a\") ?(\"b\"))");
test_parse_query_to_ast_helper("a OR b AND c", "(?(\"a\") ?((+(\"b\") +(\"c\"))))");
test_parse_query_to_ast_helper("a AND b AND c", "(+(\"a\") +(\"b\") +(\"c\"))");
test_parse_query_to_ast_helper("a AND b", "(+\"a\" +\"b\")");
test_parse_query_to_ast_helper("a OR b", "(?\"a\" ?\"b\")");
test_parse_query_to_ast_helper("a OR b AND c", "(?\"a\" ?(+\"b\" +\"c\"))");
test_parse_query_to_ast_helper("a AND b AND c", "(+\"a\" +\"b\" +\"c\")");
assert_eq!(
format!("{:?}", parse_to_ast().parse("a OR b aaa")),
"Err(UnexpectedParse)"
@@ -315,6 +408,32 @@ mod test {
test_parse_query_to_ast_helper("weight: <= 70.5", "weight:{\"*\" TO \"70.5\"]");
}
#[test]
fn test_occur_leaf() {
let ((occur, ast), _) = super::occur_leaf().parse("+abc").unwrap();
assert_eq!(occur, Some(Occur::Must));
assert_eq!(format!("{:?}", ast), "\"abc\"");
}
#[test]
fn test_field_name() -> TestParseResult {
assert_eq!(
super::field().parse("my-field-name:a")?,
("my-field-name".to_string(), "a")
);
assert_eq!(
super::field().parse("my_field_name:a")?,
("my_field_name".to_string(), "a")
);
assert!(super::field().parse(":a").is_err());
assert!(super::field().parse("-my_field:a").is_err());
assert_eq!(
super::field().parse("_my_field:a")?,
("_my_field".to_string(), "a")
);
Ok(())
}
#[test]
fn test_range_parser() {
// testing the range() parser separately
@@ -343,32 +462,67 @@ mod test {
fn test_parse_query_to_triming_spaces() {
test_parse_query_to_ast_helper(" abc", "\"abc\"");
test_parse_query_to_ast_helper("abc ", "\"abc\"");
test_parse_query_to_ast_helper("( a OR abc)", "(?(\"a\") ?(\"abc\"))");
test_parse_query_to_ast_helper("(a OR abc)", "(?(\"a\") ?(\"abc\"))");
test_parse_query_to_ast_helper("(a OR abc)", "(?(\"a\") ?(\"abc\"))");
test_parse_query_to_ast_helper("a OR abc ", "(?(\"a\") ?(\"abc\"))");
test_parse_query_to_ast_helper("(a OR abc )", "(?(\"a\") ?(\"abc\"))");
test_parse_query_to_ast_helper("(a OR abc) ", "(?(\"a\") ?(\"abc\"))");
test_parse_query_to_ast_helper("( a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("a OR abc ", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc )", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc) ", "(?\"a\" ?\"abc\")");
}
#[test]
fn test_parse_query_to_ast() {
fn test_parse_query_single_term() {
test_parse_query_to_ast_helper("abc", "\"abc\"");
test_parse_query_to_ast_helper("a b", "(\"a\" \"b\")");
test_parse_query_to_ast_helper("+(a b)", "+((\"a\" \"b\"))");
test_parse_query_to_ast_helper("+d", "+(\"d\")");
test_parse_query_to_ast_helper("+(a b) +d", "(+((\"a\" \"b\")) +(\"d\"))");
test_parse_query_to_ast_helper("(+a +b) d", "((+(\"a\") +(\"b\")) \"d\")");
test_parse_query_to_ast_helper("(+a)", "+(\"a\")");
test_parse_query_to_ast_helper("(+a +b)", "(+(\"a\") +(\"b\"))");
}
#[test]
fn test_parse_query_default_clause() {
test_parse_query_to_ast_helper("a b", "(*\"a\" *\"b\")");
}
#[test]
fn test_parse_query_must_default_clause() {
test_parse_query_to_ast_helper("+(a b)", "(*\"a\" *\"b\")");
}
#[test]
fn test_parse_query_must_single_term() {
test_parse_query_to_ast_helper("+d", "\"d\"");
}
#[test]
fn test_single_term_with_field() {
test_parse_query_to_ast_helper("abc:toto", "abc:\"toto\"");
}
#[test]
fn test_single_term_with_float() {
test_parse_query_to_ast_helper("abc:1.1", "abc:\"1.1\"");
test_parse_query_to_ast_helper("+abc:toto", "+(abc:\"toto\")");
test_parse_query_to_ast_helper("(+abc:toto -titi)", "(+(abc:\"toto\") -(\"titi\"))");
test_parse_query_to_ast_helper("-abc:toto", "-(abc:\"toto\")");
test_parse_query_to_ast_helper("abc:a b", "(abc:\"a\" \"b\")");
}
#[test]
fn test_must_clause() {
test_parse_query_to_ast_helper("(+a +b)", "(+\"a\" +\"b\")");
}
#[test]
fn test_parse_test_query_plus_a_b_plus_d() {
test_parse_query_to_ast_helper("+(a b) +d", "(+(*\"a\" *\"b\") +\"d\")");
}
#[test]
fn test_parse_test_query_other() {
test_parse_query_to_ast_helper("(+a +b) d", "(*(+\"a\" +\"b\") *\"d\")");
test_parse_query_to_ast_helper("+abc:toto", "abc:\"toto\"");
test_parse_query_to_ast_helper("(+abc:toto -titi)", "(+abc:\"toto\" -\"titi\")");
test_parse_query_to_ast_helper("-abc:toto", "(-abc:\"toto\")");
test_parse_query_to_ast_helper("abc:a b", "(*abc:\"a\" *\"b\")");
test_parse_query_to_ast_helper("abc:\"a b\"", "abc:\"a b\"");
test_parse_query_to_ast_helper("foo:[1 TO 5]", "foo:[\"1\" TO \"5\"]");
}
#[test]
fn test_parse_query_with_range() {
test_parse_query_to_ast_helper("[1 TO 5]", "[\"1\" TO \"5\"]");
test_parse_query_to_ast_helper("foo:{a TO z}", "foo:{\"a\" TO \"z\"}");
test_parse_query_to_ast_helper("foo:[1 TO toto}", "foo:[\"1\" TO \"toto\"}");

32
query-grammar/src/user_input_ast.rs
View File

@@ -85,14 +85,14 @@ impl UserInputBound {
}
pub enum UserInputAST {
Clause(Vec<UserInputAST>),
Unary(Occur, Box<UserInputAST>),
Clause(Vec<(Option<Occur>, UserInputAST)>),
Leaf(Box<UserInputLeaf>),
Boost(Box<UserInputAST>, f64),
}
impl UserInputAST {
pub fn unary(self, occur: Occur) -> UserInputAST {
UserInputAST::Unary(occur, Box::new(self))
UserInputAST::Clause(vec![(Some(occur), self)])
}
fn compose(occur: Occur, asts: Vec<UserInputAST>) -> UserInputAST {
@@ -103,7 +103,7 @@ impl UserInputAST {
} else {
UserInputAST::Clause(
asts.into_iter()
.map(|ast: UserInputAST| ast.unary(occur))
.map(|ast: UserInputAST| (Some(occur), ast))
.collect::<Vec<_>>(),
)
}
@@ -134,26 +134,38 @@ impl From<UserInputLeaf> for UserInputAST {
}
}
fn print_occur_ast(
occur_opt: Option<Occur>,
ast: &UserInputAST,
formatter: &mut fmt::Formatter,
) -> fmt::Result {
if let Some(occur) = occur_opt {
write!(formatter, "{}{:?}", occur, ast)?;
} else {
write!(formatter, "*{:?}", ast)?;
}
Ok(())
}
impl fmt::Debug for UserInputAST {
fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
match *self {
UserInputAST::Clause(ref subqueries) => {
if subqueries.is_empty() {
write!(formatter, "<emptyclause>")?;
} else {
write!(formatter, "(")?;
write!(formatter, "{:?}", &subqueries[0])?;
print_occur_ast(subqueries[0].0, &subqueries[0].1, formatter)?;
for subquery in &subqueries[1..] {
write!(formatter, " {:?}", subquery)?;
write!(formatter, " ")?;
print_occur_ast(subquery.0, &subquery.1, formatter)?;
}
write!(formatter, ")")?;
}
Ok(())
}
UserInputAST::Unary(ref occur, ref subquery) => {
write!(formatter, "{}({:?})", occur, subquery)
}
UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
UserInputAST::Boost(ref leaf, boost) => write!(formatter, "({:?})^{}", leaf, boost),
}
}
}

68
src/collector/count_collector.rs
View File

@@ -1,7 +1,6 @@
use super::Collector;
use crate::collector::SegmentCollector;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -13,44 +12,29 @@ use crate::SegmentReader;
/// use tantivy::collector::Count;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result};
/// use tantivy::{doc, Index};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer(3_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
/// let mut index_writer = index.writer(3_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// assert!(index_writer.commit().is_ok());
///
/// {
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary")?;
/// let count = searcher.search(&query, &Count).unwrap();
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// assert_eq!(count, 2);
/// }
/// // Here comes the important part
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let count = searcher.search(&query, &Count).unwrap();
///
/// Ok(())
/// }
/// assert_eq!(count, 2);
/// ```
pub struct Count;
@@ -59,7 +43,11 @@ impl Collector for Count {
type Child = SegmentCountCollector;
fn for_segment(&self, _: SegmentLocalId, _: &SegmentReader) -> Result<SegmentCountCollector> {
fn for_segment(
&self,
_: SegmentLocalId,
_: &SegmentReader,
) -> crate::Result<SegmentCountCollector> {
Ok(SegmentCountCollector::default())
}
@@ -67,7 +55,7 @@ impl Collector for Count {
false
}
fn merge_fruits(&self, segment_counts: Vec<usize>) -> Result<usize> {
fn merge_fruits(&self, segment_counts: Vec<usize>) -> crate::Result<usize> {
Ok(segment_counts.into_iter().sum())
}
}
@@ -108,18 +96,18 @@ mod tests {
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1f32);
count_collector.collect(0u32, 1.0);
assert_eq!(count_collector.harvest(), 1);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1f32);
count_collector.collect(0u32, 1.0);
assert_eq!(count_collector.harvest(), 1);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1f32);
count_collector.collect(1u32, 1f32);
count_collector.collect(0u32, 1.0);
count_collector.collect(1u32, 1.0);
assert_eq!(count_collector.harvest(), 2);
}
}

25
src/collector/custom_score_top_collector.rs
View File

@@ -1,6 +1,5 @@
use crate::collector::top_collector::{TopCollector, TopSegmentCollector};
use crate::collector::{Collector, SegmentCollector};
use crate::Result;
use crate::{DocAddress, DocId, Score, SegmentReader};
pub(crate) struct CustomScoreTopCollector<TCustomScorer, TScore = Score> {
@@ -12,13 +11,13 @@ impl<TCustomScorer, TScore> CustomScoreTopCollector<TCustomScorer, TScore>
where
TScore: Clone + PartialOrd,
{
pub fn new(
pub(crate) fn new(
custom_scorer: TCustomScorer,
limit: usize,
collector: TopCollector<TScore>,
) -> CustomScoreTopCollector<TCustomScorer, TScore> {
CustomScoreTopCollector {
custom_scorer,
collector: TopCollector::with_limit(limit),
collector,
}
}
}
@@ -29,7 +28,7 @@ where
/// It is the segment local version of the [`CustomScorer`](./trait.CustomScorer.html).
pub trait CustomSegmentScorer<TScore>: 'static {
/// Computes the score of a specific `doc`.
fn score(&self, doc: DocId) -> TScore;
fn score(&mut self, doc: DocId) -> TScore;
}
/// `CustomScorer` makes it possible to define any kind of score.
@@ -42,12 +41,12 @@ pub trait CustomScorer<TScore>: Sync {
type Child: CustomSegmentScorer<TScore>;
/// Builds a child scorer for a specific segment. The child scorer is associated to
/// a specific segment.
fn segment_scorer(&self, segment_reader: &SegmentReader) -> Result<Self::Child>;
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child>;
}
impl<TCustomScorer, TScore> Collector for CustomScoreTopCollector<TCustomScorer, TScore>
where
TCustomScorer: CustomScorer<TScore>,
TCustomScorer: CustomScorer<TScore> + Send + Sync,
TScore: 'static + PartialOrd + Clone + Send + Sync,
{
type Fruit = Vec<(TScore, DocAddress)>;
@@ -58,11 +57,11 @@ where
&self,
segment_local_id: u32,
segment_reader: &SegmentReader,
) -> Result<Self::Child> {
let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
) -> crate::Result<Self::Child> {
let segment_collector = self
.collector
.for_segment(segment_local_id, segment_reader)?;
let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
Ok(CustomScoreTopSegmentCollector {
segment_collector,
segment_scorer,
@@ -73,7 +72,7 @@ where
false
}
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit> {
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
self.collector.merge_fruits(segment_fruits)
}
}
@@ -111,16 +110,16 @@ where
{
type Child = T;
fn segment_scorer(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
Ok((self)(segment_reader))
}
}
impl<F, TScore> CustomSegmentScorer<TScore> for F
where
F: 'static + Sync + Send + Fn(DocId) -> TScore,
F: 'static + FnMut(DocId) -> TScore,
{
fn score(&self, doc: DocId) -> TScore {
fn score(&mut self, doc: DocId) -> TScore {
(self)(doc)
}
}

61
src/collector/docset_collector.rs Normal file
View File

@@ -0,0 +1,61 @@
use std::collections::HashSet;
use crate::{DocAddress, DocId, Score};
use super::{Collector, SegmentCollector};
/// Collectors that returns the set of DocAddress that matches the query.
///
/// This collector is mostly useful for tests.
pub struct DocSetCollector;
impl Collector for DocSetCollector {
type Fruit = HashSet<DocAddress>;
type Child = DocSetChildCollector;
fn for_segment(
&self,
segment_local_id: crate::SegmentLocalId,
_segment: &crate::SegmentReader,
) -> crate::Result<Self::Child> {
Ok(DocSetChildCollector {
segment_local_id,
docs: HashSet::new(),
})
}
fn requires_scoring(&self) -> bool {
false
}
fn merge_fruits(
&self,
segment_fruits: Vec<(u32, HashSet<DocId>)>,
) -> crate::Result<Self::Fruit> {
let len: usize = segment_fruits.iter().map(|(_, docset)| docset.len()).sum();
let mut result = HashSet::with_capacity(len);
for (segment_local_id, docs) in segment_fruits {
for doc in docs {
result.insert(DocAddress(segment_local_id, doc));
}
}
Ok(result)
}
}
pub struct DocSetChildCollector {
segment_local_id: u32,
docs: HashSet<DocId>,
}
impl SegmentCollector for DocSetChildCollector {
type Fruit = (u32, HashSet<DocId>);
fn collect(&mut self, doc: crate::DocId, _score: Score) {
self.docs.insert(doc);
}
fn harvest(self) -> (u32, HashSet<DocId>) {
(self.segment_local_id, self.docs)
}
}

120
src/collector/facet_collector.rs
View File

@@ -1,15 +1,12 @@
use crate::collector::Collector;
use crate::collector::SegmentCollector;
use crate::docset::SkipResult;
use crate::fastfield::FacetReader;
use crate::schema::Facet;
use crate::schema::Field;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use crate::TantivyError;
use std::cmp::Ordering;
use std::collections::btree_map;
use std::collections::BTreeMap;
@@ -84,10 +81,9 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// use tantivy::collector::FacetCollector;
/// use tantivy::query::AllQuery;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{doc, Index, Result};
/// use tantivy::{doc, Index};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// fn example() -> tantivy::Result<()> {
/// let mut schema_builder = Schema::builder();
///
/// // Facet have their own specific type.
@@ -127,7 +123,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// let searcher = reader.searcher();
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/lang");
/// facet_collector.add_facet("/category");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
@@ -143,7 +139,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// }
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/category/fiction");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
///
@@ -158,8 +154,8 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// ]);
/// }
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/category/fiction");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
///
@@ -172,6 +168,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
/// Ok(())
/// }
/// # assert!(example().is_ok());
/// ```
pub struct FacetCollector {
field: Field,
@@ -189,6 +186,11 @@ pub struct FacetSegmentCollector {
collapse_facet_ords: Vec<u64>,
}
enum SkipResult {
Found,
NotFound,
}
fn skip<'a, I: Iterator<Item = &'a Facet>>(
target: &[u8],
collapse_it: &mut Peekable<I>,
@@ -198,14 +200,14 @@ fn skip<'a, I: Iterator<Item = &'a Facet>>(
Some(facet_bytes) => match facet_bytes.encoded_str().as_bytes().cmp(target) {
Ordering::Less => {}
Ordering::Greater => {
return SkipResult::OverStep;
return SkipResult::NotFound;
}
Ordering::Equal => {
return SkipResult::Reached;
return SkipResult::Found;
}
},
None => {
return SkipResult::End;
return SkipResult::NotFound;
}
}
collapse_it.next();
@@ -262,11 +264,8 @@ impl Collector for FacetCollector {
&self,
_: SegmentLocalId,
reader: &SegmentReader,
) -> Result<FacetSegmentCollector> {
let field_name = reader.schema().get_field_name(self.field);
let facet_reader = reader.facet_reader(self.field).ok_or_else(|| {
TantivyError::SchemaError(format!("Field {:?} is not a facet field.", field_name))
})?;
) -> crate::Result<FacetSegmentCollector> {
let facet_reader = reader.facet_reader(self.field)?;
let mut collapse_mapping = Vec::new();
let mut counts = Vec::new();
@@ -275,14 +274,14 @@ impl Collector for FacetCollector {
let mut collapse_facet_it = self.facets.iter().peekable();
collapse_facet_ords.push(0);
{
let mut facet_streamer = facet_reader.facet_dict().range().into_stream();
let mut facet_streamer = facet_reader.facet_dict().range().into_stream()?;
if facet_streamer.advance() {
'outer: loop {
// at the begining of this loop, facet_streamer
// is positionned on a term that has not been processed yet.
let skip_result = skip(facet_streamer.key(), &mut collapse_facet_it);
match skip_result {
SkipResult::Reached => {
SkipResult::Found => {
// we reach a facet we decided to collapse.
let collapse_depth = facet_depth(facet_streamer.key());
let mut collapsed_id = 0;
@@ -302,7 +301,7 @@ impl Collector for FacetCollector {
}
break;
}
SkipResult::End | SkipResult::OverStep => {
SkipResult::NotFound => {
collapse_mapping.push(0);
if !facet_streamer.advance() {
break;
@@ -328,7 +327,7 @@ impl Collector for FacetCollector {
false
}
fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> Result<FacetCounts> {
fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> crate::Result<FacetCounts> {
let mut facet_counts: BTreeMap<Facet, u64> = BTreeMap::new();
for segment_facet_counts in segments_facet_counts {
for (facet, count) in segment_facet_counts.facet_counts {
@@ -369,9 +368,12 @@ impl SegmentCollector for FacetSegmentCollector {
}
let mut facet = vec![];
let facet_ord = self.collapse_facet_ords[collapsed_facet_ord];
facet_dict.ord_to_term(facet_ord as u64, &mut facet);
// TODO
facet_counts.insert(Facet::from_encoded(facet).unwrap(), count);
// TODO handle errors.
if facet_dict.ord_to_term(facet_ord as u64, &mut facet).is_ok() {
if let Ok(facet) = Facet::from_encoded(facet) {
facet_counts.insert(facet, count);
}
}
}
FacetCounts { facet_counts }
}
@@ -396,6 +398,8 @@ impl<'a> Iterator for FacetChildIterator<'a> {
}
impl FacetCounts {
/// Returns an iterator over all of the facet count pairs inside this result.
/// See the documentation for `FacetCollector` for a usage example.
pub fn get<T>(&self, facet_from: T) -> FacetChildIterator<'_>
where
Facet: From<T>,
@@ -415,6 +419,8 @@ impl FacetCounts {
FacetChildIterator { underlying }
}
/// Returns a vector of top `k` facets with their counts, sorted highest-to-lowest by counts.
/// See the documentation for `FacetCollector` for a usage example.
pub fn top_k<T>(&self, facet: T, k: usize) -> Vec<(&Facet, u64)>
where
Facet: From<T>,
@@ -452,9 +458,11 @@ impl FacetCounts {
#[cfg(test)]
mod tests {
use super::{FacetCollector, FacetCounts};
use crate::collector::Count;
use crate::core::Index;
use crate::query::AllQuery;
use crate::schema::{Document, Facet, Field, Schema};
use crate::query::{AllQuery, QueryParser, TermQuery};
use crate::schema::{Document, Facet, Field, IndexRecordOption, Schema};
use crate::Term;
use rand::distributions::Uniform;
use rand::prelude::SliceRandom;
use rand::{thread_rng, Rng};
@@ -467,7 +475,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let num_facets: usize = 3 * 4 * 5;
let facets: Vec<Facet> = (0..num_facets)
.map(|mut n| {
@@ -526,7 +534,7 @@ mod tests {
let facet_field = schema_builder.add_facet_field("facets");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/subjects/A/a"),
facet_field => Facet::from_text(&"/subjects/B/a"),
@@ -544,6 +552,56 @@ mod tests {
assert_eq!(facets[0].1, 1);
}
#[test]
fn test_doc_search_by_facet() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/B"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/C/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/D/C/A"),
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 4);
let count_facet = |facet_str: &str| {
let term = Term::from_facet(facet_field, &Facet::from_text(facet_str));
searcher
.search(&TermQuery::new(term, IndexRecordOption::Basic), &Count)
.unwrap()
};
assert_eq!(count_facet("/"), 4);
assert_eq!(count_facet("/A"), 3);
assert_eq!(count_facet("/A/B"), 1);
assert_eq!(count_facet("/A/C"), 1);
assert_eq!(count_facet("/A/C/A"), 1);
assert_eq!(count_facet("/C/A"), 0);
let query_parser = QueryParser::for_index(&index, vec![]);
{
let query = query_parser.parse_query("facet:/A/B")?;
assert_eq!(1, searcher.search(&query, &Count).unwrap());
}
{
let query = query_parser.parse_query("facet:/A")?;
assert_eq!(3, searcher.search(&query, &Count)?);
}
Ok(())
}
#[test]
fn test_non_used_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
@@ -576,7 +634,7 @@ mod tests {
.collect();
docs[..].shuffle(&mut thread_rng());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for doc in docs {
index_writer.add_document(doc);
}
@@ -629,7 +687,7 @@ mod bench {
// 40425 docs
docs[..].shuffle(&mut thread_rng());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for doc in docs {
index_writer.add_document(doc);
}

183
src/collector/filter_collector_wrapper.rs Normal file
View File

@@ -0,0 +1,183 @@
// # Custom collector example
//
// This example shows how you can implement your own
// collector. As an example, we will compute a collector
// that computes the standard deviation of a given fast field.
//
// Of course, you can have a look at the tantivy's built-in collectors
// such as the `CountCollector` for more examples.
// ---
// Importing tantivy...
use std::marker::PhantomData;
use crate::collector::{Collector, SegmentCollector};
use crate::fastfield::{FastFieldReader, FastValue};
use crate::schema::Field;
use crate::{Score, SegmentReader, TantivyError};
/// The `FilterCollector` collector filters docs using a u64 fast field value and a predicate.
/// Only the documents for which the predicate returned "true" will be passed on to the next collector.
///
/// ```rust
/// use tantivy::collector::{TopDocs, FilterCollector};
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT, INDEXED, FAST};
/// use tantivy::{doc, DocAddress, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let price = schema_builder.add_u64_field("price", INDEXED | FAST);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind", price => 30_200u64));
/// index_writer.add_document(doc!(title => "The Diary of Muadib", price => 29_240u64));
/// index_writer.add_document(doc!(title => "A Dairy Cow", price => 21_240u64));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl", price => 20_120u64));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let no_filter_collector = FilterCollector::new(price, &|value: u64| value > 20_120u64, TopDocs::with_limit(2));
/// let top_docs = searcher.search(&query, &no_filter_collector).unwrap();
///
/// assert_eq!(top_docs.len(), 1);
/// assert_eq!(top_docs[0].1, DocAddress(0, 1));
///
/// let filter_all_collector: FilterCollector<_, _, u64> = FilterCollector::new(price, &|value| value < 5u64, TopDocs::with_limit(2));
/// let filtered_top_docs = searcher.search(&query, &filter_all_collector).unwrap();
///
/// assert_eq!(filtered_top_docs.len(), 0);
/// ```
pub struct FilterCollector<TCollector, TPredicate, TPredicateValue: FastValue>
where
TPredicate: 'static,
{
field: Field,
collector: TCollector,
predicate: &'static TPredicate,
t_predicate_value: PhantomData<TPredicateValue>,
}
impl<TCollector, TPredicate, TPredicateValue: FastValue>
FilterCollector<TCollector, TPredicate, TPredicateValue>
where
TCollector: Collector + Send + Sync,
TPredicate: Fn(TPredicateValue) -> bool + Send + Sync,
{
/// Create a new FilterCollector.
pub fn new(
field: Field,
predicate: &'static TPredicate,
collector: TCollector,
) -> FilterCollector<TCollector, TPredicate, TPredicateValue> {
FilterCollector {
field,
predicate,
collector,
t_predicate_value: PhantomData,
}
}
}
impl<TCollector, TPredicate, TPredicateValue: FastValue> Collector
for FilterCollector<TCollector, TPredicate, TPredicateValue>
where
TCollector: Collector + Send + Sync,
TPredicate: 'static + Fn(TPredicateValue) -> bool + Send + Sync,
TPredicateValue: 'static + FastValue,
{
// That's the type of our result.
// Our standard deviation will be a float.
type Fruit = TCollector::Fruit;
type Child = FilterSegmentCollector<TCollector::Child, TPredicate, TPredicateValue>;
fn for_segment(
&self,
segment_local_id: u32,
segment_reader: &SegmentReader,
) -> crate::Result<FilterSegmentCollector<TCollector::Child, TPredicate, TPredicateValue>> {
let schema = segment_reader.schema();
let field_entry = schema.get_field_entry(self.field);
if !field_entry.is_fast() {
return Err(TantivyError::SchemaError(format!(
"Field {:?} is not a fast field.",
field_entry.name()
)));
}
let requested_type = TPredicateValue::to_type();
let field_schema_type = field_entry.field_type().value_type();
if requested_type != field_schema_type {
return Err(TantivyError::SchemaError(format!(
"Field {:?} is of type {:?}!={:?}",
field_entry.name(),
requested_type,
field_schema_type
)));
}
let fast_field_reader = segment_reader
.fast_fields()
.typed_fast_field_reader(self.field)?;
let segment_collector = self
.collector
.for_segment(segment_local_id, segment_reader)?;
Ok(FilterSegmentCollector {
fast_field_reader,
segment_collector,
predicate: self.predicate,
t_predicate_value: PhantomData,
})
}
fn requires_scoring(&self) -> bool {
self.collector.requires_scoring()
}
fn merge_fruits(
&self,
segment_fruits: Vec<<TCollector::Child as SegmentCollector>::Fruit>,
) -> crate::Result<TCollector::Fruit> {
self.collector.merge_fruits(segment_fruits)
}
}
pub struct FilterSegmentCollector<TSegmentCollector, TPredicate, TPredicateValue>
where
TPredicate: 'static,
TPredicateValue: 'static + FastValue,
{
fast_field_reader: FastFieldReader<TPredicateValue>,
segment_collector: TSegmentCollector,
predicate: &'static TPredicate,
t_predicate_value: PhantomData<TPredicateValue>,
}
impl<TSegmentCollector, TPredicate, TPredicateValue> SegmentCollector
for FilterSegmentCollector<TSegmentCollector, TPredicate, TPredicateValue>
where
TSegmentCollector: SegmentCollector,
TPredicate: 'static + Fn(TPredicateValue) -> bool + Send + Sync,
TPredicateValue: 'static + FastValue,
{
type Fruit = TSegmentCollector::Fruit;
fn collect(&mut self, doc: u32, score: Score) {
let value = self.fast_field_reader.get(doc);
if (self.predicate)(value) {
self.segment_collector.collect(doc, score)
}
}
fn harvest(self) -> <TSegmentCollector as SegmentCollector>::Fruit {
self.segment_collector.harvest()
}
}

127
src/collector/int_facet_collector.rs
View File

@@ -1,127 +0,0 @@
use std::cmp::Eq;
use std::collections::HashMap;
use std::hash::Hash;
use collector::Collector;
use fastfield::FastFieldReader;
use schema::Field;
use DocId;
use Result;
use Score;
use SegmentReader;
use SegmentLocalId;
/// Facet collector for i64/u64 fast field
pub struct IntFacetCollector<T>
where
T: FastFieldReader,
T::ValueType: Eq + Hash,
{
counters: HashMap<T::ValueType, u64>,
field: Field,
ff_reader: Option<T>,
}
impl<T> IntFacetCollector<T>
where
T: FastFieldReader,
T::ValueType: Eq + Hash,
{
/// Creates a new facet collector for aggregating a given field.
pub fn new(field: Field) -> IntFacetCollector<T> {
IntFacetCollector {
counters: HashMap::new(),
field: field,
ff_reader: None,
}
}
}
impl<T> Collector for IntFacetCollector<T>
where
T: FastFieldReader,
T::ValueType: Eq + Hash,
{
fn set_segment(&mut self, _: SegmentLocalId, reader: &SegmentReader) -> Result<()> {
self.ff_reader = Some(reader.get_fast_field_reader(self.field)?);
Ok(())
}
fn collect(&mut self, doc: DocId, _: Score) {
let val = self.ff_reader
.as_ref()
.expect(
"collect() was called before set_segment. \
This should never happen.",
)
.get(doc);
*(self.counters.entry(val).or_insert(0)) += 1;
}
}
#[cfg(test)]
mod tests {
use collector::{chain, IntFacetCollector};
use query::QueryParser;
use fastfield::{I64FastFieldReader, U64FastFieldReader};
use schema::{self, FAST, STRING};
use Index;
#[test]
// create 10 documents, set num field value to 0 or 1 for even/odd ones
// make sure we have facet counters correctly filled
fn test_facet_collector_results() {
let mut schema_builder = schema::Schema::builder();
let num_field_i64 = schema_builder.add_i64_field("num_i64", FAST);
let num_field_u64 = schema_builder.add_u64_field("num_u64", FAST);
let num_field_f64 = schema_builder.add_f64_field("num_f64", FAST);
let text_field = schema_builder.add_text_field("text", STRING);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
{
for i in 0u64..10u64 {
index_writer.add_document(doc!(
num_field_i64 => ((i as i64) % 3i64) as i64,
num_field_u64 => (i % 2u64) as u64,
num_field_f64 => (i % 4u64) as f64,
text_field => "text"
));
}
}
assert_eq!(index_writer.commit().unwrap(), 10u64);
}
let searcher = index.reader().searcher();
let mut ffvf_i64: IntFacetCollector<I64FastFieldReader> = IntFacetCollector::new(num_field_i64);
let mut ffvf_u64: IntFacetCollector<U64FastFieldReader> = IntFacetCollector::new(num_field_u64);
let mut ffvf_f64: IntFacetCollector<F64FastFieldReader> = IntFacetCollector::new(num_field_f64);
{
// perform the query
let mut facet_collectors = chain().push(&mut ffvf_i64).push(&mut ffvf_u64).push(&mut ffvf_f64);
let mut query_parser = QueryParser::for_index(index, vec![text_field]);
let query = query_parser.parse_query("text:text").unwrap();
query.search(&searcher, &mut facet_collectors).unwrap();
}
assert_eq!(ffvf_u64.counters[&0], 5);
assert_eq!(ffvf_u64.counters[&1], 5);
assert_eq!(ffvf_i64.counters[&0], 4);
assert_eq!(ffvf_i64.counters[&1], 3);
assert_eq!(ffvf_f64.counters[&0.0], 3);
assert_eq!(ffvf_f64.counters[&2.0], 2);
}
}

77
src/collector/mod.rs
View File

@@ -85,7 +85,6 @@ See the `custom_collector` example.
*/
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -110,6 +109,14 @@ pub use self::tweak_score_top_collector::{ScoreSegmentTweaker, ScoreTweaker};
mod facet_collector;
pub use self::facet_collector::FacetCollector;
pub use self::facet_collector::FacetCounts;
use crate::query::Weight;
mod docset_collector;
pub use self::docset_collector::DocSetCollector;
mod filter_collector_wrapper;
pub use self::filter_collector_wrapper::FilterCollector;
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
@@ -133,13 +140,13 @@ impl<T> Fruit for T where T: Send + downcast_rs::Downcast {}
/// The collection logic itself is in the `SegmentCollector`.
///
/// Segments are not guaranteed to be visited in any specific order.
pub trait Collector: Sync {
pub trait Collector: Sync + Send {
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
type Fruit: Fruit;
/// Type of the `SegmentCollector` associated to this collector.
type Child: SegmentCollector<Fruit = Self::Fruit>;
type Child: SegmentCollector;
/// `set_segment` is called before beginning to enumerate
/// on this segment.
@@ -147,14 +154,40 @@ pub trait Collector: Sync {
&self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> Result<Self::Child>;
) -> crate::Result<Self::Child>;
/// Returns true iff the collector requires to compute scores for documents.
fn requires_scoring(&self) -> bool;
/// Combines the fruit associated to the collection of each segments
/// into one fruit.
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit>;
fn merge_fruits(
&self,
segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit>;
/// Created a segment collector and
fn collect_segment(
&self,
weight: &dyn Weight,
segment_ord: u32,
reader: &SegmentReader,
) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
let mut segment_collector = self.for_segment(segment_ord as u32, reader)?;
if let Some(delete_bitset) = reader.delete_bitset() {
weight.for_each(reader, &mut |doc, score| {
if delete_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
}
})?;
} else {
weight.for_each(reader, &mut |doc, score| {
segment_collector.collect(doc, score);
})?;
}
Ok(segment_collector.harvest())
}
}
/// The `SegmentCollector` is the trait in charge of defining the
@@ -185,7 +218,11 @@ where
type Fruit = (Left::Fruit, Right::Fruit);
type Child = (Left::Child, Right::Child);
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let left = self.0.for_segment(segment_local_id, segment)?;
let right = self.1.for_segment(segment_local_id, segment)?;
Ok((left, right))
@@ -197,11 +234,11 @@ where
fn merge_fruits(
&self,
children: Vec<(Left::Fruit, Right::Fruit)>,
) -> Result<(Left::Fruit, Right::Fruit)> {
segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<(Left::Fruit, Right::Fruit)> {
let mut left_fruits = vec![];
let mut right_fruits = vec![];
for (left_fruit, right_fruit) in children {
for (left_fruit, right_fruit) in segment_fruits {
left_fruits.push(left_fruit);
right_fruits.push(right_fruit);
}
@@ -240,7 +277,11 @@ where
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit);
type Child = (One::Child, Two::Child, Three::Child);
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let one = self.0.for_segment(segment_local_id, segment)?;
let two = self.1.for_segment(segment_local_id, segment)?;
let three = self.2.for_segment(segment_local_id, segment)?;
@@ -251,7 +292,10 @@ where
self.0.requires_scoring() || self.1.requires_scoring() || self.2.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
fn merge_fruits(
&self,
children: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];
@@ -299,7 +343,11 @@ where
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit, Four::Fruit);
type Child = (One::Child, Two::Child, Three::Child, Four::Child);
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> Result<Self::Child> {
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let one = self.0.for_segment(segment_local_id, segment)?;
let two = self.1.for_segment(segment_local_id, segment)?;
let three = self.2.for_segment(segment_local_id, segment)?;
@@ -314,7 +362,10 @@ where
|| self.3.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
fn merge_fruits(
&self,
children: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];

90
src/collector/multi_collector.rs
View File

@@ -2,7 +2,6 @@ use super::Collector;
use super::SegmentCollector;
use crate::collector::Fruit;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -24,7 +23,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
&self,
segment_local_id: u32,
reader: &SegmentReader,
) -> Result<Box<dyn BoxableSegmentCollector>> {
) -> crate::Result<Box<dyn BoxableSegmentCollector>> {
let child = self.0.for_segment(segment_local_id, reader)?;
Ok(Box::new(SegmentCollectorWrapper(child)))
}
@@ -33,18 +32,21 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
self.0.requires_scoring()
}
fn merge_fruits(&self, children: Vec<<Self as Collector>::Fruit>) -> Result<Box<dyn Fruit>> {
let typed_fruit: Vec<TCollector::Fruit> = children
fn merge_fruits(
&self,
children: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Box<dyn Fruit>> {
let typed_fruit: Vec<<TCollector::Child as SegmentCollector>::Fruit> = children
.into_iter()
.map(|untyped_fruit| {
untyped_fruit
.downcast::<TCollector::Fruit>()
.downcast::<<TCollector::Child as SegmentCollector>::Fruit>()
.map(|boxed_but_typed| *boxed_but_typed)
.map_err(|_| {
TantivyError::InvalidArgument("Failed to cast child fruit.".to_string())
})
})
.collect::<Result<_>>()?;
.collect::<crate::Result<_>>()?;
let merged_fruit = self.0.merge_fruits(typed_fruit)?;
Ok(Box::new(merged_fruit))
}
@@ -53,7 +55,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
impl SegmentCollector for Box<dyn BoxableSegmentCollector> {
type Fruit = Box<dyn Fruit>;
fn collect(&mut self, doc: u32, score: f32) {
fn collect(&mut self, doc: u32, score: Score) {
self.as_mut().collect(doc, score);
}
@@ -63,7 +65,7 @@ impl SegmentCollector for Box<dyn BoxableSegmentCollector> {
}
pub trait BoxableSegmentCollector {
fn collect(&mut self, doc: u32, score: f32);
fn collect(&mut self, doc: u32, score: Score);
fn harvest_from_box(self: Box<Self>) -> Box<dyn Fruit>;
}
@@ -72,7 +74,7 @@ pub struct SegmentCollectorWrapper<TSegmentCollector: SegmentCollector>(TSegment
impl<TSegmentCollector: SegmentCollector> BoxableSegmentCollector
for SegmentCollectorWrapper<TSegmentCollector>
{
fn collect(&mut self, doc: u32, score: f32) {
fn collect(&mut self, doc: u32, score: Score) {
self.0.collect(doc, score);
}
@@ -108,49 +110,35 @@ impl<TFruit: Fruit> FruitHandle<TFruit> {
/// use tantivy::collector::{Count, TopDocs, MultiCollector};
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result};
/// use tantivy::{doc, Index};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer(3_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
/// let mut index_writer = index.writer(3_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// assert!(index_writer.commit().is_ok());
///
/// let mut collectors = MultiCollector::new();
/// let top_docs_handle = collectors.add_collector(TopDocs::with_limit(2));
/// let count_handle = collectors.add_collector(Count);
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary")?;
/// let mut multi_fruit = searcher.search(&query, &collectors)?;
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let count = count_handle.extract(&mut multi_fruit);
/// let top_docs = top_docs_handle.extract(&mut multi_fruit);
/// let mut collectors = MultiCollector::new();
/// let top_docs_handle = collectors.add_collector(TopDocs::with_limit(2));
/// let count_handle = collectors.add_collector(Count);
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let mut multi_fruit = searcher.search(&query, &collectors).unwrap();
///
/// # assert_eq!(count, 2);
/// # assert_eq!(top_docs.len(), 2);
/// let count = count_handle.extract(&mut multi_fruit);
/// let top_docs = top_docs_handle.extract(&mut multi_fruit);
///
/// Ok(())
/// }
/// assert_eq!(count, 2);
/// assert_eq!(top_docs.len(), 2);
/// ```
#[allow(clippy::type_complexity)]
#[derive(Default)]
@@ -189,12 +177,12 @@ impl<'a> Collector for MultiCollector<'a> {
&self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> Result<MultiCollectorChild> {
) -> crate::Result<MultiCollectorChild> {
let children = self
.collector_wrappers
.iter()
.map(|collector_wrapper| collector_wrapper.for_segment(segment_local_id, segment))
.collect::<Result<Vec<_>>>()?;
.collect::<crate::Result<Vec<_>>>()?;
Ok(MultiCollectorChild { children })
}
@@ -205,7 +193,7 @@ impl<'a> Collector for MultiCollector<'a> {
.any(Collector::requires_scoring)
}
fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> Result<MultiFruit> {
fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> crate::Result<MultiFruit> {
let mut segment_fruits_list: Vec<Vec<Box<dyn Fruit>>> = (0..self.collector_wrappers.len())
.map(|_| Vec::with_capacity(segments_multifruits.len()))
.collect::<Vec<_>>();
@@ -223,7 +211,7 @@ impl<'a> Collector for MultiCollector<'a> {
.map(|(child_collector, segment_fruits)| {
Ok(Some(child_collector.merge_fruits(segment_fruits)?))
})
.collect::<Result<_>>()?;
.collect::<crate::Result<_>>()?;
Ok(MultiFruit { sub_fruits })
}
}
@@ -271,7 +259,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text=>"abc"));
index_writer.add_document(doc!(text=>"abc abc abc"));
index_writer.add_document(doc!(text=>"abc abc"));

75
src/collector/tests.rs
View File

@@ -8,6 +8,13 @@ use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
use crate::collector::{FilterCollector, TopDocs};
use crate::query::QueryParser;
use crate::schema::{Schema, FAST, TEXT};
use crate::DateTime;
use crate::{doc, Index};
use std::str::FromStr;
pub const TEST_COLLECTOR_WITH_SCORE: TestCollector = TestCollector {
compute_score: true,
};
@@ -16,6 +23,54 @@ pub const TEST_COLLECTOR_WITHOUT_SCORE: TestCollector = TestCollector {
compute_score: true,
};
#[test]
pub fn test_filter_collector() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field("title", TEXT);
let price = schema_builder.add_u64_field("price", FAST);
let date = schema_builder.add_date_field("date", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
index_writer.add_document(doc!(title => "The Name of the Wind", price => 30_200u64, date => DateTime::from_str("1898-04-09T00:00:00+00:00").unwrap()));
index_writer.add_document(doc!(title => "The Diary of Muadib", price => 29_240u64, date => DateTime::from_str("2020-04-09T00:00:00+00:00").unwrap()));
index_writer.add_document(doc!(title => "The Diary of Anne Frank", price => 18_240u64, date => DateTime::from_str("2019-04-20T00:00:00+00:00").unwrap()));
index_writer.add_document(doc!(title => "A Dairy Cow", price => 21_240u64, date => DateTime::from_str("2019-04-09T00:00:00+00:00").unwrap()));
index_writer.add_document(doc!(title => "The Diary of a Young Girl", price => 20_120u64, date => DateTime::from_str("2018-04-09T00:00:00+00:00").unwrap()));
assert!(index_writer.commit().is_ok());
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let query_parser = QueryParser::for_index(&index, vec![title]);
let query = query_parser.parse_query("diary").unwrap();
let filter_some_collector = FilterCollector::new(
price,
&|value: u64| value > 20_120u64,
TopDocs::with_limit(2),
);
let top_docs = searcher.search(&query, &filter_some_collector).unwrap();
assert_eq!(top_docs.len(), 1);
assert_eq!(top_docs[0].1, DocAddress(0, 1));
let filter_all_collector: FilterCollector<_, _, u64> =
FilterCollector::new(price, &|value| value < 5u64, TopDocs::with_limit(2));
let filtered_top_docs = searcher.search(&query, &filter_all_collector).unwrap();
assert_eq!(filtered_top_docs.len(), 0);
fn date_filter(value: DateTime) -> bool {
(value - DateTime::from_str("2019-04-09T00:00:00+00:00").unwrap()).num_weeks() > 0
}
let filter_dates_collector = FilterCollector::new(date, &date_filter, TopDocs::with_limit(5));
let filtered_date_docs = searcher.search(&query, &filter_dates_collector).unwrap();
assert_eq!(filtered_date_docs.len(), 2);
}
/// Stores all of the doc ids.
/// This collector is only used for tests.
/// It is unusable in pr
@@ -55,7 +110,7 @@ impl Collector for TestCollector {
&self,
segment_id: SegmentLocalId,
_reader: &SegmentReader,
) -> Result<TestSegmentCollector> {
) -> crate::Result<TestSegmentCollector> {
Ok(TestSegmentCollector {
segment_id,
fruit: TestFruit::default(),
@@ -66,7 +121,7 @@ impl Collector for TestCollector {
self.compute_score
}
fn merge_fruits(&self, mut children: Vec<TestFruit>) -> Result<TestFruit> {
fn merge_fruits(&self, mut children: Vec<TestFruit>) -> crate::Result<TestFruit> {
children.sort_by_key(|fruit| {
if fruit.docs().is_empty() {
0
@@ -124,7 +179,7 @@ impl Collector for FastFieldTestCollector {
&self,
_: SegmentLocalId,
segment_reader: &SegmentReader,
) -> Result<FastFieldSegmentCollector> {
) -> crate::Result<FastFieldSegmentCollector> {
let reader = segment_reader
.fast_fields()
.u64(self.field)
@@ -139,7 +194,7 @@ impl Collector for FastFieldTestCollector {
false
}
fn merge_fruits(&self, children: Vec<Vec<u64>>) -> Result<Vec<u64>> {
fn merge_fruits(&self, children: Vec<Vec<u64>>) -> crate::Result<Vec<u64>> {
Ok(children.into_iter().flat_map(|v| v.into_iter()).collect())
}
}
@@ -184,13 +239,11 @@ impl Collector for BytesFastFieldTestCollector {
&self,
_segment_local_id: u32,
segment_reader: &SegmentReader,
) -> Result<BytesFastFieldSegmentCollector> {
) -> crate::Result<BytesFastFieldSegmentCollector> {
let reader = segment_reader.fast_fields().bytes(self.field)?;
Ok(BytesFastFieldSegmentCollector {
vals: Vec::new(),
reader: segment_reader
.fast_fields()
.bytes(self.field)
.expect("Field is not a bytes fast field."),
reader,
})
}
@@ -198,7 +251,7 @@ impl Collector for BytesFastFieldTestCollector {
false
}
fn merge_fruits(&self, children: Vec<Vec<u8>>) -> Result<Vec<u8>> {
fn merge_fruits(&self, children: Vec<Vec<u8>>) -> crate::Result<Vec<u8>> {
Ok(children.into_iter().flat_map(|c| c.into_iter()).collect())
}
}
@@ -206,7 +259,7 @@ impl Collector for BytesFastFieldTestCollector {
impl SegmentCollector for BytesFastFieldSegmentCollector {
type Fruit = Vec<u8>;
fn collect(&mut self, doc: u32, _score: f32) {
fn collect(&mut self, doc: u32, _score: Score) {
let data = self.reader.get_bytes(doc);
self.vals.extend(data);
}

93
src/collector/top_collector.rs
View File

@@ -1,11 +1,10 @@
use crate::DocAddress;
use crate::DocId;
use crate::Result;
use crate::SegmentLocalId;
use crate::SegmentReader;
use serde::export::PhantomData;
use std::cmp::Ordering;
use std::collections::BinaryHeap;
use std::marker::PhantomData;
/// Contains a feature (field, score, etc.) of a document along with the document address.
///
@@ -19,9 +18,9 @@ use std::collections::BinaryHeap;
/// Two elements are equal if their feature is equal, and regardless of whether `doc`
/// is equal. This should be perfectly fine for this usage, but let's make sure this
/// struct is never public.
struct ComparableDoc<T, D> {
feature: T,
doc: D,
pub(crate) struct ComparableDoc<T, D> {
pub feature: T,
pub doc: D,
}
impl<T: PartialOrd, D: PartialOrd> PartialOrd for ComparableDoc<T, D> {
@@ -57,7 +56,8 @@ impl<T: PartialOrd, D: PartialOrd> PartialEq for ComparableDoc<T, D> {
impl<T: PartialOrd, D: PartialOrd> Eq for ComparableDoc<T, D> {}
pub(crate) struct TopCollector<T> {
limit: usize,
pub limit: usize,
pub offset: usize,
_marker: PhantomData<T>,
}
@@ -73,27 +73,33 @@ where
if limit < 1 {
panic!("Limit must be strictly greater than 0.");
}
TopCollector {
Self {
limit,
offset: 0,
_marker: PhantomData,
}
}
pub fn limit(&self) -> usize {
self.limit
/// Skip the first "offset" documents when collecting.
///
/// This is equivalent to `OFFSET` in MySQL or PostgreSQL and `start` in
/// Lucene's TopDocsCollector.
pub fn and_offset(mut self, offset: usize) -> TopCollector<T> {
self.offset = offset;
self
}
pub fn merge_fruits(
&self,
children: Vec<Vec<(T, DocAddress)>>,
) -> Result<Vec<(T, DocAddress)>> {
) -> crate::Result<Vec<(T, DocAddress)>> {
if self.limit == 0 {
return Ok(Vec::new());
}
let mut top_collector = BinaryHeap::new();
for child_fruit in children {
for (feature, doc) in child_fruit {
if top_collector.len() < self.limit {
if top_collector.len() < (self.limit + self.offset) {
top_collector.push(ComparableDoc { feature, doc });
} else if let Some(mut head) = top_collector.peek_mut() {
if head.feature < feature {
@@ -105,6 +111,7 @@ where
Ok(top_collector
.into_sorted_vec()
.into_iter()
.skip(self.offset)
.map(|cdoc| (cdoc.feature, cdoc.doc))
.collect())
}
@@ -113,8 +120,24 @@ where
&self,
segment_id: SegmentLocalId,
_: &SegmentReader,
) -> Result<TopSegmentCollector<F>> {
Ok(TopSegmentCollector::new(segment_id, self.limit))
) -> crate::Result<TopSegmentCollector<F>> {
Ok(TopSegmentCollector::new(
segment_id,
self.limit + self.offset,
))
}
/// Create a new TopCollector with the same limit and offset.
///
/// Ideally we would use Into but the blanket implementation seems to cause the Scorer traits
/// to fail.
#[doc(hidden)]
pub(crate) fn into_tscore<TScore: PartialOrd + Clone>(self) -> TopCollector<TScore> {
TopCollector {
limit: self.limit,
offset: self.offset,
_marker: PhantomData,
}
}
}
@@ -188,7 +211,7 @@ impl<T: PartialOrd + Clone> TopSegmentCollector<T> {
#[cfg(test)]
mod tests {
use super::TopSegmentCollector;
use super::{TopCollector, TopSegmentCollector};
use crate::DocAddress;
#[test]
@@ -249,6 +272,48 @@ mod tests {
top_collector_limit_3.harvest()[..2].to_vec(),
);
}
#[test]
fn test_top_collector_with_limit_and_offset() {
let collector = TopCollector::with_limit(2).and_offset(1);
let results = collector
.merge_fruits(vec![vec![
(0.9, DocAddress(0, 1)),
(0.8, DocAddress(0, 2)),
(0.7, DocAddress(0, 3)),
(0.6, DocAddress(0, 4)),
(0.5, DocAddress(0, 5)),
]])
.unwrap();
assert_eq!(
results,
vec![(0.8, DocAddress(0, 2)), (0.7, DocAddress(0, 3)),]
);
}
#[test]
fn test_top_collector_with_limit_larger_than_set_and_offset() {
let collector = TopCollector::with_limit(2).and_offset(1);
let results = collector
.merge_fruits(vec![vec![(0.9, DocAddress(0, 1)), (0.8, DocAddress(0, 2))]])
.unwrap();
assert_eq!(results, vec![(0.8, DocAddress(0, 2)),]);
}
#[test]
fn test_top_collector_with_limit_and_offset_larger_than_set() {
let collector = TopCollector::with_limit(2).and_offset(20);
let results = collector
.merge_fruits(vec![vec![(0.9, DocAddress(0, 1)), (0.8, DocAddress(0, 2))]])
.unwrap();
assert_eq!(results, vec![]);
}
}
#[cfg(all(test, feature = "unstable"))]

729
src/collector/top_score_collector.rs
View File

@@ -1,19 +1,82 @@
use super::Collector;
use crate::collector::custom_score_top_collector::CustomScoreTopCollector;
use crate::collector::top_collector::TopCollector;
use crate::collector::top_collector::TopSegmentCollector;
use crate::collector::top_collector::{ComparableDoc, TopCollector};
use crate::collector::tweak_score_top_collector::TweakedScoreTopCollector;
use crate::collector::{
CustomScorer, CustomSegmentScorer, ScoreSegmentTweaker, ScoreTweaker, SegmentCollector,
};
use crate::fastfield::FastFieldReader;
use crate::query::Weight;
use crate::schema::Field;
use crate::DocAddress;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use crate::{collector::custom_score_top_collector::CustomScoreTopCollector, fastfield::FastValue};
use crate::{collector::top_collector::TopSegmentCollector, TantivyError};
use std::fmt;
use std::{collections::BinaryHeap, marker::PhantomData};
struct FastFieldConvertCollector<
TCollector: Collector<Fruit = Vec<(u64, DocAddress)>>,
TFastValue: FastValue,
> {
pub collector: TCollector,
pub field: Field,
pub fast_value: std::marker::PhantomData<TFastValue>,
}
impl<TCollector, TFastValue> Collector for FastFieldConvertCollector<TCollector, TFastValue>
where
TCollector: Collector<Fruit = Vec<(u64, DocAddress)>>,
TFastValue: FastValue + 'static,
{
type Fruit = Vec<(TFastValue, DocAddress)>;
type Child = TCollector::Child;
fn for_segment(
&self,
segment_local_id: crate::SegmentLocalId,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let schema = segment.schema();
let field_entry = schema.get_field_entry(self.field);
if !field_entry.is_fast() {
return Err(TantivyError::SchemaError(format!(
"Field {:?} is not a fast field.",
field_entry.name()
)));
}
let schema_type = TFastValue::to_type();
let requested_type = field_entry.field_type().value_type();
if schema_type != requested_type {
return Err(TantivyError::SchemaError(format!(
"Field {:?} is of type {:?}!={:?}",
field_entry.name(),
schema_type,
requested_type
)));
}
self.collector.for_segment(segment_local_id, segment)
}
fn requires_scoring(&self) -> bool {
self.collector.requires_scoring()
}
fn merge_fruits(
&self,
segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit> {
let raw_result = self.collector.merge_fruits(segment_fruits)?;
let transformed_result = raw_result
.into_iter()
.map(|(score, doc_address)| (TFastValue::from_u64(score), doc_address))
.collect::<Vec<_>>();
Ok(transformed_result)
}
}
/// The `TopDocs` collector keeps track of the top `K` documents
/// sorted by their score.
@@ -29,49 +92,69 @@ use std::fmt;
/// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, DocAddress, Index, Result};
/// use tantivy::{doc, DocAddress, Index};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// assert!(index_writer.commit().is_ok());
///
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary")?;
/// let top_docs = searcher.search(&query, &TopDocs::with_limit(2))?;
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// assert_eq!(&top_docs[0], &(0.7261542, DocAddress(0, 1)));
/// assert_eq!(&top_docs[1], &(0.6099695, DocAddress(0, 3)));
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let top_docs = searcher.search(&query, &TopDocs::with_limit(2)).unwrap();
///
/// Ok(())
/// }
/// assert_eq!(top_docs[0].1, DocAddress(0, 1));
/// assert_eq!(top_docs[1].1, DocAddress(0, 3));
/// ```
pub struct TopDocs(TopCollector<Score>);
impl fmt::Debug for TopDocs {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "TopDocs({})", self.0.limit())
write!(
f,
"TopDocs(limit={}, offset={})",
self.0.limit, self.0.offset
)
}
}
struct ScorerByFastFieldReader {
ff_reader: FastFieldReader<u64>,
}
impl CustomSegmentScorer<u64> for ScorerByFastFieldReader {
fn score(&mut self, doc: DocId) -> u64 {
self.ff_reader.get(doc)
}
}
struct ScorerByField {
field: Field,
}
impl CustomScorer<u64> for ScorerByField {
type Child = ScorerByFastFieldReader;
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
// We interpret this field as u64, regardless of its type, that way,
// we avoid needless conversion. Regardless of the fast field type, the
// mapping is monotonic, so it is sufficient to compute our top-K docs.
//
// The conversion will then happen only on the top-K docs.
let ff_reader: FastFieldReader<u64> = segment_reader
.fast_fields()
.typed_fast_field_reader(self.field)?;
Ok(ScorerByFastFieldReader { ff_reader })
}
}
@@ -84,11 +167,60 @@ impl TopDocs {
TopDocs(TopCollector::with_limit(limit))
}
/// Skip the first "offset" documents when collecting.
///
/// This is equivalent to `OFFSET` in MySQL or PostgreSQL and `start` in
/// Lucene's TopDocsCollector.
///
/// # Example
///
/// ```rust
/// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, DocAddress, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// index_writer.add_document(doc!(title => "The Diary of Lena Mukhina"));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let top_docs = searcher.search(&query, &TopDocs::with_limit(2).and_offset(1)).unwrap();
///
/// assert_eq!(top_docs.len(), 2);
/// assert_eq!(top_docs[0].1, DocAddress(0, 4));
/// assert_eq!(top_docs[1].1, DocAddress(0, 3));
/// ```
pub fn and_offset(self, offset: usize) -> TopDocs {
TopDocs(self.0.and_offset(offset))
}
/// Set top-K to rank documents by a given fast field.
///
/// If the field is not a fast or does not exist, this method returns successfully (it is not aware of any schema).
/// An error will be returned at the moment of search.
///
/// If the field is a FAST field but not a u64 field, search will return successfully but it will return
/// returns a monotonic u64-representation (ie. the order is still correct) of the requested field type.
///
/// # Example
///
/// ```rust
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, Result, DocAddress};
/// # use tantivy::{doc, Index, DocAddress};
/// # use tantivy::query::{Query, QueryParser};
/// use tantivy::Searcher;
/// use tantivy::collector::TopDocs;
@@ -99,17 +231,14 @@ impl TopDocs {
/// # let title = schema_builder.add_text_field("title", TEXT);
/// # let rating = schema_builder.add_u64_field("rating", FAST);
/// # let schema = schema_builder.build();
/// #
/// #
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # index_writer.add_document(doc!(
/// # title => "The Name of the Wind",
/// # rating => 92u64,
/// # ));
/// # let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
/// # index_writer.add_document(doc!(title => "The Name of the Wind", rating => 92u64));
/// # index_writer.add_document(doc!(title => "The Diary of Muadib", rating => 97u64));
/// # index_writer.add_document(doc!(title => "A Dairy Cow", rating => 63u64));
/// # index_writer.add_document(doc!(title => "The Diary of a Young Girl", rating => 80u64));
/// # index_writer.commit()?;
/// # assert!(index_writer.commit().is_ok());
/// # let reader = index.reader()?;
/// # let query = QueryParser::for_index(&index, vec![title]).parse_query("diary")?;
/// # let top_docs = docs_sorted_by_rating(&reader.searcher(), &query, rating)?;
@@ -118,26 +247,21 @@ impl TopDocs {
/// # (80u64, DocAddress(0u32, 3))]);
/// # Ok(())
/// # }
///
///
/// /// Searches the document matching the given query, and
/// /// collects the top 10 documents, order by the u64-`field`
/// /// given in argument.
/// ///
/// /// `field` is required to be a FAST field.
/// fn docs_sorted_by_rating(searcher: &Searcher,
/// query: &dyn Query,
/// sort_by_field: Field)
/// -> Result<Vec<(u64, DocAddress)>> {
/// rating_field: Field)
/// -> tantivy::Result<Vec<(u64, DocAddress)>> {
///
/// // This is where we build our topdocs collector
/// //
/// // Note the generics parameter that needs to match the
/// // type `sort_by_field`.
/// let top_docs_by_rating = TopDocs
/// // Note the `rating_field` needs to be a FAST field here.
/// let top_books_by_rating = TopDocs
/// ::with_limit(10)
/// .order_by_u64_field(sort_by_field);
///
/// .order_by_u64_field(rating_field);
///
/// // ... and here are our documents. Note this is a simple vec.
/// // The `u64` in the pair is the value of our fast field for
/// // each documents.
@@ -146,28 +270,105 @@ impl TopDocs {
/// // length of 10, or less if not enough documents matched the
/// // query.
/// let resulting_docs: Vec<(u64, DocAddress)> =
/// searcher.search(query, &top_docs_by_rating)?;
///
/// searcher.search(query, &top_books_by_rating)?;
///
/// Ok(resulting_docs)
/// }
/// ```
///
/// # Panics
///
/// May panic if the field requested is not a fast field.
/// # See also
///
/// To confortably work with `u64`s, `i64`s, `f64`s, or `date`s, please refer to
/// [.order_by_fast_field(...)](#method.order_by_fast_field) method.
pub fn order_by_u64_field(
self,
field: Field,
) -> impl Collector<Fruit = Vec<(u64, DocAddress)>> {
self.custom_score(move |segment_reader: &SegmentReader| {
let ff_reader = segment_reader
.fast_fields()
.u64(field)
.expect("Field requested is not a i64/u64 fast field.");
//TODO error message missmatch actual behavior for i64
move |doc: DocId| ff_reader.get(doc)
})
CustomScoreTopCollector::new(ScorerByField { field }, self.0.into_tscore())
}
/// Set top-K to rank documents by a given fast field.
///
/// If the field is not a fast field, or its field type does not match the generic type, this method does not panic,
/// but an explicit error will be returned at the moment of collection.
///
/// Note that this method is a generic. The requested fast field type will be often
/// inferred in your code by the rust compiler.
///
/// Implementation-wise, for performance reason, tantivy will manipulate the u64 representation of your fast
/// field until the last moment.
///
/// # Example
///
/// ```rust
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, DocAddress};
/// # use tantivy::query::{Query, AllQuery};
/// use tantivy::Searcher;
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::Field;
///
/// # fn main() -> tantivy::Result<()> {
/// # let mut schema_builder = Schema::builder();
/// # let title = schema_builder.add_text_field("company", TEXT);
/// # let rating = schema_builder.add_i64_field("revenue", FAST);
/// # let schema = schema_builder.build();
/// #
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
/// # index_writer.add_document(doc!(title => "MadCow Inc.", rating => 92_000_000i64));
/// # index_writer.add_document(doc!(title => "Zozo Cow KKK", rating => 119_000_000i64));
/// # index_writer.add_document(doc!(title => "Declining Cow", rating => -63_000_000i64));
/// # assert!(index_writer.commit().is_ok());
/// # let reader = index.reader()?;
/// # let top_docs = docs_sorted_by_revenue(&reader.searcher(), &AllQuery, rating)?;
/// # assert_eq!(top_docs,
/// # vec![(119_000_000i64, DocAddress(0, 1)),
/// # (92_000_000i64, DocAddress(0, 0))]);
/// # Ok(())
/// # }
/// /// Searches the document matching the given query, and
/// /// collects the top 10 documents, order by the u64-`field`
/// /// given in argument.
/// fn docs_sorted_by_revenue(searcher: &Searcher,
/// query: &dyn Query,
/// revenue_field: Field)
/// -> tantivy::Result<Vec<(i64, DocAddress)>> {
///
/// // This is where we build our topdocs collector
/// //
/// // Note the generics parameter that needs to match the
/// // type `sort_by_field`. revenue_field here is a FAST i64 field.
/// let top_company_by_revenue = TopDocs
/// ::with_limit(2)
/// .order_by_fast_field(revenue_field);
///
/// // ... and here are our documents. Note this is a simple vec.
/// // The `i64` in the pair is the value of our fast field for
/// // each documents.
/// //
/// // The vec is sorted decreasingly by `sort_by_field`, and has a
/// // length of 10, or less if not enough documents matched the
/// // query.
/// let resulting_docs: Vec<(i64, DocAddress)> =
/// searcher.search(query, &top_company_by_revenue)?;
///
/// Ok(resulting_docs)
/// }
/// ```
pub fn order_by_fast_field<TFastValue>(
self,
fast_field: Field,
) -> impl Collector<Fruit = Vec<(TFastValue, DocAddress)>>
where
TFastValue: FastValue + 'static,
{
let u64_collector = self.order_by_u64_field(fast_field);
FastFieldConvertCollector {
collector: u64_collector,
field: fast_field,
fast_value: PhantomData,
}
}
/// Ranks the documents using a custom score.
@@ -190,7 +391,7 @@ impl TopDocs {
///
/// In the following example will will tweak our ranking a bit by
/// boosting popular products a notch.
///
///
/// In more serious application, this tweaking could involved running a
/// learning-to-rank model over various features
///
@@ -202,27 +403,33 @@ impl TopDocs {
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::Field;
///
/// # fn create_schema() -> Schema {
/// # let mut schema_builder = Schema::builder();
/// # schema_builder.add_text_field("product_name", TEXT);
/// # schema_builder.add_u64_field("popularity", FAST);
/// # schema_builder.build()
/// # }
/// #
/// # fn main() -> tantivy::Result<()> {
/// # let schema = create_schema();
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # let product_name = index.schema().get_field("product_name").unwrap();
/// #
/// fn create_schema() -> Schema {
/// let mut schema_builder = Schema::builder();
/// schema_builder.add_text_field("product_name", TEXT);
/// schema_builder.add_u64_field("popularity", FAST);
/// schema_builder.build()
/// }
///
/// fn create_index() -> tantivy::Result<Index> {
/// let schema = create_schema();
/// let index = Index::create_in_ram(schema);
/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
/// let product_name = index.schema().get_field("product_name").unwrap();
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
/// index_writer.add_document(doc!(product_name => "The Diary of Muadib", popularity => 1u64));
/// index_writer.add_document(doc!(product_name => "A Dairy Cow", popularity => 10u64));
/// index_writer.add_document(doc!(product_name => "The Diary of a Young Girl", popularity => 15u64));
/// index_writer.commit()?;
/// Ok(index)
/// }
///
/// let index = create_index().unwrap();
/// let product_name = index.schema().get_field("product_name").unwrap();
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
/// # index_writer.add_document(doc!(product_name => "The Diary of Muadib", popularity => 1u64));
/// # index_writer.add_document(doc!(product_name => "A Dairy Cow", popularity => 10u64));
/// # index_writer.add_document(doc!(product_name => "The Diary of a Young Girl", popularity => 15u64));
/// # index_writer.commit()?;
/// // ...
/// # let user_query = "diary";
/// # let query = QueryParser::for_index(&index, vec![product_name]).parse_query(user_query)?;
///
/// let user_query_str = "diary";
/// let query_parser = QueryParser::for_index(&index, vec![product_name]);
/// let query = query_parser.parse_query(user_query_str).unwrap();
///
/// // This is where we build our collector with our custom score.
/// let top_docs_by_custom_score = TopDocs
@@ -245,19 +452,16 @@ impl TopDocs {
/// let popularity: u64 = popularity_reader.get(doc);
/// // Well.. For the sake of the example we use a simple logarithm
/// // function.
/// let popularity_boost_score = ((2u64 + popularity) as f32).log2();
/// let popularity_boost_score = ((2u64 + popularity) as Score).log2();
/// popularity_boost_score * original_score
/// }
/// });
/// # let reader = index.reader()?;
/// # let searcher = reader.searcher();
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
/// // ... and here are our documents. Note this is a simple vec.
/// // The `Score` in the pair is our tweaked score.
/// let resulting_docs: Vec<(Score, DocAddress)> =
/// searcher.search(&*query, &top_docs_by_custom_score)?;
///
/// # Ok(())
/// # }
/// searcher.search(&query, &top_docs_by_custom_score).unwrap();
/// ```
///
/// # See also
@@ -269,9 +473,9 @@ impl TopDocs {
where
TScore: 'static + Send + Sync + Clone + PartialOrd,
TScoreSegmentTweaker: ScoreSegmentTweaker<TScore> + 'static,
TScoreTweaker: ScoreTweaker<TScore, Child = TScoreSegmentTweaker>,
TScoreTweaker: ScoreTweaker<TScore, Child = TScoreSegmentTweaker> + Send + Sync,
{
TweakedScoreTopCollector::new(score_tweaker, self.0.limit())
TweakedScoreTopCollector::new(score_tweaker, self.0.into_tscore())
}
/// Ranks the documents using a custom score.
@@ -316,9 +520,9 @@ impl TopDocs {
/// # fn main() -> tantivy::Result<()> {
/// # let schema = create_schema();
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # let mut index_writer = index.writer_with_num_threads(1, 10_000_000)?;
/// # let product_name = index.schema().get_field("product_name").unwrap();
/// #
/// #
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
/// let boosted: Field = index.schema().get_field("boosted").unwrap();
/// # index_writer.add_document(doc!(boosted=>1u64, product_name => "The Diary of Muadib", popularity => 1u64));
@@ -352,7 +556,7 @@ impl TopDocs {
/// segment_reader.fast_fields().u64(popularity).unwrap();
/// let boosted_reader =
/// segment_reader.fast_fields().u64(boosted).unwrap();
///
///
/// // We can now define our actual scoring function
/// move |doc: DocId| {
/// let popularity: u64 = popularity_reader.get(doc);
@@ -383,9 +587,9 @@ impl TopDocs {
where
TScore: 'static + Send + Sync + Clone + PartialOrd,
TCustomSegmentScorer: CustomSegmentScorer<TScore> + 'static,
TCustomScorer: CustomScorer<TScore, Child = TCustomSegmentScorer>,
TCustomScorer: CustomScorer<TScore, Child = TCustomSegmentScorer> + Send + Sync,
{
CustomScoreTopCollector::new(custom_score, self.0.limit())
CustomScoreTopCollector::new(custom_score, self.0.into_tscore())
}
}
@@ -398,7 +602,7 @@ impl Collector for TopDocs {
&self,
segment_local_id: SegmentLocalId,
reader: &SegmentReader,
) -> Result<Self::Child> {
) -> crate::Result<Self::Child> {
let collector = self.0.for_segment(segment_local_id, reader)?;
Ok(TopScoreSegmentCollector(collector))
}
@@ -407,9 +611,70 @@ impl Collector for TopDocs {
true
}
fn merge_fruits(&self, child_fruits: Vec<Vec<(Score, DocAddress)>>) -> Result<Self::Fruit> {
fn merge_fruits(
&self,
child_fruits: Vec<Vec<(Score, DocAddress)>>,
) -> crate::Result<Self::Fruit> {
self.0.merge_fruits(child_fruits)
}
fn collect_segment(
&self,
weight: &dyn Weight,
segment_ord: u32,
reader: &SegmentReader,
) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
let heap_len = self.0.limit + self.0.offset;
let mut heap: BinaryHeap<ComparableDoc<Score, DocId>> = BinaryHeap::with_capacity(heap_len);
if let Some(delete_bitset) = reader.delete_bitset() {
let mut threshold = Score::MIN;
weight.for_each_pruning(threshold, reader, &mut |doc, score| {
if delete_bitset.is_deleted(doc) {
return threshold;
}
let heap_item = ComparableDoc {
feature: score,
doc,
};
if heap.len() < heap_len {
heap.push(heap_item);
if heap.len() == heap_len {
threshold = heap.peek().map(|el| el.feature).unwrap_or(Score::MIN);
}
return threshold;
}
*heap.peek_mut().unwrap() = heap_item;
threshold = heap.peek().map(|el| el.feature).unwrap_or(Score::MIN);
threshold
})?;
} else {
weight.for_each_pruning(Score::MIN, reader, &mut |doc, score| {
let heap_item = ComparableDoc {
feature: score,
doc,
};
if heap.len() < heap_len {
heap.push(heap_item);
// TODO the threshold is suboptimal for heap.len == heap_len
if heap.len() == heap_len {
return heap.peek().map(|el| el.feature).unwrap_or(Score::MIN);
} else {
return Score::MIN;
}
}
*heap.peek_mut().unwrap() = heap_item;
heap.peek().map(|el| el.feature).unwrap_or(Score::MIN)
})?;
}
let fruit = heap
.into_sorted_vec()
.into_iter()
.map(|cid| (cid.feature, DocAddress(segment_ord, cid.doc)))
.collect();
Ok(fruit)
}
}
/// Segment Collector associated to `TopDocs`.
@@ -419,7 +684,7 @@ impl SegmentCollector for TopScoreSegmentCollector {
type Fruit = Vec<(Score, DocAddress)>;
fn collect(&mut self, doc: DocId, score: Score) {
self.0.collect(doc, score)
self.0.collect(doc, score);
}
fn harvest(self) -> Vec<(Score, DocAddress)> {
@@ -433,11 +698,10 @@ mod tests {
use crate::collector::Collector;
use crate::query::{AllQuery, Query, QueryParser};
use crate::schema::{Field, Schema, FAST, STORED, TEXT};
use crate::DocAddress;
use crate::Index;
use crate::IndexWriter;
use crate::Score;
use itertools::Itertools;
use crate::{DocAddress, DocId, SegmentReader};
fn make_index() -> Index {
let mut schema_builder = Schema::builder();
@@ -446,7 +710,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
index_writer.add_document(doc!(text_field=>"Hello happy tax payer."));
index_writer.add_document(doc!(text_field=>"Droopy says hello happy tax payer"));
index_writer.add_document(doc!(text_field=>"I like Droopy"));
@@ -455,8 +719,15 @@ mod tests {
index
}
fn assert_results_equals(results: &[(Score, DocAddress)], expected: &[(Score, DocAddress)]) {
for (result, expected) in results.iter().zip(expected.iter()) {
assert_eq!(result.1, expected.1);
crate::assert_nearly_equals!(result.0, expected.0);
}
}
#[test]
fn test_top_collector_not_at_capacity() {
fn test_top_collector_not_at_capacity_without_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
@@ -467,16 +738,31 @@ mod tests {
.searcher()
.search(&text_query, &TopDocs::with_limit(4))
.unwrap();
assert_eq!(
score_docs,
vec![
assert_results_equals(
&score_docs,
&[
(0.81221175, DocAddress(0u32, 1)),
(0.5376842, DocAddress(0u32, 2)),
(0.48527452, DocAddress(0, 0))
]
(0.48527452, DocAddress(0, 0)),
],
);
}
#[test]
fn test_top_collector_not_at_capacity_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let score_docs: Vec<(Score, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &TopDocs::with_limit(4).and_offset(2))
.unwrap();
assert_results_equals(&score_docs[..], &[(0.48527452, DocAddress(0, 0))]);
}
#[test]
fn test_top_collector_at_capacity() {
let index = make_index();
@@ -489,12 +775,33 @@ mod tests {
.searcher()
.search(&text_query, &TopDocs::with_limit(2))
.unwrap();
assert_eq!(
score_docs,
vec![
assert_results_equals(
&score_docs,
&[
(0.81221175, DocAddress(0u32, 1)),
(0.5376842, DocAddress(0u32, 2)),
]
],
);
}
#[test]
fn test_top_collector_at_capacity_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let score_docs: Vec<(Score, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &TopDocs::with_limit(2).and_offset(1))
.unwrap();
assert_results_equals(
&score_docs[..],
&[
(0.5376842, DocAddress(0u32, 2)),
(0.48527452, DocAddress(0, 0)),
],
);
}
@@ -511,8 +818,8 @@ mod tests {
// precondition for the test to be meaningful: we did get documents
// with the same score
assert!(page_1.iter().map(|result| result.0).all_equal());
assert!(page_2.iter().map(|result| result.0).all_equal());
assert!(page_1.iter().all(|result| result.0 == page_1[0].0));
assert!(page_2.iter().all(|result| result.0 == page_2[0].0));
// sanity check since we're relying on make_index()
assert_eq!(page_1.len(), 2);
@@ -555,8 +862,8 @@ mod tests {
let top_collector = TopDocs::with_limit(4).order_by_u64_field(size);
let top_docs: Vec<(u64, DocAddress)> = searcher.search(&query, &top_collector).unwrap();
assert_eq!(
top_docs,
vec![
&top_docs[..],
&[
(64, DocAddress(0, 1)),
(16, DocAddress(0, 2)),
(12, DocAddress(0, 0))
@@ -564,6 +871,94 @@ mod tests {
);
}
#[test]
fn test_top_field_collector_datetime() -> crate::Result<()> {
use std::str::FromStr;
let mut schema_builder = Schema::builder();
let name = schema_builder.add_text_field("name", TEXT);
let birthday = schema_builder.add_date_field("birthday", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
let pr_birthday = crate::DateTime::from_str("1898-04-09T00:00:00+00:00")?;
index_writer.add_document(doc!(
name => "Paul Robeson",
birthday => pr_birthday
));
let mr_birthday = crate::DateTime::from_str("1947-11-08T00:00:00+00:00")?;
index_writer.add_document(doc!(
name => "Minnie Riperton",
birthday => mr_birthday
));
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let top_collector = TopDocs::with_limit(3).order_by_fast_field(birthday);
let top_docs: Vec<(crate::DateTime, DocAddress)> =
searcher.search(&AllQuery, &top_collector)?;
assert_eq!(
&top_docs[..],
&[
(mr_birthday, DocAddress(0, 1)),
(pr_birthday, DocAddress(0, 0)),
]
);
Ok(())
}
#[test]
fn test_top_field_collector_i64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let city = schema_builder.add_text_field("city", TEXT);
let altitude = schema_builder.add_i64_field("altitude", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(
city => "georgetown",
altitude => -1i64,
));
index_writer.add_document(doc!(
city => "tokyo",
altitude => 40i64,
));
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let top_collector = TopDocs::with_limit(3).order_by_fast_field(altitude);
let top_docs: Vec<(i64, DocAddress)> = searcher.search(&AllQuery, &top_collector)?;
assert_eq!(
&top_docs[..],
&[(40i64, DocAddress(0, 1)), (-1i64, DocAddress(0, 0)),]
);
Ok(())
}
#[test]
fn test_top_field_collector_f64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let city = schema_builder.add_text_field("city", TEXT);
let altitude = schema_builder.add_f64_field("altitude", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(
city => "georgetown",
altitude => -1.0f64,
));
index_writer.add_document(doc!(
city => "tokyo",
altitude => 40f64,
));
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let top_collector = TopDocs::with_limit(3).order_by_fast_field(altitude);
let top_docs: Vec<(f64, DocAddress)> = searcher.search(&AllQuery, &top_collector)?;
assert_eq!(
&top_docs[..],
&[(40f64, DocAddress(0, 1)), (-1.0f64, DocAddress(0, 0)),]
);
Ok(())
}
#[test]
#[should_panic]
fn test_field_does_not_exist() {
@@ -586,22 +981,83 @@ mod tests {
}
#[test]
#[should_panic(expected = "Field requested is not a i64/u64 fast field")]
fn test_field_not_fast_field() {
fn test_field_not_fast_field() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field(TITLE, TEXT);
let size = schema_builder.add_u64_field(SIZE, STORED);
let schema = schema_builder.build();
let (index, _) = index("beer", title, schema, |index_writer| {
index_writer.add_document(doc!(
title => "bottle of beer",
size => 12u64,
));
});
let searcher = index.reader().unwrap().searcher();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(size=>1u64));
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let segment = searcher.segment_reader(0);
let top_collector = TopDocs::with_limit(4).order_by_u64_field(size);
assert!(top_collector.for_segment(0, segment).is_ok());
let err = top_collector.for_segment(0, segment).err().unwrap();
assert!(matches!(err, crate::TantivyError::SchemaError(_)));
Ok(())
}
#[test]
fn test_field_wrong_type() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let size = schema_builder.add_u64_field(SIZE, STORED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(size=>1u64));
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let segment = searcher.segment_reader(0);
let top_collector = TopDocs::with_limit(4).order_by_fast_field::<i64>(size);
let err = top_collector.for_segment(0, segment).err().unwrap();
assert!(
matches!(err, crate::TantivyError::SchemaError(msg) if msg == "Field \"size\" is not a fast field.")
);
Ok(())
}
#[test]
fn test_tweak_score_top_collector_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let collector = TopDocs::with_limit(2).and_offset(1).tweak_score(
move |_segment_reader: &SegmentReader| move |doc: DocId, _original_score: Score| doc,
);
let score_docs: Vec<(u32, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &collector)
.unwrap();
assert_eq!(
score_docs,
vec![(1, DocAddress(0, 1)), (0, DocAddress(0, 0)),]
);
}
#[test]
fn test_custom_score_top_collector_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let collector = TopDocs::with_limit(2)
.and_offset(1)
.custom_score(move |_segment_reader: &SegmentReader| move |doc: DocId| doc);
let score_docs: Vec<(u32, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &collector)
.unwrap();
assert_eq!(
score_docs,
vec![(1, DocAddress(0, 1)), (0, DocAddress(0, 0)),]
);
}
fn index(
@@ -611,8 +1067,7 @@ mod tests {
mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
) -> (Index, Box<dyn Query>) {
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
doc_adder(&mut index_writer);
index_writer.commit().unwrap();
let query_parser = QueryParser::for_index(&index, vec![query_field]);

12
src/collector/tweak_score_top_collector.rs
View File

@@ -14,11 +14,11 @@ where
{
pub fn new(
score_tweaker: TScoreTweaker,
limit: usize,
collector: TopCollector<TScore>,
) -> TweakedScoreTopCollector<TScoreTweaker, TScore> {
TweakedScoreTopCollector {
score_tweaker,
collector: TopCollector::with_limit(limit),
collector,
}
}
}
@@ -29,7 +29,7 @@ where
/// It is the segment local version of the [`ScoreTweaker`](./trait.ScoreTweaker.html).
pub trait ScoreSegmentTweaker<TScore>: 'static {
/// Tweak the given `score` for the document `doc`.
fn score(&self, doc: DocId, score: Score) -> TScore;
fn score(&mut self, doc: DocId, score: Score) -> TScore;
}
/// `ScoreTweaker` makes it possible to tweak the score
@@ -49,7 +49,7 @@ pub trait ScoreTweaker<TScore>: Sync {
impl<TScoreTweaker, TScore> Collector for TweakedScoreTopCollector<TScoreTweaker, TScore>
where
TScoreTweaker: ScoreTweaker<TScore>,
TScoreTweaker: ScoreTweaker<TScore> + Send + Sync,
TScore: 'static + PartialOrd + Clone + Send + Sync,
{
type Fruit = Vec<(TScore, DocAddress)>;
@@ -121,9 +121,9 @@ where
impl<F, TScore> ScoreSegmentTweaker<TScore> for F
where
F: 'static + Sync + Send + Fn(DocId, Score) -> TScore,
F: 'static + FnMut(DocId, Score) -> TScore,
{
fn score(&self, doc: DocId, score: Score) -> TScore {
fn score(&mut self, doc: DocId, score: Score) -> TScore {
(self)(doc, score)
}
}

24
src/common/bitpacker.rs
View File

@@ -1,6 +1,7 @@
use byteorder::{ByteOrder, LittleEndian, WriteBytesExt};
use std::io;
use std::ops::Deref;
use crate::directory::OwnedBytes;
pub(crate) struct BitPacker {
mini_buffer: u64,
@@ -60,20 +61,14 @@ impl BitPacker {
}
#[derive(Clone)]
pub struct BitUnpacker<Data>
where
Data: Deref<Target = [u8]>,
{
pub struct BitUnpacker {
num_bits: u64,
mask: u64,
data: Data,
data: OwnedBytes,
}
impl<Data> BitUnpacker<Data>
where
Data: Deref<Target = [u8]>,
{
pub fn new(data: Data, num_bits: u8) -> BitUnpacker<Data> {
impl BitUnpacker {
pub fn new(data: OwnedBytes, num_bits: u8) -> BitUnpacker {
let mask: u64 = if num_bits == 64 {
!0u64
} else {
@@ -90,7 +85,7 @@ where
if self.num_bits == 0 {
return 0u64;
}
let data: &[u8] = &*self.data;
let data: &[u8] = self.data.as_slice();
let num_bits = self.num_bits;
let mask = self.mask;
let addr_in_bits = idx * num_bits;
@@ -109,8 +104,9 @@ where
#[cfg(test)]
mod test {
use super::{BitPacker, BitUnpacker};
use crate::directory::OwnedBytes;
fn create_fastfield_bitpacker(len: usize, num_bits: u8) -> (BitUnpacker<Vec<u8>>, Vec<u64>) {
fn create_fastfield_bitpacker(len: usize, num_bits: u8) -> (BitUnpacker, Vec<u64>) {
let mut data = Vec::new();
let mut bitpacker = BitPacker::new();
let max_val: u64 = (1u64 << num_bits as u64) - 1u64;
@@ -122,7 +118,7 @@ mod test {
}
bitpacker.close(&mut data).unwrap();
assert_eq!(data.len(), ((num_bits as usize) * len + 7) / 8 + 7);
let bitunpacker = BitUnpacker::new(data, num_bits);
let bitunpacker = BitUnpacker::new(OwnedBytes::new(data), num_bits);
(bitunpacker, vals)
}

29
src/common/bitset.rs
View File

@@ -33,6 +33,10 @@ impl TinySet {
TinySet(0u64)
}
pub fn clear(&mut self) {
self.0 = 0u64;
}
/// Returns the complement of the set in `[0, 64[`.
fn complement(self) -> TinySet {
TinySet(!self.0)
@@ -43,6 +47,11 @@ impl TinySet {
!self.intersect(TinySet::singleton(el)).is_empty()
}
/// Returns the number of elements in the TinySet.
pub fn len(self) -> u32 {
self.0.count_ones()
}
/// Returns the intersection of `self` and `other`
pub fn intersect(self, other: TinySet) -> TinySet {
TinySet(self.0 & other.0)
@@ -109,22 +118,12 @@ impl TinySet {
pub fn range_greater_or_equal(from_included: u32) -> TinySet {
TinySet::range_lower(from_included).complement()
}
pub fn clear(&mut self) {
self.0 = 0u64;
}
pub fn len(self) -> u32 {
self.0.count_ones()
}
}
#[derive(Clone)]
pub struct BitSet {
tinysets: Box<[TinySet]>,
len: usize, //< Technically it should be u32, but we
// count multiple inserts.
// `usize` guards us from overflow.
len: usize,
max_value: u32,
}
@@ -204,7 +203,7 @@ mod tests {
use super::BitSet;
use super::TinySet;
use crate::docset::DocSet;
use crate::docset::{DocSet, TERMINATED};
use crate::query::BitSetDocSet;
use crate::tests;
use crate::tests::generate_nonunique_unsorted;
@@ -278,11 +277,13 @@ mod tests {
}
assert_eq!(btreeset.len(), bitset.len());
let mut bitset_docset = BitSetDocSet::from(bitset);
let mut remaining = true;
for el in btreeset.into_iter() {
bitset_docset.advance();
assert!(remaining);
assert_eq!(bitset_docset.doc(), el);
remaining = bitset_docset.advance() != TERMINATED;
}
assert!(!bitset_docset.advance());
assert!(!remaining);
}
#[test]

68
src/common/composite_file.rs
View File

@@ -1,14 +1,15 @@
use crate::common::BinarySerializable;
use crate::common::CountingWriter;
use crate::common::VInt;
use crate::directory::ReadOnlySource;
use crate::directory::FileSlice;
use crate::directory::{TerminatingWrite, WritePtr};
use crate::schema::Field;
use crate::space_usage::FieldUsage;
use crate::space_usage::PerFieldSpaceUsage;
use std::collections::HashMap;
use std::io::Write;
use std::io::{self, Read};
use std::io::{self, Read, Write};
use super::HasLen;
#[derive(Eq, PartialEq, Hash, Copy, Ord, PartialOrd, Clone, Debug)]
pub struct FileAddr {
@@ -103,25 +104,26 @@ impl<W: TerminatingWrite + Write> CompositeWrite<W> {
/// for each field.
#[derive(Clone)]
pub struct CompositeFile {
data: ReadOnlySource,
data: FileSlice,
offsets_index: HashMap<FileAddr, (usize, usize)>,
}
impl CompositeFile {
/// Opens a composite file stored in a given
/// `ReadOnlySource`.
pub fn open(data: &ReadOnlySource) -> io::Result<CompositeFile> {
/// `FileSlice`.
pub fn open(data: &FileSlice) -> io::Result<CompositeFile> {
let end = data.len();
let footer_len_data = data.slice_from(end - 4);
let footer_len_data = data.slice_from(end - 4).read_bytes()?;
let footer_len = u32::deserialize(&mut footer_len_data.as_slice())? as usize;
let footer_start = end - 4 - footer_len;
let footer_data = data.slice(footer_start, footer_start + footer_len);
let footer_data = data
.slice(footer_start, footer_start + footer_len)
.read_bytes()?;
let mut footer_buffer = footer_data.as_slice();
let num_fields = VInt::deserialize(&mut footer_buffer)?.0 as usize;
let mut file_addrs = vec![];
let mut offsets = vec![];
let mut field_index = HashMap::new();
let mut offset = 0;
@@ -150,19 +152,19 @@ impl CompositeFile {
pub fn empty() -> CompositeFile {
CompositeFile {
offsets_index: HashMap::new(),
data: ReadOnlySource::empty(),
data: FileSlice::empty(),
}
}
/// Returns the `ReadOnlySource` associated
/// Returns the `FileSlice` associated
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read(&self, field: Field) -> Option<ReadOnlySource> {
pub fn open_read(&self, field: Field) -> Option<FileSlice> {
self.open_read_with_idx(field, 0)
}
/// Returns the `ReadOnlySource` associated
/// Returns the `FileSlice` associated
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<ReadOnlySource> {
pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<FileSlice> {
self.offsets_index
.get(&FileAddr { field, idx })
.map(|&(from, to)| self.data.slice(from, to))
@@ -192,46 +194,44 @@ mod test {
use std::path::Path;
#[test]
fn test_composite_file() {
fn test_composite_file() -> crate::Result<()> {
let path = Path::new("test_path");
let mut directory = RAMDirectory::create();
let directory = RAMDirectory::create();
{
let w = directory.open_write(path).unwrap();
let mut composite_write = CompositeWrite::wrap(w);
{
let mut write_0 = composite_write.for_field(Field::from_field_id(0u32));
VInt(32431123u64).serialize(&mut write_0).unwrap();
write_0.flush().unwrap();
}
{
let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
VInt(2).serialize(&mut write_4).unwrap();
write_4.flush().unwrap();
}
composite_write.close().unwrap();
let mut write_0 = composite_write.for_field(Field::from_field_id(0u32));
VInt(32431123u64).serialize(&mut write_0)?;
write_0.flush()?;
let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
VInt(2).serialize(&mut write_4)?;
write_4.flush()?;
composite_write.close()?;
}
{
let r = directory.open_read(path).unwrap();
let composite_file = CompositeFile::open(&r).unwrap();
let r = directory.open_read(path)?;
let composite_file = CompositeFile::open(&r)?;
{
let file0 = composite_file
.open_read(Field::from_field_id(0u32))
.unwrap();
.unwrap()
.read_bytes()?;
let mut file0_buf = file0.as_slice();
let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0;
let payload_0 = VInt::deserialize(&mut file0_buf)?.0;
assert_eq!(file0_buf.len(), 0);
assert_eq!(payload_0, 32431123u64);
}
{
let file4 = composite_file
.open_read(Field::from_field_id(4u32))
.unwrap();
.unwrap()
.read_bytes()?;
let mut file4_buf = file4.as_slice();
let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
let payload_4 = VInt::deserialize(&mut file4_buf)?.0;
assert_eq!(file4_buf.len(), 0);
assert_eq!(payload_4, 2u64);
}
}
Ok(())
}
}

13
src/common/counting_writer.rs
View File

@@ -20,9 +20,10 @@ impl<W: Write> CountingWriter<W> {
self.written_bytes
}
pub fn finish(mut self) -> io::Result<(W, u64)> {
self.flush()?;
Ok((self.underlying, self.written_bytes))
/// Returns the underlying write object.
/// Note that this method does not trigger any flushing.
pub fn finish(self) -> W {
self.underlying
}
}
@@ -46,7 +47,6 @@ impl<W: Write> Write for CountingWriter<W> {
impl<W: TerminatingWrite> TerminatingWrite for CountingWriter<W> {
fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
self.flush()?;
self.underlying.terminate_ref(token)
}
}
@@ -63,8 +63,9 @@ mod test {
let mut counting_writer = CountingWriter::wrap(buffer);
let bytes = (0u8..10u8).collect::<Vec<u8>>();
counting_writer.write_all(&bytes).unwrap();
let (w, len): (Vec<u8>, u64) = counting_writer.finish().unwrap();
let len = counting_writer.written_bytes();
let buffer_restituted: Vec<u8> = counting_writer.finish();
assert_eq!(len, 10u64);
assert_eq!(w.len(), 10);
assert_eq!(buffer_restituted.len(), 10);
}
}

56
src/common/mod.rs
View File

@@ -10,7 +10,9 @@ pub(crate) use self::bitset::TinySet;
pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
pub use self::counting_writer::CountingWriter;
pub use self::serialize::{BinarySerializable, FixedSize};
pub use self::vint::{read_u32_vint, serialize_vint_u32, write_u32_vint, VInt};
pub use self::vint::{
read_u32_vint, read_u32_vint_no_advance, serialize_vint_u32, write_u32_vint, VInt,
};
pub use byteorder::LittleEndian as Endianness;
/// Segment's max doc must be `< MAX_DOC_LIMIT`.
@@ -18,6 +20,19 @@ pub use byteorder::LittleEndian as Endianness;
/// We do not allow segments with more than
pub const MAX_DOC_LIMIT: u32 = 1 << 31;
pub fn minmax<I, T>(mut vals: I) -> Option<(T, T)>
where
I: Iterator<Item = T>,
T: Copy + Ord,
{
if let Some(first_el) = vals.next() {
return Some(vals.fold((first_el, first_el), |(min_val, max_val), el| {
(min_val.min(el), max_val.max(el))
}));
}
None
}
/// Computes the number of bits that will be used for bitpacking.
///
/// In general the target is the minimum number of bits
@@ -51,10 +66,6 @@ pub(crate) fn compute_num_bits(n: u64) -> u8 {
}
}
pub(crate) fn is_power_of_2(n: usize) -> bool {
(n > 0) && (n & (n - 1) == 0)
}
/// Has length trait
pub trait HasLen {
/// Return length
@@ -104,11 +115,16 @@ pub fn u64_to_i64(val: u64) -> i64 {
/// For simplicity, tantivy internally handles `f64` as `u64`.
/// The mapping is defined by this function.
///
/// Maps `f64` to `u64` so that lexical order is preserved.
/// Maps `f64` to `u64` in a monotonic manner, so that bytes lexical order is preserved.
///
/// This is more suited than simply casting (`val as u64`)
/// which would truncate the result
///
/// # Reference
///
/// Daniel Lemire's [blog post](https://lemire.me/blog/2020/12/14/converting-floating-point-numbers-to-integers-while-preserving-order/)
/// explains the mapping in a clear manner.
///
/// # See also
/// The [reverse mapping is `u64_to_f64`](./fn.u64_to_f64.html).
#[inline(always)]
@@ -134,8 +150,10 @@ pub fn u64_to_f64(val: u64) -> f64 {
#[cfg(test)]
pub(crate) mod test {
pub use super::minmax;
pub use super::serialize::test::fixed_size_test;
use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
use proptest::prelude::*;
use std::f64;
fn test_i64_converter_helper(val: i64) {
@@ -146,6 +164,15 @@ pub(crate) mod test {
assert_eq!(u64_to_f64(f64_to_u64(val)), val);
}
proptest! {
#[test]
fn test_f64_converter_monotonicity_proptest((left, right) in (proptest::num::f64::NORMAL, proptest::num::f64::NORMAL)) {
let left_u64 = f64_to_u64(left);
let right_u64 = f64_to_u64(right);
assert_eq!(left_u64 < right_u64, left < right);
}
}
#[test]
fn test_i64_converter() {
assert_eq!(i64_to_u64(i64::min_value()), u64::min_value());
@@ -199,4 +226,21 @@ pub(crate) mod test {
assert!(((super::MAX_DOC_LIMIT - 1) as i32) >= 0);
assert!((super::MAX_DOC_LIMIT as i32) < 0);
}
#[test]
fn test_minmax_empty() {
let vals: Vec<u32> = vec![];
assert_eq!(minmax(vals.into_iter()), None);
}
#[test]
fn test_minmax_one() {
assert_eq!(minmax(vec![1].into_iter()), Some((1, 1)));
}
#[test]
fn test_minmax_two() {
assert_eq!(minmax(vec![1, 2].into_iter()), Some((1, 2)));
assert_eq!(minmax(vec![2, 1].into_iter()), Some((1, 2)));
}
}

13
src/common/serialize.rs
View File

@@ -89,6 +89,19 @@ impl FixedSize for u64 {
const SIZE_IN_BYTES: usize = 8;
}
impl BinarySerializable for f32 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_f32::<Endianness>(*self)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
reader.read_f32::<Endianness>()
}
}
impl FixedSize for f32 {
const SIZE_IN_BYTES: usize = 4;
}
impl BinarySerializable for i64 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_i64::<Endianness>(*self)

38
src/common/vint.rs
View File

@@ -5,12 +5,12 @@ use std::io::Read;
use std::io::Write;
/// Wrapper over a `u64` that serializes as a variable int.
#[derive(Debug, Eq, PartialEq)]
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
pub struct VInt(pub u64);
const STOP_BIT: u8 = 128;
pub fn serialize_vint_u32(val: u32) -> (u64, usize) {
pub fn serialize_vint_u32(val: u32, buf: &mut [u8; 8]) -> &[u8] {
const START_2: u64 = 1 << 7;
const START_3: u64 = 1 << 14;
const START_4: u64 = 1 << 21;
@@ -29,7 +29,7 @@ pub fn serialize_vint_u32(val: u32) -> (u64, usize) {
let val = u64::from(val);
const STOP_BIT: u64 = 128u64;
match val {
let (res, num_bytes) = match val {
0..=STOP_1 => (val | STOP_BIT, 1),
START_2..=STOP_2 => (
(val & MASK_1) | ((val & MASK_2) << 1) | (STOP_BIT << (8)),
@@ -56,7 +56,9 @@ pub fn serialize_vint_u32(val: u32) -> (u64, usize) {
| (STOP_BIT << (8 * 4)),
5,
),
}
};
LittleEndian::write_u64(&mut buf[..], res);
&buf[0..num_bytes]
}
/// Returns the number of bytes covered by a
@@ -85,23 +87,26 @@ fn vint_len(data: &[u8]) -> usize {
/// If the buffer does not start by a valid
/// vint payload
pub fn read_u32_vint(data: &mut &[u8]) -> u32 {
let vlen = vint_len(*data);
let (result, vlen) = read_u32_vint_no_advance(*data);
*data = &data[vlen..];
result
}
pub fn read_u32_vint_no_advance(data: &[u8]) -> (u32, usize) {
let vlen = vint_len(data);
let mut result = 0u32;
let mut shift = 0u64;
for &b in &data[..vlen] {
result |= u32::from(b & 127u8) << shift;
shift += 7;
}
*data = &data[vlen..];
result
(result, vlen)
}
/// Write a `u32` as a vint payload.
pub fn write_u32_vint<W: io::Write>(val: u32, writer: &mut W) -> io::Result<()> {
let (val, num_bytes) = serialize_vint_u32(val);
let mut buffer = [0u8; 8];
LittleEndian::write_u64(&mut buffer, val);
writer.write_all(&buffer[..num_bytes])
let mut buf = [0u8; 8];
let data = serialize_vint_u32(val, &mut buf);
writer.write_all(&data)
}
impl VInt {
@@ -172,7 +177,6 @@ mod tests {
use super::serialize_vint_u32;
use super::VInt;
use crate::common::BinarySerializable;
use byteorder::{ByteOrder, LittleEndian};
fn aux_test_vint(val: u64) {
let mut v = [14u8; 10];
@@ -208,12 +212,10 @@ mod tests {
fn aux_test_serialize_vint_u32(val: u32) {
let mut buffer = [0u8; 10];
let mut buffer2 = [0u8; 10];
let mut buffer2 = [0u8; 8];
let len_vint = VInt(val as u64).serialize_into(&mut buffer);
let (vint, len) = serialize_vint_u32(val);
assert_eq!(len, len_vint, "len wrong for val {}", val);
LittleEndian::write_u64(&mut buffer2, vint);
assert_eq!(&buffer[..len], &buffer2[..len], "array wrong for {}", val);
let res2 = serialize_vint_u32(val, &mut buffer2);
assert_eq!(&buffer[..len_vint], res2, "array wrong for {}", val);
}
#[test]

39
src/core/executor.rs
View File

@@ -1,6 +1,5 @@
use crate::Result;
use crossbeam::channel;
use scoped_pool::{Pool, ThreadConfig};
use rayon::{ThreadPool, ThreadPoolBuilder};
/// Search executor whether search request are single thread or multithread.
///
@@ -10,8 +9,10 @@ use scoped_pool::{Pool, ThreadConfig};
/// API of a dependency, knowing it might conflict with a different version
/// used by the client. Second, we may stop using rayon in the future.
pub enum Executor {
/// Single thread variant of an Executor
SingleThread,
ThreadPool(Pool),
/// Thread pool variant of an Executor
ThreadPool(ThreadPool),
}
impl Executor {
@@ -20,37 +21,39 @@ impl Executor {
Executor::SingleThread
}
// Creates an Executor that dispatches the tasks in a thread pool.
pub fn multi_thread(num_threads: usize, prefix: &'static str) -> Executor {
let thread_config = ThreadConfig::new().prefix(prefix);
let pool = Pool::with_thread_config(num_threads, thread_config);
Executor::ThreadPool(pool)
/// Creates an Executor that dispatches the tasks in a thread pool.
pub fn multi_thread(num_threads: usize, prefix: &'static str) -> crate::Result<Executor> {
let pool = ThreadPoolBuilder::new()
.num_threads(num_threads)
.thread_name(move |num| format!("{}{}", prefix, num))
.build()?;
Ok(Executor::ThreadPool(pool))
}
// Perform a map in the thread pool.
//
// Regardless of the executor (`SingleThread` or `ThreadPool`), panics in the task
// will propagate to the caller.
/// Perform a map in the thread pool.
///
/// Regardless of the executor (`SingleThread` or `ThreadPool`), panics in the task
/// will propagate to the caller.
pub fn map<
A: Send,
R: Send,
AIterator: Iterator<Item = A>,
F: Sized + Sync + Fn(A) -> Result<R>,
F: Sized + Sync + Fn(A) -> crate::Result<R>,
>(
&self,
f: F,
args: AIterator,
) -> Result<Vec<R>> {
) -> crate::Result<Vec<R>> {
match self {
Executor::SingleThread => args.map(f).collect::<Result<_>>(),
Executor::SingleThread => args.map(f).collect::<crate::Result<_>>(),
Executor::ThreadPool(pool) => {
let args_with_indices: Vec<(usize, A)> = args.enumerate().collect();
let num_fruits = args_with_indices.len();
let fruit_receiver = {
let (fruit_sender, fruit_receiver) = channel::unbounded();
pool.scoped(|scope| {
pool.scope(|scope| {
for arg_with_idx in args_with_indices {
scope.execute(|| {
scope.spawn(|_| {
let (idx, arg) = arg_with_idx;
let fruit = f(arg);
if let Err(err) = fruit_sender.send((idx, fruit)) {
@@ -103,6 +106,7 @@ mod tests {
#[should_panic] //< unfortunately the panic message is not propagated
fn test_panic_propagates_multi_thread() {
let _result: Vec<usize> = Executor::multi_thread(1, "search-test")
.unwrap()
.map(
|_| {
panic!("panic should propagate");
@@ -126,6 +130,7 @@ mod tests {
#[test]
fn test_map_multithread() {
let result: Vec<usize> = Executor::multi_thread(3, "search-test")
.unwrap()
.map(|i| Ok(i * 2), 0..10)
.unwrap();
assert_eq!(result.len(), 10);

228
src/core/index.rs
View File

@@ -1,4 +1,3 @@
use super::segment::create_segment;
use super::segment::Segment;
use crate::core::Executor;
use crate::core::IndexMeta;
@@ -6,6 +5,7 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SegmentMetaInventory;
use crate::core::META_FILEPATH;
use crate::directory::error::OpenReadError;
use crate::directory::ManagedDirectory;
#[cfg(feature = "mmap")]
use crate::directory::MmapDirectory;
@@ -20,26 +20,36 @@ use crate::reader::IndexReaderBuilder;
use crate::schema::Field;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::TokenizerManager;
use crate::tokenizer::{TextAnalyzer, TokenizerManager};
use crate::IndexWriter;
use crate::Result;
use num_cpus;
use std::borrow::BorrowMut;
use std::collections::HashSet;
use std::fmt;
#[cfg(feature = "mmap")]
use std::path::{Path, PathBuf};
use std::path::Path;
use std::path::PathBuf;
use std::sync::Arc;
fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> {
fn load_metas(
directory: &dyn Directory,
inventory: &SegmentMetaInventory,
) -> crate::Result<IndexMeta> {
let meta_data = directory.atomic_read(&META_FILEPATH)?;
let meta_string = String::from_utf8_lossy(&meta_data);
let meta_string = String::from_utf8(meta_data).map_err(|_utf8_err| {
error!("Meta data is not valid utf8.");
DataCorruption::new(
META_FILEPATH.to_path_buf(),
"Meta file does not contain valid utf8 file.".to_string(),
)
})?;
IndexMeta::deserialize(&meta_string, &inventory)
.map_err(|e| {
DataCorruption::new(
META_FILEPATH.to_path_buf(),
format!("Meta file cannot be deserialized. {:?}.", e),
format!(
"Meta file cannot be deserialized. {:?}. Content: {:?}",
e, meta_string
),
)
})
.map_err(From::from)
@@ -56,8 +66,10 @@ pub struct Index {
}
impl Index {
/// Examines the director to see if it contains an index
pub fn exists<Dir: Directory>(dir: &Dir) -> bool {
/// Examines the directory to see if it contains an index.
///
/// Effectively, it only checks for the presence of the `meta.json` file.
pub fn exists<Dir: Directory>(dir: &Dir) -> Result<bool, OpenReadError> {
dir.exists(&META_FILEPATH)
}
@@ -73,15 +85,16 @@ impl Index {
/// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads.
pub fn set_multithread_executor(&mut self, num_threads: usize) {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-"));
pub fn set_multithread_executor(&mut self, num_threads: usize) -> crate::Result<()> {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")?);
Ok(())
}
/// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads.
pub fn set_default_multithread_executor(&mut self) {
pub fn set_default_multithread_executor(&mut self) -> crate::Result<()> {
let default_num_threads = num_cpus::get();
self.set_multithread_executor(default_num_threads);
self.set_multithread_executor(default_num_threads)
}
/// Creates a new index using the `RAMDirectory`.
@@ -98,28 +111,29 @@ impl Index {
///
/// If a previous index was in this directory, then its meta file will be destroyed.
#[cfg(feature = "mmap")]
pub fn create_in_dir<P: AsRef<Path>>(directory_path: P, schema: Schema) -> Result<Index> {
pub fn create_in_dir<P: AsRef<Path>>(
directory_path: P,
schema: Schema,
) -> crate::Result<Index> {
let mmap_directory = MmapDirectory::open(directory_path)?;
if Index::exists(&mmap_directory) {
if Index::exists(&mmap_directory)? {
return Err(TantivyError::IndexAlreadyExists);
}
Index::create(mmap_directory, schema)
}
/// Opens or creates a new index in the provided directory
pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
if Index::exists(&dir) {
let index = Index::open(dir)?;
if index.schema() == schema {
Ok(index)
} else {
Err(TantivyError::SchemaError(
"An index exists but the schema does not match.".to_string(),
))
}
pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
if !Index::exists(&dir)? {
return Index::create(dir, schema);
}
let index = Index::open(dir)?;
if index.schema() == schema {
Ok(index)
} else {
Index::create(dir, schema)
Err(TantivyError::SchemaError(
"An index exists but the schema does not match.".to_string(),
))
}
}
@@ -132,13 +146,15 @@ impl Index {
/// The temp directory is only used for testing the `MmapDirectory`.
/// For other unit tests, prefer the `RAMDirectory`, see: `create_in_ram`.
#[cfg(feature = "mmap")]
pub fn create_from_tempdir(schema: Schema) -> Result<Index> {
pub fn create_from_tempdir(schema: Schema) -> crate::Result<Index> {
let mmap_directory = MmapDirectory::create_from_tempdir()?;
Index::create(mmap_directory, schema)
}
/// Creates a new index given an implementation of the trait `Directory`
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
/// Creates a new index given an implementation of the trait `Directory`.
///
/// If a directory previously existed, it will be erased.
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
let directory = ManagedDirectory::wrap(dir)?;
Index::from_directory(directory, schema)
}
@@ -146,8 +162,8 @@ impl Index {
/// Create a new index from a directory.
///
/// This will overwrite existing meta.json
fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> Result<Index> {
save_new_metas(schema.clone(), directory.borrow_mut())?;
fn from_directory(directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
save_new_metas(schema.clone(), &directory)?;
let metas = IndexMeta::with_schema(schema);
Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
}
@@ -157,7 +173,7 @@ impl Index {
directory: ManagedDirectory,
metas: &IndexMeta,
inventory: SegmentMetaInventory,
) -> Result<Index> {
) -> crate::Result<Index> {
let schema = metas.schema.clone();
Ok(Index {
directory,
@@ -174,11 +190,11 @@ impl Index {
}
/// Helper to access the tokenizer associated to a specific field.
pub fn tokenizer_for_field(&self, field: Field) -> Result<BoxedTokenizer> {
pub fn tokenizer_for_field(&self, field: Field) -> crate::Result<TextAnalyzer> {
let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type();
let tokenizer_manager: &TokenizerManager = self.tokenizers();
let tokenizer_name_opt: Option<BoxedTokenizer> = match field_type {
let tokenizer_name_opt: Option<TextAnalyzer> = match field_type {
FieldType::Str(text_options) => text_options
.get_indexing_options()
.map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -197,7 +213,7 @@ impl Index {
/// Create a default `IndexReader` for the given index.
///
/// See [`Index.reader_builder()`](#method.reader_builder).
pub fn reader(&self) -> Result<IndexReader> {
pub fn reader(&self) -> crate::Result<IndexReader> {
self.reader_builder().try_into()
}
@@ -212,7 +228,7 @@ impl Index {
/// Opens a new directory from an index path.
#[cfg(feature = "mmap")]
pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> Result<Index> {
pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> crate::Result<Index> {
let mmap_directory = MmapDirectory::open(directory_path)?;
Index::open(mmap_directory)
}
@@ -236,7 +252,7 @@ impl Index {
}
/// Open the index using the provided directory
pub fn open<D: Directory>(directory: D) -> Result<Index> {
pub fn open<D: Directory>(directory: D) -> crate::Result<Index> {
let directory = ManagedDirectory::wrap(directory)?;
let inventory = SegmentMetaInventory::default();
let metas = load_metas(&directory, &inventory)?;
@@ -244,7 +260,7 @@ impl Index {
}
/// Reads the index meta file from the directory.
pub fn load_metas(&self) -> Result<IndexMeta> {
pub fn load_metas(&self) -> crate::Result<IndexMeta> {
load_metas(self.directory(), &self.inventory)
}
@@ -272,7 +288,7 @@ impl Index {
&self,
num_threads: usize,
overall_heap_size_in_bytes: usize,
) -> Result<IndexWriter> {
) -> crate::Result<IndexWriter> {
let directory_lock = self
.directory
.acquire_lock(&INDEX_WRITER_LOCK)
@@ -280,7 +296,7 @@ impl Index {
TantivyError::LockFailure(
err,
Some(
"Failed to acquire index lock. If you are using\
"Failed to acquire index lock. If you are using \
a regular directory, this means there is already an \
`IndexWriter` working on this `Directory`, in this process \
or in a different process."
@@ -297,6 +313,15 @@ impl Index {
)
}
/// Helper to create an index writer for tests.
///
/// That index writer only simply has a single thread and a heap of 5 MB.
/// Using a single thread gives us a deterministic allocation of DocId.
#[cfg(test)]
pub fn writer_for_tests(&self) -> crate::Result<IndexWriter> {
self.writer_with_num_threads(1, 10_000_000)
}
/// Creates a multithreaded writer
///
/// Tantivy will automatically define the number of threads to use.
@@ -307,7 +332,7 @@ impl Index {
/// If the lockfile already exists, returns `Error::FileAlreadyExists`.
/// # Panics
/// If the heap size per thread is too small, panics.
pub fn writer(&self, overall_heap_size_in_bytes: usize) -> Result<IndexWriter> {
pub fn writer(&self, overall_heap_size_in_bytes: usize) -> crate::Result<IndexWriter> {
let mut num_threads = num_cpus::get();
let heap_size_in_bytes_per_thread = overall_heap_size_in_bytes / num_threads;
if heap_size_in_bytes_per_thread < HEAP_SIZE_MIN {
@@ -324,7 +349,7 @@ impl Index {
}
/// Returns the list of segments that are searchable
pub fn searchable_segments(&self) -> Result<Vec<Segment>> {
pub fn searchable_segments(&self) -> crate::Result<Vec<Segment>> {
Ok(self
.searchable_segment_metas()?
.into_iter()
@@ -334,7 +359,7 @@ impl Index {
#[doc(hidden)]
pub fn segment(&self, segment_meta: SegmentMeta) -> Segment {
create_segment(self.clone(), segment_meta)
Segment::for_index(self.clone(), segment_meta)
}
/// Creates a new segment.
@@ -357,12 +382,12 @@ impl Index {
/// Reads the meta.json and returns the list of
/// `SegmentMeta` from the last commit.
pub fn searchable_segment_metas(&self) -> Result<Vec<SegmentMeta>> {
pub fn searchable_segment_metas(&self) -> crate::Result<Vec<SegmentMeta>> {
Ok(self.load_metas()?.segments)
}
/// Returns the list of segment ids that are searchable.
pub fn searchable_segment_ids(&self) -> Result<Vec<SegmentId>> {
pub fn searchable_segment_ids(&self) -> crate::Result<Vec<SegmentId>> {
Ok(self
.searchable_segment_metas()?
.iter()
@@ -371,7 +396,7 @@ impl Index {
}
/// Returns the set of corrupted files
pub fn validate_checksum(&self) -> Result<HashSet<PathBuf>> {
pub fn validate_checksum(&self) -> crate::Result<HashSet<PathBuf>> {
self.directory.list_damaged().map_err(Into::into)
}
}
@@ -384,15 +409,12 @@ impl fmt::Debug for Index {
#[cfg(test)]
mod tests {
use crate::directory::RAMDirectory;
use crate::directory::{RAMDirectory, WatchCallback};
use crate::schema::Field;
use crate::schema::{Schema, INDEXED, TEXT};
use crate::Index;
use crate::IndexReader;
use crate::IndexWriter;
use crate::ReloadPolicy;
use std::thread;
use std::time::Duration;
use crate::{Directory, Index};
#[test]
fn test_indexer_for_field() {
@@ -411,24 +433,24 @@ mod tests {
#[test]
fn test_index_exists() {
let directory = RAMDirectory::create();
assert!(!Index::exists(&directory));
assert!(!Index::exists(&directory).unwrap());
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::exists(&directory).unwrap());
}
#[test]
fn open_or_create_should_create() {
let directory = RAMDirectory::create();
assert!(!Index::exists(&directory));
assert!(!Index::exists(&directory).unwrap());
assert!(Index::open_or_create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::exists(&directory).unwrap());
}
#[test]
fn open_or_create_should_open() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::exists(&directory).unwrap());
assert!(Index::open_or_create(directory, throw_away_schema()).is_ok());
}
@@ -436,7 +458,7 @@ mod tests {
fn create_should_wipeoff_existing() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::exists(&directory).unwrap());
assert!(Index::create(directory.clone(), Schema::builder().build()).is_ok());
}
@@ -444,7 +466,7 @@ mod tests {
fn open_or_create_exists_but_schema_does_not_match() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::exists(&directory).unwrap());
assert!(Index::open_or_create(directory.clone(), throw_away_schema()).is_ok());
let err = Index::open_or_create(directory, Schema::builder().build());
assert_eq!(
@@ -470,14 +492,14 @@ mod tests {
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
}
#[cfg(feature = "mmap")]
mod mmap_specific {
use super::*;
use crate::Directory;
use std::path::PathBuf;
use tempfile::TempDir;
@@ -488,36 +510,38 @@ mod tests {
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
}
#[test]
fn test_index_manual_policy_mmap() {
fn test_index_manual_policy_mmap() -> crate::Result<()> {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let index = Index::create_from_tempdir(schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let mut index = Index::create_from_tempdir(schema)?;
let mut writer = index.writer_for_tests()?;
writer.commit()?;
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
.try_into()?;
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
writer.commit().unwrap();
thread::sleep(Duration::from_millis(500));
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = index.directory_mut().watch(WatchCallback::new(move || {
let _ = sender.send(());
}));
writer.commit()?;
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 0);
reader.reload().unwrap();
reader.reload()?;
assert_eq!(reader.searcher().num_docs(), 1);
Ok(())
}
#[test]
@@ -534,39 +558,38 @@ mod tests {
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
let mut writer = write_index.writer_with_num_threads(1, 3_000_000).unwrap();
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
test_index_on_commit_reload_policy_aux(field, &write_index, &reader);
}
}
fn test_index_on_commit_reload_policy_aux(
field: Field,
writer: &mut IndexWriter,
reader: &IndexReader,
) {
fn test_index_on_commit_reload_policy_aux(field: Field, index: &Index, reader: &IndexReader) {
let mut reader_index = reader.index();
let (sender, receiver) = crossbeam::channel::unbounded();
let _watch_handle = reader_index
.directory_mut()
.watch(WatchCallback::new(move || {
let _ = sender.send(());
}));
let mut writer = index.writer_for_tests().unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
writer.commit().unwrap();
let mut count = 0;
for _ in 0..100 {
count = reader.searcher().num_docs();
if count > 0 {
// We need a loop here because it is possible for notify to send more than
// one modify event. It was observed on CI on MacOS.
loop {
assert!(receiver.recv().is_ok());
if reader.searcher().num_docs() == 1 {
break;
}
thread::sleep(Duration::from_millis(100));
}
assert_eq!(count, 1);
writer.add_document(doc!(field=>2u64));
writer.commit().unwrap();
let mut count = 0;
for _ in 0..10 {
count = reader.searcher().num_docs();
if count > 1 {
// ... Same as above
loop {
assert!(receiver.recv().is_ok());
if reader.searcher().num_docs() == 2 {
break;
}
thread::sleep(Duration::from_millis(100));
}
assert_eq!(count, 2);
}
// This test will not pass on windows, because windows
@@ -583,9 +606,13 @@ mod tests {
for i in 0u64..8_000u64 {
writer.add_document(doc!(field => i));
}
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = directory.watch(WatchCallback::new(move || {
let _ = sender.send(());
}));
writer.commit().unwrap();
let mem_right_after_commit = directory.total_mem_usage();
thread::sleep(Duration::from_millis(1_000));
assert!(receiver.recv().is_ok());
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
@@ -599,6 +626,11 @@ mod tests {
reader.reload().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 8_000);
assert!(mem_right_after_merge_finished < mem_right_after_commit);
assert!(
mem_right_after_merge_finished < mem_right_after_commit,
"(mem after merge){} is expected < (mem before merge){}",
mem_right_after_merge_finished,
mem_right_after_commit
);
}
}

25
src/core/index_meta.rs
View File

@@ -3,8 +3,7 @@ use crate::core::SegmentId;
use crate::schema::Schema;
use crate::Opstamp;
use census::{Inventory, TrackedObject};
use serde;
use serde_json;
use serde::{Deserialize, Serialize};
use std::collections::HashSet;
use std::fmt;
use std::path::PathBuf;
@@ -150,6 +149,21 @@ impl SegmentMeta {
self.num_deleted_docs() > 0
}
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> SegmentMeta {
assert_eq!(self.tracked.max_doc, 0);
assert!(self.tracked.deletes.is_none());
let tracked = self.tracked.map(move |inner_meta| InnerSegmentMeta {
segment_id: inner_meta.segment_id,
max_doc,
deletes: None,
});
SegmentMeta { tracked }
}
#[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta {
let delete_meta = DeleteMeta {
@@ -199,7 +213,7 @@ pub struct IndexMeta {
#[serde(skip_serializing_if = "Option::is_none")]
/// Payload associated to the last commit.
///
/// Upon commit, clients can optionally add a small `Striing` payload to their commit
/// Upon commit, clients can optionally add a small `String` payload to their commit
/// to help identify this commit.
/// This payload is entirely unused by tantivy.
pub payload: Option<String>,
@@ -285,6 +299,9 @@ mod tests {
payload: None,
};
let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
assert_eq!(json, r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#);
assert_eq!(
json,
r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#
);
}
}

117
src/core/inverted_index_reader.rs
View File

@@ -1,13 +1,13 @@
use std::io;
use crate::common::BinarySerializable;
use crate::directory::ReadOnlySource;
use crate::directory::FileSlice;
use crate::positions::PositionReader;
use crate::postings::TermInfo;
use crate::postings::{BlockSegmentPostings, SegmentPostings};
use crate::schema::FieldType;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::termdict::TermDictionary;
use owned_read::OwnedRead;
/// The inverted index reader is in charge of accessing
/// the inverted index associated to a specific field.
@@ -16,7 +16,7 @@ use owned_read::OwnedRead;
///
/// It is safe to delete the segment associated to
/// an `InvertedIndexReader`. As long as it is open,
/// the `ReadOnlySource` it is relying on should
/// the `FileSlice` it is relying on should
/// stay available.
///
///
@@ -24,9 +24,9 @@ use owned_read::OwnedRead;
/// the `SegmentReader`'s [`.inverted_index(...)`] method
pub struct InvertedIndexReader {
termdict: TermDictionary,
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
postings_file_slice: FileSlice,
positions_file_slice: FileSlice,
positions_idx_file_slice: FileSlice,
record_option: IndexRecordOption,
total_num_tokens: u64,
}
@@ -35,42 +35,38 @@ impl InvertedIndexReader {
#[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))] // for symmetry
pub(crate) fn new(
termdict: TermDictionary,
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
postings_file_slice: FileSlice,
positions_file_slice: FileSlice,
positions_idx_file_slice: FileSlice,
record_option: IndexRecordOption,
) -> InvertedIndexReader {
let total_num_tokens_data = postings_source.slice(0, 8);
let mut total_num_tokens_cursor = total_num_tokens_data.as_slice();
let total_num_tokens = u64::deserialize(&mut total_num_tokens_cursor).unwrap_or(0u64);
InvertedIndexReader {
) -> io::Result<InvertedIndexReader> {
let (total_num_tokens_slice, postings_body) = postings_file_slice.split(8);
let total_num_tokens = u64::deserialize(&mut total_num_tokens_slice.read_bytes()?)?;
Ok(InvertedIndexReader {
termdict,
postings_source: postings_source.slice_from(8),
positions_source,
positions_idx_source,
postings_file_slice: postings_body,
positions_file_slice,
positions_idx_file_slice,
record_option,
total_num_tokens,
}
})
}
/// Creates an empty `InvertedIndexReader` object, which
/// contains no terms at all.
pub fn empty(field_type: &FieldType) -> InvertedIndexReader {
let record_option = field_type
.get_index_record_option()
.unwrap_or(IndexRecordOption::Basic);
pub fn empty(record_option: IndexRecordOption) -> InvertedIndexReader {
InvertedIndexReader {
termdict: TermDictionary::empty(&field_type),
postings_source: ReadOnlySource::empty(),
positions_source: ReadOnlySource::empty(),
positions_idx_source: ReadOnlySource::empty(),
termdict: TermDictionary::empty(),
postings_file_slice: FileSlice::empty(),
positions_file_slice: FileSlice::empty(),
positions_idx_file_slice: FileSlice::empty(),
record_option,
total_num_tokens: 0u64,
}
}
/// Returns the term info associated with the term.
pub fn get_term_info(&self, term: &Term) -> Option<TermInfo> {
pub fn get_term_info(&self, term: &Term) -> io::Result<Option<TermInfo>> {
self.termdict.get(term.value_bytes())
}
@@ -93,12 +89,12 @@ impl InvertedIndexReader {
&self,
term_info: &TermInfo,
block_postings: &mut BlockSegmentPostings,
) {
let offset = term_info.postings_offset as usize;
let end_source = self.postings_source.len();
let postings_slice = self.postings_source.slice(offset, end_source);
let postings_reader = OwnedRead::new(postings_slice);
block_postings.reset(term_info.doc_freq, postings_reader);
) -> io::Result<()> {
let start_offset = term_info.postings_start_offset as usize;
let stop_offset = term_info.postings_stop_offset as usize;
let postings_slice = self.postings_file_slice.slice(start_offset, stop_offset);
block_postings.reset(term_info.doc_freq, postings_slice.read_bytes()?);
Ok(())
}
/// Returns a block postings given a `Term`.
@@ -109,9 +105,10 @@ impl InvertedIndexReader {
&self,
term: &Term,
option: IndexRecordOption,
) -> Option<BlockSegmentPostings> {
self.get_term_info(term)
) -> io::Result<Option<BlockSegmentPostings>> {
self.get_term_info(term)?
.map(move |term_info| self.read_block_postings_from_terminfo(&term_info, option))
.transpose()
}
/// Returns a block postings given a `term_info`.
@@ -122,12 +119,14 @@ impl InvertedIndexReader {
&self,
term_info: &TermInfo,
requested_option: IndexRecordOption,
) -> BlockSegmentPostings {
let offset = term_info.postings_offset as usize;
let postings_data = self.postings_source.slice_from(offset);
BlockSegmentPostings::from_data(
) -> io::Result<BlockSegmentPostings> {
let postings_data = self.postings_file_slice.slice(
term_info.postings_start_offset as usize,
term_info.postings_stop_offset as usize,
);
BlockSegmentPostings::open(
term_info.doc_freq,
OwnedRead::new(postings_data),
postings_data,
self.record_option,
requested_option,
)
@@ -141,20 +140,23 @@ impl InvertedIndexReader {
&self,
term_info: &TermInfo,
option: IndexRecordOption,
) -> SegmentPostings {
let block_postings = self.read_block_postings_from_terminfo(term_info, option);
) -> io::Result<SegmentPostings> {
let block_postings = self.read_block_postings_from_terminfo(term_info, option)?;
let position_stream = {
if option.has_positions() {
let position_reader = self.positions_source.clone();
let skip_reader = self.positions_idx_source.clone();
let position_reader = self.positions_file_slice.clone();
let skip_reader = self.positions_idx_file_slice.clone();
let position_reader =
PositionReader::new(position_reader, skip_reader, term_info.positions_idx);
PositionReader::new(position_reader, skip_reader, term_info.positions_idx)?;
Some(position_reader)
} else {
None
}
};
SegmentPostings::from_block_postings(block_postings, position_stream)
Ok(SegmentPostings::from_block_postings(
block_postings,
position_stream,
))
}
/// Returns the total number of tokens recorded for all documents
@@ -173,24 +175,31 @@ impl InvertedIndexReader {
/// For instance, requesting `IndexRecordOption::Freq` for a
/// `TextIndexingOptions` that does not index position will return a `SegmentPostings`
/// with `DocId`s and frequencies.
pub fn read_postings(&self, term: &Term, option: IndexRecordOption) -> Option<SegmentPostings> {
self.get_term_info(term)
pub fn read_postings(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
self.get_term_info(term)?
.map(move |term_info| self.read_postings_from_terminfo(&term_info, option))
.transpose()
}
pub(crate) fn read_postings_no_deletes(
&self,
term: &Term,
option: IndexRecordOption,
) -> Option<SegmentPostings> {
self.get_term_info(term)
) -> io::Result<Option<SegmentPostings>> {
self.get_term_info(term)?
.map(|term_info| self.read_postings_from_terminfo(&term_info, option))
.transpose()
}
/// Returns the number of documents containing the term.
pub fn doc_freq(&self, term: &Term) -> u32 {
self.get_term_info(term)
pub fn doc_freq(&self, term: &Term) -> io::Result<u32> {
Ok(self
.get_term_info(term)?
.map(|term_info| term_info.doc_freq)
.unwrap_or(0u32)
.unwrap_or(0u32))
}
}

112
src/core/searcher.rs
View File

@@ -1,42 +1,17 @@
use crate::collector::Collector;
use crate::collector::SegmentCollector;
use crate::core::Executor;
use crate::core::InvertedIndexReader;
use crate::core::SegmentReader;
use crate::query::Query;
use crate::query::Scorer;
use crate::query::Weight;
use crate::schema::Document;
use crate::schema::Schema;
use crate::schema::{Field, Term};
use crate::schema::Term;
use crate::space_usage::SearcherSpaceUsage;
use crate::store::StoreReader;
use crate::termdict::TermMerger;
use crate::DocAddress;
use crate::Index;
use crate::Result;
use std::fmt;
use std::sync::Arc;
fn collect_segment<C: Collector>(
collector: &C,
weight: &dyn Weight,
segment_ord: u32,
segment_reader: &SegmentReader,
) -> Result<C::Fruit> {
let mut scorer = weight.scorer(segment_reader)?;
let mut segment_collector = collector.for_segment(segment_ord as u32, segment_reader)?;
if let Some(delete_bitset) = segment_reader.delete_bitset() {
scorer.for_each(&mut |doc, score| {
if delete_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
}
});
} else {
scorer.for_each(&mut |doc, score| segment_collector.collect(doc, score));
}
Ok(segment_collector.harvest())
}
use std::{fmt, io};
/// Holds a list of `SegmentReader`s ready for search.
///
@@ -56,17 +31,17 @@ impl Searcher {
schema: Schema,
index: Index,
segment_readers: Vec<SegmentReader>,
) -> Searcher {
let store_readers = segment_readers
) -> io::Result<Searcher> {
let store_readers: Vec<StoreReader> = segment_readers
.iter()
.map(SegmentReader::get_store_reader)
.collect();
Searcher {
.collect::<io::Result<Vec<_>>>()?;
Ok(Searcher {
schema,
index,
segment_readers,
store_readers,
}
})
}
/// Returns the `Index` associated to the `Searcher`
@@ -78,7 +53,7 @@ impl Searcher {
///
/// The searcher uses the segment ordinal to route the
/// the request to the right `Segment`.
pub fn doc(&self, doc_address: DocAddress) -> Result<Document> {
pub fn doc(&self, doc_address: DocAddress) -> crate::Result<Document> {
let DocAddress(segment_local_id, doc_id) = doc_address;
let store_reader = &self.store_readers[segment_local_id as usize];
store_reader.get(doc_id)
@@ -99,13 +74,14 @@ impl Searcher {
/// Return the overall number of documents containing
/// the given term.
pub fn doc_freq(&self, term: &Term) -> u64 {
self.segment_readers
.iter()
.map(|segment_reader| {
u64::from(segment_reader.inverted_index(term.field()).doc_freq(term))
})
.sum::<u64>()
pub fn doc_freq(&self, term: &Term) -> crate::Result<u64> {
let mut total_doc_freq = 0;
for segment_reader in &self.segment_readers {
let inverted_index = segment_reader.inverted_index(term.field())?;
let doc_freq = inverted_index.doc_freq(term)?;
total_doc_freq += u64::from(doc_freq);
}
Ok(total_doc_freq)
}
/// Return the list of segment readers
@@ -132,7 +108,11 @@ impl Searcher {
///
/// Finally, the Collector merges each of the child collectors into itself for result usability
/// by the caller.
pub fn search<C: Collector>(&self, query: &dyn Query, collector: &C) -> Result<C::Fruit> {
pub fn search<C: Collector>(
&self,
query: &dyn Query,
collector: &C,
) -> crate::Result<C::Fruit> {
let executor = self.index.search_executor();
self.search_with_executor(query, collector, executor)
}
@@ -154,62 +134,26 @@ impl Searcher {
query: &dyn Query,
collector: &C,
executor: &Executor,
) -> Result<C::Fruit> {
) -> crate::Result<C::Fruit> {
let scoring_enabled = collector.requires_scoring();
let weight = query.weight(self, scoring_enabled)?;
let segment_readers = self.segment_readers();
let fruits = executor.map(
|(segment_ord, segment_reader)| {
collect_segment(
collector,
weight.as_ref(),
segment_ord as u32,
segment_reader,
)
collector.collect_segment(weight.as_ref(), segment_ord as u32, segment_reader)
},
segment_readers.iter().enumerate(),
)?;
collector.merge_fruits(fruits)
}
/// Return the field searcher associated to a `Field`.
pub fn field(&self, field: Field) -> FieldSearcher {
let inv_index_readers = self
.segment_readers
.iter()
.map(|segment_reader| segment_reader.inverted_index(field))
.collect::<Vec<_>>();
FieldSearcher::new(inv_index_readers)
}
/// Summarize total space usage of this searcher.
pub fn space_usage(&self) -> SearcherSpaceUsage {
pub fn space_usage(&self) -> io::Result<SearcherSpaceUsage> {
let mut space_usage = SearcherSpaceUsage::new();
for segment_reader in self.segment_readers.iter() {
space_usage.add_segment(segment_reader.space_usage());
for segment_reader in &self.segment_readers {
space_usage.add_segment(segment_reader.space_usage()?);
}
space_usage
}
}
pub struct FieldSearcher {
inv_index_readers: Vec<Arc<InvertedIndexReader>>,
}
impl FieldSearcher {
fn new(inv_index_readers: Vec<Arc<InvertedIndexReader>>) -> FieldSearcher {
FieldSearcher { inv_index_readers }
}
/// Returns a Stream over all of the sorted unique terms of
/// for the given field.
pub fn terms(&self) -> TermMerger<'_> {
let term_streamers: Vec<_> = self
.inv_index_readers
.iter()
.map(|inverted_index| inverted_index.terms().stream())
.collect();
TermMerger::new(term_streamers)
Ok(space_usage)
}
}

43
src/core/segment.rs
View File

@@ -4,14 +4,12 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::directory::error::{OpenReadError, OpenWriteError};
use crate::directory::Directory;
use crate::directory::{ReadOnlySource, WritePtr};
use crate::directory::{FileSlice, WritePtr};
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::schema::Schema;
use crate::Opstamp;
use crate::Result;
use std::fmt;
use std::path::PathBuf;
use std::result;
/// A segment is a piece of the index.
#[derive(Clone)]
@@ -26,15 +24,12 @@ impl fmt::Debug for Segment {
}
}
/// Creates a new segment given an `Index` and a `SegmentId`
///
/// The function is here to make it private outside `tantivy`.
/// #[doc(hidden)]
pub fn create_segment(index: Index, meta: SegmentMeta) -> Segment {
Segment { index, meta }
}
impl Segment {
/// Creates a new segment given an `Index` and a `SegmentId`
pub(crate) fn for_index(index: Index, meta: SegmentMeta) -> Segment {
Segment { index, meta }
}
/// Returns the index the segment belongs to.
pub fn index(&self) -> &Index {
&self.index
@@ -50,6 +45,17 @@ impl Segment {
&self.meta
}
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> Segment {
Segment {
index: self.index,
meta: self.meta.with_max_doc(max_doc),
}
}
#[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment {
Segment {
@@ -72,20 +78,13 @@ impl Segment {
}
/// Open one of the component file for a *regular* read.
pub fn open_read(
&self,
component: SegmentComponent,
) -> result::Result<ReadOnlySource, OpenReadError> {
pub fn open_read(&self, component: SegmentComponent) -> Result<FileSlice, OpenReadError> {
let path = self.relative_path(component);
let source = self.index.directory().open_read(&path)?;
Ok(source)
self.index.directory().open_read(&path)
}
/// Open one of the component file for *regular* write.
pub fn open_write(
&mut self,
component: SegmentComponent,
) -> result::Result<WritePtr, OpenWriteError> {
pub fn open_write(&mut self, component: SegmentComponent) -> Result<WritePtr, OpenWriteError> {
let path = self.relative_path(component);
let write = self.index.directory_mut().open_write(&path)?;
Ok(write)
@@ -98,5 +97,5 @@ pub trait SerializableSegment {
///
/// # Returns
/// The number of documents in the segment.
fn write(&self, serializer: SegmentSerializer) -> Result<u32>;
fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32>;
}

2
src/core/segment_component.rs
View File

@@ -20,7 +20,7 @@ pub enum SegmentComponent {
/// Dictionary associating `Term`s to `TermInfo`s which is
/// simply an address into the `postings` file and the `positions` file.
TERMS,
/// Row-oriented, LZ4-compressed storage of the documents.
/// Row-oriented, compressed storage of the documents.
/// Accessing a document from the store is relatively slow, as it
/// requires to decompress the entire block it belongs to.
STORE,

1
src/core/segment_id.rs
View File

@@ -4,6 +4,7 @@ use uuid::Uuid;
#[cfg(test)]
use once_cell::sync::Lazy;
use serde::{Deserialize, Serialize};
use std::error::Error;
use std::str::FromStr;
#[cfg(test)]

207
src/core/segment_reader.rs
View File

@@ -1,27 +1,26 @@
use crate::common::CompositeFile;
use crate::common::HasLen;
use crate::core::InvertedIndexReader;
use crate::core::Segment;
use crate::core::SegmentComponent;
use crate::core::SegmentId;
use crate::directory::ReadOnlySource;
use crate::directory::FileSlice;
use crate::fastfield::DeleteBitSet;
use crate::fastfield::FacetReader;
use crate::fastfield::FastFieldReaders;
use crate::fieldnorm::FieldNormReader;
use crate::schema::Field;
use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::schema::{Field, IndexRecordOption};
use crate::space_usage::SegmentSpaceUsage;
use crate::store::StoreReader;
use crate::termdict::TermDictionary;
use crate::DocId;
use crate::Result;
use crate::{common::CompositeFile, error::DataCorruption};
use fail::fail_point;
use std::collections::HashMap;
use std::fmt;
use std::sync::Arc;
use std::sync::RwLock;
use std::{collections::HashMap, io};
/// Entry point to access all of the datastructures of the `Segment`
///
@@ -49,9 +48,9 @@ pub struct SegmentReader {
positions_composite: CompositeFile,
positions_idx_composite: CompositeFile,
fast_fields_readers: Arc<FastFieldReaders>,
fieldnorms_composite: CompositeFile,
fieldnorm_readers: FieldNormReaders,
store_source: ReadOnlySource,
store_file: FileSlice,
delete_bitset_opt: Option<DeleteBitSet>,
schema: Schema,
}
@@ -107,16 +106,21 @@ impl SegmentReader {
}
/// Accessor to the `FacetReader` associated to a given `Field`.
pub fn facet_reader(&self, field: Field) -> Option<FacetReader> {
pub fn facet_reader(&self, field: Field) -> crate::Result<FacetReader> {
let field_entry = self.schema.get_field_entry(field);
if field_entry.field_type() != &FieldType::HierarchicalFacet {
return None;
return Err(crate::TantivyError::InvalidArgument(format!(
"Field {:?} is not a facet field.",
field_entry.name()
)));
}
let term_ords_reader = self.fast_fields().u64s(field)?;
let termdict_source = self.termdict_composite.open_read(field)?;
let termdict = TermDictionary::from_source(&termdict_source);
let facet_reader = FacetReader::new(term_ords_reader, termdict);
Some(facet_reader)
let termdict = self
.termdict_composite
.open_read(field)
.map(TermDictionary::open)
.unwrap_or_else(|| Ok(TermDictionary::empty()))?;
Ok(FacetReader::new(term_ords_reader, termdict))
}
/// Accessor to the segment's `Field norms`'s reader.
@@ -126,47 +130,45 @@ impl SegmentReader {
///
/// They are simply stored as a fast field, serialized in
/// the `.fieldnorm` file of the segment.
pub fn get_fieldnorms_reader(&self, field: Field) -> FieldNormReader {
if let Some(fieldnorm_source) = self.fieldnorms_composite.open_read(field) {
FieldNormReader::open(fieldnorm_source)
} else {
pub fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader> {
self.fieldnorm_readers.get_field(field)?.ok_or_else(|| {
let field_name = self.schema.get_field_name(field);
let err_msg = format!(
"Field norm not found for field {:?}. Was it market as indexed during indexing.",
"Field norm not found for field {:?}. Was it marked as indexed during indexing?",
field_name
);
panic!(err_msg);
}
crate::TantivyError::SchemaError(err_msg)
})
}
/// Accessor to the segment's `StoreReader`.
pub fn get_store_reader(&self) -> StoreReader {
StoreReader::from_source(self.store_source.clone())
pub fn get_store_reader(&self) -> io::Result<StoreReader> {
StoreReader::open(self.store_file.clone())
}
/// Open a new segment for reading.
pub fn open(segment: &Segment) -> Result<SegmentReader> {
let termdict_source = segment.open_read(SegmentComponent::TERMS)?;
let termdict_composite = CompositeFile::open(&termdict_source)?;
pub fn open(segment: &Segment) -> crate::Result<SegmentReader> {
let termdict_file = segment.open_read(SegmentComponent::TERMS)?;
let termdict_composite = CompositeFile::open(&termdict_file)?;
let store_source = segment.open_read(SegmentComponent::STORE)?;
let store_file = segment.open_read(SegmentComponent::STORE)?;
fail_point!("SegmentReader::open#middle");
let postings_source = segment.open_read(SegmentComponent::POSTINGS)?;
let postings_composite = CompositeFile::open(&postings_source)?;
let postings_file = segment.open_read(SegmentComponent::POSTINGS)?;
let postings_composite = CompositeFile::open(&postings_file)?;
let positions_composite = {
if let Ok(source) = segment.open_read(SegmentComponent::POSITIONS) {
CompositeFile::open(&source)?
if let Ok(positions_file) = segment.open_read(SegmentComponent::POSITIONS) {
CompositeFile::open(&positions_file)?
} else {
CompositeFile::empty()
}
};
let positions_idx_composite = {
if let Ok(source) = segment.open_read(SegmentComponent::POSITIONSSKIP) {
CompositeFile::open(&source)?
if let Ok(positions_skip_file) = segment.open_read(SegmentComponent::POSITIONSSKIP) {
CompositeFile::open(&positions_skip_file)?
} else {
CompositeFile::empty()
}
@@ -176,29 +178,32 @@ impl SegmentReader {
let fast_fields_data = segment.open_read(SegmentComponent::FASTFIELDS)?;
let fast_fields_composite = CompositeFile::open(&fast_fields_data)?;
let fast_field_readers =
Arc::new(FastFieldReaders::load_all(&schema, &fast_fields_composite)?);
let fast_field_readers = Arc::new(FastFieldReaders::new(
schema.clone(),
fast_fields_composite,
)?);
let fieldnorms_data = segment.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorms_composite = CompositeFile::open(&fieldnorms_data)?;
let fieldnorm_data = segment.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
let delete_bitset_opt = if segment.meta().has_deletes() {
let delete_data = segment.open_read(SegmentComponent::DELETE)?;
Some(DeleteBitSet::open(delete_data))
let delete_bitset = DeleteBitSet::open(delete_data)?;
Some(delete_bitset)
} else {
None
};
Ok(SegmentReader {
inv_idx_reader_cache: Arc::new(RwLock::new(HashMap::new())),
inv_idx_reader_cache: Default::default(),
max_doc: segment.meta().max_doc(),
num_docs: segment.meta().num_docs(),
termdict_composite,
postings_composite,
fast_fields_readers: fast_field_readers,
fieldnorms_composite,
fieldnorm_readers,
segment_id: segment.id(),
store_source,
store_file,
delete_bitset_opt,
positions_composite,
positions_idx_composite,
@@ -213,58 +218,64 @@ impl SegmentReader {
/// The field reader is in charge of iterating through the
/// term dictionary associated to a specific field,
/// and opening the posting list associated to any term.
pub fn inverted_index(&self, field: Field) -> Arc<InvertedIndexReader> {
///
/// If the field is marked as index, a warn is logged and an empty `InvertedIndexReader`
/// is returned.
/// Similarly if the field is marked as indexed but no term has been indexed for the given
/// index. an empty `InvertedIndexReader` is returned (but no warning is logged).
pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
if let Some(inv_idx_reader) = self
.inv_idx_reader_cache
.read()
.expect("Lock poisoned. This should never happen")
.get(&field)
{
return Arc::clone(inv_idx_reader);
return Ok(Arc::clone(inv_idx_reader));
}
let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type();
let record_option_opt = field_type.get_index_record_option();
if record_option_opt.is_none() {
panic!("Field {:?} does not seem indexed.", field_entry.name());
warn!("Field {:?} does not seem indexed.", field_entry.name());
}
let record_option = record_option_opt.unwrap();
let postings_file_opt = self.postings_composite.open_read(field);
let postings_source_opt = self.postings_composite.open_read(field);
if postings_source_opt.is_none() {
if postings_file_opt.is_none() || record_option_opt.is_none() {
// no documents in the segment contained this field.
// As a result, no data is associated to the inverted index.
//
// Returns an empty inverted index.
return Arc::new(InvertedIndexReader::empty(field_type));
let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
return Ok(Arc::new(InvertedIndexReader::empty(record_option)));
}
let postings_source = postings_source_opt.unwrap();
let record_option = record_option_opt.unwrap();
let postings_file = postings_file_opt.unwrap();
let termdict_source = self.termdict_composite.open_read(field).expect(
"Failed to open field term dictionary in composite file. Is the field indexed?",
);
let termdict_file: FileSlice = self.termdict_composite.open_read(field)
.ok_or_else(||
DataCorruption::comment_only(format!("Failed to open field {:?}'s term dictionary in the composite file. Has the schema been modified?", field_entry.name()))
)?;
let positions_source = self
let positions_file = self
.positions_composite
.open_read(field)
.expect("Index corrupted. Failed to open field positions in composite file.");
let positions_idx_source = self
let positions_idx_file = self
.positions_idx_composite
.open_read(field)
.expect("Index corrupted. Failed to open field positions in composite file.");
let inv_idx_reader = Arc::new(InvertedIndexReader::new(
TermDictionary::from_source(&termdict_source),
postings_source,
positions_source,
positions_idx_source,
TermDictionary::open(termdict_file)?,
postings_file,
positions_file,
positions_idx_file,
record_option,
));
)?);
// by releasing the lock in between, we may end up opening the inverting index
// twice, but this is fine.
@@ -273,7 +284,7 @@ impl SegmentReader {
.expect("Field reader cache lock poisoned. This should never happen.")
.insert(field, Arc::clone(&inv_idx_reader));
inv_idx_reader
Ok(inv_idx_reader)
}
/// Returns the segment id
@@ -296,26 +307,26 @@ impl SegmentReader {
}
/// Returns an iterator that will iterate over the alive document ids
pub fn doc_ids_alive(&self) -> SegmentReaderAliveDocsIterator<'_> {
SegmentReaderAliveDocsIterator::new(&self)
pub fn doc_ids_alive(&self) -> impl Iterator<Item = DocId> + '_ {
(0u32..self.max_doc).filter(move |doc| !self.is_deleted(*doc))
}
/// Summarize total space usage of this segment.
pub fn space_usage(&self) -> SegmentSpaceUsage {
SegmentSpaceUsage::new(
pub fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
Ok(SegmentSpaceUsage::new(
self.num_docs(),
self.termdict_composite.space_usage(),
self.postings_composite.space_usage(),
self.positions_composite.space_usage(),
self.positions_idx_composite.space_usage(),
self.fast_fields_readers.space_usage(),
self.fieldnorms_composite.space_usage(),
self.get_store_reader().space_usage(),
self.fieldnorm_readers.space_usage(),
self.get_store_reader()?.space_usage(),
self.delete_bitset_opt
.as_ref()
.map(DeleteBitSet::space_usage)
.unwrap_or(0),
)
))
}
}
@@ -325,52 +336,6 @@ impl fmt::Debug for SegmentReader {
}
}
/// Implements the iterator trait to allow easy iteration
/// over non-deleted ("alive") DocIds in a SegmentReader
pub struct SegmentReaderAliveDocsIterator<'a> {
reader: &'a SegmentReader,
max_doc: DocId,
current: DocId,
}
impl<'a> SegmentReaderAliveDocsIterator<'a> {
pub fn new(reader: &'a SegmentReader) -> SegmentReaderAliveDocsIterator<'a> {
SegmentReaderAliveDocsIterator {
reader,
max_doc: reader.max_doc(),
current: 0,
}
}
}
impl<'a> Iterator for SegmentReaderAliveDocsIterator<'a> {
type Item = DocId;
fn next(&mut self) -> Option<Self::Item> {
// TODO: Use TinySet (like in BitSetDocSet) to speed this process up
if self.current >= self.max_doc {
return None;
}
// find the next alive doc id
while self.reader.is_deleted(self.current) {
self.current += 1;
if self.current >= self.max_doc {
return None;
}
}
// capture the current alive DocId
let result = Some(self.current);
// move down the chain
self.current += 1;
result
}
}
#[cfg(test)]
mod test {
use crate::core::Index;
@@ -378,7 +343,7 @@ mod test {
use crate::DocId;
#[test]
fn test_alive_docs_iterator() {
fn test_alive_docs_iterator() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("name", TEXT | STORED);
let schema = schema_builder.build();
@@ -386,26 +351,26 @@ mod test {
let name = schema.get_field("name").unwrap();
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(name => "tantivy"));
index_writer.add_document(doc!(name => "horse"));
index_writer.add_document(doc!(name => "jockey"));
index_writer.add_document(doc!(name => "cap"));
// we should now have one segment with two docs
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
let mut index_writer2 = index.writer(50_000_000).unwrap();
let mut index_writer2 = index.writer(50_000_000)?;
index_writer2.delete_term(Term::from_field_text(name, "horse"));
index_writer2.delete_term(Term::from_field_text(name, "cap"));
// ok, now we should have a deleted doc
index_writer2.commit().unwrap();
index_writer2.commit()?;
}
let searcher = index.reader().unwrap().searcher();
let searcher = index.reader()?.searcher();
let docs: Vec<DocId> = searcher.segment_reader(0).doc_ids_alive().collect();
assert_eq!(vec![0u32, 2u32], docs);
Ok(())
}
}

39
src/directory/directory.rs
View File

@@ -1,9 +1,9 @@
use crate::directory::directory_lock::Lock;
use crate::directory::error::LockError;
use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
use crate::directory::WatchCallback;
use crate::directory::WatchHandle;
use crate::directory::{ReadOnlySource, WritePtr};
use crate::directory::{FileHandle, WatchCallback};
use crate::directory::{FileSlice, WritePtr};
use std::fmt;
use std::io;
use std::io::Write;
@@ -11,7 +11,6 @@ use std::marker::Send;
use std::marker::Sync;
use std::path::Path;
use std::path::PathBuf;
use std::result;
use std::thread;
use std::time::Duration;
@@ -80,7 +79,7 @@ fn try_acquire_lock(
) -> Result<DirectoryLock, TryAcquireLockError> {
let mut write = directory.open_write(filepath).map_err(|e| match e {
OpenWriteError::FileAlreadyExists(_) => TryAcquireLockError::FileExists,
OpenWriteError::IOError(io_error) => TryAcquireLockError::IOError(io_error.into()),
OpenWriteError::IOError { io_error, .. } => TryAcquireLockError::IOError(io_error),
})?;
write.flush().map_err(TryAcquireLockError::IOError)?;
Ok(DirectoryLock::from(Box::new(DirectoryLockGuard {
@@ -109,37 +108,43 @@ fn retry_policy(is_blocking: bool) -> RetryPolicy {
/// should be your default choice.
/// - The [`RAMDirectory`](struct.RAMDirectory.html), which
/// should be used mostly for tests.
///
pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// Opens a virtual file for read.
/// Opens a file and returns a boxed `FileHandle`.
///
/// Users of `Directory` should typically call `Directory::open_read(...)`,
/// while `Directory` implementor should implement `get_file_handle()`.
fn get_file_handle(&self, path: &Path) -> Result<Box<dyn FileHandle>, OpenReadError>;
/// Once a virtual file is open, its data may not
/// change.
///
/// Specifically, subsequent writes or flushes should
/// have no effect on the returned `ReadOnlySource` object.
/// have no effect on the returned `FileSlice` object.
///
/// You should only use this to read files create with [`open_write`]
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
/// You should only use this to read files create with [Directory::open_write].
fn open_read(&self, path: &Path) -> Result<FileSlice, OpenReadError> {
let file_handle = self.get_file_handle(path)?;
Ok(FileSlice::new(file_handle))
}
/// Removes a file
///
/// Removing a file will not affect an eventual
/// existing ReadOnlySource pointing to it.
/// existing FileSlice pointing to it.
///
/// Removing a nonexistent file, yields a
/// `DeleteError::DoesNotExist`.
fn delete(&self, path: &Path) -> result::Result<(), DeleteError>;
fn delete(&self, path: &Path) -> Result<(), DeleteError>;
/// Returns true iff the file exists
fn exists(&self, path: &Path) -> bool;
fn exists(&self, path: &Path) -> Result<bool, OpenReadError>;
/// Opens a writer for the *virtual file* associated with
/// a Path.
///
/// Right after this call, the file should be created
/// and any subsequent call to `open_read` for the
/// same path should return a `ReadOnlySource`.
/// same path should return a `FileSlice`.
///
/// Write operations may be aggressively buffered.
/// The client of this trait is responsible for calling flush
@@ -153,14 +158,14 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// was not called.
///
/// The file may not previously exist.
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError>;
fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError>;
/// Reads the full content file that has been written using
/// atomic_write.
///
/// This should only be used for small files.
///
/// You should only use this to read files create with [`atomic_write`]
/// You should only use this to read files create with [Directory::atomic_write].
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
/// Atomically replace the content of a file with data.
@@ -169,7 +174,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// a partially written file.
///
/// The file may or may not previously exist.
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()>;
fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()>;
/// Acquire a lock in the given directory.
///
@@ -197,7 +202,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// Registers a callback that will be called whenever a change on the `meta.json`
/// using the `atomic_write` API is detected.
///
/// The behavior when using `.watch()` on a file using `.open_write(...)` is, on the other
/// The behavior when using `.watch()` on a file using [Directory::open_write] is, on the other
/// hand, undefined.
///
/// The file will be watched for the lifetime of the returned `WatchHandle`. The caller is

296
src/directory/error.rs
View File

@@ -1,243 +1,173 @@
use std::error::Error as StdError;
use crate::Version;
use std::fmt;
use std::io;
use std::path::PathBuf;
/// Error while trying to acquire a directory lock.
#[derive(Debug, Fail)]
#[derive(Debug, Error)]
pub enum LockError {
/// Failed to acquired a lock as it is already held by another
/// client.
/// - In the context of a blocking lock, this means the lock was not released within some `timeout` period.
/// - In the context of a non-blocking lock, this means the lock was busy at the moment of the call.
#[fail(
display = "Could not acquire lock as it is already held, possibly by a different process."
)]
#[error("Could not acquire lock as it is already held, possibly by a different process.")]
LockBusy,
/// Trying to acquire a lock failed with an `IOError`
#[fail(display = "Failed to acquire the lock due to an io:Error.")]
#[error("Failed to acquire the lock due to an io:Error.")]
IOError(io::Error),
}
/// General IO error with an optional path to the offending file.
#[derive(Debug)]
pub struct IOError {
path: Option<PathBuf>,
err: io::Error,
}
impl Into<io::Error> for IOError {
fn into(self) -> io::Error {
self.err
}
}
impl fmt::Display for IOError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self.path {
Some(ref path) => write!(f, "io error occurred on path '{:?}': '{}'", path, self.err),
None => write!(f, "io error occurred: '{}'", self.err),
}
}
}
impl StdError for IOError {
fn description(&self) -> &str {
"io error occurred"
}
fn cause(&self) -> Option<&dyn StdError> {
Some(&self.err)
}
}
impl IOError {
pub(crate) fn with_path(path: PathBuf, err: io::Error) -> Self {
IOError {
path: Some(path),
err,
}
}
}
impl From<io::Error> for IOError {
fn from(err: io::Error) -> IOError {
IOError { path: None, err }
}
}
/// Error that may occur when opening a directory
#[derive(Debug)]
#[derive(Debug, Error)]
pub enum OpenDirectoryError {
/// The underlying directory does not exists.
#[error("Directory does not exist: '{0}'.")]
DoesNotExist(PathBuf),
/// The path exists but is not a directory.
#[error("Path exists but is not a directory: '{0}'.")]
NotADirectory(PathBuf),
/// Failed to create a temp directory.
#[error("Failed to create a temporary directory: '{0}'.")]
FailedToCreateTempDir(io::Error),
/// IoError
IoError(io::Error),
}
impl From<io::Error> for OpenDirectoryError {
fn from(io_err: io::Error) -> Self {
OpenDirectoryError::IoError(io_err)
}
}
impl fmt::Display for OpenDirectoryError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
OpenDirectoryError::DoesNotExist(ref path) => {
write!(f, "the underlying directory '{:?}' does not exist", path)
}
OpenDirectoryError::NotADirectory(ref path) => {
write!(f, "the path '{:?}' exists but is not a directory", path)
}
OpenDirectoryError::IoError(ref err) => write!(
f,
"IOError while trying to open/create the directory. {:?}",
err
),
}
}
}
impl StdError for OpenDirectoryError {
fn description(&self) -> &str {
"error occurred while opening a directory"
}
fn cause(&self) -> Option<&dyn StdError> {
None
}
#[error("IOError '{io_error:?}' while create directory in: '{directory_path:?}'.")]
IoError {
/// underlying io Error.
io_error: io::Error,
/// directory we tried to open.
directory_path: PathBuf,
},
}
/// Error that may occur when starting to write in a file
#[derive(Debug)]
#[derive(Debug, Error)]
pub enum OpenWriteError {
/// Our directory is WORM, writing an existing file is forbidden.
/// Checkout the `Directory` documentation.
#[error("File already exists: '{0}'")]
FileAlreadyExists(PathBuf),
/// Any kind of IO error that happens when
/// writing in the underlying IO device.
IOError(IOError),
#[error("IOError '{io_error:?}' while opening file for write: '{filepath}'.")]
IOError {
/// The underlying `io::Error`.
io_error: io::Error,
/// File path of the file that tantivy failed to open for write.
filepath: PathBuf,
},
}
impl From<IOError> for OpenWriteError {
fn from(err: IOError) -> OpenWriteError {
OpenWriteError::IOError(err)
impl OpenWriteError {
/// Wraps an io error.
pub fn wrap_io_error(io_error: io::Error, filepath: PathBuf) -> Self {
Self::IOError { io_error, filepath }
}
}
/// Type of index incompatibility between the library and the index found on disk
/// Used to catch and provide a hint to solve this incompatibility issue
pub enum Incompatibility {
/// This library cannot decompress the index found on disk
CompressionMismatch {
/// Compression algorithm used by the current version of tantivy
library_compression_format: String,
/// Compression algorithm that was used to serialise the index
index_compression_format: String,
},
/// The index format found on disk isn't supported by this version of the library
IndexMismatch {
/// Version used by the library
library_version: Version,
/// Version the index was built with
index_version: Version,
},
}
impl fmt::Display for OpenWriteError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
OpenWriteError::FileAlreadyExists(ref path) => {
write!(f, "the file '{:?}' already exists", path)
impl fmt::Debug for Incompatibility {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
match self {
Incompatibility::CompressionMismatch {
library_compression_format,
index_compression_format,
} => {
let err = format!(
"Library was compiled with {:?} compression, index was compressed with {:?}",
library_compression_format, index_compression_format
);
let advice = format!(
"Change the feature flag to {:?} and rebuild the library",
index_compression_format
);
write!(f, "{}. {}", err, advice)?;
}
Incompatibility::IndexMismatch {
library_version,
index_version,
} => {
let err = format!(
"Library version: {}, index version: {}",
library_version.index_format_version, index_version.index_format_version
);
// TODO make a more useful error message
// include the version range that supports this index_format_version
let advice = format!(
"Change tantivy to a version compatible with index format {} (e.g. {}.{}.x) \
and rebuild your project.",
index_version.index_format_version, index_version.major, index_version.minor
);
write!(f, "{}. {}", err, advice)?;
}
OpenWriteError::IOError(ref err) => write!(
f,
"an io error occurred while opening a file for writing: '{}'",
err
),
}
}
}
impl StdError for OpenWriteError {
fn description(&self) -> &str {
"error occurred while opening a file for writing"
}
fn cause(&self) -> Option<&dyn StdError> {
match *self {
OpenWriteError::FileAlreadyExists(_) => None,
OpenWriteError::IOError(ref err) => Some(err),
}
Ok(())
}
}
/// Error that may occur when accessing a file read
#[derive(Debug)]
#[derive(Debug, Error)]
pub enum OpenReadError {
/// The file does not exists.
#[error("Files does not exists: {0:?}")]
FileDoesNotExist(PathBuf),
/// Any kind of IO error that happens when
/// interacting with the underlying IO device.
IOError(IOError),
/// Any kind of io::Error.
#[error(
"IOError: '{io_error:?}' happened while opening the following file for Read: {filepath}."
)]
IOError {
/// The underlying `io::Error`.
io_error: io::Error,
/// File path of the file that tantivy failed to open for read.
filepath: PathBuf,
},
/// This library does not support the index version found in file footer.
#[error("Index version unsupported: {0:?}")]
IncompatibleIndex(Incompatibility),
}
impl From<IOError> for OpenReadError {
fn from(err: IOError) -> OpenReadError {
OpenReadError::IOError(err)
impl OpenReadError {
/// Wraps an io error.
pub fn wrap_io_error(io_error: io::Error, filepath: PathBuf) -> Self {
Self::IOError { io_error, filepath }
}
}
impl fmt::Display for OpenReadError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
OpenReadError::FileDoesNotExist(ref path) => {
write!(f, "the file '{:?}' does not exist", path)
}
OpenReadError::IOError(ref err) => write!(
f,
"an io error occurred while opening a file for reading: '{}'",
err
),
}
}
}
impl StdError for OpenReadError {
fn description(&self) -> &str {
"error occurred while opening a file for reading"
}
fn cause(&self) -> Option<&dyn StdError> {
match *self {
OpenReadError::FileDoesNotExist(_) => None,
OpenReadError::IOError(ref err) => Some(err),
}
}
}
/// Error that may occur when trying to delete a file
#[derive(Debug)]
#[derive(Debug, Error)]
pub enum DeleteError {
/// The file does not exists.
#[error("File does not exists: '{0}'.")]
FileDoesNotExist(PathBuf),
/// Any kind of IO error that happens when
/// interacting with the underlying IO device.
IOError(IOError),
#[error("The following IO error happened while deleting file '{filepath}': '{io_error:?}'.")]
IOError {
/// The underlying `io::Error`.
io_error: io::Error,
/// File path of the file that tantivy failed to delete.
filepath: PathBuf,
},
}
impl From<IOError> for DeleteError {
fn from(err: IOError) -> DeleteError {
DeleteError::IOError(err)
}
}
impl fmt::Display for DeleteError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
DeleteError::FileDoesNotExist(ref path) => {
write!(f, "the file '{:?}' does not exist", path)
}
DeleteError::IOError(ref err) => {
write!(f, "an io error occurred while deleting a file: '{}'", err)
}
}
}
}
impl StdError for DeleteError {
fn description(&self) -> &str {
"error occurred while deleting a file"
}
fn cause(&self) -> Option<&dyn StdError> {
match *self {
DeleteError::FileDoesNotExist(_) => None,
DeleteError::IOError(ref err) => Some(err),
}
impl From<Incompatibility> for OpenReadError {
fn from(incompatibility: Incompatibility) -> Self {
OpenReadError::IncompatibleIndex(incompatibility)
}
}

247
src/directory/file_slice.rs Normal file
View File

@@ -0,0 +1,247 @@
use stable_deref_trait::StableDeref;
use crate::common::HasLen;
use crate::directory::OwnedBytes;
use std::sync::{Arc, Weak};
use std::{io, ops::Deref};
pub type ArcBytes = Arc<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
pub type WeakArcBytes = Weak<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
/// Objects that represents files sections in tantivy.
///
/// By contract, whatever happens to the directory file, as long as a FileHandle
/// is alive, the data associated with it cannot be altered or destroyed.
///
/// The underlying behavior is therefore specific to the `Directory` that created it.
/// Despite its name, a `FileSlice` may or may not directly map to an actual file
/// on the filesystem.
pub trait FileHandle: 'static + Send + Sync + HasLen {
/// Reads a slice of bytes.
///
/// This method may panic if the range requested is invalid.
fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes>;
}
impl FileHandle for &'static [u8] {
fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
let bytes = &self[from..to];
Ok(OwnedBytes::new(bytes))
}
}
impl<T: Deref<Target = [u8]>> HasLen for T {
fn len(&self) -> usize {
self.as_ref().len()
}
}
impl<B> From<B> for FileSlice
where
B: StableDeref + Deref<Target = [u8]> + 'static + Send + Sync,
{
fn from(bytes: B) -> FileSlice {
FileSlice::new(Box::new(OwnedBytes::new(bytes)))
}
}
/// Logical slice of read only file in tantivy.
//
/// It can be cloned and sliced cheaply.
///
#[derive(Clone)]
pub struct FileSlice {
data: Arc<dyn FileHandle>,
start: usize,
stop: usize,
}
impl FileSlice {
/// Wraps a FileHandle.
pub fn new(file_handle: Box<dyn FileHandle>) -> Self {
let num_bytes = file_handle.len();
FileSlice::new_with_num_bytes(file_handle, num_bytes)
}
/// Wraps a FileHandle.
#[doc(hidden)]
pub fn new_with_num_bytes(file_handle: Box<dyn FileHandle>, num_bytes: usize) -> Self {
FileSlice {
data: Arc::from(file_handle),
start: 0,
stop: num_bytes,
}
}
/// Creates a fileslice that is just a view over a slice of the data.
///
/// # Panics
///
/// Panics if `to < from` or if `to` exceeds the filesize.
pub fn slice(&self, from: usize, to: usize) -> FileSlice {
assert!(to <= self.len());
assert!(to >= from);
FileSlice {
data: self.data.clone(),
start: self.start + from,
stop: self.start + to,
}
}
/// Creates an empty FileSlice
pub fn empty() -> FileSlice {
const EMPTY_SLICE: &[u8] = &[];
FileSlice::from(EMPTY_SLICE)
}
/// Returns a `OwnedBytes` with all of the data in the `FileSlice`.
///
/// The behavior is strongly dependant on the implementation of the underlying
/// `Directory` and the `FileSliceTrait` it creates.
/// In particular, it is up to the `Directory` implementation
/// to handle caching if needed.
pub fn read_bytes(&self) -> io::Result<OwnedBytes> {
self.data.read_bytes(self.start, self.stop)
}
/// Reads a specific slice of data.
///
/// This is equivalent to running `file_slice.slice(from, to).read_bytes()`.
pub fn read_bytes_slice(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
assert!(from <= to);
assert!(
self.start + to <= self.stop,
"`to` exceeds the fileslice length"
);
self.data.read_bytes(self.start + from, self.start + to)
}
/// Splits the FileSlice at the given offset and return two file slices.
/// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
///
/// This operation is cheap and must not copy any underlying data.
pub fn split(self, left_len: usize) -> (FileSlice, FileSlice) {
let left = self.slice_to(left_len);
let right = self.slice_from(left_len);
(left, right)
}
/// Splits the file slice at the given offset and return two file slices.
/// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
pub fn split_from_end(self, right_len: usize) -> (FileSlice, FileSlice) {
let left_len = self.len() - right_len;
self.split(left_len)
}
/// Like `.slice(...)` but enforcing only the `from`
/// boundary.
///
/// Equivalent to `.slice(from_offset, self.len())`
pub fn slice_from(&self, from_offset: usize) -> FileSlice {
self.slice(from_offset, self.len())
}
/// Like `.slice(...)` but enforcing only the `to`
/// boundary.
///
/// Equivalent to `.slice(0, to_offset)`
pub fn slice_to(&self, to_offset: usize) -> FileSlice {
self.slice(0, to_offset)
}
}
impl FileHandle for FileSlice {
fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
self.read_bytes_slice(from, to)
}
}
impl HasLen for FileSlice {
fn len(&self) -> usize {
self.stop - self.start
}
}
#[cfg(test)]
mod tests {
use super::{FileHandle, FileSlice};
use crate::common::HasLen;
use std::io;
#[test]
fn test_file_slice() -> io::Result<()> {
let file_slice = FileSlice::new(Box::new(b"abcdef".as_ref()));
assert_eq!(file_slice.len(), 6);
assert_eq!(file_slice.slice_from(2).read_bytes()?.as_slice(), b"cdef");
assert_eq!(file_slice.slice_to(2).read_bytes()?.as_slice(), b"ab");
assert_eq!(
file_slice
.slice_from(1)
.slice_to(2)
.read_bytes()?
.as_slice(),
b"bc"
);
{
let (left, right) = file_slice.clone().split(0);
assert_eq!(left.read_bytes()?.as_slice(), b"");
assert_eq!(right.read_bytes()?.as_slice(), b"abcdef");
}
{
let (left, right) = file_slice.clone().split(2);
assert_eq!(left.read_bytes()?.as_slice(), b"ab");
assert_eq!(right.read_bytes()?.as_slice(), b"cdef");
}
{
let (left, right) = file_slice.clone().split_from_end(0);
assert_eq!(left.read_bytes()?.as_slice(), b"abcdef");
assert_eq!(right.read_bytes()?.as_slice(), b"");
}
{
let (left, right) = file_slice.clone().split_from_end(2);
assert_eq!(left.read_bytes()?.as_slice(), b"abcd");
assert_eq!(right.read_bytes()?.as_slice(), b"ef");
}
Ok(())
}
#[test]
fn test_file_slice_trait_slice_len() {
let blop: &'static [u8] = b"abc";
let owned_bytes: Box<dyn FileHandle> = Box::new(blop);
assert_eq!(owned_bytes.len(), 3);
}
#[test]
fn test_slice_simple_read() -> io::Result<()> {
let slice = FileSlice::new(Box::new(&b"abcdef"[..]));
assert_eq!(slice.len(), 6);
assert_eq!(slice.read_bytes()?.as_ref(), b"abcdef");
assert_eq!(slice.slice(1, 4).read_bytes()?.as_ref(), b"bcd");
Ok(())
}
#[test]
fn test_slice_read_slice() -> io::Result<()> {
let slice_deref = FileSlice::new(Box::new(&b"abcdef"[..]));
assert_eq!(slice_deref.read_bytes_slice(1, 4)?.as_ref(), b"bcd");
Ok(())
}
#[test]
#[should_panic(expected = "assertion failed: from <= to")]
fn test_slice_read_slice_invalid_range() {
let slice_deref = FileSlice::new(Box::new(&b"abcdef"[..]));
assert_eq!(slice_deref.read_bytes_slice(1, 0).unwrap().as_ref(), b"bcd");
}
#[test]
#[should_panic(expected = "`to` exceeds the fileslice length")]
fn test_slice_read_slice_invalid_range_exceeds() {
let slice_deref = FileSlice::new(Box::new(&b"abcdef"[..]));
assert_eq!(
slice_deref.read_bytes_slice(0, 10).unwrap().as_ref(),
b"bcd"
);
}
}

178
src/directory/file_watcher.rs Normal file
View File

@@ -0,0 +1,178 @@
use crate::directory::{WatchCallback, WatchCallbackList, WatchHandle};
use crc32fast::Hasher;
use std::fs;
use std::io;
use std::io::BufRead;
use std::path::Path;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
use std::thread;
use std::time::Duration;
pub const POLLING_INTERVAL: Duration = Duration::from_millis(if cfg!(test) { 1 } else { 500 });
// Watches a file and executes registered callbacks when the file is modified.
pub struct FileWatcher {
path: Arc<Path>,
callbacks: Arc<WatchCallbackList>,
state: Arc<AtomicUsize>, // 0: new, 1: runnable, 2: terminated
}
impl FileWatcher {
pub fn new(path: &Path) -> FileWatcher {
FileWatcher {
path: Arc::from(path),
callbacks: Default::default(),
state: Default::default(),
}
}
pub fn spawn(&self) {
if self.state.compare_and_swap(0, 1, Ordering::SeqCst) > 0 {
return;
}
let path = self.path.clone();
let callbacks = self.callbacks.clone();
let state = self.state.clone();
thread::Builder::new()
.name("thread-tantivy-meta-file-watcher".to_string())
.spawn(move || {
let mut current_checksum = None;
while state.load(Ordering::SeqCst) == 1 {
if let Ok(checksum) = FileWatcher::compute_checksum(&path) {
// `None.unwrap_or_else(|| !checksum) != checksum` evaluates to `true`
if current_checksum.unwrap_or_else(|| !checksum) != checksum {
info!("Meta file {:?} was modified", path);
current_checksum = Some(checksum);
futures::executor::block_on(callbacks.broadcast());
}
}
thread::sleep(POLLING_INTERVAL);
}
})
.expect("Failed to spawn meta file watcher thread");
}
pub fn watch(&self, callback: WatchCallback) -> WatchHandle {
let handle = self.callbacks.subscribe(callback);
self.spawn();
handle
}
fn compute_checksum(path: &Path) -> Result<u32, io::Error> {
let reader = match fs::File::open(path) {
Ok(f) => io::BufReader::new(f),
Err(e) => {
warn!("Failed to open meta file {:?}: {:?}", path, e);
return Err(e);
}
};
let mut hasher = Hasher::new();
for line in reader.lines() {
hasher.update(line?.as_bytes())
}
Ok(hasher.finalize())
}
}
impl Drop for FileWatcher {
fn drop(&mut self) {
self.state.store(2, Ordering::SeqCst);
}
}
#[cfg(test)]
mod tests {
use std::mem;
use crate::directory::mmap_directory::atomic_write;
use super::*;
#[test]
fn test_file_watcher_drop_watcher() -> crate::Result<()> {
let tmp_dir = tempfile::TempDir::new()?;
let tmp_file = tmp_dir.path().join("watched.txt");
let counter: Arc<AtomicUsize> = Default::default();
let (tx, rx) = crossbeam::channel::unbounded();
let timeout = Duration::from_millis(100);
let watcher = FileWatcher::new(&tmp_file);
let state = watcher.state.clone();
assert_eq!(state.load(Ordering::SeqCst), 0);
let counter_clone = counter.clone();
let _handle = watcher.watch(WatchCallback::new(move || {
let val = counter_clone.fetch_add(1, Ordering::SeqCst);
tx.send(val + 1).unwrap();
}));
assert_eq!(counter.load(Ordering::SeqCst), 0);
assert_eq!(state.load(Ordering::SeqCst), 1);
atomic_write(&tmp_file, b"foo")?;
assert_eq!(rx.recv_timeout(timeout), Ok(1));
atomic_write(&tmp_file, b"foo")?;
assert!(rx.recv_timeout(timeout).is_err());
atomic_write(&tmp_file, b"bar")?;
assert_eq!(rx.recv_timeout(timeout), Ok(2));
mem::drop(watcher);
atomic_write(&tmp_file, b"qux")?;
thread::sleep(Duration::from_millis(10));
assert_eq!(counter.load(Ordering::SeqCst), 2);
assert_eq!(state.load(Ordering::SeqCst), 2);
Ok(())
}
#[test]
fn test_file_watcher_drop_handle() -> crate::Result<()> {
let tmp_dir = tempfile::TempDir::new()?;
let tmp_file = tmp_dir.path().join("watched.txt");
let counter: Arc<AtomicUsize> = Default::default();
let (tx, rx) = crossbeam::channel::unbounded();
let timeout = Duration::from_millis(100);
let watcher = FileWatcher::new(&tmp_file);
let state = watcher.state.clone();
assert_eq!(state.load(Ordering::SeqCst), 0);
let counter_clone = counter.clone();
let handle = watcher.watch(WatchCallback::new(move || {
let val = counter_clone.fetch_add(1, Ordering::SeqCst);
tx.send(val + 1).unwrap();
}));
assert_eq!(counter.load(Ordering::SeqCst), 0);
assert_eq!(state.load(Ordering::SeqCst), 1);
atomic_write(&tmp_file, b"foo")?;
assert_eq!(rx.recv_timeout(timeout), Ok(1));
mem::drop(handle);
atomic_write(&tmp_file, b"qux")?;
assert_eq!(counter.load(Ordering::SeqCst), 1);
assert_eq!(state.load(Ordering::SeqCst), 1);
Ok(())
}
}

447
src/directory/footer.rs
View File

@@ -1,159 +1,237 @@
use crate::directory::read_only_source::ReadOnlySource;
use crate::common::{BinarySerializable, CountingWriter, FixedSize, HasLen, VInt};
use crate::directory::error::Incompatibility;
use crate::directory::FileSlice;
use crate::directory::{AntiCallToken, TerminatingWrite};
use byteorder::{ByteOrder, LittleEndian};
use crate::Version;
use crc32fast::Hasher;
use std::io;
use std::io::Write;
const COMMON_FOOTER_SIZE: usize = 4 * 5;
const FOOTER_MAX_LEN: usize = 10_000;
type CrcHashU32 = u32;
#[derive(Debug, Clone, PartialEq)]
pub struct Footer {
pub tantivy_version: (u32, u32, u32),
pub version: Version,
pub meta: String,
pub versioned_footer: VersionedFooter,
}
/// Serialises the footer to a byte-array
/// - versioned_footer_len : 4 bytes
///- versioned_footer: variable bytes
/// - meta_len: 4 bytes
/// - meta: variable bytes
/// - version_len: 4 bytes
/// - version json: variable bytes
impl BinarySerializable for Footer {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
BinarySerializable::serialize(&self.versioned_footer, writer)?;
BinarySerializable::serialize(&self.meta, writer)?;
let version_string =
serde_json::to_string(&self.version).map_err(|_err| io::ErrorKind::InvalidInput)?;
BinarySerializable::serialize(&version_string, writer)?;
Ok(())
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let versioned_footer = VersionedFooter::deserialize(reader)?;
let meta = String::deserialize(reader)?;
let version_json = String::deserialize(reader)?;
let version = serde_json::from_str(&version_json)?;
Ok(Footer {
version,
meta,
versioned_footer,
})
}
}
impl Footer {
pub fn new(versioned_footer: VersionedFooter) -> Self {
let tantivy_version = (
env!("CARGO_PKG_VERSION_MAJOR").parse().unwrap(),
env!("CARGO_PKG_VERSION_MINOR").parse().unwrap(),
env!("CARGO_PKG_VERSION_PATCH").parse().unwrap(),
);
let version = crate::VERSION.clone();
let meta = version.to_string();
Footer {
tantivy_version,
meta: format!(
"tantivy {}.{}.{}, index v{}",
tantivy_version.0,
tantivy_version.1,
tantivy_version.2,
versioned_footer.version()
),
version,
meta,
versioned_footer,
}
}
pub fn to_bytes(&self) -> Vec<u8> {
let mut res = self.versioned_footer.to_bytes();
res.extend_from_slice(self.meta.as_bytes());
let len = res.len();
res.resize(len + COMMON_FOOTER_SIZE, 0);
let mut common_footer = &mut res[len..];
LittleEndian::write_u32(&mut common_footer, self.meta.len() as u32);
LittleEndian::write_u32(&mut common_footer[4..], self.tantivy_version.0);
LittleEndian::write_u32(&mut common_footer[8..], self.tantivy_version.1);
LittleEndian::write_u32(&mut common_footer[12..], self.tantivy_version.2);
LittleEndian::write_u32(&mut common_footer[16..], (len + COMMON_FOOTER_SIZE) as u32);
res
pub fn append_footer<W: io::Write>(&self, mut write: &mut W) -> io::Result<()> {
let mut counting_write = CountingWriter::wrap(&mut write);
self.serialize(&mut counting_write)?;
let written_len = counting_write.written_bytes();
(written_len as u32).serialize(write)?;
Ok(())
}
pub fn from_bytes(data: &[u8]) -> Result<Self, io::Error> {
let len = data.len();
if len < COMMON_FOOTER_SIZE + 4 {
// 4 bytes for index version, stored in versioned footer
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!("File corrupted. The footer len must be over 24, while the entire file len is {}", len)
)
);
}
let size = LittleEndian::read_u32(&data[len - 4..]) as usize;
if len < size as usize {
pub fn extract_footer(file: FileSlice) -> io::Result<(Footer, FileSlice)> {
if file.len() < 4 {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The footer len is {}, while the entire file len is {}",
size, len
"File corrupted. The file is smaller than 4 bytes (len={}).",
file.len()
),
));
}
let footer = &data[len - size as usize..];
let meta_len = LittleEndian::read_u32(&footer[size - 20..]) as usize;
let tantivy_major = LittleEndian::read_u32(&footer[size - 16..]);
let tantivy_minor = LittleEndian::read_u32(&footer[size - 12..]);
let tantivy_patch = LittleEndian::read_u32(&footer[size - 8..]);
Ok(Footer {
tantivy_version: (tantivy_major, tantivy_minor, tantivy_patch),
meta: String::from_utf8_lossy(&footer[size - meta_len - 20..size - 20]).into_owned(),
versioned_footer: VersionedFooter::from_bytes(&footer[..size - meta_len - 20])?,
})
let (body_footer, footer_len_file) = file.split_from_end(u32::SIZE_IN_BYTES);
let mut footer_len_bytes = footer_len_file.read_bytes()?;
let footer_len = u32::deserialize(&mut footer_len_bytes)? as usize;
let (body, footer) = body_footer.split_from_end(footer_len);
let mut footer_bytes = footer.read_bytes()?;
let footer = Footer::deserialize(&mut footer_bytes)?;
Ok((footer, body))
}
pub fn extract_footer(source: ReadOnlySource) -> Result<(Footer, ReadOnlySource), io::Error> {
let footer = Footer::from_bytes(source.as_slice())?;
let reader = source.slice_to(source.as_slice().len() - footer.size());
Ok((footer, reader))
}
pub fn size(&self) -> usize {
self.versioned_footer.size() as usize + self.meta.len() + 20
}
}
#[derive(Debug, Clone, PartialEq)]
pub enum VersionedFooter {
UnknownVersion { version: u32, size: u32 },
V0(u32), // crc
}
impl VersionedFooter {
pub fn to_bytes(&self) -> Vec<u8> {
match self {
VersionedFooter::V0(crc) => {
let mut res = vec![0; 8];
LittleEndian::write_u32(&mut res, 0);
LittleEndian::write_u32(&mut res[4..], *crc);
res
}
VersionedFooter::UnknownVersion { .. } => {
panic!("Unsupported index should never get serialized");
}
}
}
pub fn from_bytes(footer: &[u8]) -> Result<Self, io::Error> {
assert!(footer.len() >= 4);
let version = LittleEndian::read_u32(footer);
match version {
0 => {
if footer.len() == 8 {
Ok(VersionedFooter::V0(LittleEndian::read_u32(&footer[4..])))
} else {
Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The versioned footer len is {}, while it should be 8",
footer.len()
),
))
/// Confirms that the index will be read correctly by this version of tantivy
/// Has to be called after `extract_footer` to make sure it's not accessing uninitialised memory
pub fn is_compatible(&self) -> Result<(), Incompatibility> {
let library_version = crate::version();
match &self.versioned_footer {
VersionedFooter::V1 {
crc32: _crc,
store_compression,
} => {
if &library_version.store_compression != store_compression {
return Err(Incompatibility::CompressionMismatch {
library_compression_format: library_version.store_compression.to_string(),
index_compression_format: store_compression.to_string(),
});
}
Ok(())
}
version => Ok(VersionedFooter::UnknownVersion {
version,
size: footer.len() as u32,
VersionedFooter::V2 {
crc32: _crc,
store_compression,
} => {
if &library_version.store_compression != store_compression {
return Err(Incompatibility::CompressionMismatch {
library_compression_format: library_version.store_compression.to_string(),
index_compression_format: store_compression.to_string(),
});
}
Ok(())
}
VersionedFooter::V3 {
crc32: _crc,
store_compression,
} => {
if &library_version.store_compression != store_compression {
return Err(Incompatibility::CompressionMismatch {
library_compression_format: library_version.store_compression.to_string(),
index_compression_format: store_compression.to_string(),
});
}
Ok(())
}
VersionedFooter::UnknownVersion => Err(Incompatibility::IndexMismatch {
library_version: library_version.clone(),
index_version: self.version.clone(),
}),
}
}
}
pub fn size(&self) -> u32 {
/// Footer that includes a crc32 hash that enables us to checksum files in the index
#[derive(Debug, Clone, PartialEq)]
pub enum VersionedFooter {
UnknownVersion,
V1 {
crc32: CrcHashU32,
store_compression: String,
},
// Introduction of the Block WAND information.
V2 {
crc32: CrcHashU32,
store_compression: String,
},
// Block wand max termfred on 1 byte
V3 {
crc32: CrcHashU32,
store_compression: String,
},
}
impl BinarySerializable for VersionedFooter {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
let mut buf = Vec::new();
match self {
VersionedFooter::V0(_) => 8,
VersionedFooter::UnknownVersion { size, .. } => *size,
VersionedFooter::V3 {
crc32,
store_compression: compression,
} => {
// Serializes a valid `VersionedFooter` or panics if the version is unknown
// [ version | crc_hash | compression_mode ]
// [ 0..4 | 4..8 | variable ]
BinarySerializable::serialize(&3u32, &mut buf)?;
BinarySerializable::serialize(crc32, &mut buf)?;
BinarySerializable::serialize(compression, &mut buf)?;
}
VersionedFooter::V2 { .. }
| VersionedFooter::V1 { .. }
| VersionedFooter::UnknownVersion => {
return Err(io::Error::new(
io::ErrorKind::InvalidInput,
"Cannot serialize an unknown versioned footer ",
));
}
}
BinarySerializable::serialize(&VInt(buf.len() as u64), writer)?;
assert!(buf.len() <= FOOTER_MAX_LEN);
writer.write_all(&buf[..])?;
Ok(())
}
pub fn version(&self) -> u32 {
match self {
VersionedFooter::V0(_) => 0,
VersionedFooter::UnknownVersion { version, .. } => *version,
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let len = VInt::deserialize(reader)?.0 as usize;
if len > FOOTER_MAX_LEN {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
format!(
"Footer seems invalid as it suggests a footer len of {}. File is corrupted, \
or the index was created with a different & old version of tantivy.",
len
),
));
}
let mut buf = vec![0u8; len];
reader.read_exact(&mut buf[..])?;
let mut cursor = &buf[..];
let version = u32::deserialize(&mut cursor)?;
if version > 3 {
return Ok(VersionedFooter::UnknownVersion);
}
let crc32 = u32::deserialize(&mut cursor)?;
let store_compression = String::deserialize(&mut cursor)?;
Ok(if version == 1 {
VersionedFooter::V1 {
crc32,
store_compression,
}
} else if version == 2 {
VersionedFooter::V2 {
crc32,
store_compression,
}
} else {
assert_eq!(version, 3);
VersionedFooter::V3 {
crc32,
store_compression,
}
})
}
}
pub fn crc(&self) -> Option<u32> {
impl VersionedFooter {
pub fn crc(&self) -> Option<CrcHashU32> {
match self {
VersionedFooter::V0(crc) => Some(*crc),
VersionedFooter::V3 { crc32, .. } => Some(*crc32),
VersionedFooter::V2 { crc32, .. } => Some(*crc32),
VersionedFooter::V1 { crc32, .. } => Some(*crc32),
VersionedFooter::UnknownVersion { .. } => None,
}
}
@@ -189,25 +267,152 @@ impl<W: TerminatingWrite> Write for FooterProxy<W> {
impl<W: TerminatingWrite> TerminatingWrite for FooterProxy<W> {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
let crc = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V0(crc)).to_bytes();
let crc32 = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V3 {
crc32,
store_compression: crate::store::COMPRESSION.to_string(),
});
let mut writer = self.writer.take().unwrap();
writer.write_all(&footer)?;
footer.append_footer(&mut writer)?;
writer.terminate()
}
}
#[cfg(test)]
mod tests {
use super::CrcHashU32;
use super::FooterProxy;
use crate::common::{BinarySerializable, VInt};
use crate::directory::footer::{Footer, VersionedFooter};
use crate::directory::TerminatingWrite;
use byteorder::{ByteOrder, LittleEndian};
use regex::Regex;
use std::io;
#[test]
fn test_versioned_footer() {
let mut vec = Vec::new();
let footer_proxy = FooterProxy::new(&mut vec);
assert!(footer_proxy.terminate().is_ok());
if crate::store::COMPRESSION == "lz4" {
assert_eq!(vec.len(), 158);
} else {
assert_eq!(vec.len(), 167);
}
let footer = Footer::deserialize(&mut &vec[..]).unwrap();
assert!(matches!(
footer.versioned_footer,
VersionedFooter::V3 { store_compression, .. }
if store_compression == crate::store::COMPRESSION
));
assert_eq!(&footer.version, crate::version());
}
#[test]
fn test_serialize_deserialize_footer() {
let crc = 123456;
let footer = Footer::new(VersionedFooter::V0(crc));
let footer_bytes = footer.to_bytes();
let mut buffer = Vec::new();
let crc32 = 123456u32;
let footer: Footer = Footer::new(VersionedFooter::V3 {
crc32,
store_compression: "lz4".to_string(),
});
footer.serialize(&mut buffer).unwrap();
let footer_deser = Footer::deserialize(&mut &buffer[..]).unwrap();
assert_eq!(footer_deser, footer);
}
assert_eq!(Footer::from_bytes(&footer_bytes).unwrap(), footer);
#[test]
fn footer_length() {
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V3 {
crc32,
store_compression: "lz4".to_string(),
};
let mut buf = Vec::new();
versioned_footer.serialize(&mut buf).unwrap();
assert_eq!(buf.len(), 13);
let footer = Footer::new(versioned_footer);
let regex_ptn = Regex::new(
"tantivy v[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.{0,10}, index_format v[0-9]{1,5}",
)
.unwrap();
assert!(regex_ptn.is_match(&footer.meta));
}
#[test]
fn versioned_footer_from_bytes() {
let v_footer_bytes = vec![
// versionned footer length
12 | 128,
// index format version
3,
0,
0,
0,
// crc 32
12,
35,
89,
18,
// compression format
3 | 128,
b'l',
b'z',
b'4',
];
let mut cursor = &v_footer_bytes[..];
let versioned_footer = VersionedFooter::deserialize(&mut cursor).unwrap();
assert!(cursor.is_empty());
let expected_crc: u32 = LittleEndian::read_u32(&v_footer_bytes[5..9]) as CrcHashU32;
let expected_versioned_footer: VersionedFooter = VersionedFooter::V3 {
crc32: expected_crc,
store_compression: "lz4".to_string(),
};
assert_eq!(versioned_footer, expected_versioned_footer);
let mut buffer = Vec::new();
assert!(versioned_footer.serialize(&mut buffer).is_ok());
assert_eq!(&v_footer_bytes[..], &buffer[..]);
}
#[test]
fn versioned_footer_panic() {
let v_footer_bytes = vec![6u8 | 128u8, 3u8, 0u8, 0u8, 1u8, 0u8, 0u8];
let mut b = &v_footer_bytes[..];
let versioned_footer = VersionedFooter::deserialize(&mut b).unwrap();
assert!(b.is_empty());
let expected_versioned_footer = VersionedFooter::UnknownVersion;
assert_eq!(versioned_footer, expected_versioned_footer);
let mut buf = Vec::new();
assert!(versioned_footer.serialize(&mut buf).is_err());
}
#[test]
#[cfg(not(feature = "lz4"))]
fn compression_mismatch() {
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V1 {
crc32,
store_compression: "lz4".to_string(),
};
let footer = Footer::new(versioned_footer);
let res = footer.is_compatible();
assert!(res.is_err());
}
#[test]
fn test_deserialize_too_large_footer() {
let mut buf = vec![];
assert!(FooterProxy::new(&mut buf).terminate().is_ok());
let mut long_len_buf = [0u8; 10];
let num_bytes = VInt(super::FOOTER_MAX_LEN as u64 + 1u64).serialize_into(&mut long_len_buf);
buf[0..num_bytes].copy_from_slice(&long_len_buf[..num_bytes]);
let err = Footer::deserialize(&mut &buf[..]).unwrap_err();
assert_eq!(err.kind(), io::ErrorKind::InvalidData);
assert_eq!(
err.to_string(),
"Footer seems invalid as it suggests a footer len of 10001. File is corrupted, \
or the index was created with a different & old version of tantivy."
);
}
}

181
src/directory/managed_directory.rs
View File

@@ -1,16 +1,16 @@
use crate::core::MANAGED_FILEPATH;
use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError};
use crate::core::{MANAGED_FILEPATH, META_FILEPATH};
use crate::directory::error::{DeleteError, LockError, OpenReadError, OpenWriteError};
use crate::directory::footer::{Footer, FooterProxy};
use crate::directory::DirectoryLock;
use crate::directory::GarbageCollectionResult;
use crate::directory::Lock;
use crate::directory::META_LOCK;
use crate::directory::{ReadOnlySource, WritePtr};
use crate::directory::{DirectoryLock, FileHandle};
use crate::directory::{FileSlice, WritePtr};
use crate::directory::{WatchCallback, WatchHandle};
use crate::error::DataCorruption;
use crate::Directory;
use crate::Result;
use crc32fast::Hasher;
use serde_json;
use std::collections::HashSet;
use std::io;
use std::io::Write;
@@ -53,7 +53,7 @@ struct MetaInformation {
/// Saves the file containing the list of existing files
/// that were created by tantivy.
fn save_managed_paths(
directory: &mut dyn Directory,
directory: &dyn Directory,
wlock: &RwLockWriteGuard<'_, MetaInformation>,
) -> io::Result<()> {
let mut w = serde_json::to_vec(&wlock.managed_paths)?;
@@ -64,7 +64,7 @@ fn save_managed_paths(
impl ManagedDirectory {
/// Wraps a directory as managed directory.
pub fn wrap<Dir: Directory>(directory: Dir) -> Result<ManagedDirectory> {
pub fn wrap<Dir: Directory>(directory: Dir) -> crate::Result<ManagedDirectory> {
match directory.atomic_read(&MANAGED_FILEPATH) {
Ok(data) => {
let managed_files_json = String::from_utf8_lossy(&data);
@@ -86,7 +86,12 @@ impl ManagedDirectory {
directory: Box::new(directory),
meta_informations: Arc::default(),
}),
Err(OpenReadError::IOError(e)) => Err(From::from(e)),
io_err @ Err(OpenReadError::IOError { .. }) => Err(io_err.err().unwrap().into()),
Err(OpenReadError::IncompatibleIndex(incompatibility)) => {
// For the moment, this should never happen `meta.json`
// do not have any footer and cannot detect incompatibility.
Err(crate::TantivyError::IncompatibleIndex(incompatibility))
}
}
}
@@ -104,7 +109,10 @@ impl ManagedDirectory {
/// If a file cannot be deleted (for permission reasons for instance)
/// an error is simply logged, and the file remains in the list of managed
/// files.
pub fn garbage_collect<L: FnOnce() -> HashSet<PathBuf>>(&mut self, get_living_files: L) {
pub fn garbage_collect<L: FnOnce() -> HashSet<PathBuf>>(
&mut self,
get_living_files: L,
) -> crate::Result<GarbageCollectionResult> {
info!("Garbage collect");
let mut files_to_delete = vec![];
@@ -130,19 +138,25 @@ impl ManagedDirectory {
// 2) writer change meta.json (for instance after a merge or a commit)
// 3) gc kicks in.
// 4) gc removes a file that was useful for process B, before process B opened it.
if let Ok(_meta_lock) = self.acquire_lock(&META_LOCK) {
let living_files = get_living_files();
for managed_path in &meta_informations_rlock.managed_paths {
if !living_files.contains(managed_path) {
files_to_delete.push(managed_path.clone());
match self.acquire_lock(&META_LOCK) {
Ok(_meta_lock) => {
let living_files = get_living_files();
for managed_path in &meta_informations_rlock.managed_paths {
if !living_files.contains(managed_path) {
files_to_delete.push(managed_path.clone());
}
}
}
} else {
error!("Failed to acquire lock for GC");
Err(err) => {
error!("Failed to acquire lock for GC");
return Err(crate::TantivyError::from(err));
}
}
}
let mut failed_to_delete_files = vec![];
let mut deleted_files = vec![];
for file_to_delete in files_to_delete {
match self.delete(&file_to_delete) {
Ok(_) => {
@@ -152,9 +166,10 @@ impl ManagedDirectory {
Err(file_error) => {
match file_error {
DeleteError::FileDoesNotExist(_) => {
deleted_files.push(file_to_delete);
deleted_files.push(file_to_delete.clone());
}
DeleteError::IOError(_) => {
DeleteError::IOError { .. } => {
failed_to_delete_files.push(file_to_delete.clone());
if !cfg!(target_os = "windows") {
// On windows, delete is expected to fail if the file
// is mmapped.
@@ -177,10 +192,13 @@ impl ManagedDirectory {
for delete_file in &deleted_files {
managed_paths_write.remove(delete_file);
}
if save_managed_paths(self.directory.as_mut(), &meta_informations_wlock).is_err() {
error!("Failed to save the list of managed files.");
}
save_managed_paths(self.directory.as_mut(), &meta_informations_wlock)?;
}
Ok(GarbageCollectionResult {
deleted_files,
failed_to_delete_files,
})
}
/// Registers a file as managed
@@ -194,7 +212,7 @@ impl ManagedDirectory {
/// File starting by "." are reserved to locks.
/// They are not managed and cannot be subjected
/// to garbage collection.
fn register_file_as_managed(&mut self, filepath: &Path) -> io::Result<()> {
fn register_file_as_managed(&self, filepath: &Path) -> io::Result<()> {
// Files starting by "." (e.g. lock files) are not managed.
if !is_managed(filepath) {
return Ok(());
@@ -205,7 +223,7 @@ impl ManagedDirectory {
.expect("Managed file lock poisoned");
let has_changed = meta_wlock.managed_paths.insert(filepath.to_owned());
if has_changed {
save_managed_paths(self.directory.as_mut(), &meta_wlock)?;
save_managed_paths(self.directory.as_ref(), &meta_wlock)?;
}
Ok(())
}
@@ -213,10 +231,19 @@ impl ManagedDirectory {
/// Verify checksum of a managed file
pub fn validate_checksum(&self, path: &Path) -> result::Result<bool, OpenReadError> {
let reader = self.directory.open_read(path)?;
let (footer, data) = Footer::extract_footer(reader)
.map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
let (footer, data) =
Footer::extract_footer(reader).map_err(|io_error| OpenReadError::IOError {
io_error,
filepath: path.to_path_buf(),
})?;
let bytes = data
.read_bytes()
.map_err(|io_error| OpenReadError::IOError {
filepath: path.to_path_buf(),
io_error,
})?;
let mut hasher = Hasher::new();
hasher.update(data.as_slice());
hasher.update(bytes.as_slice());
let crc = hasher.finalize();
Ok(footer
.versioned_footer
@@ -227,34 +254,42 @@ impl ManagedDirectory {
/// List files for which checksum does not match content
pub fn list_damaged(&self) -> result::Result<HashSet<PathBuf>, OpenReadError> {
let mut hashset = HashSet::new();
let managed_paths = self
let mut managed_paths = self
.meta_informations
.read()
.expect("Managed directory rlock poisoned in list damaged.")
.managed_paths
.clone();
for path in managed_paths.into_iter() {
managed_paths.remove(*META_FILEPATH);
let mut damaged_files = HashSet::new();
for path in managed_paths {
if !self.validate_checksum(&path)? {
hashset.insert(path);
damaged_files.insert(path);
}
}
Ok(hashset)
Ok(damaged_files)
}
}
impl Directory for ManagedDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
let read_only_source = self.directory.open_read(path)?;
let (_footer, reader) = Footer::extract_footer(read_only_source)
.map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
fn get_file_handle(&self, path: &Path) -> Result<Box<dyn FileHandle>, OpenReadError> {
let file_slice = self.open_read(path)?;
Ok(Box::new(file_slice))
}
fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
let file_slice = self.directory.open_read(path)?;
let (footer, reader) = Footer::extract_footer(file_slice)
.map_err(|io_error| OpenReadError::wrap_io_error(io_error, path.to_path_buf()))?;
footer.is_compatible()?;
Ok(reader)
}
fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
fn open_write(&self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
self.register_file_as_managed(path)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
.map_err(|io_error| OpenWriteError::wrap_io_error(io_error, path.to_path_buf()))?;
Ok(io::BufWriter::new(Box::new(FooterProxy::new(
self.directory
.open_write(path)?
@@ -264,7 +299,7 @@ impl Directory for ManagedDirectory {
))))
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()> {
self.register_file_as_managed(path)?;
self.directory.atomic_write(path, data)
}
@@ -277,7 +312,7 @@ impl Directory for ManagedDirectory {
self.directory.delete(path)
}
fn exists(&self, path: &Path) -> bool {
fn exists(&self, path: &Path) -> Result<bool, OpenReadError> {
self.directory.exists(path)
}
@@ -325,22 +360,22 @@ mod tests_mmap_specific {
managed_directory
.atomic_write(test_path2, &[0u8, 1u8])
.unwrap();
assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path2));
assert!(managed_directory.exists(test_path1).unwrap());
assert!(managed_directory.exists(test_path2).unwrap());
let living_files: HashSet<PathBuf> = [test_path1.to_owned()].iter().cloned().collect();
managed_directory.garbage_collect(|| living_files);
assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path2).unwrap());
}
{
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
assert!(managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path2).unwrap());
let living_files: HashSet<PathBuf> = HashSet::new();
managed_directory.garbage_collect(|| living_files);
assert!(!managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(!managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path2).unwrap());
}
}
@@ -357,56 +392,58 @@ mod tests_mmap_specific {
let mut write = managed_directory.open_write(test_path1).unwrap();
write.write_all(&[0u8, 1u8]).unwrap();
write.terminate().unwrap();
assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path1).unwrap());
let _mmap_read = managed_directory.open_read(test_path1).unwrap();
managed_directory.garbage_collect(|| living_files.clone());
assert!(managed_directory
.garbage_collect(|| living_files.clone())
.is_ok());
if cfg!(target_os = "windows") {
// On Windows, gc should try and fail the file as it is mmapped.
assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path1).unwrap());
// unmap should happen here.
drop(_mmap_read);
// The file should still be in the list of managed file and
// eventually be deleted once mmap is released.
managed_directory.garbage_collect(|| living_files);
assert!(!managed_directory.exists(test_path1));
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(!managed_directory.exists(test_path1).unwrap());
} else {
assert!(!managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path1).unwrap());
}
}
#[test]
fn test_checksum() {
fn test_checksum() -> crate::Result<()> {
let test_path1: &'static Path = Path::new("some_path_for_test");
let test_path2: &'static Path = Path::new("other_test_path");
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let mut write = managed_directory.open_write(test_path1).unwrap();
write.write_all(&[0u8, 1u8]).unwrap();
write.terminate().unwrap();
let mmap_directory = MmapDirectory::open(&tempdir_path)?;
let managed_directory = ManagedDirectory::wrap(mmap_directory)?;
let mut write = managed_directory.open_write(test_path1)?;
write.write_all(&[0u8, 1u8])?;
write.terminate()?;
let mut write = managed_directory.open_write(test_path2).unwrap();
write.write_all(&[3u8, 4u8, 5u8]).unwrap();
write.terminate().unwrap();
let mut write = managed_directory.open_write(test_path2)?;
write.write_all(&[3u8, 4u8, 5u8])?;
write.terminate()?;
let read_file = managed_directory.open_read(test_path2)?.read_bytes()?;
assert_eq!(read_file.as_slice(), &[3u8, 4u8, 5u8]);
assert!(managed_directory.list_damaged().unwrap().is_empty());
let mut corrupted_path = tempdir_path.clone();
corrupted_path.push(test_path2);
let mut file = OpenOptions::new()
.write(true)
.open(&corrupted_path)
.unwrap();
file.write_all(&[255u8]).unwrap();
file.flush().unwrap();
let mut file = OpenOptions::new().write(true).open(&corrupted_path)?;
file.write_all(&[255u8])?;
file.flush()?;
drop(file);
let damaged = managed_directory.list_damaged().unwrap();
let damaged = managed_directory.list_damaged()?;
assert_eq!(damaged.len(), 1);
assert!(damaged.contains(test_path2));
Ok(())
}
}

312
src/directory/mmap_directory.rs
View File

@@ -1,28 +1,19 @@
use fs2;
use notify;
use self::fs2::FileExt;
use self::notify::RawEvent;
use self::notify::RecursiveMode;
use self::notify::Watcher;
use crate::core::META_FILEPATH;
use crate::directory::error::LockError;
use crate::directory::error::{
DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
};
use crate::directory::read_only_source::BoxedData;
use crate::directory::AntiCallToken;
use crate::directory::error::{DeleteError, OpenDirectoryError, OpenReadError, OpenWriteError};
use crate::directory::file_watcher::FileWatcher;
use crate::directory::Directory;
use crate::directory::DirectoryLock;
use crate::directory::Lock;
use crate::directory::ReadOnlySource;
use crate::directory::WatchCallback;
use crate::directory::WatchCallbackList;
use crate::directory::WatchHandle;
use crate::directory::{AntiCallToken, FileHandle, OwnedBytes};
use crate::directory::{ArcBytes, WeakArcBytes};
use crate::directory::{TerminatingWrite, WritePtr};
use atomicwrites;
use fs2::FileExt;
use memmap::Mmap;
use std::collections::HashMap;
use serde::{Deserialize, Serialize};
use stable_deref_trait::StableDeref;
use std::convert::From;
use std::fmt;
use std::fs::OpenOptions;
@@ -31,12 +22,9 @@ use std::io::{self, Seek, SeekFrom};
use std::io::{BufWriter, Read, Write};
use std::path::{Path, PathBuf};
use std::result;
use std::sync::mpsc::{channel, Receiver, Sender};
use std::sync::Arc;
use std::sync::Mutex;
use std::sync::RwLock;
use std::sync::Weak;
use std::thread;
use std::{collections::HashMap, ops::Deref};
use tempfile::TempDir;
/// Create a default io error given a string.
@@ -47,17 +35,17 @@ pub(crate) fn make_io_err(msg: String) -> io::Error {
/// Returns None iff the file exists, can be read, but is empty (and hence
/// cannot be mmapped)
fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
let file = File::open(full_path).map_err(|e| {
if e.kind() == io::ErrorKind::NotFound {
OpenReadError::FileDoesNotExist(full_path.to_owned())
let file = File::open(full_path).map_err(|io_err| {
if io_err.kind() == io::ErrorKind::NotFound {
OpenReadError::FileDoesNotExist(full_path.to_path_buf())
} else {
OpenReadError::IOError(IOError::with_path(full_path.to_owned(), e))
OpenReadError::wrap_io_error(io_err, full_path.to_path_buf())
}
})?;
let meta_data = file
.metadata()
.map_err(|e| IOError::with_path(full_path.to_owned(), e))?;
.map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_owned()))?;
if meta_data.len() == 0 {
// if the file size is 0, it will not be possible
// to mmap the file, so we return None
@@ -67,7 +55,7 @@ fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
unsafe {
memmap::Mmap::map(&file)
.map(Some)
.map_err(|e| From::from(IOError::with_path(full_path.to_owned(), e)))
.map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_path_buf()))
}
}
@@ -88,7 +76,7 @@ pub struct CacheInfo {
struct MmapCache {
counters: CacheCounters,
cache: HashMap<PathBuf, Weak<BoxedData>>,
cache: HashMap<PathBuf, WeakArcBytes>,
}
impl Default for MmapCache {
@@ -122,7 +110,7 @@ impl MmapCache {
}
// Returns None if the file exists but as a len of 0 (and hence is not mmappable).
fn get_mmap(&mut self, full_path: &Path) -> Result<Option<Arc<BoxedData>>, OpenReadError> {
fn get_mmap(&mut self, full_path: &Path) -> Result<Option<ArcBytes>, OpenReadError> {
if let Some(mmap_weak) = self.cache.get(full_path) {
if let Some(mmap_arc) = mmap_weak.upgrade() {
self.counters.hit += 1;
@@ -131,71 +119,13 @@ impl MmapCache {
}
self.cache.remove(full_path);
self.counters.miss += 1;
Ok(if let Some(mmap) = open_mmap(full_path)? {
let mmap_arc: Arc<BoxedData> = Arc::new(Box::new(mmap));
let mmap_opt = open_mmap(full_path)?;
Ok(mmap_opt.map(|mmap| {
let mmap_arc: ArcBytes = Arc::new(mmap);
let mmap_weak = Arc::downgrade(&mmap_arc);
self.cache.insert(full_path.to_owned(), mmap_weak);
Some(mmap_arc)
} else {
None
})
}
}
struct WatcherWrapper {
_watcher: Mutex<notify::RecommendedWatcher>,
watcher_router: Arc<WatchCallbackList>,
}
impl WatcherWrapper {
pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
// We need to initialize the
let watcher = notify::raw_watcher(tx)
.and_then(|mut watcher| {
watcher.watch(path, RecursiveMode::Recursive)?;
Ok(watcher)
})
.map_err(|err| match err {
notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()),
_ => {
panic!("Unknown error while starting watching directory {:?}", path);
}
})?;
let watcher_router: Arc<WatchCallbackList> = Default::default();
let watcher_router_clone = watcher_router.clone();
thread::Builder::new()
.name("meta-file-watch-thread".to_string())
.spawn(move || {
loop {
match watcher_recv.recv().map(|evt| evt.path) {
Ok(Some(changed_path)) => {
// ... Actually subject to false positive.
// We might want to be more accurate than this at one point.
if let Some(filename) = changed_path.file_name() {
if filename == *META_FILEPATH {
watcher_router_clone.broadcast();
}
}
}
Ok(None) => {
// not an event we are interested in.
}
Err(_e) => {
// the watch send channel was dropped
break;
}
}
}
})?;
Ok(WatcherWrapper {
_watcher: Mutex::new(watcher),
watcher_router,
})
}
pub fn watch(&mut self, watch_callback: WatchCallback) -> WatchHandle {
self.watcher_router.subscribe(watch_callback)
mmap_arc
}))
}
}
@@ -220,44 +150,21 @@ struct MmapDirectoryInner {
root_path: PathBuf,
mmap_cache: RwLock<MmapCache>,
_temp_directory: Option<TempDir>,
watcher: RwLock<Option<WatcherWrapper>>,
watcher: FileWatcher,
}
impl MmapDirectoryInner {
fn new(
root_path: PathBuf,
temp_directory: Option<TempDir>,
) -> Result<MmapDirectoryInner, OpenDirectoryError> {
let mmap_directory_inner = MmapDirectoryInner {
root_path,
fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectoryInner {
MmapDirectoryInner {
mmap_cache: Default::default(),
_temp_directory: temp_directory,
watcher: RwLock::new(None),
};
Ok(mmap_directory_inner)
watcher: FileWatcher::new(&root_path.join(*META_FILEPATH)),
root_path,
}
}
fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle> {
// a lot of juggling here, to ensure we don't do anything that panics
// while the rwlock is held. That way we ensure that the rwlock cannot
// be poisoned.
//
// The downside is that we might create a watch wrapper that is not useful.
let need_initialization = self.watcher.read().unwrap().is_none();
if need_initialization {
let watch_wrapper = WatcherWrapper::new(&self.root_path)?;
let mut watch_wlock = self.watcher.write().unwrap();
// the watcher could have been initialized when we released the lock, and
// we do not want to lose the watched files that were set.
if watch_wlock.is_none() {
*watch_wlock = Some(watch_wrapper);
}
}
if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() {
Ok(watch_wrapper.watch(watch_callback))
} else {
unreachable!("At this point, watch wrapper is supposed to be initialized");
}
fn watch(&self, callback: WatchCallback) -> crate::Result<WatchHandle> {
Ok(self.watcher.watch(callback))
}
}
@@ -268,14 +175,11 @@ impl fmt::Debug for MmapDirectory {
}
impl MmapDirectory {
fn new(
root_path: PathBuf,
temp_directory: Option<TempDir>,
) -> Result<MmapDirectory, OpenDirectoryError> {
let inner = MmapDirectoryInner::new(root_path, temp_directory)?;
Ok(MmapDirectory {
fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectory {
let inner = MmapDirectoryInner::new(root_path, temp_directory);
MmapDirectory {
inner: Arc::new(inner),
})
}
}
/// Creates a new MmapDirectory in a temporary directory.
@@ -283,9 +187,11 @@ impl MmapDirectory {
/// This is mostly useful to test the MmapDirectory itself.
/// For your unit tests, prefer the RAMDirectory.
pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> {
let tempdir = TempDir::new().map_err(OpenDirectoryError::IoError)?;
let tempdir_path = PathBuf::from(tempdir.path());
MmapDirectory::new(tempdir_path, Some(tempdir))
let tempdir = TempDir::new().map_err(OpenDirectoryError::FailedToCreateTempDir)?;
Ok(MmapDirectory::new(
tempdir.path().to_path_buf(),
Some(tempdir),
))
}
/// Opens a MmapDirectory in a directory.
@@ -303,7 +209,7 @@ impl MmapDirectory {
directory_path,
)))
} else {
Ok(MmapDirectory::new(PathBuf::from(directory_path), None)?)
Ok(MmapDirectory::new(PathBuf::from(directory_path), None))
}
}
@@ -407,8 +313,38 @@ impl TerminatingWrite for SafeFileWriter {
}
}
#[derive(Clone)]
struct MmapArc(Arc<dyn Deref<Target = [u8]> + Send + Sync>);
impl Deref for MmapArc {
type Target = [u8];
fn deref(&self) -> &[u8] {
self.0.deref()
}
}
unsafe impl StableDeref for MmapArc {}
/// Writes a file in an atomic manner.
pub(crate) fn atomic_write(path: &Path, content: &[u8]) -> io::Result<()> {
// We create the temporary file in the same directory as the target file.
// Indeed the canonical temp directory and the target file might sit in different
// filesystem, in which case the atomic write may actually not work.
let parent_path = path.parent().ok_or_else(|| {
io::Error::new(
io::ErrorKind::InvalidInput,
"Path {:?} does not have parent directory.",
)
})?;
let mut tempfile = tempfile::Builder::new().tempfile_in(&parent_path)?;
tempfile.write_all(content)?;
tempfile.flush()?;
tempfile.into_temp_path().persist(path)?;
Ok(())
}
impl Directory for MmapDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
fn get_file_handle(&self, path: &Path) -> result::Result<Box<dyn FileHandle>, OpenReadError> {
debug!("Open Read {:?}", path);
let full_path = self.resolve_path(path);
@@ -418,12 +354,19 @@ impl Directory for MmapDirectory {
on mmap cache while reading {:?}",
path
);
IOError::with_path(path.to_owned(), make_io_err(msg))
let io_err = make_io_err(msg);
OpenReadError::wrap_io_error(io_err, path.to_path_buf())
})?;
Ok(mmap_cache
let owned_bytes = mmap_cache
.get_mmap(&full_path)?
.map(ReadOnlySource::from)
.unwrap_or_else(ReadOnlySource::empty))
.map(|mmap_arc| {
let mmap_arc_obj = MmapArc(mmap_arc);
OwnedBytes::new(mmap_arc_obj)
})
.unwrap_or_else(OwnedBytes::empty);
Ok(Box::new(owned_bytes))
}
/// Any entry associated to the path in the mmap will be
@@ -431,25 +374,29 @@ impl Directory for MmapDirectory {
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
let full_path = self.resolve_path(path);
match fs::remove_file(&full_path) {
Ok(_) => self
.sync_directory()
.map_err(|e| IOError::with_path(path.to_owned(), e).into()),
Ok(_) => self.sync_directory().map_err(|e| DeleteError::IOError {
io_error: e,
filepath: path.to_path_buf(),
}),
Err(e) => {
if e.kind() == io::ErrorKind::NotFound {
Err(DeleteError::FileDoesNotExist(path.to_owned()))
} else {
Err(IOError::with_path(path.to_owned(), e).into())
Err(DeleteError::IOError {
io_error: e,
filepath: path.to_path_buf(),
})
}
}
}
}
fn exists(&self, path: &Path) -> bool {
fn exists(&self, path: &Path) -> Result<bool, OpenReadError> {
let full_path = self.resolve_path(path);
full_path.exists()
Ok(full_path.exists())
}
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
debug!("Open Write {:?}", path);
let full_path = self.resolve_path(path);
@@ -458,22 +405,22 @@ impl Directory for MmapDirectory {
.create_new(true)
.open(full_path);
let mut file = open_res.map_err(|err| {
if err.kind() == io::ErrorKind::AlreadyExists {
OpenWriteError::FileAlreadyExists(path.to_owned())
let mut file = open_res.map_err(|io_err| {
if io_err.kind() == io::ErrorKind::AlreadyExists {
OpenWriteError::FileAlreadyExists(path.to_path_buf())
} else {
IOError::with_path(path.to_owned(), err).into()
OpenWriteError::wrap_io_error(io_err, path.to_path_buf())
}
})?;
// making sure the file is created.
file.flush()
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
.map_err(|io_error| OpenWriteError::wrap_io_error(io_error, path.to_path_buf()))?;
// Apparetntly, on some filesystem syncing the parent
// directory is required.
self.sync_directory()
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
.map_err(|io_err| OpenWriteError::wrap_io_error(io_err, path.to_path_buf()))?;
let writer = SafeFileWriter::new(file);
Ok(BufWriter::new(Box::new(writer)))
@@ -484,26 +431,26 @@ impl Directory for MmapDirectory {
let mut buffer = Vec::new();
match File::open(&full_path) {
Ok(mut file) => {
file.read_to_end(&mut buffer)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
file.read_to_end(&mut buffer).map_err(|io_error| {
OpenReadError::wrap_io_error(io_error, path.to_path_buf())
})?;
Ok(buffer)
}
Err(e) => {
if e.kind() == io::ErrorKind::NotFound {
Err(io_error) => {
if io_error.kind() == io::ErrorKind::NotFound {
Err(OpenReadError::FileDoesNotExist(path.to_owned()))
} else {
Err(IOError::with_path(path.to_owned(), e).into())
Err(OpenReadError::wrap_io_error(io_error, path.to_path_buf()))
}
}
}
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fn atomic_write(&self, path: &Path, content: &[u8]) -> io::Result<()> {
debug!("Atomic Write {:?}", path);
let full_path = self.resolve_path(path);
let meta_file = atomicwrites::AtomicFile::new(full_path, atomicwrites::AllowOverwrite);
meta_file.write(|f| f.write_all(data))?;
Ok(())
atomic_write(&full_path, content)?;
self.sync_directory()
}
fn acquire_lock(&self, lock: &Lock) -> Result<DirectoryLock, LockError> {
@@ -541,13 +488,10 @@ mod tests {
use crate::schema::{Schema, SchemaBuilder, TEXT};
use crate::Index;
use crate::ReloadPolicy;
use std::fs;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::thread;
use std::time::Duration;
use crate::{common::HasLen, indexer::LogMergePolicy};
#[test]
fn test_open_non_existant_path() {
fn test_open_non_existent_path() {
assert!(MmapDirectory::open(PathBuf::from("./nowhere")).is_err());
}
@@ -557,7 +501,7 @@ mod tests {
// cannot be mmapped.
//
// In that case the directory returns a SharedVecSlice.
let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let path = PathBuf::from("test");
{
let mut w = mmap_directory.open_write(&path).unwrap();
@@ -573,7 +517,7 @@ mod tests {
// here we test if the cache releases
// mmaps correctly.
let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let num_paths = 10;
let paths: Vec<PathBuf> = (0..num_paths)
.map(|i| PathBuf::from(&*format!("file_{}", i)))
@@ -633,56 +577,48 @@ mod tests {
assert_eq!(mmap_directory.get_cache_info().mmapped.len(), 0);
}
#[test]
fn test_watch_wrapper() {
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let tmp_dir = tempfile::TempDir::new().unwrap();
let tmp_dirpath = tmp_dir.path().to_owned();
let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath).unwrap();
let tmp_file = tmp_dirpath.join("coucou");
let _handle = watch_wrapper.watch(Box::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
}));
assert_eq!(counter.load(Ordering::SeqCst), 0);
fs::write(&tmp_file, b"whateverwilldo").unwrap();
thread::sleep(Duration::new(0, 1_000u32));
}
#[test]
fn test_mmap_released() {
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let mut schema_builder: SchemaBuilder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
{
let index = Index::create(mmap_directory.clone(), schema).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for _num_commits in 0..16 {
let mut index_writer = index.writer_for_tests().unwrap();
let mut log_merge_policy = LogMergePolicy::default();
log_merge_policy.set_min_merge_size(3);
index_writer.set_merge_policy(Box::new(log_merge_policy));
for _num_commits in 0..10 {
for _ in 0..10 {
index_writer.add_document(doc!(text_field=>"abc"));
}
index_writer.commit().unwrap();
}
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
for _ in 0..30 {
for _ in 0..4 {
index_writer.add_document(doc!(text_field=>"abc"));
index_writer.commit().unwrap();
reader.reload().unwrap();
}
index_writer.wait_merging_threads().unwrap();
reader.reload().unwrap();
let num_segments = reader.searcher().segment_readers().len();
assert_eq!(num_segments, 4);
assert!(num_segments <= 4);
assert_eq!(
num_segments * 7,
mmap_directory.get_cache_info().mmapped.len()
);
}
assert_eq!(mmap_directory.get_cache_info().mmapped.len(), 0);
assert!(mmap_directory.get_cache_info().mmapped.is_empty());
}
}

36
src/directory/mod.rs
View File

@@ -9,10 +9,12 @@ mod mmap_directory;
mod directory;
mod directory_lock;
mod file_slice;
mod file_watcher;
mod footer;
mod managed_directory;
mod owned_bytes;
mod ram_directory;
mod read_only_source;
mod watch_event_router;
/// Errors specific to the directory module.
@@ -21,11 +23,27 @@ pub mod error;
pub use self::directory::DirectoryLock;
pub use self::directory::{Directory, DirectoryClone};
pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
pub(crate) use self::file_slice::{ArcBytes, WeakArcBytes};
pub use self::file_slice::{FileHandle, FileSlice};
pub use self::owned_bytes::OwnedBytes;
pub use self::ram_directory::RAMDirectory;
pub use self::read_only_source::ReadOnlySource;
pub(crate) use self::watch_event_router::WatchCallbackList;
pub use self::watch_event_router::{WatchCallback, WatchHandle};
pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};
use std::io::{self, BufWriter, Write};
use std::path::PathBuf;
/// Outcome of the Garbage collection
pub struct GarbageCollectionResult {
/// List of files that were deleted in this cycle
pub deleted_files: Vec<PathBuf>,
/// List of files that were schedule to be deleted in this cycle,
/// but deletion did not work. This typically happens on windows,
/// as deleting a memory mapped file is forbidden.
///
/// If a searcher is still held, a file cannot be deleted.
/// This is not considered a bug, the file will simply be deleted
/// in the next GC.
pub failed_to_delete_files: Vec<PathBuf>,
}
#[cfg(feature = "mmap")]
pub use self::mmap_directory::MmapDirectory;
@@ -33,6 +51,9 @@ pub use self::mmap_directory::MmapDirectory;
pub use self::managed_directory::ManagedDirectory;
/// Struct used to prevent from calling [`terminate_ref`](trait.TerminatingWrite#method.terminate_ref) directly
///
/// The point is that while the type is public, it cannot be built by anyone
/// outside of this module.
pub struct AntiCallToken(());
/// Trait used to indicate when no more write need to be done on a writer
@@ -63,6 +84,13 @@ impl<W: TerminatingWrite> TerminatingWrite for BufWriter<W> {
}
}
#[cfg(test)]
impl<'a> TerminatingWrite for &'a mut Vec<u8> {
fn terminate_ref(&mut self, _a: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
/// Write object for Directory.
///
/// `WritePtr` are required to implement both Write

290
src/directory/owned_bytes.rs Normal file
View File

@@ -0,0 +1,290 @@
use crate::directory::FileHandle;
use stable_deref_trait::StableDeref;
use std::convert::TryInto;
use std::mem;
use std::ops::Deref;
use std::sync::Arc;
use std::{fmt, io};
/// An OwnedBytes simply wraps an object that owns a slice of data and exposes
/// this data as a static slice.
///
/// The backing object is required to be `StableDeref`.
#[derive(Clone)]
pub struct OwnedBytes {
data: &'static [u8],
box_stable_deref: Arc<dyn Deref<Target = [u8]> + Sync + Send>,
}
impl FileHandle for OwnedBytes {
fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
Ok(self.slice(from, to))
}
}
impl OwnedBytes {
/// Creates an empty `OwnedBytes`.
pub fn empty() -> OwnedBytes {
OwnedBytes::new(&[][..])
}
/// Creates an `OwnedBytes` intance given a `StableDeref` object.
pub fn new<T: StableDeref + Deref<Target = [u8]> + 'static + Send + Sync>(
data_holder: T,
) -> OwnedBytes {
let box_stable_deref = Arc::new(data_holder);
let bytes: &[u8] = box_stable_deref.as_ref();
let data = unsafe { mem::transmute::<_, &'static [u8]>(bytes.deref()) };
OwnedBytes {
box_stable_deref,
data,
}
}
/// creates a fileslice that is just a view over a slice of the data.
pub fn slice(&self, from: usize, to: usize) -> Self {
OwnedBytes {
data: &self.data[from..to],
box_stable_deref: self.box_stable_deref.clone(),
}
}
/// Returns the underlying slice of data.
/// `Deref` and `AsRef` are also available.
#[inline(always)]
pub fn as_slice(&self) -> &[u8] {
self.data
}
/// Returns the len of the slice.
#[inline(always)]
pub fn len(&self) -> usize {
self.data.len()
}
/// Splits the OwnedBytes into two OwnedBytes `(left, right)`.
///
/// Left will hold `split_len` bytes.
///
/// This operation is cheap and does not require to copy any memory.
/// On the other hand, both `left` and `right` retain a handle over
/// the entire slice of memory. In other words, the memory will only
/// be released when both left and right are dropped.
pub fn split(self, split_len: usize) -> (OwnedBytes, OwnedBytes) {
let right_box_stable_deref = self.box_stable_deref.clone();
let left = OwnedBytes {
data: &self.data[..split_len],
box_stable_deref: self.box_stable_deref,
};
let right = OwnedBytes {
data: &self.data[split_len..],
box_stable_deref: right_box_stable_deref,
};
(left, right)
}
/// Returns true iff this `OwnedBytes` is empty.
#[inline(always)]
pub fn is_empty(&self) -> bool {
self.as_slice().is_empty()
}
/// Drops the left most `advance_len` bytes.
///
/// See also [.clip(clip_len: usize))](#method.clip).
#[inline(always)]
pub fn advance(&mut self, advance_len: usize) {
self.data = &self.data[advance_len..]
}
/// Reads an `u8` from the `OwnedBytes` and advance by one byte.
pub fn read_u8(&mut self) -> u8 {
assert!(!self.is_empty());
let byte = self.as_slice()[0];
self.advance(1);
byte
}
/// Reads an `u64` encoded as little-endian from the `OwnedBytes` and advance by 8 bytes.
pub fn read_u64(&mut self) -> u64 {
assert!(self.len() > 7);
let octlet: [u8; 8] = self.as_slice()[..8].try_into().unwrap();
self.advance(8);
u64::from_le_bytes(octlet)
}
}
impl fmt::Debug for OwnedBytes {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
// We truncate the bytes in order to make sure the debug string
// is not too long.
let bytes_truncated: &[u8] = if self.len() > 8 {
&self.as_slice()[..10]
} else {
self.as_slice()
};
write!(f, "OwnedBytes({:?}, len={})", bytes_truncated, self.len())
}
}
impl Deref for OwnedBytes {
type Target = [u8];
fn deref(&self) -> &Self::Target {
self.as_slice()
}
}
impl io::Read for OwnedBytes {
fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> {
let read_len = {
let data = self.as_slice();
if data.len() >= buf.len() {
let buf_len = buf.len();
buf.copy_from_slice(&data[..buf_len]);
buf.len()
} else {
let data_len = data.len();
buf[..data_len].copy_from_slice(data);
data_len
}
};
self.advance(read_len);
Ok(read_len)
}
fn read_to_end(&mut self, buf: &mut Vec<u8>) -> io::Result<usize> {
let read_len = {
let data = self.as_slice();
buf.extend(data);
data.len()
};
self.advance(read_len);
Ok(read_len)
}
fn read_exact(&mut self, buf: &mut [u8]) -> io::Result<()> {
let read_len = self.read(buf)?;
if read_len != buf.len() {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
"failed to fill whole buffer",
));
}
Ok(())
}
}
impl AsRef<[u8]> for OwnedBytes {
fn as_ref(&self) -> &[u8] {
self.as_slice()
}
}
#[cfg(test)]
mod tests {
use std::io::{self, Read};
use super::OwnedBytes;
#[test]
fn test_owned_bytes_debug() {
let short_bytes = OwnedBytes::new(b"abcd".as_ref());
assert_eq!(
format!("{:?}", short_bytes),
"OwnedBytes([97, 98, 99, 100], len=4)"
);
let long_bytes = OwnedBytes::new(b"abcdefghijklmnopq".as_ref());
assert_eq!(
format!("{:?}", long_bytes),
"OwnedBytes([97, 98, 99, 100, 101, 102, 103, 104, 105, 106], len=17)"
);
}
#[test]
fn test_owned_bytes_read() -> io::Result<()> {
let mut bytes = OwnedBytes::new(b"abcdefghiklmnopqrstuvwxyz".as_ref());
{
let mut buf = [0u8; 5];
bytes.read_exact(&mut buf[..]).unwrap();
assert_eq!(&buf, b"abcde");
assert_eq!(bytes.as_slice(), b"fghiklmnopqrstuvwxyz")
}
{
let mut buf = [0u8; 2];
bytes.read_exact(&mut buf[..]).unwrap();
assert_eq!(&buf, b"fg");
assert_eq!(bytes.as_slice(), b"hiklmnopqrstuvwxyz")
}
Ok(())
}
#[test]
fn test_owned_bytes_read_right_at_the_end() -> io::Result<()> {
let mut bytes = OwnedBytes::new(b"abcde".as_ref());
let mut buf = [0u8; 5];
assert_eq!(bytes.read(&mut buf[..]).unwrap(), 5);
assert_eq!(&buf, b"abcde");
assert_eq!(bytes.as_slice(), b"");
assert_eq!(bytes.read(&mut buf[..]).unwrap(), 0);
assert_eq!(&buf, b"abcde");
Ok(())
}
#[test]
fn test_owned_bytes_read_incomplete() -> io::Result<()> {
let mut bytes = OwnedBytes::new(b"abcde".as_ref());
let mut buf = [0u8; 7];
assert_eq!(bytes.read(&mut buf[..]).unwrap(), 5);
assert_eq!(&buf[..5], b"abcde");
assert_eq!(bytes.read(&mut buf[..]).unwrap(), 0);
Ok(())
}
#[test]
fn test_owned_bytes_read_to_end() -> io::Result<()> {
let mut bytes = OwnedBytes::new(b"abcde".as_ref());
let mut buf = Vec::new();
bytes.read_to_end(&mut buf)?;
assert_eq!(buf.as_slice(), b"abcde".as_ref());
Ok(())
}
#[test]
fn test_owned_bytes_read_u8() -> io::Result<()> {
let mut bytes = OwnedBytes::new(b"\xFF".as_ref());
assert_eq!(bytes.read_u8(), 255);
assert_eq!(bytes.len(), 0);
Ok(())
}
#[test]
fn test_owned_bytes_read_u64() -> io::Result<()> {
let mut bytes = OwnedBytes::new(b"\0\xFF\xFF\xFF\xFF\xFF\xFF\xFF".as_ref());
assert_eq!(bytes.read_u64(), u64::MAX - 255);
assert_eq!(bytes.len(), 0);
Ok(())
}
#[test]
fn test_owned_bytes_split() {
let bytes = OwnedBytes::new(b"abcdefghi".as_ref());
let (left, right) = bytes.split(3);
assert_eq!(left.as_slice(), b"abc");
assert_eq!(right.as_slice(), b"defghi");
}
#[test]
fn test_owned_bytes_split_boundary() {
let bytes = OwnedBytes::new(b"abcdefghi".as_ref());
{
let (left, right) = bytes.clone().split(0);
assert_eq!(left.as_slice(), b"");
assert_eq!(right.as_slice(), b"abcdefghi");
}
{
let (left, right) = bytes.split(9);
assert_eq!(left.as_slice(), b"abcdefghi");
assert_eq!(right.as_slice(), b"");
}
}
}

101
src/directory/ram_directory.rs
View File

@@ -1,9 +1,9 @@
use crate::core::META_FILEPATH;
use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
use crate::directory::AntiCallToken;
use crate::directory::WatchCallbackList;
use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
use crate::directory::{Directory, FileSlice, WatchCallback, WatchHandle};
use crate::directory::{TerminatingWrite, WritePtr};
use crate::{common::HasLen, core::META_FILEPATH};
use fail::fail_point;
use std::collections::HashMap;
use std::fmt;
@@ -12,6 +12,8 @@ use std::path::{Path, PathBuf};
use std::result;
use std::sync::{Arc, RwLock};
use super::FileHandle;
/// Writer associated with the `RAMDirectory`
///
/// The Writer just writes a buffer.
@@ -80,17 +82,17 @@ impl TerminatingWrite for VecWriter {
#[derive(Default)]
struct InnerDirectory {
fs: HashMap<PathBuf, ReadOnlySource>,
fs: HashMap<PathBuf, FileSlice>,
watch_router: WatchCallbackList,
}
impl InnerDirectory {
fn write(&mut self, path: PathBuf, data: &[u8]) -> bool {
let data = ReadOnlySource::new(Vec::from(data));
let data = FileSlice::from(data.to_vec());
self.fs.insert(path, data).is_some()
}
fn open_read(&self, path: &Path) -> Result<ReadOnlySource, OpenReadError> {
fn open_read(&self, path: &Path) -> Result<FileSlice, OpenReadError> {
self.fs
.get(path)
.ok_or_else(|| OpenReadError::FileDoesNotExist(PathBuf::from(path)))
@@ -144,27 +146,56 @@ impl RAMDirectory {
pub fn total_mem_usage(&self) -> usize {
self.fs.read().unwrap().total_mem_usage()
}
/// Write a copy of all of the files saved in the RAMDirectory in the target `Directory`.
///
/// Files are all written using the `Directory::write` meaning, even if they were
/// written using the `atomic_write` api.
///
/// If an error is encounterred, files may be persisted partially.
pub fn persist(&self, dest: &dyn Directory) -> crate::Result<()> {
let wlock = self.fs.write().unwrap();
for (path, file) in wlock.fs.iter() {
let mut dest_wrt = dest.open_write(path)?;
dest_wrt.write_all(file.read_bytes()?.as_slice())?;
dest_wrt.terminate()?;
}
Ok(())
}
}
impl Directory for RAMDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
fn get_file_handle(&self, path: &Path) -> Result<Box<dyn FileHandle>, OpenReadError> {
let file_slice = self.open_read(path)?;
Ok(Box::new(file_slice))
}
fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
self.fs.read().unwrap().open_read(path)
}
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
fail_point!("RAMDirectory::delete", |_| {
use crate::directory::error::IOError;
let io_error = IOError::from(io::Error::from(io::ErrorKind::Other));
Err(DeleteError::from(io_error))
Err(DeleteError::IOError {
io_error: io::Error::from(io::ErrorKind::Other),
filepath: path.to_path_buf(),
})
});
self.fs.write().unwrap().delete(path)
}
fn exists(&self, path: &Path) -> bool {
self.fs.read().unwrap().exists(path)
fn exists(&self, path: &Path) -> Result<bool, OpenReadError> {
Ok(self
.fs
.read()
.map_err(|e| OpenReadError::IOError {
io_error: io::Error::new(io::ErrorKind::Other, e.to_string()),
filepath: path.to_path_buf(),
})?
.exists(path))
}
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
let mut fs = self.fs.write().unwrap();
let path_buf = PathBuf::from(path);
let vec_writer = VecWriter::new(path_buf.clone(), self.clone());
@@ -178,24 +209,27 @@ impl Directory for RAMDirectory {
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
Ok(self.open_read(path)?.as_slice().to_owned())
let bytes =
self.open_read(path)?
.read_bytes()
.map_err(|io_error| OpenReadError::IOError {
io_error,
filepath: path.to_path_buf(),
})?;
Ok(bytes.as_slice().to_owned())
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()> {
fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
io::ErrorKind::Other,
msg.unwrap_or_else(|| "Undefined".to_string())
)));
let path_buf = PathBuf::from(path);
// Reserve the path to prevent calls to .write() to succeed.
self.fs.write().unwrap().write(path_buf.clone(), &[]);
self.fs.write().unwrap().write(path_buf, data);
let mut vec_writer = VecWriter::new(path_buf.clone(), self.clone());
vec_writer.write_all(data)?;
vec_writer.flush()?;
if path == Path::new(&*META_FILEPATH) {
self.fs.write().unwrap().watch_router.broadcast();
if path == *META_FILEPATH {
let _ = self.fs.write().unwrap().watch_router.broadcast();
}
Ok(())
}
@@ -204,3 +238,28 @@ impl Directory for RAMDirectory {
Ok(self.fs.write().unwrap().watch(watch_callback))
}
}
#[cfg(test)]
mod tests {
use super::RAMDirectory;
use crate::Directory;
use std::io::Write;
use std::path::Path;
#[test]
fn test_persist() {
let msg_atomic: &'static [u8] = b"atomic is the way";
let msg_seq: &'static [u8] = b"sequential is the way";
let path_atomic: &'static Path = Path::new("atomic");
let path_seq: &'static Path = Path::new("seq");
let directory = RAMDirectory::create();
assert!(directory.atomic_write(path_atomic, msg_atomic).is_ok());
let mut wrt = directory.open_write(path_seq).unwrap();
assert!(wrt.write_all(msg_seq).is_ok());
assert!(wrt.flush().is_ok());
let directory_copy = RAMDirectory::create();
assert!(directory.persist(&directory_copy).is_ok());
assert_eq!(directory_copy.atomic_read(path_atomic).unwrap(), msg_atomic);
assert_eq!(directory_copy.atomic_read(path_seq).unwrap(), msg_seq);
}
}

131
src/directory/read_only_source.rs
View File

@@ -1,131 +0,0 @@
use crate::common::HasLen;
use stable_deref_trait::{CloneStableDeref, StableDeref};
use std::ops::Deref;
use std::sync::Arc;
pub type BoxedData = Box<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
/// Read object that represents files in tantivy.
///
/// These read objects are only in charge to deliver
/// the data in the form of a constant read-only `&[u8]`.
/// Whatever happens to the directory file, the data
/// hold by this object should never be altered or destroyed.
pub struct ReadOnlySource {
data: Arc<BoxedData>,
start: usize,
stop: usize,
}
unsafe impl StableDeref for ReadOnlySource {}
unsafe impl CloneStableDeref for ReadOnlySource {}
impl Deref for ReadOnlySource {
type Target = [u8];
fn deref(&self) -> &[u8] {
self.as_slice()
}
}
impl From<Arc<BoxedData>> for ReadOnlySource {
fn from(data: Arc<BoxedData>) -> Self {
let len = data.len();
ReadOnlySource {
data,
start: 0,
stop: len,
}
}
}
impl ReadOnlySource {
pub(crate) fn new<D>(data: D) -> ReadOnlySource
where
D: Deref<Target = [u8]> + Send + Sync + 'static,
{
let len = data.len();
ReadOnlySource {
data: Arc::new(Box::new(data)),
start: 0,
stop: len,
}
}
/// Creates an empty ReadOnlySource
pub fn empty() -> ReadOnlySource {
ReadOnlySource::new(&[][..])
}
/// Returns the data underlying the ReadOnlySource object.
pub fn as_slice(&self) -> &[u8] {
&self.data[self.start..self.stop]
}
/// Splits into 2 `ReadOnlySource`, at the offset given
/// as an argument.
pub fn split(self, addr: usize) -> (ReadOnlySource, ReadOnlySource) {
let left = self.slice(0, addr);
let right = self.slice_from(addr);
(left, right)
}
/// Creates a ReadOnlySource that is just a
/// view over a slice of the data.
///
/// Keep in mind that any living slice extends
/// the lifetime of the original ReadOnlySource,
///
/// For instance, if `ReadOnlySource` wraps 500MB
/// worth of data in anonymous memory, and only a
/// 1KB slice is remaining, the whole `500MBs`
/// are retained in memory.
pub fn slice(&self, start: usize, stop: usize) -> ReadOnlySource {
assert!(
start <= stop,
"Requested negative slice [{}..{}]",
start,
stop
);
assert!(stop <= self.len());
ReadOnlySource {
data: self.data.clone(),
start: self.start + start,
stop: self.start + stop,
}
}
/// Like `.slice(...)` but enforcing only the `from`
/// boundary.
///
/// Equivalent to `.slice(from_offset, self.len())`
pub fn slice_from(&self, from_offset: usize) -> ReadOnlySource {
self.slice(from_offset, self.len())
}
/// Like `.slice(...)` but enforcing only the `to`
/// boundary.
///
/// Equivalent to `.slice(0, to_offset)`
pub fn slice_to(&self, to_offset: usize) -> ReadOnlySource {
self.slice(0, to_offset)
}
}
impl HasLen for ReadOnlySource {
fn len(&self) -> usize {
self.stop - self.start
}
}
impl Clone for ReadOnlySource {
fn clone(&self) -> Self {
self.slice_from(0)
}
}
impl From<Vec<u8>> for ReadOnlySource {
fn from(data: Vec<u8>) -> ReadOnlySource {
ReadOnlySource::new(data)
}
}

272
src/directory/tests.rs
View File

@@ -1,93 +1,182 @@
use super::*;
use futures::channel::oneshot;
use futures::executor::block_on;
use std::io::Write;
use std::mem;
use std::path::{Path, PathBuf};
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering;
use std::sync::atomic::Ordering::SeqCst;
use std::sync::atomic::{AtomicBool, AtomicUsize};
use std::sync::Arc;
use std::thread;
use std::time;
use std::time::Duration;
#[test]
fn test_ram_directory() {
let mut ram_directory = RAMDirectory::create();
test_directory(&mut ram_directory);
#[cfg(feature = "mmap")]
mod mmap_directory_tests {
use crate::directory::MmapDirectory;
type DirectoryImpl = MmapDirectory;
fn make_directory() -> DirectoryImpl {
MmapDirectory::create_from_tempdir().unwrap()
}
#[test]
fn test_simple() -> crate::Result<()> {
let directory = make_directory();
super::test_simple(&directory)
}
#[test]
fn test_write_create_the_file() {
let directory = make_directory();
super::test_write_create_the_file(&directory);
}
#[test]
fn test_rewrite_forbidden() -> crate::Result<()> {
let directory = make_directory();
super::test_rewrite_forbidden(&directory)?;
Ok(())
}
#[test]
fn test_directory_delete() -> crate::Result<()> {
let directory = make_directory();
super::test_directory_delete(&directory)?;
Ok(())
}
#[test]
fn test_lock_non_blocking() {
let directory = make_directory();
super::test_lock_non_blocking(&directory);
}
#[test]
fn test_lock_blocking() {
let directory = make_directory();
super::test_lock_blocking(&directory);
}
#[test]
fn test_watch() {
let directory = make_directory();
super::test_watch(&directory);
}
}
#[test]
#[cfg(feature = "mmap")]
fn test_mmap_directory() {
let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
test_directory(&mut mmap_directory);
mod ram_directory_tests {
use crate::directory::RAMDirectory;
type DirectoryImpl = RAMDirectory;
fn make_directory() -> DirectoryImpl {
RAMDirectory::default()
}
#[test]
fn test_simple() -> crate::Result<()> {
let directory = make_directory();
super::test_simple(&directory)
}
#[test]
fn test_write_create_the_file() {
let directory = make_directory();
super::test_write_create_the_file(&directory);
}
#[test]
fn test_rewrite_forbidden() -> crate::Result<()> {
let directory = make_directory();
super::test_rewrite_forbidden(&directory)?;
Ok(())
}
#[test]
fn test_directory_delete() -> crate::Result<()> {
let directory = make_directory();
super::test_directory_delete(&directory)?;
Ok(())
}
#[test]
fn test_lock_non_blocking() {
let directory = make_directory();
super::test_lock_non_blocking(&directory);
}
#[test]
fn test_lock_blocking() {
let directory = make_directory();
super::test_lock_blocking(&directory);
}
#[test]
fn test_watch() {
let directory = make_directory();
super::test_watch(&directory);
}
}
#[test]
#[should_panic]
fn ram_directory_panics_if_flush_forgotten() {
let test_path: &'static Path = Path::new("some_path_for_test");
let mut ram_directory = RAMDirectory::create();
let ram_directory = RAMDirectory::create();
let mut write_file = ram_directory.open_write(test_path).unwrap();
assert!(write_file.write_all(&[4]).is_ok());
}
fn test_simple(directory: &mut dyn Directory) {
fn test_simple(directory: &dyn Directory) -> crate::Result<()> {
let test_path: &'static Path = Path::new("some_path_for_test");
{
let mut write_file = directory.open_write(test_path).unwrap();
assert!(directory.exists(test_path));
write_file.write_all(&[4]).unwrap();
write_file.write_all(&[3]).unwrap();
write_file.write_all(&[7, 3, 5]).unwrap();
write_file.flush().unwrap();
}
{
let read_file = directory.open_read(test_path).unwrap();
let data: &[u8] = &*read_file;
assert_eq!(data, &[4u8, 3u8, 7u8, 3u8, 5u8]);
}
let mut write_file = directory.open_write(test_path)?;
assert!(directory.exists(test_path).unwrap());
write_file.write_all(&[4])?;
write_file.write_all(&[3])?;
write_file.write_all(&[7, 3, 5])?;
write_file.flush()?;
let read_file = directory.open_read(test_path)?.read_bytes()?;
assert_eq!(read_file.as_slice(), &[4u8, 3u8, 7u8, 3u8, 5u8]);
mem::drop(read_file);
assert!(directory.delete(test_path).is_ok());
assert!(!directory.exists(test_path));
assert!(!directory.exists(test_path).unwrap());
Ok(())
}
fn test_rewrite_forbidden(directory: &mut dyn Directory) {
fn test_rewrite_forbidden(directory: &dyn Directory) -> crate::Result<()> {
let test_path: &'static Path = Path::new("some_path_for_test");
{
directory.open_write(test_path).unwrap();
assert!(directory.exists(test_path));
}
{
assert!(directory.open_write(test_path).is_err());
}
directory.open_write(test_path)?;
assert!(directory.exists(test_path).unwrap());
assert!(directory.open_write(test_path).is_err());
assert!(directory.delete(test_path).is_ok());
Ok(())
}
fn test_write_create_the_file(directory: &mut dyn Directory) {
fn test_write_create_the_file(directory: &dyn Directory) {
let test_path: &'static Path = Path::new("some_path_for_test");
{
assert!(directory.open_read(test_path).is_err());
let _w = directory.open_write(test_path).unwrap();
assert!(directory.exists(test_path));
assert!(directory.exists(test_path).unwrap());
assert!(directory.open_read(test_path).is_ok());
assert!(directory.delete(test_path).is_ok());
}
}
fn test_directory_delete(directory: &mut dyn Directory) {
fn test_directory_delete(directory: &dyn Directory) -> crate::Result<()> {
let test_path: &'static Path = Path::new("some_path_for_test");
assert!(directory.open_read(test_path).is_err());
let mut write_file = directory.open_write(&test_path).unwrap();
write_file.write_all(&[1, 2, 3, 4]).unwrap();
write_file.flush().unwrap();
let mut write_file = directory.open_write(&test_path)?;
write_file.write_all(&[1, 2, 3, 4])?;
write_file.flush()?;
{
let read_handle = directory.open_read(&test_path).unwrap();
assert_eq!(&*read_handle, &[1u8, 2u8, 3u8, 4u8]);
let read_handle = directory.open_read(&test_path)?.read_bytes()?;
assert_eq!(read_handle.as_slice(), &[1u8, 2u8, 3u8, 4u8]);
// Mapped files can't be deleted on Windows
if !cfg!(windows) {
assert!(directory.delete(&test_path).is_ok());
assert_eq!(&*read_handle, &[1u8, 2u8, 3u8, 4u8]);
assert_eq!(read_handle.as_slice(), &[1u8, 2u8, 3u8, 4u8]);
}
assert!(directory.delete(Path::new("SomeOtherPath")).is_err());
}
@@ -97,53 +186,40 @@ fn test_directory_delete(directory: &mut dyn Directory) {
assert!(directory.open_read(&test_path).is_err());
assert!(directory.delete(&test_path).is_err());
Ok(())
}
fn test_directory(directory: &mut dyn Directory) {
test_simple(directory);
test_rewrite_forbidden(directory);
test_write_create_the_file(directory);
test_directory_delete(directory);
test_lock_non_blocking(directory);
test_lock_blocking(directory);
test_watch(directory);
}
fn test_watch(directory: &mut dyn Directory) {
fn test_watch(directory: &dyn Directory) {
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let watch_callback = Box::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
});
assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data")
.is_ok());
thread::sleep(Duration::new(0, 10_000));
assert_eq!(0, counter.load(Ordering::SeqCst));
let (tx, rx) = crossbeam::channel::unbounded();
let timeout = Duration::from_millis(500);
let handle = directory
.watch(WatchCallback::new(move || {
let val = counter.fetch_add(1, SeqCst);
tx.send(val + 1).unwrap();
}))
.unwrap();
let watch_handle = directory.watch(watch_callback).unwrap();
for i in 0..10 {
assert_eq!(i, counter.load(Ordering::SeqCst));
assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data_2")
.is_ok());
for _ in 0..1_000 {
if counter.load(Ordering::SeqCst) > i {
break;
}
thread::sleep(Duration::from_millis(10));
}
assert_eq!(i + 1, counter.load(Ordering::SeqCst));
}
mem::drop(watch_handle);
assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data")
.atomic_write(Path::new("meta.json"), b"foo")
.is_ok());
thread::sleep(Duration::from_millis(200));
assert_eq!(10, counter.load(Ordering::SeqCst));
assert_eq!(rx.recv_timeout(timeout), Ok(1));
assert!(directory
.atomic_write(Path::new("meta.json"), b"bar")
.is_ok());
assert_eq!(rx.recv_timeout(timeout), Ok(2));
mem::drop(handle);
assert!(directory
.atomic_write(Path::new("meta.json"), b"qux")
.is_ok());
assert!(rx.recv_timeout(timeout).is_err());
}
fn test_lock_non_blocking(directory: &mut dyn Directory) {
fn test_lock_non_blocking(directory: &dyn Directory) {
{
let lock_a_res = directory.acquire_lock(&Lock {
filepath: PathBuf::from("a.lock"),
@@ -168,15 +244,19 @@ fn test_lock_non_blocking(directory: &mut dyn Directory) {
assert!(lock_a_res.is_ok());
}
fn test_lock_blocking(directory: &mut dyn Directory) {
fn test_lock_blocking(directory: &dyn Directory) {
let lock_a_res = directory.acquire_lock(&Lock {
filepath: PathBuf::from("a.lock"),
is_blocking: true,
});
assert!(lock_a_res.is_ok());
let in_thread = Arc::new(AtomicBool::default());
let in_thread_clone = in_thread.clone();
let (sender, receiver) = oneshot::channel();
std::thread::spawn(move || {
//< lock_a_res is sent to the thread.
std::thread::sleep(time::Duration::from_millis(10));
in_thread_clone.store(true, SeqCst);
let _just_sync = block_on(receiver);
// explicitely droping lock_a_res. It would have been sufficient to just force it
// to be part of the move, but the intent seems clearer that way.
drop(lock_a_res);
@@ -189,14 +269,18 @@ fn test_lock_blocking(directory: &mut dyn Directory) {
});
assert!(lock_a_res.is_err());
}
{
// the blocking call should wait for at least 10ms.
let start = time::Instant::now();
let lock_a_res = directory.acquire_lock(&Lock {
let directory_clone = directory.box_clone();
let (sender2, receiver2) = oneshot::channel();
let join_handle = std::thread::spawn(move || {
assert!(sender2.send(()).is_ok());
let lock_a_res = directory_clone.acquire_lock(&Lock {
filepath: PathBuf::from("a.lock"),
is_blocking: true,
});
assert!(in_thread.load(SeqCst));
assert!(lock_a_res.is_ok());
assert!(start.elapsed().subsec_millis() >= 10);
}
});
assert!(block_on(receiver2).is_ok());
assert!(sender.send(()).is_ok());
assert!(join_handle.join().is_ok());
}

118
src/directory/watch_event_router.rs
View File

@@ -1,9 +1,23 @@
use futures::channel::oneshot;
use futures::{Future, TryFutureExt};
use std::sync::Arc;
use std::sync::RwLock;
use std::sync::Weak;
/// Type alias for callbacks registered when watching files of a `Directory`.
pub type WatchCallback = Box<dyn Fn() -> () + Sync + Send>;
/// Cloneable wrapper for callbacks registered when watching files of a `Directory`.
#[derive(Clone)]
pub struct WatchCallback(Arc<dyn Fn() + Sync + Send>);
impl WatchCallback {
/// Wraps a `Fn()` to create a WatchCallback.
pub fn new<F: Fn() + Sync + Send + 'static>(op: F) -> Self {
WatchCallback(Arc::new(op))
}
fn call(&self) {
self.0()
}
}
/// Helper struct to implement the watch method in `Directory` implementations.
///
@@ -22,22 +36,36 @@ pub struct WatchCallbackList {
#[derive(Clone)]
pub struct WatchHandle(Arc<WatchCallback>);
impl WatchHandle {
/// Create a WatchHandle handle.
pub fn new(watch_callback: Arc<WatchCallback>) -> WatchHandle {
WatchHandle(watch_callback)
}
/// Returns an empty watch handle.
///
/// This function is only useful when implementing a readonly directory.
pub fn empty() -> WatchHandle {
WatchHandle::new(Arc::new(WatchCallback::new(|| {})))
}
}
impl WatchCallbackList {
/// Suscribes a new callback and returns a handle that controls the lifetime of the callback.
/// Subscribes a new callback and returns a handle that controls the lifetime of the callback.
pub fn subscribe(&self, watch_callback: WatchCallback) -> WatchHandle {
let watch_callback_arc = Arc::new(watch_callback);
let watch_callback_weak = Arc::downgrade(&watch_callback_arc);
self.router.write().unwrap().push(watch_callback_weak);
WatchHandle(watch_callback_arc)
WatchHandle::new(watch_callback_arc)
}
fn list_callback(&self) -> Vec<Arc<WatchCallback>> {
let mut callbacks = vec![];
fn list_callback(&self) -> Vec<WatchCallback> {
let mut callbacks: Vec<WatchCallback> = vec![];
let mut router_wlock = self.router.write().unwrap();
let mut i = 0;
while i < router_wlock.len() {
if let Some(watch) = router_wlock[i].upgrade() {
callbacks.push(watch);
callbacks.push(watch.as_ref().clone());
i += 1;
} else {
router_wlock.swap_remove(i);
@@ -47,14 +75,21 @@ impl WatchCallbackList {
}
/// Triggers all callbacks
pub fn broadcast(&self) {
pub fn broadcast(&self) -> impl Future<Output = ()> {
let callbacks = self.list_callback();
let (sender, receiver) = oneshot::channel();
let result = receiver.unwrap_or_else(|_| ());
if callbacks.is_empty() {
let _ = sender.send(());
return result;
}
let spawn_res = std::thread::Builder::new()
.name("watch-callbacks".to_string())
.spawn(move || {
for callback in callbacks {
callback();
callback.call();
}
let _ = sender.send(());
});
if let Err(err) = spawn_res {
error!(
@@ -62,44 +97,42 @@ impl WatchCallbackList {
err
);
}
result
}
}
#[cfg(test)]
mod tests {
use crate::directory::WatchCallbackList;
use crate::directory::{WatchCallback, WatchCallbackList};
use futures::executor::block_on;
use std::mem;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::sync::Arc;
use std::thread;
use std::time::Duration;
const WAIT_TIME: u64 = 20;
#[test]
fn test_watch_event_router_simple() {
let watch_event_router = WatchCallbackList::default();
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let inc_callback = Box::new(move || {
let inc_callback = WatchCallback::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
});
watch_event_router.broadcast();
block_on(watch_event_router.broadcast());
assert_eq!(0, counter.load(Ordering::SeqCst));
let handle_a = watch_event_router.subscribe(inc_callback);
thread::sleep(Duration::from_millis(WAIT_TIME));
assert_eq!(0, counter.load(Ordering::SeqCst));
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(watch_event_router.broadcast());
assert_eq!(1, counter.load(Ordering::SeqCst));
watch_event_router.broadcast();
watch_event_router.broadcast();
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(async {
(
watch_event_router.broadcast().await,
watch_event_router.broadcast().await,
watch_event_router.broadcast().await,
)
});
assert_eq!(4, counter.load(Ordering::SeqCst));
mem::drop(handle_a);
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(watch_event_router.broadcast());
assert_eq!(4, counter.load(Ordering::SeqCst));
}
@@ -109,26 +142,26 @@ mod tests {
let counter: Arc<AtomicUsize> = Default::default();
let inc_callback = |inc: usize| {
let counter_clone = counter.clone();
Box::new(move || {
WatchCallback::new(move || {
counter_clone.fetch_add(inc, Ordering::SeqCst);
})
};
let handle_a = watch_event_router.subscribe(inc_callback(1));
let handle_a2 = watch_event_router.subscribe(inc_callback(10));
thread::sleep(Duration::from_millis(WAIT_TIME));
assert_eq!(0, counter.load(Ordering::SeqCst));
watch_event_router.broadcast();
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(async {
futures::join!(
watch_event_router.broadcast(),
watch_event_router.broadcast()
)
});
assert_eq!(22, counter.load(Ordering::SeqCst));
mem::drop(handle_a);
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(watch_event_router.broadcast());
assert_eq!(32, counter.load(Ordering::SeqCst));
mem::drop(handle_a2);
watch_event_router.broadcast();
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(watch_event_router.broadcast());
block_on(watch_event_router.broadcast());
assert_eq!(32, counter.load(Ordering::SeqCst));
}
@@ -137,19 +170,20 @@ mod tests {
let watch_event_router = WatchCallbackList::default();
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let inc_callback = Box::new(move || {
let inc_callback = WatchCallback::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
});
let handle_a = watch_event_router.subscribe(inc_callback);
assert_eq!(0, counter.load(Ordering::SeqCst));
watch_event_router.broadcast();
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
block_on(async {
let future1 = watch_event_router.broadcast();
let future2 = watch_event_router.broadcast();
futures::join!(future1, future2)
});
assert_eq!(2, counter.load(Ordering::SeqCst));
thread::sleep(Duration::from_millis(WAIT_TIME));
mem::drop(handle_a);
watch_event_router.broadcast();
thread::sleep(Duration::from_millis(WAIT_TIME));
let _ = watch_event_router.broadcast();
block_on(watch_event_router.broadcast());
assert_eq!(2, counter.load(Ordering::SeqCst));
}
}

141
src/docset.rs
View File

@@ -1,58 +1,48 @@
use crate::common::BitSet;
use crate::fastfield::DeleteBitSet;
use crate::DocId;
use std::borrow::Borrow;
use std::borrow::BorrowMut;
use std::cmp::Ordering;
/// Expresses the outcome of a call to `DocSet`'s `.skip_next(...)`.
#[derive(PartialEq, Eq, Debug)]
pub enum SkipResult {
/// target was in the docset
Reached,
/// target was not in the docset, skipping stopped as a greater element was found
OverStep,
/// the docset was entirely consumed without finding the target, nor any
/// element greater than the target.
End,
}
/// Sentinel value returned when a DocSet has been entirely consumed.
///
/// This is not u32::MAX as one would have expected, due to the lack of SSE2 instructions
/// to compare [u32; 4].
pub const TERMINATED: DocId = std::i32::MAX as u32;
/// Represents an iterable set of sorted doc ids.
pub trait DocSet {
pub trait DocSet: Send {
/// Goes to the next element.
/// `.advance(...)` needs to be called a first time to point to the correct
/// element.
fn advance(&mut self) -> bool;
///
/// The DocId of the next element is returned.
/// In other words we should always have :
/// ```ignore
/// let doc = docset.advance();
/// assert_eq!(doc, docset.doc());
/// ```
///
/// If we reached the end of the DocSet, TERMINATED should be returned.
///
/// Calling `.advance()` on a terminated DocSet should be supported, and TERMINATED should
/// be returned.
/// TODO Test existing docsets.
fn advance(&mut self) -> DocId;
/// After skipping, position the iterator in such a way that `.doc()`
/// will return a value greater than or equal to target.
/// Advances the DocSet forward until reaching the target, or going to the
/// lowest DocId greater than the target.
///
/// SkipResult expresses whether the `target value` was reached, overstepped,
/// or if the `DocSet` was entirely consumed without finding any value
/// greater or equal to the `target`.
/// If the end of the DocSet is reached, TERMINATED is returned.
///
/// WARNING: Calling skip always advances the docset.
/// More specifically, if the docset is already positionned on the target
/// skipping will advance to the next position and return SkipResult::Overstep.
/// Calling `.seek(target)` on a terminated DocSet is legal. Implementation
/// of DocSet should support it.
///
/// If `.skip_next()` oversteps, then the docset must be positionned correctly
/// on an existing document. In other words, `.doc()` should return the first document
/// greater than `DocId`.
fn skip_next(&mut self, target: DocId) -> SkipResult {
if !self.advance() {
return SkipResult::End;
}
loop {
match self.doc().cmp(&target) {
Ordering::Less => {
if !self.advance() {
return SkipResult::End;
}
}
Ordering::Equal => return SkipResult::Reached,
Ordering::Greater => return SkipResult::OverStep,
}
/// Calling `seek(TERMINATED)` is also legal and is the normal way to consume a DocSet.
fn seek(&mut self, target: DocId) -> DocId {
let mut doc = self.doc();
debug_assert!(doc <= target);
while doc < target {
doc = self.advance();
}
doc
}
/// Fills a given mutable buffer with the next doc ids from the
@@ -71,38 +61,38 @@ pub trait DocSet {
/// use case where batching. The normal way to
/// go through the `DocId`'s is to call `.advance()`.
fn fill_buffer(&mut self, buffer: &mut [DocId]) -> usize {
if self.doc() == TERMINATED {
return 0;
}
for (i, buffer_val) in buffer.iter_mut().enumerate() {
if self.advance() {
*buffer_val = self.doc();
} else {
return i;
*buffer_val = self.doc();
if self.advance() == TERMINATED {
return i + 1;
}
}
buffer.len()
}
/// Returns the current document
/// Right after creating a new DocSet, the docset points to the first document.
///
/// If the DocSet is empty, .doc() should return `TERMINATED`.
fn doc(&self) -> DocId;
/// Returns a best-effort hint of the
/// length of the docset.
fn size_hint(&self) -> u32;
/// Appends all docs to a `bitset`.
fn append_to_bitset(&mut self, bitset: &mut BitSet) {
while self.advance() {
bitset.insert(self.doc());
}
}
/// Returns the number documents matching.
/// Calling this method consumes the `DocSet`.
fn count(&mut self, delete_bitset: &DeleteBitSet) -> u32 {
let mut count = 0u32;
while self.advance() {
if !delete_bitset.is_deleted(self.doc()) {
let mut doc = self.doc();
while doc != TERMINATED {
if !delete_bitset.is_deleted(doc) {
count += 1u32;
}
doc = self.advance();
}
count
}
@@ -114,22 +104,50 @@ pub trait DocSet {
/// given by `count()`.
fn count_including_deleted(&mut self) -> u32 {
let mut count = 0u32;
while self.advance() {
let mut doc = self.doc();
while doc != TERMINATED {
count += 1u32;
doc = self.advance();
}
count
}
}
impl<'a> DocSet for &'a mut dyn DocSet {
fn advance(&mut self) -> u32 {
(**self).advance()
}
fn seek(&mut self, target: DocId) -> DocId {
(**self).seek(target)
}
fn doc(&self) -> u32 {
(**self).doc()
}
fn size_hint(&self) -> u32 {
(**self).size_hint()
}
fn count(&mut self, delete_bitset: &DeleteBitSet) -> u32 {
(**self).count(delete_bitset)
}
fn count_including_deleted(&mut self) -> u32 {
(**self).count_including_deleted()
}
}
impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
fn advance(&mut self) -> bool {
fn advance(&mut self) -> DocId {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.advance()
}
fn skip_next(&mut self, target: DocId) -> SkipResult {
fn seek(&mut self, target: DocId) -> DocId {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.skip_next(target)
unboxed.seek(target)
}
fn doc(&self) -> DocId {
@@ -151,9 +169,4 @@ impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.count_including_deleted()
}
fn append_to_bitset(&mut self, bitset: &mut BitSet) {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.append_to_bitset(bitset);
}
}

117
src/error.rs
View File

@@ -2,22 +2,27 @@
use std::io;
use crate::directory::error::LockError;
use crate::directory::error::{IOError, OpenDirectoryError, OpenReadError, OpenWriteError};
use crate::directory::error::{Incompatibility, LockError};
use crate::fastfield::FastFieldNotAvailableError;
use crate::query;
use crate::schema;
use serde_json;
use crate::{
directory::error::{OpenDirectoryError, OpenReadError, OpenWriteError},
schema,
};
use std::fmt;
use std::path::PathBuf;
use std::sync::PoisonError;
/// Represents a `DataCorruption` error.
///
/// When facing data corruption, tantivy actually panic or return this error.
pub struct DataCorruption {
filepath: Option<PathBuf>,
comment: String,
}
impl DataCorruption {
/// Creates a `DataCorruption` Error.
pub fn new(filepath: PathBuf, comment: String) -> DataCorruption {
DataCorruption {
filepath: Some(filepath),
@@ -25,10 +30,11 @@ impl DataCorruption {
}
}
pub fn comment_only(comment: String) -> DataCorruption {
/// Creates a `DataCorruption` Error, when the filepath is irrelevant.
pub fn comment_only<TStr: ToString>(comment: TStr) -> DataCorruption {
DataCorruption {
filepath: None,
comment,
comment: comment.to_string(),
}
}
}
@@ -44,42 +50,48 @@ impl fmt::Debug for DataCorruption {
}
}
/// The library's failure based error enum
#[derive(Debug, Fail)]
/// The library's error enum
#[derive(Debug, Error)]
pub enum TantivyError {
/// Path does not exist.
#[fail(display = "Path does not exist: '{:?}'", _0)]
PathDoesNotExist(PathBuf),
/// File already exists, this is a problem when we try to write into a new file.
#[fail(display = "File already exists: '{:?}'", _0)]
FileAlreadyExists(PathBuf),
/// Failed to open the directory.
#[error("Failed to open the directory: '{0:?}'")]
OpenDirectoryError(#[from] OpenDirectoryError),
/// Failed to open a file for read.
#[error("Failed to open file for read: '{0:?}'")]
OpenReadError(#[from] OpenReadError),
/// Failed to open a file for write.
#[error("Failed to open file for write: '{0:?}'")]
OpenWriteError(#[from] OpenWriteError),
/// Index already exists in this directory
#[fail(display = "Index already exists")]
#[error("Index already exists")]
IndexAlreadyExists,
/// Failed to acquire file lock
#[fail(display = "Failed to acquire Lockfile: {:?}. {:?}", _0, _1)]
#[error("Failed to acquire Lockfile: {0:?}. {1:?}")]
LockFailure(LockError, Option<String>),
/// IO Error.
#[fail(display = "An IO error occurred: '{}'", _0)]
IOError(#[cause] IOError),
#[error("An IO error occurred: '{0}'")]
IOError(#[from] io::Error),
/// Data corruption.
#[fail(display = "{:?}", _0)]
#[error("Data corrupted: '{0:?}'")]
DataCorruption(DataCorruption),
/// A thread holding the locked panicked and poisoned the lock.
#[fail(display = "A thread holding the locked panicked and poisoned the lock")]
#[error("A thread holding the locked panicked and poisoned the lock")]
Poisoned,
/// Invalid argument was passed by the user.
#[fail(display = "An invalid argument was passed: '{}'", _0)]
#[error("An invalid argument was passed: '{0}'")]
InvalidArgument(String),
/// An Error happened in one of the thread.
#[fail(display = "An error occurred in a thread: '{}'", _0)]
#[error("An error occurred in a thread: '{0}'")]
ErrorInThread(String),
/// An Error appeared related to the schema.
#[fail(display = "Schema error: '{}'", _0)]
#[error("Schema error: '{0}'")]
SchemaError(String),
/// System error. (e.g.: We failed spawning a new thread)
#[fail(display = "System error.'{}'", _0)]
#[error("System error.'{0}'")]
SystemError(String),
/// Index incompatible with current version of tantivy
#[error("{0:?}")]
IncompatibleIndex(Incompatibility),
}
impl From<DataCorruption> for TantivyError {
@@ -87,31 +99,17 @@ impl From<DataCorruption> for TantivyError {
TantivyError::DataCorruption(data_corruption)
}
}
impl From<FastFieldNotAvailableError> for TantivyError {
fn from(fastfield_error: FastFieldNotAvailableError) -> TantivyError {
TantivyError::SchemaError(format!("{}", fastfield_error))
}
}
impl From<LockError> for TantivyError {
fn from(lock_error: LockError) -> TantivyError {
TantivyError::LockFailure(lock_error, None)
}
}
impl From<IOError> for TantivyError {
fn from(io_error: IOError) -> TantivyError {
TantivyError::IOError(io_error)
}
}
impl From<io::Error> for TantivyError {
fn from(io_error: io::Error) -> TantivyError {
TantivyError::IOError(io_error.into())
}
}
impl From<query::QueryParserError> for TantivyError {
fn from(parsing_error: query::QueryParserError) -> TantivyError {
TantivyError::InvalidArgument(format!("Query is invalid. {:?}", parsing_error))
@@ -124,12 +122,9 @@ impl<Guard> From<PoisonError<Guard>> for TantivyError {
}
}
impl From<OpenReadError> for TantivyError {
fn from(error: OpenReadError) -> TantivyError {
match error {
OpenReadError::FileDoesNotExist(filepath) => TantivyError::PathDoesNotExist(filepath),
OpenReadError::IOError(io_error) => TantivyError::IOError(io_error),
}
impl From<chrono::ParseError> for TantivyError {
fn from(err: chrono::ParseError) -> TantivyError {
TantivyError::InvalidArgument(err.to_string())
}
}
@@ -139,34 +134,14 @@ impl From<schema::DocParsingError> for TantivyError {
}
}
impl From<OpenWriteError> for TantivyError {
fn from(error: OpenWriteError) -> TantivyError {
match error {
OpenWriteError::FileAlreadyExists(filepath) => {
TantivyError::FileAlreadyExists(filepath)
}
OpenWriteError::IOError(io_error) => TantivyError::IOError(io_error),
}
}
}
impl From<OpenDirectoryError> for TantivyError {
fn from(error: OpenDirectoryError) -> TantivyError {
match error {
OpenDirectoryError::DoesNotExist(directory_path) => {
TantivyError::PathDoesNotExist(directory_path)
}
OpenDirectoryError::NotADirectory(directory_path) => {
TantivyError::InvalidArgument(format!("{:?} is not a directory", directory_path))
}
OpenDirectoryError::IoError(err) => TantivyError::IOError(IOError::from(err)),
}
}
}
impl From<serde_json::Error> for TantivyError {
fn from(error: serde_json::Error) -> TantivyError {
let io_err = io::Error::from(error);
TantivyError::IOError(io_err.into())
TantivyError::IOError(error.into())
}
}
impl From<rayon::ThreadPoolBuildError> for TantivyError {
fn from(error: rayon::ThreadPoolBuildError) -> TantivyError {
TantivyError::SystemError(error.to_string())
}
}

111
src/fastfield/bytes/mod.rs
View File

@@ -6,31 +6,114 @@ pub use self::writer::BytesFastFieldWriter;
#[cfg(test)]
mod tests {
use crate::schema::Schema;
use crate::Index;
use crate::schema::{BytesOptions, IndexRecordOption, Schema, Value};
use crate::{query::TermQuery, schema::FAST, schema::INDEXED, schema::STORED};
use crate::{DocAddress, DocSet, Index, Searcher, Term};
use std::ops::Deref;
#[test]
fn test_bytes() {
fn test_bytes() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let field = schema_builder.add_bytes_field("bytesfield");
let bytes_field = schema_builder.add_bytes_field("bytesfield", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(field=>vec![0u8, 1, 2, 3]));
index_writer.add_document(doc!(field=>vec![]));
index_writer.add_document(doc!(field=>vec![255u8]));
index_writer.add_document(doc!(field=>vec![1u8, 3, 5, 7, 9]));
index_writer.add_document(doc!(field=>vec![0u8; 1000]));
assert!(index_writer.commit().is_ok());
let searcher = index.reader().unwrap().searcher();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(bytes_field=>vec![0u8, 1, 2, 3]));
index_writer.add_document(doc!(bytes_field=>vec![]));
index_writer.add_document(doc!(bytes_field=>vec![255u8]));
index_writer.add_document(doc!(bytes_field=>vec![1u8, 3, 5, 7, 9]));
index_writer.add_document(doc!(bytes_field=>vec![0u8; 1000]));
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let segment_reader = searcher.segment_reader(0);
let bytes_reader = segment_reader.fast_fields().bytes(field).unwrap();
let bytes_reader = segment_reader.fast_fields().bytes(bytes_field).unwrap();
assert_eq!(bytes_reader.get_bytes(0), &[0u8, 1, 2, 3]);
assert!(bytes_reader.get_bytes(1).is_empty());
assert_eq!(bytes_reader.get_bytes(2), &[255u8]);
assert_eq!(bytes_reader.get_bytes(3), &[1u8, 3, 5, 7, 9]);
let long = vec![0u8; 1000];
assert_eq!(bytes_reader.get_bytes(4), long.as_slice());
Ok(())
}
fn create_index_for_test<T: Into<BytesOptions>>(
byte_options: T,
) -> crate::Result<impl Deref<Target = Searcher>> {
let mut schema_builder = Schema::builder();
let field = schema_builder.add_bytes_field("string_bytes", byte_options.into());
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(
field => b"tantivy".as_ref(),
field => b"lucene".as_ref()
));
index_writer.commit()?;
Ok(index.reader()?.searcher())
}
#[test]
fn test_stored_bytes() -> crate::Result<()> {
let searcher = create_index_for_test(STORED)?;
assert_eq!(searcher.num_docs(), 1);
let retrieved_doc = searcher.doc(DocAddress(0u32, 0u32))?;
let field = searcher.schema().get_field("string_bytes").unwrap();
let values: Vec<&Value> = retrieved_doc.get_all(field).collect();
assert_eq!(values.len(), 2);
let values_bytes: Vec<&[u8]> = values
.into_iter()
.flat_map(|value| value.bytes_value())
.collect();
assert_eq!(values_bytes, &[&b"tantivy"[..], &b"lucene"[..]]);
Ok(())
}
#[test]
fn test_non_stored_bytes() -> crate::Result<()> {
let searcher = create_index_for_test(INDEXED)?;
assert_eq!(searcher.num_docs(), 1);
let retrieved_doc = searcher.doc(DocAddress(0u32, 0u32))?;
let field = searcher.schema().get_field("string_bytes").unwrap();
assert!(retrieved_doc.get_first(field).is_none());
Ok(())
}
#[test]
fn test_index_bytes() -> crate::Result<()> {
let searcher = create_index_for_test(INDEXED)?;
assert_eq!(searcher.num_docs(), 1);
let field = searcher.schema().get_field("string_bytes").unwrap();
let term = Term::from_field_bytes(field, b"lucene".as_ref());
let term_query = TermQuery::new(term, IndexRecordOption::Basic);
let term_weight = term_query.specialized_weight(&searcher, true)?;
let term_scorer = term_weight.specialized_scorer(searcher.segment_reader(0), 1.0)?;
assert_eq!(term_scorer.doc(), 0u32);
Ok(())
}
#[test]
fn test_non_index_bytes() -> crate::Result<()> {
let searcher = create_index_for_test(STORED)?;
assert_eq!(searcher.num_docs(), 1);
let field = searcher.schema().get_field("string_bytes").unwrap();
let term = Term::from_field_bytes(field, b"lucene".as_ref());
let term_query = TermQuery::new(term, IndexRecordOption::Basic);
let term_weight_err = term_query.specialized_weight(&searcher, false);
assert!(matches!(
term_weight_err,
Err(crate::TantivyError::SchemaError(_))
));
Ok(())
}
#[test]
fn test_fast_bytes_multivalue_value() -> crate::Result<()> {
let searcher = create_index_for_test(FAST)?;
assert_eq!(searcher.num_docs(), 1);
let fast_fields = searcher.segment_reader(0u32).fast_fields();
let field = searcher.schema().get_field("string_bytes").unwrap();
let fast_field_reader = fast_fields.bytes(field).unwrap();
assert_eq!(fast_field_reader.get_bytes(0u32), b"tantivy");
Ok(())
}
}

17
src/fastfield/bytes/reader.rs
View File

@@ -1,6 +1,5 @@
use owning_ref::OwningRef;
use crate::directory::ReadOnlySource;
use crate::directory::FileSlice;
use crate::directory::OwnedBytes;
use crate::fastfield::FastFieldReader;
use crate::DocId;
@@ -17,16 +16,16 @@ use crate::DocId;
#[derive(Clone)]
pub struct BytesFastFieldReader {
idx_reader: FastFieldReader<u64>,
values: OwningRef<ReadOnlySource, [u8]>,
values: OwnedBytes,
}
impl BytesFastFieldReader {
pub(crate) fn open(
idx_reader: FastFieldReader<u64>,
values_source: ReadOnlySource,
) -> BytesFastFieldReader {
let values = OwningRef::new(values_source).map(|source| &source[..]);
BytesFastFieldReader { idx_reader, values }
values_file: FileSlice,
) -> crate::Result<BytesFastFieldReader> {
let values = values_file.read_bytes()?;
Ok(BytesFastFieldReader { idx_reader, values })
}
fn range(&self, doc: DocId) -> (usize, usize) {
@@ -38,7 +37,7 @@ impl BytesFastFieldReader {
/// Returns the bytes associated to the given `doc`
pub fn get_bytes(&self, doc: DocId) -> &[u8] {
let (start, stop) = self.range(doc);
&self.values[start..stop]
&self.values.as_slice()[start..stop]
}
/// Returns the overall number of bytes in this bytes fast field.

39
src/fastfield/bytes/writer.rs
View File

@@ -49,16 +49,10 @@ impl BytesFastFieldWriter {
/// matching field values present in the document.
pub fn add_document(&mut self, doc: &Document) {
self.next_doc();
for field_value in doc.field_values() {
if field_value.field() == self.field {
if let Value::Bytes(ref bytes) = *field_value.value() {
self.vals.extend_from_slice(bytes);
} else {
panic!(
"Bytes field contained non-Bytes Value!. Field {:?} = {:?}",
self.field, field_value
);
}
for field_value in doc.get_all(self.field) {
if let Value::Bytes(ref bytes) = field_value {
self.vals.extend_from_slice(bytes);
return;
}
}
}
@@ -76,21 +70,18 @@ impl BytesFastFieldWriter {
/// Serializes the fast field values by pushing them to the `FastFieldSerializer`.
pub fn serialize(&self, serializer: &mut FastFieldSerializer) -> io::Result<()> {
{
// writing the offset index
let mut doc_index_serializer =
serializer.new_u64_fast_field_with_idx(self.field, 0, self.vals.len() as u64, 0)?;
for &offset in &self.doc_index {
doc_index_serializer.add_val(offset)?;
}
doc_index_serializer.add_val(self.vals.len() as u64)?;
doc_index_serializer.close_field()?;
}
{
// writing the values themselves
let mut value_serializer = serializer.new_bytes_fast_field_with_idx(self.field, 1)?;
value_serializer.write_all(&self.vals)?;
// writing the offset index
let mut doc_index_serializer =
serializer.new_u64_fast_field_with_idx(self.field, 0, self.vals.len() as u64, 0)?;
for &offset in &self.doc_index {
doc_index_serializer.add_val(offset)?;
}
doc_index_serializer.add_val(self.vals.len() as u64)?;
doc_index_serializer.close_field()?;
// writing the values themselves
serializer
.new_bytes_fast_field_with_idx(self.field, 1)?
.write_all(&self.vals)?;
Ok(())
}
}

108
src/fastfield/delete.rs
View File

@@ -1,17 +1,22 @@
use crate::common::HasLen;
use crate::directory::ReadOnlySource;
use crate::common::{BitSet, HasLen};
use crate::directory::FileSlice;
use crate::directory::OwnedBytes;
use crate::directory::WritePtr;
use crate::space_usage::ByteCount;
use crate::DocId;
use bit_set::BitSet;
use std::io;
use std::io::Write;
/// Write a delete `BitSet`
///
/// where `delete_bitset` is the set of deleted `DocId`.
pub fn write_delete_bitset(delete_bitset: &BitSet, writer: &mut WritePtr) -> io::Result<()> {
let max_doc = delete_bitset.capacity();
/// Warning: this function does not call terminate. The caller is in charge of
/// closing the writer properly.
pub fn write_delete_bitset(
delete_bitset: &BitSet,
max_doc: u32,
writer: &mut WritePtr,
) -> io::Result<()> {
let mut byte = 0u8;
let mut shift = 0u8;
for doc in 0..max_doc {
@@ -29,28 +34,47 @@ pub fn write_delete_bitset(delete_bitset: &BitSet, writer: &mut WritePtr) -> io:
if max_doc % 8 > 0 {
writer.write_all(&[byte])?;
}
writer.flush()
Ok(())
}
/// Set of deleted `DocId`s.
#[derive(Clone)]
pub struct DeleteBitSet {
data: ReadOnlySource,
data: OwnedBytes,
len: usize,
}
impl DeleteBitSet {
/// Opens a delete bitset given its data source.
pub fn open(data: ReadOnlySource) -> DeleteBitSet {
let num_deleted: usize = data
#[cfg(test)]
pub(crate) fn for_test(docs: &[DocId], max_doc: u32) -> DeleteBitSet {
use crate::directory::{Directory, RAMDirectory, TerminatingWrite};
use std::path::Path;
assert!(docs.iter().all(|&doc| doc < max_doc));
let mut bitset = BitSet::with_max_value(max_doc);
for &doc in docs {
bitset.insert(doc);
}
let directory = RAMDirectory::create();
let path = Path::new("dummydeletebitset");
let mut wrt = directory.open_write(path).unwrap();
write_delete_bitset(&bitset, max_doc, &mut wrt).unwrap();
wrt.terminate().unwrap();
let file = directory.open_read(path).unwrap();
Self::open(file).unwrap()
}
/// Opens a delete bitset given its file.
pub fn open(file: FileSlice) -> crate::Result<DeleteBitSet> {
let bytes = file.read_bytes()?;
let num_deleted: usize = bytes
.as_slice()
.iter()
.map(|b| b.count_ones() as usize)
.sum();
DeleteBitSet {
data,
Ok(DeleteBitSet {
data: bytes,
len: num_deleted,
}
})
}
/// Returns true iff the document is still "alive". In other words, if it has not been deleted.
@@ -62,7 +86,7 @@ impl DeleteBitSet {
#[inline(always)]
pub fn is_deleted(&self, doc: DocId) -> bool {
let byte_offset = doc / 8u32;
let b: u8 = (*self.data)[byte_offset as usize];
let b: u8 = self.data.as_slice()[byte_offset as usize];
let shift = (doc & 7u32) as u8;
b & (1u8 << shift) != 0
}
@@ -81,45 +105,35 @@ impl HasLen for DeleteBitSet {
#[cfg(test)]
mod tests {
use super::*;
use crate::directory::*;
use bit_set::BitSet;
use std::path::PathBuf;
use super::DeleteBitSet;
use crate::common::HasLen;
fn test_delete_bitset_helper(bitset: &BitSet) {
let test_path = PathBuf::from("test");
let mut directory = RAMDirectory::create();
{
let mut writer = directory.open_write(&*test_path).unwrap();
write_delete_bitset(bitset, &mut writer).unwrap();
}
{
let source = directory.open_read(&test_path).unwrap();
let delete_bitset = DeleteBitSet::open(source);
let n = bitset.capacity();
for doc in 0..n {
assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId));
}
assert_eq!(delete_bitset.len(), bitset.len());
#[test]
fn test_delete_bitset_empty() {
let delete_bitset = DeleteBitSet::for_test(&[], 10);
for doc in 0..10 {
assert_eq!(delete_bitset.is_deleted(doc), !delete_bitset.is_alive(doc));
}
assert_eq!(delete_bitset.len(), 0);
}
#[test]
fn test_delete_bitset() {
{
let mut bitset = BitSet::with_capacity(10);
bitset.insert(1);
bitset.insert(9);
test_delete_bitset_helper(&bitset);
}
{
let mut bitset = BitSet::with_capacity(8);
bitset.insert(1);
bitset.insert(2);
bitset.insert(3);
bitset.insert(5);
bitset.insert(7);
test_delete_bitset_helper(&bitset);
let delete_bitset = DeleteBitSet::for_test(&[1, 9], 10);
assert!(delete_bitset.is_alive(0));
assert!(delete_bitset.is_deleted(1));
assert!(delete_bitset.is_alive(2));
assert!(delete_bitset.is_alive(3));
assert!(delete_bitset.is_alive(4));
assert!(delete_bitset.is_alive(5));
assert!(delete_bitset.is_alive(6));
assert!(delete_bitset.is_alive(6));
assert!(delete_bitset.is_alive(7));
assert!(delete_bitset.is_alive(8));
assert!(delete_bitset.is_deleted(9));
for doc in 0..10 {
assert_eq!(delete_bitset.is_deleted(doc), !delete_bitset.is_alive(doc));
}
assert_eq!(delete_bitset.len(), 2);
}
}

4
src/fastfield/error.rs
View File

@@ -4,8 +4,8 @@ use std::result;
/// `FastFieldNotAvailableError` is returned when the
/// user requested for a fast field reader, and the field was not
/// defined in the schema as a fast field.
#[derive(Debug, Fail)]
#[fail(display = "Fast field not available: '{:?}'", field_name)]
#[derive(Debug, Error)]
#[error("Fast field not available: '{field_name:?}'")]
pub struct FastFieldNotAvailableError {
field_name: String,
}

72
src/fastfield/facet_reader.rs
View File

@@ -1,4 +1,5 @@
use super::MultiValueIntFastFieldReader;
use super::MultiValuedFastFieldReader;
use crate::error::DataCorruption;
use crate::schema::Facet;
use crate::termdict::TermDictionary;
use crate::termdict::TermOrdinal;
@@ -19,7 +20,7 @@ use std::str;
/// list of facets. This ordinal is segment local and
/// only makes sense for a given segment.
pub struct FacetReader {
term_ords: MultiValueIntFastFieldReader<u64>,
term_ords: MultiValuedFastFieldReader<u64>,
term_dict: TermDictionary,
buffer: Vec<u8>,
}
@@ -28,12 +29,12 @@ impl FacetReader {
/// Creates a new `FacetReader`.
///
/// A facet reader just wraps :
/// - a `MultiValueIntFastFieldReader` that makes it possible to
/// - a `MultiValuedFastFieldReader` that makes it possible to
/// access the list of facet ords for a given document.
/// - a `TermDictionary` that helps associating a facet to
/// an ordinal and vice versa.
pub fn new(
term_ords: MultiValueIntFastFieldReader<u64>,
term_ords: MultiValuedFastFieldReader<u64>,
term_dict: TermDictionary,
) -> FacetReader {
FacetReader {
@@ -62,18 +63,73 @@ impl FacetReader {
&mut self,
facet_ord: TermOrdinal,
output: &mut Facet,
) -> Result<(), str::Utf8Error> {
) -> crate::Result<()> {
let found_term = self
.term_dict
.ord_to_term(facet_ord as u64, &mut self.buffer);
.ord_to_term(facet_ord as u64, &mut self.buffer)?;
assert!(found_term, "Term ordinal {} no found.", facet_ord);
let facet_str = str::from_utf8(&self.buffer[..])?;
let facet_str = str::from_utf8(&self.buffer[..])
.map_err(|utf8_err| DataCorruption::comment_only(utf8_err.to_string()))?;
output.set_facet_str(facet_str);
Ok(())
}
/// Return the list of facet ordinals associated to a document.
pub fn facet_ords(&mut self, doc: DocId, output: &mut Vec<u64>) {
pub fn facet_ords(&self, doc: DocId, output: &mut Vec<u64>) {
self.term_ords.get_vals(doc, output);
}
}
#[cfg(test)]
mod tests {
use crate::Index;
use crate::{
schema::{Facet, SchemaBuilder},
Document,
};
#[test]
fn test_facet_not_populated_for_all_docs() -> crate::Result<()> {
let mut schema_builder = SchemaBuilder::default();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(facet_field=>Facet::from_text("/a/b")));
index_writer.add_document(Document::default());
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let facet_reader = searcher
.segment_reader(0u32)
.facet_reader(facet_field)
.unwrap();
let mut facet_ords = Vec::new();
facet_reader.facet_ords(0u32, &mut facet_ords);
assert_eq!(&facet_ords, &[2u64]);
facet_reader.facet_ords(1u32, &mut facet_ords);
assert!(facet_ords.is_empty());
Ok(())
}
#[test]
fn test_facet_not_populated_for_any_docs() -> crate::Result<()> {
let mut schema_builder = SchemaBuilder::default();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(Document::default());
index_writer.add_document(Document::default());
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let facet_reader = searcher
.segment_reader(0u32)
.facet_reader(facet_field)
.unwrap();
let mut facet_ords = Vec::new();
facet_reader.facet_ords(0u32, &mut facet_ords);
assert!(facet_ords.is_empty());
facet_reader.facet_ords(1u32, &mut facet_ords);
assert!(facet_ords.is_empty());
Ok(())
}
}

297
src/fastfield/mod.rs
View File

@@ -28,7 +28,7 @@ pub use self::delete::write_delete_bitset;
pub use self::delete::DeleteBitSet;
pub use self::error::{FastFieldNotAvailableError, Result};
pub use self::facet_reader::FacetReader;
pub use self::multivalued::{MultiValueIntFastFieldReader, MultiValueIntFastFieldWriter};
pub use self::multivalued::{MultiValuedFastFieldReader, MultiValuedFastFieldWriter};
pub use self::reader::FastFieldReader;
pub use self::readers::FastFieldReaders;
pub use self::serializer::FastFieldSerializer;
@@ -37,6 +37,10 @@ use crate::common;
use crate::schema::Cardinality;
use crate::schema::FieldType;
use crate::schema::Value;
use crate::{
chrono::{NaiveDateTime, Utc},
schema::Type,
};
mod bytes;
mod delete;
@@ -49,7 +53,7 @@ mod serializer;
mod writer;
/// Trait for types that are allowed for fast fields: (u64, i64 and f64).
pub trait FastValue: Default + Clone + Copy + Send + Sync + PartialOrd {
pub trait FastValue: Clone + Copy + Send + Sync + PartialOrd {
/// Converts a value from u64
///
/// Internally all fast field values are encoded as u64.
@@ -69,6 +73,15 @@ pub trait FastValue: Default + Clone + Copy + Send + Sync + PartialOrd {
/// Cast value to `u64`.
/// The value is just reinterpreted in memory.
fn as_u64(&self) -> u64;
/// Build a default value. This default value is never used, so the value does not
/// really matter.
fn make_zero() -> Self {
Self::from_u64(0i64.to_u64())
}
/// Returns the `schema::Type` for this FastValue.
fn to_type() -> Type;
}
impl FastValue for u64 {
@@ -91,6 +104,10 @@ impl FastValue for u64 {
fn as_u64(&self) -> u64 {
*self
}
fn to_type() -> Type {
Type::U64
}
}
impl FastValue for i64 {
@@ -112,6 +129,10 @@ impl FastValue for i64 {
fn as_u64(&self) -> u64 {
*self as u64
}
fn to_type() -> Type {
Type::I64
}
}
impl FastValue for f64 {
@@ -133,6 +154,36 @@ impl FastValue for f64 {
fn as_u64(&self) -> u64 {
self.to_bits()
}
fn to_type() -> Type {
Type::F64
}
}
impl FastValue for crate::DateTime {
fn from_u64(timestamp_u64: u64) -> Self {
let timestamp_i64 = i64::from_u64(timestamp_u64);
crate::DateTime::from_utc(NaiveDateTime::from_timestamp(timestamp_i64, 0), Utc)
}
fn to_u64(&self) -> u64 {
self.timestamp().to_u64()
}
fn fast_field_cardinality(field_type: &FieldType) -> Option<Cardinality> {
match *field_type {
FieldType::Date(ref integer_options) => integer_options.get_fastfield_cardinality(),
_ => None,
}
}
fn as_u64(&self) -> u64 {
self.timestamp().as_u64()
}
fn to_type() -> Type {
Type::Date
}
}
fn value_to_u64(value: &Value) -> u64 {
@@ -140,6 +191,7 @@ fn value_to_u64(value: &Value) -> u64 {
Value::U64(ref val) => *val,
Value::I64(ref val) => common::i64_to_u64(*val),
Value::F64(ref val) => common::f64_to_u64(*val),
Value::Date(ref datetime) => common::i64_to_u64(datetime.timestamp()),
_ => panic!("Expected a u64/i64/f64 field, got {:?} ", value),
}
}
@@ -151,10 +203,13 @@ mod tests {
use crate::common::CompositeFile;
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::FastFieldReader;
use crate::schema::Document;
use crate::merge_policy::NoMergePolicy;
use crate::schema::Field;
use crate::schema::Schema;
use crate::schema::FAST;
use crate::schema::{Document, IntOptions};
use crate::{Index, SegmentId, SegmentReader};
use common::HasLen;
use once_cell::sync::Lazy;
use rand::prelude::SliceRandom;
use rand::rngs::StdRng;
@@ -179,9 +234,15 @@ mod tests {
}
#[test]
fn test_intfastfield_small() {
pub fn test_fastfield_i64_u64() {
let datetime = crate::DateTime::from_utc(NaiveDateTime::from_timestamp(0i64, 0), Utc);
assert_eq!(i64::from_u64(datetime.to_u64()), 0i64);
}
#[test]
fn test_intfastfield_small() -> crate::Result<()> {
let path = Path::new("test");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -194,27 +255,24 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
{
assert_eq!(source.len(), 36 as usize);
}
{
let composite_file = CompositeFile::open(&source).unwrap();
let field_source = composite_file.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(field_source);
assert_eq!(fast_field_reader.get(0), 13u64);
assert_eq!(fast_field_reader.get(1), 14u64);
assert_eq!(fast_field_reader.get(2), 2u64);
}
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 36 as usize);
let composite_file = CompositeFile::open(&file)?;
let file = composite_file.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(file)?;
assert_eq!(fast_field_reader.get(0), 13u64);
assert_eq!(fast_field_reader.get(1), 14u64);
assert_eq!(fast_field_reader.get(2), 2u64);
Ok(())
}
#[test]
fn test_intfastfield_large() {
fn test_intfastfield_large() -> crate::Result<()> {
let path = Path::new("test");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
let write: WritePtr = directory.open_write(Path::new("test"))?;
let mut serializer = FastFieldSerializer::from_write(write)?;
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
fast_field_writers.add_document(&doc!(*FIELD=>4u64));
fast_field_writers.add_document(&doc!(*FIELD=>14_082_001u64));
@@ -225,19 +283,15 @@ mod tests {
fast_field_writers.add_document(&doc!(*FIELD=>1_002u64));
fast_field_writers.add_document(&doc!(*FIELD=>1_501u64));
fast_field_writers.add_document(&doc!(*FIELD=>215u64));
fast_field_writers
.serialize(&mut serializer, &HashMap::new())
.unwrap();
serializer.close().unwrap();
fast_field_writers.serialize(&mut serializer, &HashMap::new())?;
serializer.close()?;
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path)?;
assert_eq!(file.len(), 61 as usize);
{
assert_eq!(source.len(), 61 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file)?;
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
assert_eq!(fast_field_reader.get(0), 4u64);
assert_eq!(fast_field_reader.get(1), 14_082_001u64);
assert_eq!(fast_field_reader.get(2), 3_052u64);
@@ -248,12 +302,13 @@ mod tests {
assert_eq!(fast_field_reader.get(7), 1_501u64);
assert_eq!(fast_field_reader.get(8), 215u64);
}
Ok(())
}
#[test]
fn test_intfastfield_null_amplitude() {
fn test_intfastfield_null_amplitude() -> crate::Result<()> {
let path = Path::new("test");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
@@ -267,24 +322,23 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 34 as usize);
{
assert_eq!(source.len(), 34 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
for doc in 0..10_000 {
assert_eq!(fast_field_reader.get(doc), 100_000u64);
}
}
Ok(())
}
#[test]
fn test_intfastfield_large_numbers() {
fn test_intfastfield_large_numbers() -> crate::Result<()> {
let path = Path::new("test");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
@@ -300,14 +354,12 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 80042 as usize);
{
assert_eq!(source.len(), 80042 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file)?;
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
assert_eq!(fast_field_reader.get(0), 0u64);
for doc in 1..10_001 {
assert_eq!(
@@ -316,12 +368,13 @@ mod tests {
);
}
}
Ok(())
}
#[test]
fn test_signed_intfastfield() {
fn test_signed_intfastfield() -> crate::Result<()> {
let path = Path::new("test");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
let mut schema_builder = Schema::builder();
let i64_field = schema_builder.add_i64_field("field", FAST);
@@ -340,14 +393,12 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 17709 as usize);
{
assert_eq!(source.len(), 17709 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file)?;
let data = fast_fields_composite.open_read(i64_field).unwrap();
let fast_field_reader = FastFieldReader::<i64>::open(data);
let fast_field_reader = FastFieldReader::<i64>::open(data)?;
assert_eq!(fast_field_reader.min_value(), -100i64);
assert_eq!(fast_field_reader.max_value(), 9_999i64);
@@ -360,12 +411,13 @@ mod tests {
assert_eq!(buffer[i], -100i64 + 53i64 + i as i64);
}
}
Ok(())
}
#[test]
fn test_signed_intfastfield_default_val() {
fn test_signed_intfastfield_default_val() -> crate::Result<()> {
let path = Path::new("test");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
let mut schema_builder = Schema::builder();
let i64_field = schema_builder.add_i64_field("field", FAST);
let schema = schema_builder.build();
@@ -382,13 +434,14 @@ mod tests {
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let data = fast_fields_composite.open_read(i64_field).unwrap();
let fast_field_reader = FastFieldReader::<i64>::open(data);
let fast_field_reader = FastFieldReader::<i64>::open(data)?;
assert_eq!(fast_field_reader.get(0u32), 0i64);
}
Ok(())
}
// Warning: this generates the same permutation at each call
@@ -399,28 +452,26 @@ mod tests {
}
#[test]
fn test_intfastfield_permutation() {
fn test_intfastfield_permutation() -> crate::Result<()> {
let path = Path::new("test");
let permutation = generate_permutation();
let n = permutation.len();
let mut directory = RAMDirectory::create();
let directory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
let write: WritePtr = directory.open_write(Path::new("test"))?;
let mut serializer = FastFieldSerializer::from_write(write)?;
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
for &x in &permutation {
fast_field_writers.add_document(&doc!(*FIELD=>x));
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new())
.unwrap();
serializer.close().unwrap();
fast_field_writers.serialize(&mut serializer, &HashMap::new())?;
serializer.close()?;
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path)?;
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file)?;
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
let mut a = 0u64;
for _ in 0..n {
@@ -428,6 +479,94 @@ mod tests {
a = fast_field_reader.get(a as u32);
}
}
Ok(())
}
#[test]
fn test_merge_missing_date_fast_field() {
let mut schema_builder = Schema::builder();
let date_field = schema_builder.add_date_field("date", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(date_field =>crate::chrono::prelude::Utc::now()));
index_writer.commit().unwrap();
index_writer.add_document(doc!());
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let segment_ids: Vec<SegmentId> = reader
.searcher()
.segment_readers()
.iter()
.map(SegmentReader::segment_id)
.collect();
assert_eq!(segment_ids.len(), 2);
let merge_future = index_writer.merge(&segment_ids[..]);
let merge_res = futures::executor::block_on(merge_future);
assert!(merge_res.is_ok());
assert!(reader.reload().is_ok());
assert_eq!(reader.searcher().segment_readers().len(), 1);
}
#[test]
fn test_default_datetime() {
assert_eq!(crate::DateTime::make_zero().timestamp(), 0i64);
}
#[test]
fn test_datefastfield() {
use crate::fastfield::FastValue;
let mut schema_builder = Schema::builder();
let date_field = schema_builder.add_date_field("date", FAST);
let multi_date_field = schema_builder.add_date_field(
"multi_date",
IntOptions::default().set_fast(Cardinality::MultiValues),
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(1i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(2i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(3i64.to_u64())
));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(4i64.to_u64())
));
index_writer.add_document(doc!(
multi_date_field => crate::DateTime::from_u64(5i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(6i64.to_u64())
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
let segment_reader = searcher.segment_reader(0);
let fast_fields = segment_reader.fast_fields();
let date_fast_field = fast_fields.date(date_field).unwrap();
let dates_fast_field = fast_fields.dates(multi_date_field).unwrap();
let mut dates = vec![];
{
assert_eq!(date_fast_field.get(0u32).timestamp(), 1i64);
dates_fast_field.get_vals(0u32, &mut dates);
assert_eq!(dates.len(), 2);
assert_eq!(dates[0].timestamp(), 2i64);
assert_eq!(dates[1].timestamp(), 3i64);
}
{
assert_eq!(date_fast_field.get(1u32).timestamp(), 4i64);
dates_fast_field.get_vals(1u32, &mut dates);
assert!(dates.is_empty());
}
{
assert_eq!(date_fast_field.get(2u32).timestamp(), 0i64);
dates_fast_field.get_vals(2u32, &mut dates);
assert_eq!(dates.len(), 2);
assert_eq!(dates[0].timestamp(), 5i64);
assert_eq!(dates[1].timestamp(), 6i64);
}
}
}
@@ -473,7 +612,7 @@ mod bench {
fn bench_intfastfield_linear_fflookup(b: &mut Bencher) {
let path = Path::new("test");
let permutation = generate_permutation();
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -486,11 +625,11 @@ mod bench {
.unwrap();
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
let fast_field_reader = FastFieldReader::<u64>::open(data).unwrap();
b.iter(|| {
let n = test::black_box(7000u32);
@@ -507,7 +646,7 @@ mod bench {
fn bench_intfastfield_fflookup(b: &mut Bencher) {
let path = Path::new("test");
let permutation = generate_permutation();
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -520,11 +659,11 @@ mod bench {
.unwrap();
serializer.close().unwrap();
}
let source = directory.open_read(&path).unwrap();
let file = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
let fast_field_reader = FastFieldReader::<u64>::open(data).unwrap();
b.iter(|| {
let n = test::black_box(1000u32);

46
src/fastfield/multivalued/mod.rs
View File

@@ -1,15 +1,12 @@
mod reader;
mod writer;
pub use self::reader::MultiValueIntFastFieldReader;
pub use self::writer::MultiValueIntFastFieldWriter;
pub use self::reader::MultiValuedFastFieldReader;
pub use self::writer::MultiValuedFastFieldWriter;
#[cfg(test)]
mod tests {
use time;
use self::time::Duration;
use crate::collector::TopDocs;
use crate::query::QueryParser;
use crate::schema::Cardinality;
@@ -17,6 +14,7 @@ mod tests {
use crate::schema::IntOptions;
use crate::schema::Schema;
use crate::Index;
use chrono::Duration;
#[test]
fn test_multivalued_u64() {
@@ -27,7 +25,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(field=>1u64, field=>3u64));
index_writer.add_document(doc!());
index_writer.add_document(doc!(field=>4u64));
@@ -66,7 +64,7 @@ mod tests {
schema_builder.add_i64_field("time_stamp_i", IntOptions::default().set_stored());
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let first_time_stamp = chrono::Utc::now();
index_writer.add_document(
doc!(date_field=>first_time_stamp, date_field=>first_time_stamp, time_i=>1i64),
@@ -102,6 +100,7 @@ mod tests {
.get_first(date_field)
.expect("cannot find value")
.date_value()
.unwrap()
.timestamp(),
first_time_stamp.timestamp()
);
@@ -110,7 +109,7 @@ mod tests {
.get_first(time_i)
.expect("cannot find value")
.i64_value(),
1i64
Some(1i64)
);
}
}
@@ -133,6 +132,7 @@ mod tests {
.get_first(date_field)
.expect("cannot find value")
.date_value()
.unwrap()
.timestamp(),
two_secs_ahead.timestamp()
);
@@ -141,7 +141,7 @@ mod tests {
.get_first(time_i)
.expect("cannot find value")
.i64_value(),
3i64
Some(3i64)
);
}
}
@@ -188,7 +188,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(field=> 1i64, field => 3i64));
index_writer.add_document(doc!());
index_writer.add_document(doc!(field=> -4i64));
@@ -199,22 +199,14 @@ mod tests {
let segment_reader = searcher.segment_reader(0);
let mut vals = Vec::new();
let multi_value_reader = segment_reader.fast_fields().i64s(field).unwrap();
{
multi_value_reader.get_vals(2, &mut vals);
assert_eq!(&vals, &[-4i64]);
}
{
multi_value_reader.get_vals(0, &mut vals);
assert_eq!(&vals, &[1i64, 3i64]);
}
{
multi_value_reader.get_vals(1, &mut vals);
assert!(vals.is_empty());
}
{
multi_value_reader.get_vals(3, &mut vals);
assert_eq!(&vals, &[-5i64, -20i64, 1i64]);
}
multi_value_reader.get_vals(2, &mut vals);
assert_eq!(&vals, &[-4i64]);
multi_value_reader.get_vals(0, &mut vals);
assert_eq!(&vals, &[1i64, 3i64]);
multi_value_reader.get_vals(1, &mut vals);
assert!(vals.is_empty());
multi_value_reader.get_vals(3, &mut vals);
assert_eq!(&vals, &[-5i64, -20i64, 1i64]);
}
#[test]
#[ignore]
@@ -223,7 +215,7 @@ mod tests {
let field = schema_builder.add_facet_field("facetfield");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
for i in 0..100_000 {
index_writer.add_document(doc!(field=> Facet::from(format!("/lang/{}", i).as_str())));
}

19
src/fastfield/multivalued/reader.rs
View File

@@ -10,29 +10,22 @@ use crate::DocId;
/// The `idx_reader` associated, for each document, the index of its first value.
///
#[derive(Clone)]
pub struct MultiValueIntFastFieldReader<Item: FastValue> {
pub struct MultiValuedFastFieldReader<Item: FastValue> {
idx_reader: FastFieldReader<u64>,
vals_reader: FastFieldReader<Item>,
}
impl<Item: FastValue> MultiValueIntFastFieldReader<Item> {
impl<Item: FastValue> MultiValuedFastFieldReader<Item> {
pub(crate) fn open(
idx_reader: FastFieldReader<u64>,
vals_reader: FastFieldReader<Item>,
) -> MultiValueIntFastFieldReader<Item> {
MultiValueIntFastFieldReader {
) -> MultiValuedFastFieldReader<Item> {
MultiValuedFastFieldReader {
idx_reader,
vals_reader,
}
}
pub(crate) fn into_u64s_reader(self) -> MultiValueIntFastFieldReader<u64> {
MultiValueIntFastFieldReader {
idx_reader: self.idx_reader,
vals_reader: self.vals_reader.into_u64_reader(),
}
}
/// Returns `(start, stop)`, such that the values associated
/// to the given document are `start..stop`.
fn range(&self, doc: DocId) -> (u64, u64) {
@@ -45,7 +38,7 @@ impl<Item: FastValue> MultiValueIntFastFieldReader<Item> {
pub fn get_vals(&self, doc: DocId, vals: &mut Vec<Item>) {
let (start, stop) = self.range(doc);
let len = (stop - start) as usize;
vals.resize(len, Item::default());
vals.resize(len, Item::make_zero());
self.vals_reader.get_range_u64(start, &mut vals[..]);
}
@@ -74,7 +67,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index
.writer_with_num_threads(1, 30_000_000)
.writer_for_tests()
.expect("Failed to create index writer.");
index_writer.add_document(doc!(
facet_field => Facet::from("/category/cat2"),

17
src/fastfield/multivalued/writer.rs
View File

@@ -6,7 +6,6 @@ use crate::schema::{Document, Field};
use crate::termdict::TermOrdinal;
use crate::DocId;
use fnv::FnvHashMap;
use itertools::Itertools;
use std::io;
/// Writer for multi-valued (as in, more than one value per document)
@@ -19,7 +18,7 @@ use std::io;
/// in your schema
/// - add your document simply by calling `.add_document(...)`.
///
/// The `MultiValueIntFastFieldWriter` can be acquired from the
/// The `MultiValuedFastFieldWriter` can be acquired from the
/// fastfield writer, by calling [`.get_multivalue_writer(...)`](./struct.FastFieldsWriter.html#method.get_multivalue_writer).
///
/// Once acquired, writing is done by calling calls to
@@ -30,17 +29,17 @@ use std::io;
/// This makes it possible to push unordered term ids,
/// during indexing and remap them to their respective
/// term ids when the segment is getting serialized.
pub struct MultiValueIntFastFieldWriter {
pub struct MultiValuedFastFieldWriter {
field: Field,
vals: Vec<UnorderedTermId>,
doc_index: Vec<u64>,
is_facet: bool,
}
impl MultiValueIntFastFieldWriter {
impl MultiValuedFastFieldWriter {
/// Creates a new `IntFastFieldWriter`
pub(crate) fn new(field: Field, is_facet: bool) -> Self {
MultiValueIntFastFieldWriter {
MultiValuedFastFieldWriter {
field,
vals: Vec::new(),
doc_index: Vec::new(),
@@ -48,7 +47,7 @@ impl MultiValueIntFastFieldWriter {
}
}
/// Access the field associated to the `MultiValueIntFastFieldWriter`
/// Access the field associated to the `MultiValuedFastFieldWriter`
pub fn field(&self) -> Field {
self.field
}
@@ -144,15 +143,15 @@ impl MultiValueIntFastFieldWriter {
.iter()
.map(|val| *mapping.get(val).expect("Missing term ordinal"));
doc_vals.extend(remapped_vals);
doc_vals.sort();
doc_vals.sort_unstable();
for &val in &doc_vals {
value_serializer.add_val(val)?;
}
}
}
None => {
let val_min_max = self.vals.iter().cloned().minmax();
let (val_min, val_max) = val_min_max.into_option().unwrap_or((0u64, 0u64));
let val_min_max = crate::common::minmax(self.vals.iter().cloned());
let (val_min, val_max) = val_min_max.unwrap_or((0u64, 0u64));
value_serializer =
serializer.new_u64_fast_field_with_idx(self.field, val_min, val_max, 1)?;
for &val in &self.vals {

48
src/fastfield/reader.rs
View File

@@ -3,13 +3,12 @@ use crate::common::bitpacker::BitUnpacker;
use crate::common::compute_num_bits;
use crate::common::BinarySerializable;
use crate::common::CompositeFile;
use crate::directory::ReadOnlySource;
use crate::directory::FileSlice;
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::{FastFieldSerializer, FastFieldsWriter};
use crate::schema::Schema;
use crate::schema::FAST;
use crate::DocId;
use owning_ref::OwningRef;
use std::collections::HashMap;
use std::marker::PhantomData;
use std::path::Path;
@@ -20,43 +19,27 @@ use std::path::Path;
/// fast field is required.
#[derive(Clone)]
pub struct FastFieldReader<Item: FastValue> {
bit_unpacker: BitUnpacker<OwningRef<ReadOnlySource, [u8]>>,
bit_unpacker: BitUnpacker,
min_value_u64: u64,
max_value_u64: u64,
_phantom: PhantomData<Item>,
}
impl<Item: FastValue> FastFieldReader<Item> {
/// Opens a fast field given a source.
pub fn open(data: ReadOnlySource) -> Self {
let min_value: u64;
let amplitude: u64;
{
let mut cursor = data.as_slice();
min_value =
u64::deserialize(&mut cursor).expect("Failed to read the min_value of fast field.");
amplitude =
u64::deserialize(&mut cursor).expect("Failed to read the amplitude of fast field.");
}
/// Opens a fast field given a file.
pub fn open(file: FileSlice) -> crate::Result<Self> {
let mut bytes = file.read_bytes()?;
let min_value = u64::deserialize(&mut bytes)?;
let amplitude = u64::deserialize(&mut bytes)?;
let max_value = min_value + amplitude;
let num_bits = compute_num_bits(amplitude);
let owning_ref = OwningRef::new(data).map(|data| &data[16..]);
let bit_unpacker = BitUnpacker::new(owning_ref, num_bits);
FastFieldReader {
let bit_unpacker = BitUnpacker::new(bytes, num_bits);
Ok(FastFieldReader {
min_value_u64: min_value,
max_value_u64: max_value,
bit_unpacker,
_phantom: PhantomData,
}
}
pub(crate) fn into_u64_reader(self) -> FastFieldReader<u64> {
FastFieldReader {
bit_unpacker: self.bit_unpacker,
min_value_u64: self.min_value_u64,
max_value_u64: self.max_value_u64,
_phantom: PhantomData,
}
})
}
/// Return the value associated to the given document.
@@ -135,7 +118,7 @@ impl<Item: FastValue> From<Vec<Item>> for FastFieldReader<Item> {
let field = schema_builder.add_u64_field("field", FAST);
let schema = schema_builder.build();
let path = Path::new("__dummy__");
let mut directory: RAMDirectory = RAMDirectory::create();
let directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory
.open_write(path)
@@ -157,12 +140,11 @@ impl<Item: FastValue> From<Vec<Item>> for FastFieldReader<Item> {
serializer.close().unwrap();
}
let source = directory.open_read(path).expect("Failed to open the file");
let composite_file =
CompositeFile::open(&source).expect("Failed to read the composite file");
let field_source = composite_file
let file = directory.open_read(path).expect("Failed to open the file");
let composite_file = CompositeFile::open(&file).expect("Failed to read the composite file");
let field_file = composite_file
.open_read(field)
.expect("File component not found");
FastFieldReader::open(field_source)
FastFieldReader::open(field_file).unwrap()
}
}

286
src/fastfield/readers.rs
View File

@@ -1,31 +1,27 @@
use crate::common::CompositeFile;
use crate::fastfield::BytesFastFieldReader;
use crate::fastfield::MultiValueIntFastFieldReader;
use crate::directory::FileSlice;
use crate::fastfield::MultiValuedFastFieldReader;
use crate::fastfield::{BytesFastFieldReader, FastValue};
use crate::fastfield::{FastFieldNotAvailableError, FastFieldReader};
use crate::schema::{Cardinality, Field, FieldType, Schema};
use crate::space_usage::PerFieldSpaceUsage;
use crate::Result;
use std::collections::HashMap;
use crate::TantivyError;
/// Provides access to all of the FastFieldReader.
///
/// Internally, `FastFieldReaders` have preloaded fast field readers,
/// and just wraps several `HashMap`.
#[derive(Clone)]
pub struct FastFieldReaders {
fast_field_i64: HashMap<Field, FastFieldReader<i64>>,
fast_field_u64: HashMap<Field, FastFieldReader<u64>>,
fast_field_f64: HashMap<Field, FastFieldReader<f64>>,
fast_field_i64s: HashMap<Field, MultiValueIntFastFieldReader<i64>>,
fast_field_u64s: HashMap<Field, MultiValueIntFastFieldReader<u64>>,
fast_field_f64s: HashMap<Field, MultiValueIntFastFieldReader<f64>>,
fast_bytes: HashMap<Field, BytesFastFieldReader>,
schema: Schema,
fast_fields_composite: CompositeFile,
}
#[derive(Eq, PartialEq, Debug)]
enum FastType {
I64,
U64,
F64,
Date,
}
fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality)> {
@@ -39,190 +35,176 @@ fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality
FieldType::F64(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::F64, cardinality)),
FieldType::Date(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::Date, cardinality)),
FieldType::HierarchicalFacet => Some((FastType::U64, Cardinality::MultiValues)),
_ => None,
}
}
impl FastFieldReaders {
pub(crate) fn load_all(
schema: &Schema,
fast_fields_composite: &CompositeFile,
) -> Result<FastFieldReaders> {
let mut fast_field_readers = FastFieldReaders {
fast_field_i64: Default::default(),
fast_field_u64: Default::default(),
fast_field_f64: Default::default(),
fast_field_i64s: Default::default(),
fast_field_u64s: Default::default(),
fast_field_f64s: Default::default(),
fast_bytes: Default::default(),
fast_fields_composite: fast_fields_composite.clone(),
};
for (field, field_entry) in schema.fields() {
let field_type = field_entry.field_type();
if field_type == &FieldType::Bytes {
let idx_reader = fast_fields_composite
.open_read_with_idx(field, 0)
.ok_or_else(|| FastFieldNotAvailableError::new(field_entry))
.map(FastFieldReader::open)?;
let data = fast_fields_composite
.open_read_with_idx(field, 1)
.ok_or_else(|| FastFieldNotAvailableError::new(field_entry))?;
fast_field_readers
.fast_bytes
.insert(field, BytesFastFieldReader::open(idx_reader, data));
} else if let Some((fast_type, cardinality)) = type_and_cardinality(field_type) {
match cardinality {
Cardinality::SingleValue => {
if let Some(fast_field_data) = fast_fields_composite.open_read(field) {
match fast_type {
FastType::U64 => {
let fast_field_reader = FastFieldReader::open(fast_field_data);
fast_field_readers
.fast_field_u64
.insert(field, fast_field_reader);
}
FastType::I64 => {
fast_field_readers.fast_field_i64.insert(
field,
FastFieldReader::open(fast_field_data.clone()),
);
}
FastType::F64 => {
fast_field_readers.fast_field_f64.insert(
field,
FastFieldReader::open(fast_field_data.clone()),
);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
}
}
Cardinality::MultiValues => {
let idx_opt = fast_fields_composite.open_read_with_idx(field, 0);
let data_opt = fast_fields_composite.open_read_with_idx(field, 1);
if let (Some(fast_field_idx), Some(fast_field_data)) = (idx_opt, data_opt) {
let idx_reader = FastFieldReader::open(fast_field_idx);
match fast_type {
FastType::I64 => {
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_i64s
.insert(field, multivalued_int_fast_field);
}
FastType::U64 => {
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_u64s
.insert(field, multivalued_int_fast_field);
}
FastType::F64 => {
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_f64s
.insert(field, multivalued_int_fast_field);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
}
}
}
}
}
Ok(fast_field_readers)
pub(crate) fn new(
schema: Schema,
fast_fields_composite: CompositeFile,
) -> crate::Result<FastFieldReaders> {
Ok(FastFieldReaders {
fast_fields_composite,
schema,
})
}
pub(crate) fn space_usage(&self) -> PerFieldSpaceUsage {
self.fast_fields_composite.space_usage()
}
fn fast_field_data(&self, field: Field, idx: usize) -> crate::Result<FileSlice> {
self.fast_fields_composite
.open_read_with_idx(field, idx)
.ok_or_else(|| {
let field_name = self.schema.get_field_entry(field).name();
TantivyError::SchemaError(format!("Field({}) data was not found", field_name))
})
}
fn check_type(
&self,
field: Field,
expected_fast_type: FastType,
expected_cardinality: Cardinality,
) -> crate::Result<()> {
let field_entry = self.schema.get_field_entry(field);
let (fast_type, cardinality) =
type_and_cardinality(field_entry.field_type()).ok_or_else(|| {
crate::TantivyError::SchemaError(format!(
"Field {:?} is not a fast field.",
field_entry.name()
))
})?;
if fast_type != expected_fast_type {
return Err(crate::TantivyError::SchemaError(format!(
"Field {:?} is of type {:?}, expected {:?}.",
field_entry.name(),
fast_type,
expected_fast_type
)));
}
if cardinality != expected_cardinality {
return Err(crate::TantivyError::SchemaError(format!(
"Field {:?} is of cardinality {:?}, expected {:?}.",
field_entry.name(),
cardinality,
expected_cardinality
)));
}
Ok(())
}
pub(crate) fn typed_fast_field_reader<TFastValue: FastValue>(
&self,
field: Field,
) -> crate::Result<FastFieldReader<TFastValue>> {
let fast_field_slice = self.fast_field_data(field, 0)?;
FastFieldReader::open(fast_field_slice)
}
pub(crate) fn typed_fast_field_multi_reader<TFastValue: FastValue>(
&self,
field: Field,
) -> crate::Result<MultiValuedFastFieldReader<TFastValue>> {
let fast_field_slice_idx = self.fast_field_data(field, 0)?;
let fast_field_slice_vals = self.fast_field_data(field, 1)?;
let idx_reader = FastFieldReader::open(fast_field_slice_idx)?;
let vals_reader: FastFieldReader<TFastValue> =
FastFieldReader::open(fast_field_slice_vals)?;
Ok(MultiValuedFastFieldReader::open(idx_reader, vals_reader))
}
/// Returns the `u64` fast field reader reader associated to `field`.
///
/// If `field` is not a u64 fast field, this method returns `None`.
pub fn u64(&self, field: Field) -> Option<FastFieldReader<u64>> {
self.fast_field_u64.get(&field).cloned()
}
/// If the field is a u64-fast field return the associated reader.
/// If the field is a i64-fast field, return the associated u64 reader. Values are
/// mapped from i64 to u64 using a (well the, it is unique) monotonic mapping. ///
///
///TODO should it also be lenient with f64?
///
/// This method is useful when merging segment reader.
pub(crate) fn u64_lenient(&self, field: Field) -> Option<FastFieldReader<u64>> {
if let Some(u64_ff_reader) = self.u64(field) {
return Some(u64_ff_reader);
}
if let Some(i64_ff_reader) = self.i64(field) {
return Some(i64_ff_reader.into_u64_reader());
}
None
pub fn u64(&self, field: Field) -> crate::Result<FastFieldReader<u64>> {
self.check_type(field, FastType::U64, Cardinality::SingleValue)?;
self.typed_fast_field_reader(field)
}
/// Returns the `i64` fast field reader reader associated to `field`.
///
/// If `field` is not a i64 fast field, this method returns `None`.
pub fn i64(&self, field: Field) -> Option<FastFieldReader<i64>> {
self.fast_field_i64.get(&field).cloned()
pub fn i64(&self, field: Field) -> crate::Result<FastFieldReader<i64>> {
self.check_type(field, FastType::I64, Cardinality::SingleValue)?;
self.typed_fast_field_reader(field)
}
/// Returns the `i64` fast field reader reader associated to `field`.
///
/// If `field` is not a i64 fast field, this method returns `None`.
pub fn date(&self, field: Field) -> crate::Result<FastFieldReader<crate::DateTime>> {
self.check_type(field, FastType::Date, Cardinality::SingleValue)?;
self.typed_fast_field_reader(field)
}
/// Returns the `f64` fast field reader reader associated to `field`.
///
/// If `field` is not a f64 fast field, this method returns `None`.
pub fn f64(&self, field: Field) -> Option<FastFieldReader<f64>> {
self.fast_field_f64.get(&field).cloned()
pub fn f64(&self, field: Field) -> crate::Result<FastFieldReader<f64>> {
self.check_type(field, FastType::F64, Cardinality::SingleValue)?;
self.typed_fast_field_reader(field)
}
/// Returns a `u64s` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a u64 multi-valued fast field, this method returns `None`.
pub fn u64s(&self, field: Field) -> Option<MultiValueIntFastFieldReader<u64>> {
self.fast_field_u64s.get(&field).cloned()
}
/// If the field is a u64s-fast field return the associated reader.
/// If the field is a i64s-fast field, return the associated u64s reader. Values are
/// mapped from i64 to u64 using a (well the, it is unique) monotonic mapping.
///
/// This method is useful when merging segment reader.
pub(crate) fn u64s_lenient(&self, field: Field) -> Option<MultiValueIntFastFieldReader<u64>> {
if let Some(u64s_ff_reader) = self.u64s(field) {
return Some(u64s_ff_reader);
}
if let Some(i64s_ff_reader) = self.i64s(field) {
return Some(i64s_ff_reader.into_u64s_reader());
}
None
pub fn u64s(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<u64>> {
self.check_type(field, FastType::U64, Cardinality::MultiValues)?;
self.typed_fast_field_multi_reader(field)
}
/// Returns a `i64s` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a i64 multi-valued fast field, this method returns `None`.
pub fn i64s(&self, field: Field) -> Option<MultiValueIntFastFieldReader<i64>> {
self.fast_field_i64s.get(&field).cloned()
pub fn i64s(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<i64>> {
self.check_type(field, FastType::I64, Cardinality::MultiValues)?;
self.typed_fast_field_multi_reader(field)
}
/// Returns a `f64s` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a f64 multi-valued fast field, this method returns `None`.
pub fn f64s(&self, field: Field) -> Option<MultiValueIntFastFieldReader<f64>> {
self.fast_field_f64s.get(&field).cloned()
pub fn f64s(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<f64>> {
self.check_type(field, FastType::F64, Cardinality::MultiValues)?;
self.typed_fast_field_multi_reader(field)
}
/// Returns a `crate::DateTime` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a `crate::DateTime` multi-valued fast field, this method returns `None`.
pub fn dates(
&self,
field: Field,
) -> crate::Result<MultiValuedFastFieldReader<crate::DateTime>> {
self.check_type(field, FastType::Date, Cardinality::MultiValues)?;
self.typed_fast_field_multi_reader(field)
}
/// Returns the `bytes` fast field reader associated to `field`.
///
/// If `field` is not a bytes fast field, returns `None`.
pub fn bytes(&self, field: Field) -> Option<BytesFastFieldReader> {
self.fast_bytes.get(&field).cloned()
pub fn bytes(&self, field: Field) -> crate::Result<BytesFastFieldReader> {
let field_entry = self.schema.get_field_entry(field);
if let FieldType::Bytes(bytes_option) = field_entry.field_type() {
if !bytes_option.is_fast() {
return Err(crate::TantivyError::SchemaError(format!(
"Field {:?} is not a fast field.",
field_entry.name()
)));
}
let fast_field_idx_file = self.fast_field_data(field, 0)?;
let idx_reader = FastFieldReader::open(fast_field_idx_file)?;
let data = self.fast_field_data(field, 1)?;
BytesFastFieldReader::open(idx_reader, data)
} else {
Err(FastFieldNotAvailableError::new(field_entry).into())
}
}
}

40
src/fastfield/writer.rs
View File

@@ -1,10 +1,10 @@
use super::multivalued::MultiValueIntFastFieldWriter;
use super::multivalued::MultiValuedFastFieldWriter;
use crate::common;
use crate::common::BinarySerializable;
use crate::common::VInt;
use crate::fastfield::{BytesFastFieldWriter, FastFieldSerializer};
use crate::postings::UnorderedTermId;
use crate::schema::{Cardinality, Document, Field, FieldType, Schema};
use crate::schema::{Cardinality, Document, Field, FieldEntry, FieldType, Schema};
use crate::termdict::TermOrdinal;
use fnv::FnvHashMap;
use std::collections::HashMap;
@@ -13,10 +13,18 @@ use std::io;
/// The fastfieldswriter regroup all of the fast field writers.
pub struct FastFieldsWriter {
single_value_writers: Vec<IntFastFieldWriter>,
multi_values_writers: Vec<MultiValueIntFastFieldWriter>,
multi_values_writers: Vec<MultiValuedFastFieldWriter>,
bytes_value_writers: Vec<BytesFastFieldWriter>,
}
fn fast_field_default_value(field_entry: &FieldEntry) -> u64 {
match *field_entry.field_type() {
FieldType::I64(_) | FieldType::Date(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
}
}
impl FastFieldsWriter {
/// Create all `FastFieldWriter` required by the schema.
pub fn from_schema(schema: &Schema) -> FastFieldsWriter {
@@ -25,35 +33,34 @@ impl FastFieldsWriter {
let mut bytes_value_writers = Vec::new();
for (field, field_entry) in schema.fields() {
let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
};
match *field_entry.field_type() {
match field_entry.field_type() {
FieldType::I64(ref int_options)
| FieldType::U64(ref int_options)
| FieldType::F64(ref int_options) => {
| FieldType::F64(ref int_options)
| FieldType::Date(ref int_options) => {
match int_options.get_fastfield_cardinality() {
Some(Cardinality::SingleValue) => {
let mut fast_field_writer = IntFastFieldWriter::new(field);
let default_value = fast_field_default_value(field_entry);
fast_field_writer.set_val_if_missing(default_value);
single_value_writers.push(fast_field_writer);
}
Some(Cardinality::MultiValues) => {
let fast_field_writer = MultiValueIntFastFieldWriter::new(field, false);
let fast_field_writer = MultiValuedFastFieldWriter::new(field, false);
multi_values_writers.push(fast_field_writer);
}
None => {}
}
}
FieldType::HierarchicalFacet => {
let fast_field_writer = MultiValueIntFastFieldWriter::new(field, true);
let fast_field_writer = MultiValuedFastFieldWriter::new(field, true);
multi_values_writers.push(fast_field_writer);
}
FieldType::Bytes => {
let fast_field_writer = BytesFastFieldWriter::new(field);
bytes_value_writers.push(fast_field_writer);
FieldType::Bytes(bytes_option) => {
if bytes_option.is_fast() {
let fast_field_writer = BytesFastFieldWriter::new(field);
bytes_value_writers.push(fast_field_writer);
}
}
_ => {}
}
@@ -80,7 +87,7 @@ impl FastFieldsWriter {
pub fn get_multivalue_writer(
&mut self,
field: Field,
) -> Option<&mut MultiValueIntFastFieldWriter> {
) -> Option<&mut MultiValuedFastFieldWriter> {
// TODO optimize
self.multi_values_writers
.iter_mut()
@@ -121,6 +128,7 @@ impl FastFieldsWriter {
for field_writer in &self.single_value_writers {
field_writer.serialize(serializer)?;
}
for field_writer in &self.multi_values_writers {
let field = field_writer.field();
field_writer.serialize(serializer, mapping.get(&field))?;

2
src/fieldnorm/mod.rs
View File

@@ -21,7 +21,7 @@ mod reader;
mod serializer;
mod writer;
pub use self::reader::FieldNormReader;
pub use self::reader::{FieldNormReader, FieldNormReaders};
pub use self::serializer::FieldNormsSerializer;
pub use self::writer::FieldNormsWriter;

164
src/fieldnorm/reader.rs
View File

@@ -1,6 +1,47 @@
use super::{fieldnorm_to_id, id_to_fieldnorm};
use crate::directory::ReadOnlySource;
use crate::common::CompositeFile;
use crate::directory::FileSlice;
use crate::directory::OwnedBytes;
use crate::schema::Field;
use crate::space_usage::PerFieldSpaceUsage;
use crate::DocId;
use std::sync::Arc;
/// Reader for the fieldnorm (for each document, the number of tokens indexed in the
/// field) of all indexed fields in the index.
///
/// Each fieldnorm is approximately compressed over one byte. We refer to this byte as
/// `fieldnorm_id`.
/// The mapping from `fieldnorm` to `fieldnorm_id` is given by monotonic.
#[derive(Clone)]
pub struct FieldNormReaders {
data: Arc<CompositeFile>,
}
impl FieldNormReaders {
/// Creates a field norm reader.
pub fn open(file: FileSlice) -> crate::Result<FieldNormReaders> {
let data = CompositeFile::open(&file)?;
Ok(FieldNormReaders {
data: Arc::new(data),
})
}
/// Returns the FieldNormReader for a specific field.
pub fn get_field(&self, field: Field) -> crate::Result<Option<FieldNormReader>> {
if let Some(file) = self.data.open_read(field) {
let fieldnorm_reader = FieldNormReader::open(file)?;
Ok(Some(fieldnorm_reader))
} else {
Ok(None)
}
}
/// Return a break down of the space usage per field.
pub fn space_usage(&self) -> PerFieldSpaceUsage {
self.data.space_usage()
}
}
/// Reads the fieldnorm associated to a document.
/// The fieldnorm represents the length associated to
@@ -19,14 +60,57 @@ use crate::DocId;
/// Apart from compression, this scale also makes it possible to
/// precompute computationally expensive functions of the fieldnorm
/// in a very short array.
pub struct FieldNormReader {
data: ReadOnlySource,
#[derive(Clone)]
pub struct FieldNormReader(ReaderImplEnum);
impl From<ReaderImplEnum> for FieldNormReader {
fn from(reader_enum: ReaderImplEnum) -> FieldNormReader {
FieldNormReader(reader_enum)
}
}
#[derive(Clone)]
enum ReaderImplEnum {
FromData(OwnedBytes),
Const {
num_docs: u32,
fieldnorm_id: u8,
fieldnorm: u32,
},
}
impl FieldNormReader {
/// Opens a field norm reader given its data source.
pub fn open(data: ReadOnlySource) -> Self {
FieldNormReader { data }
/// Creates a `FieldNormReader` with a constant fieldnorm.
///
/// The fieldnorm will be subjected to compression as if it was coming
/// from an array-backed fieldnorm reader.
pub fn constant(num_docs: u32, fieldnorm: u32) -> FieldNormReader {
let fieldnorm_id = fieldnorm_to_id(fieldnorm);
let fieldnorm = id_to_fieldnorm(fieldnorm_id);
ReaderImplEnum::Const {
num_docs,
fieldnorm_id,
fieldnorm,
}
.into()
}
/// Opens a field norm reader given its file.
pub fn open(fieldnorm_file: FileSlice) -> crate::Result<Self> {
let data = fieldnorm_file.read_bytes()?;
Ok(FieldNormReader::new(data))
}
fn new(data: OwnedBytes) -> Self {
ReaderImplEnum::FromData(data).into()
}
/// Returns the number of documents in this segment.
pub fn num_docs(&self) -> u32 {
match &self.0 {
ReaderImplEnum::FromData(data) => data.len() as u32,
ReaderImplEnum::Const { num_docs, .. } => *num_docs,
}
}
/// Returns the `fieldnorm` associated to a doc id.
@@ -39,15 +123,25 @@ impl FieldNormReader {
/// The fieldnorm is effectively decoded from the
/// `fieldnorm_id` by doing a simple table lookup.
pub fn fieldnorm(&self, doc_id: DocId) -> u32 {
let fieldnorm_id = self.fieldnorm_id(doc_id);
id_to_fieldnorm(fieldnorm_id)
match &self.0 {
ReaderImplEnum::FromData(data) => {
let fieldnorm_id = data.as_slice()[doc_id as usize];
id_to_fieldnorm(fieldnorm_id)
}
ReaderImplEnum::Const { fieldnorm, .. } => *fieldnorm,
}
}
/// Returns the `fieldnorm_id` associated to a document.
#[inline(always)]
pub fn fieldnorm_id(&self, doc_id: DocId) -> u8 {
let fielnorms_data = self.data.as_slice();
fielnorms_data[doc_id as usize]
match &self.0 {
ReaderImplEnum::FromData(data) => {
let fieldnorm_id = data.as_slice()[doc_id as usize];
fieldnorm_id
}
ReaderImplEnum::Const { fieldnorm_id, .. } => *fieldnorm_id,
}
}
/// Converts a `fieldnorm_id` into a fieldnorm.
@@ -62,18 +156,48 @@ impl FieldNormReader {
pub fn fieldnorm_to_id(fieldnorm: u32) -> u8 {
fieldnorm_to_id(fieldnorm)
}
#[cfg(test)]
pub fn for_test(field_norms: &[u32]) -> FieldNormReader {
let field_norms_id = field_norms
.iter()
.cloned()
.map(FieldNormReader::fieldnorm_to_id)
.collect::<Vec<u8>>();
let field_norms_data = OwnedBytes::new(field_norms_id);
FieldNormReader::new(field_norms_data)
}
}
#[cfg(test)]
impl From<Vec<u32>> for FieldNormReader {
fn from(field_norms: Vec<u32>) -> FieldNormReader {
let field_norms_id = field_norms
.into_iter()
.map(FieldNormReader::fieldnorm_to_id)
.collect::<Vec<u8>>();
let field_norms_data = ReadOnlySource::from(field_norms_id);
FieldNormReader {
data: field_norms_data,
}
mod tests {
use crate::fieldnorm::FieldNormReader;
#[test]
fn test_from_fieldnorms_array() {
let fieldnorms = &[1, 2, 3, 4, 1_000_000];
let fieldnorm_reader = FieldNormReader::for_test(fieldnorms);
assert_eq!(fieldnorm_reader.num_docs(), 5);
assert_eq!(fieldnorm_reader.fieldnorm(0), 1);
assert_eq!(fieldnorm_reader.fieldnorm(1), 2);
assert_eq!(fieldnorm_reader.fieldnorm(2), 3);
assert_eq!(fieldnorm_reader.fieldnorm(3), 4);
assert_eq!(fieldnorm_reader.fieldnorm(4), 983_064);
}
#[test]
fn test_const_fieldnorm_reader_small_fieldnorm_id() {
let fieldnorm_reader = FieldNormReader::constant(1_000_000u32, 10u32);
assert_eq!(fieldnorm_reader.num_docs(), 1_000_000u32);
assert_eq!(fieldnorm_reader.fieldnorm(0u32), 10u32);
assert_eq!(fieldnorm_reader.fieldnorm_id(0u32), 10u8);
}
#[test]
fn test_const_fieldnorm_reader_large_fieldnorm_id() {
let fieldnorm_reader = FieldNormReader::constant(1_000_000u32, 300u32);
assert_eq!(fieldnorm_reader.num_docs(), 1_000_000u32);
assert_eq!(fieldnorm_reader.fieldnorm(0u32), 280u32);
assert_eq!(fieldnorm_reader.fieldnorm_id(0u32), 72u8);
}
}

9
src/fieldnorm/writer.rs
View File

@@ -4,7 +4,7 @@ use super::fieldnorm_to_id;
use super::FieldNormsSerializer;
use crate::schema::Field;
use crate::schema::Schema;
use std::io;
use std::{io, iter};
/// The `FieldNormsWriter` is in charge of tracking the fieldnorm byte
/// of each document for each field with field norms.
@@ -44,7 +44,9 @@ impl FieldNormsWriter {
.unwrap_or(0);
FieldNormsWriter {
fields,
fieldnorms_buffer: (0..max_field).map(|_| Vec::new()).collect::<Vec<_>>(),
fieldnorms_buffer: iter::repeat_with(Vec::new)
.take(max_field)
.collect::<Vec<_>>(),
}
}
@@ -78,11 +80,12 @@ impl FieldNormsWriter {
}
/// Serialize the seen fieldnorm values to the serializer for all fields.
pub fn serialize(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> io::Result<()> {
pub fn serialize(&self, mut fieldnorms_serializer: FieldNormsSerializer) -> io::Result<()> {
for &field in self.fields.iter() {
let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.field_id() as usize][..];
fieldnorms_serializer.serialize_field(field, fieldnorm_values)?;
}
fieldnorms_serializer.close()?;
Ok(())
}
}

75
src/functional_test.rs
View File

@@ -1,45 +1,93 @@
use rand::thread_rng;
use std::collections::HashSet;
use crate::schema::*;
use crate::Index;
use crate::Searcher;
use crate::{doc, schema::*};
use rand::thread_rng;
use rand::Rng;
use std::collections::HashSet;
fn check_index_content(searcher: &Searcher, vals: &HashSet<u64>) {
fn check_index_content(searcher: &Searcher, vals: &[u64]) -> crate::Result<()> {
assert!(searcher.segment_readers().len() < 20);
assert_eq!(searcher.num_docs() as usize, vals.len());
for segment_reader in searcher.segment_readers() {
let store_reader = segment_reader.get_store_reader()?;
for doc_id in 0..segment_reader.max_doc() {
let _doc = store_reader.get(doc_id)?;
}
}
Ok(())
}
#[test]
#[ignore]
fn test_indexing() {
fn test_functional_store() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let id_field = schema_builder.add_u64_field("id", INDEXED | STORED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let reader = index.reader()?;
let mut rng = thread_rng();
let mut index_writer = index.writer_with_num_threads(3, 12_000_000)?;
let mut doc_set: Vec<u64> = Vec::new();
let mut doc_id = 0u64;
for iteration in 0..500 {
dbg!(iteration);
let num_docs: usize = rng.gen_range(0..4);
if doc_set.len() >= 1 {
let doc_to_remove_id = rng.gen_range(0..doc_set.len());
let removed_doc_id = doc_set.swap_remove(doc_to_remove_id);
index_writer.delete_term(Term::from_field_u64(id_field, removed_doc_id));
}
for _ in 0..num_docs {
doc_set.push(doc_id);
index_writer.add_document(doc!(id_field=>doc_id));
doc_id += 1;
}
index_writer.commit()?;
reader.reload()?;
let searcher = reader.searcher();
check_index_content(&searcher, &doc_set)?;
}
Ok(())
}
#[test]
#[ignore]
fn test_functional_indexing() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let id_field = schema_builder.add_u64_field("id", INDEXED);
let multiples_field = schema_builder.add_u64_field("multiples", INDEXED);
let schema = schema_builder.build();
let index = Index::create_from_tempdir(schema).unwrap();
let reader = index.reader().unwrap();
let index = Index::create_from_tempdir(schema)?;
let reader = index.reader()?;
let mut rng = thread_rng();
let mut index_writer = index.writer_with_num_threads(3, 120_000_000).unwrap();
let mut index_writer = index.writer_with_num_threads(3, 120_000_000)?;
let mut committed_docs: HashSet<u64> = HashSet::new();
let mut uncommitted_docs: HashSet<u64> = HashSet::new();
for _ in 0..200 {
let random_val = rng.gen_range(0, 20);
let random_val = rng.gen_range(0..20);
if random_val == 0 {
index_writer.commit().expect("Commit failed");
index_writer.commit()?;
committed_docs.extend(&uncommitted_docs);
uncommitted_docs.clear();
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
// check that everything is correct.
check_index_content(&searcher, &committed_docs);
check_index_content(
&searcher,
&committed_docs.iter().cloned().collect::<Vec<u64>>(),
)?;
} else {
if committed_docs.remove(&random_val) || uncommitted_docs.remove(&random_val) {
let doc_id_term = Term::from_field_u64(id_field, random_val);
@@ -55,4 +103,5 @@ fn test_indexing() {
}
}
}
Ok(())
}

81
src/indexer/delete_queue.rs
View File

@@ -2,7 +2,7 @@ use super::operation::DeleteOperation;
use crate::Opstamp;
use std::mem;
use std::ops::DerefMut;
use std::sync::{Arc, RwLock};
use std::sync::{Arc, RwLock, Weak};
// The DeleteQueue is similar in conceptually to a multiple
// consumer single producer broadcast channel.
@@ -14,14 +14,15 @@ use std::sync::{Arc, RwLock};
//
// New consumer can be created in two ways
// - calling `delete_queue.cursor()` returns a cursor, that
// will include all future delete operation (and no past operations).
// will include all future delete operation (and some or none
// of the past operations... The client is in charge of checking the opstamps.).
// - cloning an existing cursor returns a new cursor, that
// is at the exact same position, and can now advance independently
// from the original cursor.
#[derive(Default)]
struct InnerDeleteQueue {
writer: Vec<DeleteOperation>,
last_block: Option<Arc<Block>>,
last_block: Weak<Block>,
}
#[derive(Clone)]
@@ -32,21 +33,31 @@ pub struct DeleteQueue {
impl DeleteQueue {
// Creates a new delete queue.
pub fn new() -> DeleteQueue {
let delete_queue = DeleteQueue {
DeleteQueue {
inner: Arc::default(),
};
let next_block = NextBlock::from(delete_queue.clone());
{
let mut delete_queue_wlock = delete_queue.inner.write().unwrap();
delete_queue_wlock.last_block = Some(Arc::new(Block {
operations: Arc::default(),
next: next_block,
}));
}
}
delete_queue
fn get_last_block(&self) -> Arc<Block> {
{
// try get the last block with simply acquiring the read lock.
let rlock = self.inner.read().unwrap();
if let Some(block) = rlock.last_block.upgrade() {
return block;
}
}
// It failed. Let's double check after acquiring the write, as someone could have called
// `get_last_block` right after we released the rlock.
let mut wlock = self.inner.write().unwrap();
if let Some(block) = wlock.last_block.upgrade() {
return block;
}
let block = Arc::new(Block {
operations: Arc::new([]),
next: NextBlock::from(self.clone()),
});
wlock.last_block = Arc::downgrade(&block);
block
}
// Creates a new cursor that makes it possible to
@@ -54,17 +65,7 @@ impl DeleteQueue {
//
// Past delete operations are not accessible.
pub fn cursor(&self) -> DeleteCursor {
let last_block = self
.inner
.read()
.expect("Read lock poisoned when opening delete queue cursor")
.last_block
.clone()
.expect(
"Failed to unwrap last_block. This should never happen
as the Option<> is only here to make
initialization possible",
);
let last_block = self.get_last_block();
let operations_len = last_block.operations.len();
DeleteCursor {
block: last_block,
@@ -100,23 +101,19 @@ impl DeleteQueue {
.write()
.expect("Failed to acquire write lock on delete queue writer");
let delete_operations;
{
let writer: &mut Vec<DeleteOperation> = &mut self_wlock.writer;
if writer.is_empty() {
return None;
}
delete_operations = mem::replace(writer, vec![]);
if self_wlock.writer.is_empty() {
return None;
}
let next_block = NextBlock::from(self.clone());
{
self_wlock.last_block = Some(Arc::new(Block {
operations: Arc::new(delete_operations),
next: next_block,
}));
}
self_wlock.last_block.clone()
let delete_operations = mem::replace(&mut self_wlock.writer, vec![]);
let new_block = Arc::new(Block {
operations: Arc::from(delete_operations.into_boxed_slice()),
next: NextBlock::from(self.clone()),
});
self_wlock.last_block = Arc::downgrade(&new_block);
Some(new_block)
}
}
@@ -170,7 +167,7 @@ impl NextBlock {
}
struct Block {
operations: Arc<Vec<DeleteOperation>>,
operations: Arc<[DeleteOperation]>,
next: NextBlock,
}

314
src/indexer/index_writer.rs
View File

@@ -1,15 +1,16 @@
use super::operation::{AddOperation, UserOperation};
use super::segment_updater::SegmentUpdater;
use super::PreparedCommit;
use crate::common::BitSet;
use crate::core::Index;
use crate::core::Segment;
use crate::core::SegmentComponent;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SegmentReader;
use crate::directory::DirectoryLock;
use crate::directory::TerminatingWrite;
use crate::docset::DocSet;
use crate::directory::{DirectoryLock, GarbageCollectionResult};
use crate::docset::{DocSet, TERMINATED};
use crate::error::TantivyError;
use crate::fastfield::write_delete_bitset;
use crate::indexer::delete_queue::{DeleteCursor, DeleteQueue};
@@ -23,10 +24,9 @@ use crate::schema::Document;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::Opstamp;
use crate::Result;
use bit_set::BitSet;
use crossbeam::channel;
use futures::{Canceled, Future};
use futures::executor::block_on;
use futures::future::Future;
use smallvec::smallvec;
use smallvec::SmallVec;
use std::mem;
@@ -72,7 +72,7 @@ pub struct IndexWriter {
heap_size_in_bytes_per_thread: usize,
workers_join_handle: Vec<JoinHandle<Result<()>>>,
workers_join_handle: Vec<JoinHandle<crate::Result<()>>>,
operation_receiver: OperationReceiver,
operation_sender: OperationSender,
@@ -95,7 +95,7 @@ fn compute_deleted_bitset(
delete_cursor: &mut DeleteCursor,
doc_opstamps: &DocToOpstampMapping,
target_opstamp: Opstamp,
) -> Result<bool> {
) -> crate::Result<bool> {
let mut might_have_changed = false;
while let Some(delete_op) = delete_cursor.get() {
if delete_op.opstamp > target_opstamp {
@@ -108,83 +108,96 @@ fn compute_deleted_bitset(
// Limit doc helps identify the first document
// that may be affected by the delete operation.
let limit_doc = doc_opstamps.compute_doc_limit(delete_op.opstamp);
let inverted_index = segment_reader.inverted_index(delete_op.term.field());
let inverted_index = segment_reader.inverted_index(delete_op.term.field())?;
if let Some(mut docset) =
inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)
inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)?
{
while docset.advance() {
let deleted_doc = docset.doc();
let mut deleted_doc = docset.doc();
while deleted_doc != TERMINATED {
if deleted_doc < limit_doc {
delete_bitset.insert(deleted_doc as usize);
delete_bitset.insert(deleted_doc);
might_have_changed = true;
}
deleted_doc = docset.advance();
}
}
delete_cursor.advance();
}
Ok(might_have_changed)
}
/// Advance delete for the given segment up
/// to the target opstamp.
/// Advance delete for the given segment up to the target opstamp.
///
/// Note that there are no guarantee that the resulting `segment_entry` delete_opstamp
/// is `==` target_opstamp.
/// For instance, there was no delete operation between the state of the `segment_entry` and
/// the `target_opstamp`, `segment_entry` is not updated.
pub(crate) fn advance_deletes(
mut segment: Segment,
segment_entry: &mut SegmentEntry,
target_opstamp: Opstamp,
) -> Result<()> {
{
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
return Ok(());
}
) -> crate::Result<()> {
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
return Ok(());
}
let segment_reader = SegmentReader::open(&segment)?;
if segment_entry.delete_bitset().is_none() && segment_entry.delete_cursor().get().is_none() {
// There has been no `DeleteOperation` between the segment status and `target_opstamp`.
return Ok(());
}
let max_doc = segment_reader.max_doc();
let mut delete_bitset: BitSet = match segment_entry.delete_bitset() {
Some(previous_delete_bitset) => (*previous_delete_bitset).clone(),
None => BitSet::with_capacity(max_doc as usize),
};
let segment_reader = SegmentReader::open(&segment)?;
let delete_cursor = segment_entry.delete_cursor();
let max_doc = segment_reader.max_doc();
let mut delete_bitset: BitSet = match segment_entry.delete_bitset() {
Some(previous_delete_bitset) => (*previous_delete_bitset).clone(),
None => BitSet::with_max_value(max_doc),
};
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
delete_cursor,
&DocToOpstampMapping::None,
target_opstamp,
)?;
let num_deleted_docs_before = segment.meta().num_deleted_docs();
// TODO optimize
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
segment_entry.delete_cursor(),
&DocToOpstampMapping::None,
target_opstamp,
)?;
// TODO optimize
// It should be possible to do something smarter by manipulation bitsets directly
// to compute this union.
if let Some(seg_delete_bitset) = segment_reader.delete_bitset() {
for doc in 0u32..max_doc {
if segment_reader.is_deleted(doc) {
delete_bitset.insert(doc as usize);
if seg_delete_bitset.is_deleted(doc) {
delete_bitset.insert(doc);
}
}
let num_deleted_docs = delete_bitset.len();
if num_deleted_docs > 0 {
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, &mut delete_file)?;
delete_file.terminate()?;
}
}
let num_deleted_docs: u32 = delete_bitset.len() as u32;
if num_deleted_docs > num_deleted_docs_before {
// There are new deletes. We need to write a new delete file.
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, max_doc, &mut delete_file)?;
delete_file.terminate()?;
}
segment_entry.set_meta(segment.meta().clone());
Ok(())
}
fn index_documents(
memory_budget: usize,
segment: &Segment,
segment: Segment,
grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>,
segment_updater: &mut SegmentUpdater,
mut delete_cursor: DeleteCursor,
) -> Result<bool> {
) -> crate::Result<bool> {
let schema = segment.schema();
let segment_id = segment.id();
let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?;
for document_group in grouped_document_iterator {
for doc in document_group {
@@ -204,22 +217,32 @@ fn index_documents(
return Ok(false);
}
let num_docs = segment_writer.max_doc();
let max_doc = segment_writer.max_doc();
// this is ensured by the call to peek before starting
// the worker thread.
assert!(num_docs > 0);
assert!(max_doc > 0);
let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?;
let segment_meta = segment.index().new_segment_meta(segment_id, num_docs);
let segment_with_max_doc = segment.with_max_doc(max_doc);
let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
let delete_bitset_opt =
apply_deletes(&segment, &mut delete_cursor, &doc_opstamps, last_docstamp)?;
let delete_bitset_opt = apply_deletes(
&segment_with_max_doc,
&mut delete_cursor,
&doc_opstamps,
last_docstamp,
)?;
let segment_entry = SegmentEntry::new(segment_meta, delete_cursor, delete_bitset_opt);
Ok(segment_updater.add_segment(segment_entry))
let segment_entry = SegmentEntry::new(
segment_with_max_doc.meta().clone(),
delete_cursor,
delete_bitset_opt,
);
block_on(segment_updater.schedule_add_segment(segment_entry))?;
Ok(true)
}
fn apply_deletes(
@@ -227,7 +250,7 @@ fn apply_deletes(
mut delete_cursor: &mut DeleteCursor,
doc_opstamps: &[Opstamp],
last_docstamp: Opstamp,
) -> Result<Option<BitSet<u32>>> {
) -> crate::Result<Option<BitSet>> {
if delete_cursor.get().is_none() {
// if there are no delete operation in the queue, no need
// to even open the segment.
@@ -235,7 +258,9 @@ fn apply_deletes(
}
let segment_reader = SegmentReader::open(segment)?;
let doc_to_opstamps = DocToOpstampMapping::from(doc_opstamps);
let mut deleted_bitset = BitSet::with_capacity(segment_reader.max_doc() as usize);
let max_doc = segment.meta().max_doc();
let mut deleted_bitset = BitSet::with_max_value(max_doc);
let may_have_deletes = compute_deleted_bitset(
&mut deleted_bitset,
&segment_reader,
@@ -270,7 +295,7 @@ impl IndexWriter {
num_threads: usize,
heap_size_in_bytes_per_thread: usize,
directory_lock: DirectoryLock,
) -> Result<IndexWriter> {
) -> crate::Result<IndexWriter> {
if heap_size_in_bytes_per_thread < HEAP_SIZE_MIN {
let err_msg = format!(
"The heap size per thread needs to be at least {}.",
@@ -319,12 +344,17 @@ impl IndexWriter {
Ok(index_writer)
}
fn drop_sender(&mut self) {
let (sender, _receiver) = channel::bounded(1);
self.operation_sender = sender;
}
/// If there are some merging threads, blocks until they all finish their work and
/// then drop the `IndexWriter`.
pub fn wait_merging_threads(mut self) -> Result<()> {
pub fn wait_merging_threads(mut self) -> crate::Result<()> {
// this will stop the indexing thread,
// dropping the last reference to the segment_updater.
drop(self.operation_sender);
self.drop_sender();
let former_workers_handles = mem::replace(&mut self.workers_join_handle, vec![]);
for join_handle in former_workers_handles {
@@ -335,7 +365,6 @@ impl IndexWriter {
TantivyError::ErrorInThread("Error in indexing worker thread.".into())
})?;
}
drop(self.workers_join_handle);
let result = self
.segment_updater
@@ -350,10 +379,10 @@ impl IndexWriter {
}
#[doc(hidden)]
pub fn add_segment(&mut self, segment_meta: SegmentMeta) {
pub fn add_segment(&self, segment_meta: SegmentMeta) -> crate::Result<()> {
let delete_cursor = self.delete_queue.cursor();
let segment_entry = SegmentEntry::new(segment_meta, delete_cursor, None);
self.segment_updater.add_segment(segment_entry);
block_on(self.segment_updater.schedule_add_segment(segment_entry))
}
/// Creates a new segment.
@@ -370,7 +399,7 @@ impl IndexWriter {
/// Spawns a new worker thread for indexing.
/// The thread consumes documents from the pipeline.
fn add_indexing_worker(&mut self) -> Result<()> {
fn add_indexing_worker(&mut self) -> crate::Result<()> {
let document_receiver_clone = self.operation_receiver.clone();
let mut segment_updater = self.segment_updater.clone();
@@ -378,7 +407,7 @@ impl IndexWriter {
let mem_budget = self.heap_size_in_bytes_per_thread;
let index = self.index.clone();
let join_handle: JoinHandle<Result<()>> = thread::Builder::new()
let join_handle: JoinHandle<crate::Result<()>> = thread::Builder::new()
.name(format!("thrd-tantivy-index{}", self.worker_id))
.spawn(move || {
loop {
@@ -407,7 +436,7 @@ impl IndexWriter {
let segment = index.new_segment();
index_documents(
mem_budget,
&segment,
segment,
&mut document_iterator,
&mut segment_updater,
delete_cursor.clone(),
@@ -420,26 +449,27 @@ impl IndexWriter {
}
/// Accessor to the merge policy.
pub fn get_merge_policy(&self) -> Arc<Box<dyn MergePolicy>> {
pub fn get_merge_policy(&self) -> Arc<dyn MergePolicy> {
self.segment_updater.get_merge_policy()
}
/// Set the merge policy.
/// Setter for the merge policy.
pub fn set_merge_policy(&self, merge_policy: Box<dyn MergePolicy>) {
self.segment_updater.set_merge_policy(merge_policy);
}
fn start_workers(&mut self) -> Result<()> {
fn start_workers(&mut self) -> crate::Result<()> {
for _ in 0..self.num_threads {
self.add_indexing_worker()?;
}
Ok(())
}
/// Detects and removes the files that
/// are not used by the index anymore.
pub fn garbage_collect_files(&mut self) -> Result<()> {
self.segment_updater.garbage_collect_files().wait()
/// Detects and removes the files that are not used by the index anymore.
pub fn garbage_collect_files(
&self,
) -> impl Future<Output = crate::Result<GarbageCollectionResult>> {
self.segment_updater.schedule_garbage_collect()
}
/// Deletes all documents from the index
@@ -478,7 +508,7 @@ impl IndexWriter {
/// Ok(())
/// }
/// ```
pub fn delete_all_documents(&mut self) -> Result<Opstamp> {
pub fn delete_all_documents(&self) -> crate::Result<Opstamp> {
// Delete segments
self.segment_updater.remove_all_segments();
// Return new stamp - reverted stamp
@@ -492,8 +522,10 @@ impl IndexWriter {
pub fn merge(
&mut self,
segment_ids: &[SegmentId],
) -> Result<impl Future<Item = SegmentMeta, Error = Canceled>> {
self.segment_updater.start_merge(segment_ids)
) -> impl Future<Output = crate::Result<SegmentMeta>> {
let merge_operation = self.segment_updater.make_merge_operation(segment_ids);
let segment_updater = self.segment_updater.clone();
async move { segment_updater.start_merge(merge_operation)?.await }
}
/// Closes the current document channel send.
@@ -504,6 +536,7 @@ impl IndexWriter {
/// when no documents are remaining.
///
/// Returns the former segment_ready channel.
#[allow(unused_must_use)]
fn recreate_document_channel(&mut self) -> OperationReceiver {
let (document_sender, document_receiver): (OperationSender, OperationReceiver) =
channel::bounded(PIPELINE_MAX_SIZE_IN_DOCS);
@@ -519,13 +552,8 @@ impl IndexWriter {
/// state as it was after the last commit.
///
/// The opstamp at the last commit is returned.
pub fn rollback(&mut self) -> Result<Opstamp> {
pub fn rollback(&mut self) -> crate::Result<Opstamp> {
info!("Rolling back to opstamp {}", self.committed_opstamp);
self.rollback_impl()
}
/// Private, implementation of rollback
fn rollback_impl(&mut self) -> Result<Opstamp> {
// marks the segment updater as killed. From now on, all
// segment updates will be ignored.
self.segment_updater.kill();
@@ -548,7 +576,7 @@ impl IndexWriter {
//
// This will drop the document queue, and the thread
// should terminate.
mem::replace(self, new_index_writer);
*self = new_index_writer;
// Drains the document receiver pipeline :
// Workers don't need to index the pending documents.
@@ -581,7 +609,7 @@ impl IndexWriter {
/// It is also possible to add a payload to the `commit`
/// using this API.
/// See [`PreparedCommit::set_payload()`](PreparedCommit.html)
pub fn prepare_commit(&mut self) -> Result<PreparedCommit<'_>> {
pub fn prepare_commit(&mut self) -> crate::Result<PreparedCommit> {
// Here, because we join all of the worker threads,
// all of the segment update for this commit have been
// sent.
@@ -628,7 +656,7 @@ impl IndexWriter {
/// Commit returns the `opstamp` of the last document
/// that made it in the commit.
///
pub fn commit(&mut self) -> Result<Opstamp> {
pub fn commit(&mut self) -> crate::Result<Opstamp> {
self.prepare_commit()?.commit()
}
@@ -669,9 +697,6 @@ impl IndexWriter {
/// The opstamp is an increasing `u64` that can
/// be used by the client to align commits with its own
/// document queue.
///
/// Currently it represents the number of documents that
/// have been added since the creation of the index.
pub fn add_document(&self, document: Document) -> Opstamp {
let opstamp = self.stamper.stamp();
let add_operation = AddOperation { opstamp, document };
@@ -745,6 +770,16 @@ impl IndexWriter {
}
}
impl Drop for IndexWriter {
fn drop(&mut self) {
self.segment_updater.kill();
self.drop_sender();
for work in self.workers_join_handle.drain(..) {
let _ = work.join();
}
}
}
#[cfg(test)]
mod tests {
@@ -754,7 +789,7 @@ mod tests {
use crate::error::*;
use crate::indexer::NoMergePolicy;
use crate::query::TermQuery;
use crate::schema::{self, IndexRecordOption};
use crate::schema::{self, IndexRecordOption, STRING};
use crate::Index;
use crate::ReloadPolicy;
use crate::Term;
@@ -765,7 +800,7 @@ mod tests {
let mut schema_builder = schema::Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_in_ram(schema_builder.build());
let index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let index_writer = index.writer_for_tests().unwrap();
let operations = vec![
UserOperation::Add(doc!(text_field=>"a")),
UserOperation::Add(doc!(text_field=>"b")),
@@ -774,6 +809,46 @@ mod tests {
assert_eq!(batch_opstamp1, 2u64);
}
#[test]
fn test_no_need_to_rewrite_delete_file_if_no_new_deletes() {
let mut schema_builder = schema::Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "hello1"));
index_writer.add_document(doc!(text_field => "hello2"));
assert!(index_writer.commit().is_ok());
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
assert_eq!(searcher.segment_reader(0u32).num_deleted_docs(), 0);
index_writer.delete_term(Term::from_field_text(text_field, "hello1"));
assert!(index_writer.commit().is_ok());
assert!(reader.reload().is_ok());
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
assert_eq!(searcher.segment_reader(0u32).num_deleted_docs(), 1);
let previous_delete_opstamp = index.load_metas().unwrap().segments[0].delete_opstamp();
// All docs containing hello1 have been already removed.
// We should not update the delete meta.
index_writer.delete_term(Term::from_field_text(text_field, "hello1"));
assert!(index_writer.commit().is_ok());
assert!(reader.reload().is_ok());
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
assert_eq!(searcher.segment_reader(0u32).num_deleted_docs(), 1);
let after_delete_opstamp = index.load_metas().unwrap().segments[0].delete_opstamp();
assert_eq!(after_delete_opstamp, previous_delete_opstamp);
}
#[test]
fn test_ordered_batched_operations() {
// * one delete for `doc!(field=>"a")`
@@ -789,7 +864,7 @@ mod tests {
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let a_term = Term::from_field_text(text_field, "a");
let b_term = Term::from_field_text(text_field, "b");
let operations = vec![
@@ -851,8 +926,8 @@ mod tests {
fn test_lockfile_already_exists_error_msg() {
let schema_builder = schema::Schema::builder();
let index = Index::create_in_ram(schema_builder.build());
let _index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
match index.writer_with_num_threads(1, 3_000_000) {
let _index_writer = index.writer_for_tests().unwrap();
match index.writer_for_tests() {
Err(err) => {
let err_msg = err.to_string();
assert!(err_msg.contains("already an `IndexWriter`"));
@@ -868,7 +943,7 @@ mod tests {
let index_writer = index.writer(3_000_000).unwrap();
assert_eq!(
format!("{:?}", index_writer.get_merge_policy()),
"LogMergePolicy { min_merge_size: 8, min_layer_size: 10000, \
"LogMergePolicy { min_merge_size: 8, max_merge_size: 10000000, min_layer_size: 10000, \
level_log_size: 0.75 }"
);
let merge_policy = Box::new(NoMergePolicy::default());
@@ -904,7 +979,7 @@ mod tests {
let num_docs_containing = |s: &str| {
let searcher = reader.searcher();
let term = Term::from_field_text(text_field, s);
searcher.doc_freq(&term)
searcher.doc_freq(&term).unwrap()
};
{
@@ -940,7 +1015,7 @@ mod tests {
.unwrap();
let num_docs_containing = |s: &str| {
let term_a = Term::from_field_text(text_field, s);
reader.searcher().doc_freq(&term_a)
reader.searcher().doc_freq(&term_a).unwrap()
};
{
// writing the segment
@@ -1035,6 +1110,7 @@ mod tests {
.unwrap()
.searcher()
.doc_freq(&term_a)
.unwrap()
};
assert_eq!(num_docs_containing("a"), 0);
assert_eq!(num_docs_containing("b"), 100);
@@ -1054,7 +1130,7 @@ mod tests {
reader.reload().unwrap();
let searcher = reader.searcher();
let term = Term::from_field_text(text_field, s);
searcher.doc_freq(&term)
searcher.doc_freq(&term).unwrap()
};
let mut index_writer = index.writer_with_num_threads(4, 12_000_000).unwrap();
@@ -1105,7 +1181,15 @@ mod tests {
// working with an empty index == no documents
let term_b = Term::from_field_text(text_field, "b");
assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_b), 0);
assert_eq!(
index
.reader()
.unwrap()
.searcher()
.doc_freq(&term_b)
.unwrap(),
0
);
}
#[test]
@@ -1125,7 +1209,15 @@ mod tests {
let term_a = Term::from_field_text(text_field, "a");
// expect the document with that term to be in the index
assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_a), 1);
assert_eq!(
index
.reader()
.unwrap()
.searcher()
.doc_freq(&term_a)
.unwrap(),
1
);
}
#[test]
@@ -1151,7 +1243,15 @@ mod tests {
// Find original docs in the index
let term_a = Term::from_field_text(text_field, "a");
// expect the document with that term to be in the index
assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_a), 1);
assert_eq!(
index
.reader()
.unwrap()
.searcher()
.doc_freq(&term_a)
.unwrap(),
1
);
}
#[test]
@@ -1179,4 +1279,16 @@ mod tests {
assert!(clear_again.is_ok());
assert!(commit_again.is_ok());
}
#[test]
fn test_index_doc_missing_field() {
let mut schema_builder = schema::Schema::builder();
let idfield = schema_builder.add_text_field("id", STRING);
schema_builder.add_text_field("optfield", STRING);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(idfield=>"myid"));
let commit = index_writer.commit();
assert!(commit.is_ok());
}
}

90
src/indexer/log_merge_policy.rs
View File

@@ -6,12 +6,14 @@ use std::f64;
const DEFAULT_LEVEL_LOG_SIZE: f64 = 0.75;
const DEFAULT_MIN_LAYER_SIZE: u32 = 10_000;
const DEFAULT_MIN_MERGE_SIZE: usize = 8;
const DEFAULT_MAX_MERGE_SIZE: usize = 10_000_000;
/// `LogMergePolicy` tries tries to merge segments that have a similar number of
/// `LogMergePolicy` tries to merge segments that have a similar number of
/// documents.
#[derive(Debug, Clone)]
pub struct LogMergePolicy {
min_merge_size: usize,
max_merge_size: usize,
min_layer_size: u32,
level_log_size: f64,
}
@@ -26,6 +28,12 @@ impl LogMergePolicy {
self.min_merge_size = min_merge_size;
}
/// Set the maximum number docs in a segment for it to be considered for
/// merging.
pub fn set_max_merge_size(&mut self, max_merge_size: usize) {
self.max_merge_size = max_merge_size;
}
/// Set the minimum segment size under which all segment belong
/// to the same level.
pub fn set_min_layer_size(&mut self, min_layer_size: u32) {
@@ -46,39 +54,44 @@ impl LogMergePolicy {
impl MergePolicy for LogMergePolicy {
fn compute_merge_candidates(&self, segments: &[SegmentMeta]) -> Vec<MergeCandidate> {
if segments.is_empty() {
return Vec::new();
}
let mut size_sorted_tuples = segments
.iter()
.map(SegmentMeta::num_docs)
.filter(|s| s <= &(self.max_merge_size as u32))
.enumerate()
.collect::<Vec<(usize, u32)>>();
size_sorted_tuples.sort_by(|x, y| y.1.cmp(&(x.1)));
if size_sorted_tuples.len() <= 1 {
return Vec::new();
}
let size_sorted_log_tuples: Vec<_> = size_sorted_tuples
.into_iter()
.map(|(ind, num_docs)| (ind, f64::from(self.clip_min_size(num_docs)).log2()))
.collect();
let (first_ind, first_score) = size_sorted_log_tuples[0];
let mut current_max_log_size = first_score;
let mut levels = vec![vec![first_ind]];
for &(ind, score) in (&size_sorted_log_tuples).iter().skip(1) {
if score < (current_max_log_size - self.level_log_size) {
current_max_log_size = score;
levels.push(Vec::new());
if let Some(&(first_ind, first_score)) = size_sorted_log_tuples.first() {
let mut current_max_log_size = first_score;
let mut levels = vec![vec![first_ind]];
for &(ind, score) in (&size_sorted_log_tuples).iter().skip(1) {
if score < (current_max_log_size - self.level_log_size) {
current_max_log_size = score;
levels.push(Vec::new());
}
levels.last_mut().unwrap().push(ind);
}
levels.last_mut().unwrap().push(ind);
levels
.iter()
.filter(|level| level.len() >= self.min_merge_size)
.map(|ind_vec| {
MergeCandidate(ind_vec.iter().map(|&ind| segments[ind].id()).collect())
})
.collect()
} else {
return vec![];
}
levels
.iter()
.filter(|level| level.len() >= self.min_merge_size)
.map(|ind_vec| MergeCandidate(ind_vec.iter().map(|&ind| segments[ind].id()).collect()))
.collect()
}
}
@@ -86,6 +99,7 @@ impl Default for LogMergePolicy {
fn default() -> LogMergePolicy {
LogMergePolicy {
min_merge_size: DEFAULT_MIN_MERGE_SIZE,
max_merge_size: DEFAULT_MAX_MERGE_SIZE,
min_layer_size: DEFAULT_MIN_LAYER_SIZE,
level_log_size: DEFAULT_LEVEL_LOG_SIZE,
}
@@ -104,6 +118,7 @@ mod tests {
fn test_merge_policy() -> LogMergePolicy {
let mut log_merge_policy = LogMergePolicy::default();
log_merge_policy.set_min_merge_size(3);
log_merge_policy.set_max_merge_size(100_000);
log_merge_policy.set_min_layer_size(2);
log_merge_policy
}
@@ -141,11 +156,11 @@ mod tests {
create_random_segment_meta(10),
create_random_segment_meta(10),
create_random_segment_meta(10),
create_random_segment_meta(1000),
create_random_segment_meta(1000),
create_random_segment_meta(1000),
create_random_segment_meta(10000),
create_random_segment_meta(10000),
create_random_segment_meta(1_000),
create_random_segment_meta(1_000),
create_random_segment_meta(1_000),
create_random_segment_meta(10_000),
create_random_segment_meta(10_000),
create_random_segment_meta(10),
create_random_segment_meta(10),
create_random_segment_meta(10),
@@ -168,6 +183,7 @@ mod tests {
let result_list = test_merge_policy().compute_merge_candidates(&test_input);
assert_eq!(result_list.len(), 2);
}
#[test]
fn test_log_merge_policy_small_segments() {
// segments under min_layer_size are merged together
@@ -182,4 +198,30 @@ mod tests {
let result_list = test_merge_policy().compute_merge_candidates(&test_input);
assert_eq!(result_list.len(), 1);
}
#[test]
fn test_log_merge_policy_all_segments_too_large_to_merge() {
let eight_large_segments: Vec<SegmentMeta> =
std::iter::repeat_with(|| create_random_segment_meta(100_001))
.take(8)
.collect();
assert!(test_merge_policy()
.compute_merge_candidates(&eight_large_segments)
.is_empty());
}
#[test]
fn test_large_merge_segments() {
let test_input = vec![
create_random_segment_meta(1_000_000),
create_random_segment_meta(100_001),
create_random_segment_meta(100_000),
create_random_segment_meta(100_000),
create_random_segment_meta(100_000),
];
let result_list = test_merge_policy().compute_merge_candidates(&test_input);
// Do not include large segments
assert_eq!(result_list.len(), 1);
assert_eq!(result_list[0].0.len(), 3)
}
}

19
src/indexer/merge_operation.rs
View File

@@ -2,14 +2,23 @@ use crate::Opstamp;
use crate::SegmentId;
use census::{Inventory, TrackedObject};
use std::collections::HashSet;
use std::ops::Deref;
#[derive(Default)]
pub struct MergeOperationInventory(Inventory<InnerMergeOperation>);
pub(crate) struct MergeOperationInventory(Inventory<InnerMergeOperation>);
impl Deref for MergeOperationInventory {
type Target = Inventory<InnerMergeOperation>;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl MergeOperationInventory {
pub fn segment_in_merge(&self) -> HashSet<SegmentId> {
let mut segment_in_merge = HashSet::default();
for merge_op in self.0.list() {
for merge_op in self.list() {
for &segment_id in &merge_op.segment_ids {
segment_in_merge.insert(segment_id);
}
@@ -35,13 +44,13 @@ pub struct MergeOperation {
inner: TrackedObject<InnerMergeOperation>,
}
struct InnerMergeOperation {
pub(crate) struct InnerMergeOperation {
target_opstamp: Opstamp,
segment_ids: Vec<SegmentId>,
}
impl MergeOperation {
pub fn new(
pub(crate) fn new(
inventory: &MergeOperationInventory,
target_opstamp: Opstamp,
segment_ids: Vec<SegmentId>,
@@ -51,7 +60,7 @@ impl MergeOperation {
segment_ids,
};
MergeOperation {
inner: inventory.0.track(inner_merge_operation),
inner: inventory.track(inner_merge_operation),
}
}

736
src/indexer/merger.rs
View File

File diff suppressed because it is too large Load Diff

26
src/indexer/mod.rs
View File

@@ -18,7 +18,7 @@ mod stamper;
pub use self::index_writer::IndexWriter;
pub use self::log_merge_policy::LogMergePolicy;
pub use self::merge_operation::{MergeOperation, MergeOperationInventory};
pub use self::merge_operation::MergeOperation;
pub use self::merge_policy::{MergeCandidate, MergePolicy, NoMergePolicy};
pub use self::prepared_commit::PreparedCommit;
pub use self::segment_entry::SegmentEntry;
@@ -28,3 +28,27 @@ pub use self::segment_writer::SegmentWriter;
/// Alias for the default merge policy, which is the `LogMergePolicy`.
pub type DefaultMergePolicy = LogMergePolicy;
#[cfg(feature = "mmap")]
#[cfg(test)]
mod tests_mmap {
use crate::schema::{self, Schema};
use crate::{Index, Term};
#[test]
fn test_advance_delete_bug() {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_from_tempdir(schema_builder.build()).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
// there must be one deleted document in the segment
index_writer.add_document(doc!(text_field=>"b"));
index_writer.delete_term(Term::from_field_text(text_field, "b"));
// we need enough data to trigger the bug (at least 32 documents)
for _ in 0..32 {
index_writer.add_document(doc!(text_field=>"c"));
}
index_writer.commit().unwrap();
index_writer.commit().unwrap();
}
}

11
src/indexer/operation.rs
View File

@@ -9,6 +9,15 @@ pub struct DeleteOperation {
pub term: Term,
}
impl Default for DeleteOperation {
fn default() -> Self {
DeleteOperation {
opstamp: 0u64,
term: Term::new(),
}
}
}
/// Timestamped Add operation.
#[derive(Eq, PartialEq, Debug)]
pub struct AddOperation {
@@ -19,6 +28,8 @@ pub struct AddOperation {
/// UserOperation is an enum type that encapsulates other operation types.
#[derive(Eq, PartialEq, Debug)]
pub enum UserOperation {
/// Add operation
Add(Document),
/// Delete operation
Delete(Term),
}

14
src/indexer/prepared_commit.rs
View File

@@ -1,6 +1,6 @@
use super::IndexWriter;
use crate::Opstamp;
use crate::Result;
use futures::executor::block_on;
/// A prepared commit
pub struct PreparedCommit<'a> {
@@ -26,15 +26,17 @@ impl<'a> PreparedCommit<'a> {
self.payload = Some(payload.to_string())
}
pub fn abort(self) -> Result<Opstamp> {
pub fn abort(self) -> crate::Result<Opstamp> {
self.index_writer.rollback()
}
pub fn commit(self) -> Result<Opstamp> {
pub fn commit(self) -> crate::Result<Opstamp> {
info!("committing {}", self.opstamp);
self.index_writer
.segment_updater()
.commit(self.opstamp, self.payload)?;
let _ = block_on(
self.index_writer
.segment_updater()
.schedule_commit(self.opstamp, self.payload),
);
Ok(self.opstamp)
}
}

2
src/indexer/segment_entry.rs
View File

@@ -1,7 +1,7 @@
use crate::common::BitSet;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::indexer::delete_queue::DeleteCursor;
use bit_set::BitSet;
use std::fmt;
/// A segment entry describes the state of

63
src/indexer/segment_manager.rs
View File

@@ -4,7 +4,6 @@ use crate::core::SegmentMeta;
use crate::error::TantivyError;
use crate::indexer::delete_queue::DeleteCursor;
use crate::indexer::SegmentEntry;
use crate::Result as TantivyResult;
use std::collections::hash_set::HashSet;
use std::fmt::{self, Debug, Formatter};
use std::sync::RwLock;
@@ -16,6 +15,28 @@ struct SegmentRegisters {
committed: SegmentRegister,
}
#[derive(PartialEq, Eq)]
pub(crate) enum SegmentsStatus {
Committed,
Uncommitted,
}
impl SegmentRegisters {
/// Check if all the segments are committed or uncommited.
///
/// If some segment is missing or segments are in a different state (this should not happen
/// if tantivy is used correctly), returns `None`.
fn segments_status(&self, segment_ids: &[SegmentId]) -> Option<SegmentsStatus> {
if self.uncommitted.contains_all(segment_ids) {
Some(SegmentsStatus::Uncommitted)
} else if self.committed.contains_all(segment_ids) {
Some(SegmentsStatus::Committed)
} else {
None
}
}
}
/// The segment manager stores the list of segments
/// as well as their state.
///
@@ -27,7 +48,7 @@ pub struct SegmentManager {
}
impl Debug for SegmentManager {
fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), fmt::Error> {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
let lock = self.read();
write!(
f,
@@ -123,7 +144,7 @@ impl SegmentManager {
/// Returns an error if some segments are missing, or if
/// the `segment_ids` are not either all committed or all
/// uncommitted.
pub fn start_merge(&self, segment_ids: &[SegmentId]) -> TantivyResult<Vec<SegmentEntry>> {
pub fn start_merge(&self, segment_ids: &[SegmentId]) -> crate::Result<Vec<SegmentEntry>> {
let registers_lock = self.read();
let mut segment_entries = vec![];
if registers_lock.uncommitted.contains_all(segment_ids) {
@@ -153,33 +174,35 @@ impl SegmentManager {
let mut registers_lock = self.write();
registers_lock.uncommitted.add_segment_entry(segment_entry);
}
pub fn end_merge(
// Replace a list of segments for their equivalent merged segment.
//
// Returns true if these segments are committed, false if the merge segments are uncommited.
pub(crate) fn end_merge(
&self,
before_merge_segment_ids: &[SegmentId],
after_merge_segment_entry: SegmentEntry,
) {
) -> crate::Result<SegmentsStatus> {
let mut registers_lock = self.write();
let target_register: &mut SegmentRegister = {
if registers_lock
.uncommitted
.contains_all(before_merge_segment_ids)
{
&mut registers_lock.uncommitted
} else if registers_lock
.committed
.contains_all(before_merge_segment_ids)
{
&mut registers_lock.committed
} else {
let segments_status = registers_lock
.segments_status(before_merge_segment_ids)
.ok_or_else(|| {
warn!("couldn't find segment in SegmentManager");
return;
}
crate::TantivyError::InvalidArgument(
"The segments that were merged could not be found in the SegmentManager. \
This is not necessarily a bug, and can happen after a rollback for instance."
.to_string(),
)
})?;
let target_register: &mut SegmentRegister = match segments_status {
SegmentsStatus::Uncommitted => &mut registers_lock.uncommitted,
SegmentsStatus::Committed => &mut registers_lock.committed,
};
for segment_id in before_merge_segment_ids {
target_register.remove_segment(segment_id);
}
target_register.add_segment_entry(after_merge_segment_entry);
Ok(segments_status)
}
pub fn committed_segment_metas(&self) -> Vec<SegmentMeta> {

30
src/indexer/segment_serializer.rs
View File

@@ -1,5 +1,3 @@
use crate::Result;
use crate::core::Segment;
use crate::core::SegmentComponent;
use crate::fastfield::FastFieldSerializer;
@@ -10,15 +8,16 @@ use crate::store::StoreWriter;
/// Segment serializer is in charge of laying out on disk
/// the data accumulated and sorted by the `SegmentWriter`.
pub struct SegmentSerializer {
segment: Segment,
store_writer: StoreWriter,
fast_field_serializer: FastFieldSerializer,
fieldnorms_serializer: FieldNormsSerializer,
fieldnorms_serializer: Option<FieldNormsSerializer>,
postings_serializer: InvertedIndexSerializer,
}
impl SegmentSerializer {
/// Creates a new `SegmentSerializer`.
pub fn for_segment(segment: &mut Segment) -> Result<SegmentSerializer> {
pub fn for_segment(mut segment: Segment) -> crate::Result<SegmentSerializer> {
let store_write = segment.open_write(SegmentComponent::STORE)?;
let fast_field_write = segment.open_write(SegmentComponent::FASTFIELDS)?;
@@ -27,15 +26,20 @@ impl SegmentSerializer {
let fieldnorms_write = segment.open_write(SegmentComponent::FIELDNORMS)?;
let fieldnorms_serializer = FieldNormsSerializer::from_write(fieldnorms_write)?;
let postings_serializer = InvertedIndexSerializer::open(segment)?;
let postings_serializer = InvertedIndexSerializer::open(&mut segment)?;
Ok(SegmentSerializer {
segment,
store_writer: StoreWriter::new(store_write),
fast_field_serializer,
fieldnorms_serializer,
fieldnorms_serializer: Some(fieldnorms_serializer),
postings_serializer,
})
}
pub fn segment(&self) -> &Segment {
&self.segment
}
/// Accessor to the `PostingsSerializer`.
pub fn get_postings_serializer(&mut self) -> &mut InvertedIndexSerializer {
&mut self.postings_serializer
@@ -46,9 +50,11 @@ impl SegmentSerializer {
&mut self.fast_field_serializer
}
/// Accessor to the field norm serializer.
pub fn get_fieldnorms_serializer(&mut self) -> &mut FieldNormsSerializer {
&mut self.fieldnorms_serializer
/// Extract the field norm serializer.
///
/// Note the fieldnorms serializer can only be extracted once.
pub fn extract_fieldnorms_serializer(&mut self) -> Option<FieldNormsSerializer> {
self.fieldnorms_serializer.take()
}
/// Accessor to the `StoreWriter`.
@@ -57,11 +63,13 @@ impl SegmentSerializer {
}
/// Finalize the segment serialization.
pub fn close(self) -> Result<()> {
pub fn close(mut self) -> crate::Result<()> {
if let Some(fieldnorms_serializer) = self.extract_fieldnorms_serializer() {
fieldnorms_serializer.close()?;
}
self.fast_field_serializer.close()?;
self.postings_serializer.close()?;
self.store_writer.close()?;
self.fieldnorms_serializer.close()?;
Ok(())
}
}

486
src/indexer/segment_updater.rs
View File

@@ -6,39 +6,33 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SerializableSegment;
use crate::core::META_FILEPATH;
use crate::directory::{Directory, DirectoryClone};
use crate::error::TantivyError;
use crate::directory::{Directory, DirectoryClone, GarbageCollectionResult};
use crate::indexer::delete_queue::DeleteCursor;
use crate::indexer::index_writer::advance_deletes;
use crate::indexer::merge_operation::MergeOperationInventory;
use crate::indexer::merger::IndexMerger;
use crate::indexer::segment_manager::SegmentsStatus;
use crate::indexer::stamper::Stamper;
use crate::indexer::MergeOperation;
use crate::indexer::SegmentEntry;
use crate::indexer::SegmentSerializer;
use crate::indexer::{DefaultMergePolicy, MergePolicy};
use crate::indexer::{MergeCandidate, MergeOperation};
use crate::schema::Schema;
use crate::Opstamp;
use crate::Result;
use futures::oneshot;
use futures::sync::oneshot::Receiver;
use futures::Future;
use futures_cpupool::Builder as CpuPoolBuilder;
use futures_cpupool::CpuFuture;
use futures_cpupool::CpuPool;
use serde_json;
use futures::channel::oneshot;
use futures::executor::{ThreadPool, ThreadPoolBuilder};
use futures::future::Future;
use futures::future::TryFutureExt;
use std::borrow::BorrowMut;
use std::collections::HashMap;
use std::collections::HashSet;
use std::io::Write;
use std::mem;
use std::ops::DerefMut;
use std::ops::Deref;
use std::path::PathBuf;
use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::Arc;
use std::sync::RwLock;
use std::thread;
use std::thread::JoinHandle;
const NUM_MERGE_THREADS: usize = 4;
/// Save the index meta file.
/// This operation is atomic :
@@ -49,7 +43,7 @@ use std::thread::JoinHandle;
/// and flushed.
///
/// This method is not part of tantivy's public API
pub fn save_new_metas(schema: Schema, directory: &mut dyn Directory) -> Result<()> {
pub fn save_new_metas(schema: Schema, directory: &dyn Directory) -> crate::Result<()> {
save_metas(
&IndexMeta {
segments: Vec::new(),
@@ -70,7 +64,7 @@ pub fn save_new_metas(schema: Schema, directory: &mut dyn Directory) -> Result<(
/// and flushed.
///
/// This method is not part of tantivy's public API
fn save_metas(metas: &IndexMeta, directory: &mut dyn Directory) -> Result<()> {
fn save_metas(metas: &IndexMeta, directory: &dyn Directory) -> crate::Result<()> {
info!("save metas");
let mut buffer = serde_json::to_vec_pretty(metas)?;
// Just adding a new line at the end of the buffer.
@@ -89,21 +83,38 @@ fn save_metas(metas: &IndexMeta, directory: &mut dyn Directory) -> Result<()> {
// We voluntarily pass a merge_operation ref to guarantee that
// the merge_operation is alive during the process
#[derive(Clone)]
pub struct SegmentUpdater(Arc<InnerSegmentUpdater>);
pub(crate) struct SegmentUpdater(Arc<InnerSegmentUpdater>);
fn perform_merge(
merge_operation: &MergeOperation,
impl Deref for SegmentUpdater {
type Target = InnerSegmentUpdater;
#[inline]
fn deref(&self) -> &Self::Target {
&self.0
}
}
async fn garbage_collect_files(
segment_updater: SegmentUpdater,
) -> crate::Result<GarbageCollectionResult> {
info!("Running garbage collection");
let mut index = segment_updater.index.clone();
index
.directory_mut()
.garbage_collect(move || segment_updater.list_files())
}
/// Merges a list of segments the list of segment givens in the `segment_entries`.
/// This function happens in the calling thread and is computationally expensive.
fn merge(
index: &Index,
mut segment_entries: Vec<SegmentEntry>,
) -> Result<SegmentEntry> {
let target_opstamp = merge_operation.target_opstamp();
target_opstamp: Opstamp,
) -> crate::Result<SegmentEntry> {
// first we need to apply deletes to our segment.
let mut merged_segment = index.new_segment();
// TODO add logging
let schema = index.schema();
let merged_segment = index.new_segment();
// First we apply all of the delet to the merged segment, up to the target opstamp.
for segment_entry in &mut segment_entries {
let segment = index.segment(segment_entry.meta().clone());
advance_deletes(segment, segment_entry, target_opstamp)?;
@@ -117,22 +128,20 @@ fn perform_merge(
.collect();
// An IndexMerger is like a "view" of our merged segments.
let merger: IndexMerger = IndexMerger::open(schema, &segments[..])?;
let merger: IndexMerger = IndexMerger::open(index.schema(), &segments[..])?;
// ... we just serialize this index merger in our new segment
// to merge the two segments.
let segment_serializer = SegmentSerializer::for_segment(&mut merged_segment)?;
// ... we just serialize this index merger in our new segment to merge the two segments.
let segment_serializer = SegmentSerializer::for_segment(merged_segment.clone())?;
let num_docs = merger.write(segment_serializer)?;
let segment_meta = index.new_segment_meta(merged_segment.id(), num_docs);
let merged_segment_id = merged_segment.id();
let after_merge_segment_entry = SegmentEntry::new(segment_meta.clone(), delete_cursor, None);
Ok(after_merge_segment_entry)
let segment_meta = index.new_segment_meta(merged_segment_id, num_docs);
Ok(SegmentEntry::new(segment_meta, delete_cursor, None))
}
struct InnerSegmentUpdater {
pub(crate) struct InnerSegmentUpdater {
// we keep a copy of the current active IndexMeta to
// avoid loading the file everytime we need it in the
// `SegmentUpdater`.
@@ -140,12 +149,12 @@ struct InnerSegmentUpdater {
// This should be up to date as all update happen through
// the unique active `SegmentUpdater`.
active_metas: RwLock<Arc<IndexMeta>>,
pool: CpuPool,
pool: ThreadPool,
merge_thread_pool: ThreadPool,
index: Index,
segment_manager: SegmentManager,
merge_policy: RwLock<Arc<Box<dyn MergePolicy>>>,
merging_thread_id: AtomicUsize,
merging_threads: RwLock<HashMap<usize, JoinHandle<Result<()>>>>,
merge_policy: RwLock<Arc<dyn MergePolicy>>,
killed: AtomicBool,
stamper: Stamper,
merge_operations: MergeOperationInventory,
@@ -156,90 +165,118 @@ impl SegmentUpdater {
index: Index,
stamper: Stamper,
delete_cursor: &DeleteCursor,
) -> Result<SegmentUpdater> {
) -> crate::Result<SegmentUpdater> {
let segments = index.searchable_segment_metas()?;
let segment_manager = SegmentManager::from_segments(segments, delete_cursor);
let pool = CpuPoolBuilder::new()
let pool = ThreadPoolBuilder::new()
.name_prefix("segment_updater")
.pool_size(1)
.create();
.create()
.map_err(|_| {
crate::TantivyError::SystemError(
"Failed to spawn segment updater thread".to_string(),
)
})?;
let merge_thread_pool = ThreadPoolBuilder::new()
.name_prefix("merge_thread")
.pool_size(NUM_MERGE_THREADS)
.create()
.map_err(|_| {
crate::TantivyError::SystemError(
"Failed to spawn segment merging thread".to_string(),
)
})?;
let index_meta = index.load_metas()?;
Ok(SegmentUpdater(Arc::new(InnerSegmentUpdater {
active_metas: RwLock::new(Arc::new(index_meta)),
pool,
merge_thread_pool,
index,
segment_manager,
merge_policy: RwLock::new(Arc::new(Box::new(DefaultMergePolicy::default()))),
merging_thread_id: AtomicUsize::default(),
merging_threads: RwLock::new(HashMap::new()),
merge_policy: RwLock::new(Arc::new(DefaultMergePolicy::default())),
killed: AtomicBool::new(false),
stamper,
merge_operations: Default::default(),
})))
}
pub fn get_merge_policy(&self) -> Arc<Box<dyn MergePolicy>> {
self.0.merge_policy.read().unwrap().clone()
pub fn get_merge_policy(&self) -> Arc<dyn MergePolicy> {
self.merge_policy.read().unwrap().clone()
}
pub fn set_merge_policy(&self, merge_policy: Box<dyn MergePolicy>) {
let arc_merge_policy = Arc::new(merge_policy);
*self.0.merge_policy.write().unwrap() = arc_merge_policy;
let arc_merge_policy = Arc::from(merge_policy);
*self.merge_policy.write().unwrap() = arc_merge_policy;
}
fn get_merging_thread_id(&self) -> usize {
self.0.merging_thread_id.fetch_add(1, Ordering::SeqCst)
}
fn run_async<T: 'static + Send, F: 'static + Send + FnOnce(SegmentUpdater) -> T>(
fn schedule_future<T: 'static + Send, F: Future<Output = crate::Result<T>> + 'static + Send>(
&self,
f: F,
) -> CpuFuture<T, TantivyError> {
let me_clone = self.clone();
self.0.pool.spawn_fn(move || Ok(f(me_clone)))
) -> impl Future<Output = crate::Result<T>> {
let (sender, receiver) = oneshot::channel();
if self.is_alive() {
self.pool.spawn_ok(async move {
let _ = sender.send(f.await);
});
} else {
let _ = sender.send(Err(crate::TantivyError::SystemError(
"Segment updater killed".to_string(),
)));
}
receiver.unwrap_or_else(|_| {
let err_msg =
"A segment_updater future did not success. This should never happen.".to_string();
Err(crate::TantivyError::SystemError(err_msg))
})
}
pub fn add_segment(&self, segment_entry: SegmentEntry) -> bool {
self.run_async(|segment_updater| {
segment_updater.0.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options();
true
pub fn schedule_add_segment(
&self,
segment_entry: SegmentEntry,
) -> impl Future<Output = crate::Result<()>> {
let segment_updater = self.clone();
self.schedule_future(async move {
segment_updater.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options().await;
Ok(())
})
.forget();
true
}
/// Orders `SegmentManager` to remove all segments
pub(crate) fn remove_all_segments(&self) {
self.0.segment_manager.remove_all_segments();
self.segment_manager.remove_all_segments();
}
pub fn kill(&mut self) {
self.0.killed.store(true, Ordering::Release);
self.killed.store(true, Ordering::Release);
}
pub fn is_alive(&self) -> bool {
!self.0.killed.load(Ordering::Acquire)
!self.killed.load(Ordering::Acquire)
}
/// Apply deletes up to the target opstamp to all segments.
///
/// The method returns copies of the segment entries,
/// updated with the delete information.
fn purge_deletes(&self, target_opstamp: Opstamp) -> Result<Vec<SegmentEntry>> {
let mut segment_entries = self.0.segment_manager.segment_entries();
fn purge_deletes(&self, target_opstamp: Opstamp) -> crate::Result<Vec<SegmentEntry>> {
let mut segment_entries = self.segment_manager.segment_entries();
for segment_entry in &mut segment_entries {
let segment = self.0.index.segment(segment_entry.meta().clone());
let segment = self.index.segment(segment_entry.meta().clone());
advance_deletes(segment, segment_entry, target_opstamp)?;
}
Ok(segment_entries)
}
pub fn save_metas(&self, opstamp: Opstamp, commit_message: Option<String>) {
pub fn save_metas(
&self,
opstamp: Opstamp,
commit_message: Option<String>,
) -> crate::Result<()> {
if self.is_alive() {
let index = &self.0.index;
let index = &self.index;
let directory = index.directory();
let mut commited_segment_metas = self.0.segment_manager.committed_segment_metas();
let mut commited_segment_metas = self.segment_manager.committed_segment_metas();
// We sort segment_readers by number of documents.
// This is an heuristic to make multithreading more efficient.
@@ -261,16 +298,18 @@ impl SegmentUpdater {
opstamp,
payload: commit_message,
};
save_metas(&index_meta, directory.box_clone().borrow_mut())
.expect("Could not save metas.");
// TODO add context to the error.
save_metas(&index_meta, directory.box_clone().borrow_mut())?;
self.store_meta(&index_meta);
}
Ok(())
}
pub fn garbage_collect_files(&self) -> CpuFuture<(), TantivyError> {
self.run_async(move |segment_updater| {
segment_updater.garbage_collect_files_exec();
})
pub fn schedule_garbage_collect(
&self,
) -> impl Future<Output = crate::Result<GarbageCollectionResult>> {
let garbage_collect_future = garbage_collect_files(self.clone());
self.schedule_future(garbage_collect_future)
}
/// List the files that are useful to the index.
@@ -278,148 +317,130 @@ impl SegmentUpdater {
/// This does not include lock files, or files that are obsolete
/// but have not yet been deleted by the garbage collector.
fn list_files(&self) -> HashSet<PathBuf> {
let mut files = HashSet::new();
let mut files: HashSet<PathBuf> = self
.index
.list_all_segment_metas()
.into_iter()
.flat_map(|segment_meta| segment_meta.list_files())
.collect();
files.insert(META_FILEPATH.to_path_buf());
for segment_meta in self.0.index.list_all_segment_metas() {
files.extend(segment_meta.list_files());
}
files
}
fn garbage_collect_files_exec(&self) {
info!("Running garbage collection");
let mut index = self.0.index.clone();
index.directory_mut().garbage_collect(|| self.list_files());
}
pub fn commit(&self, opstamp: Opstamp, payload: Option<String>) -> Result<()> {
self.run_async(move |segment_updater| {
if segment_updater.is_alive() {
let segment_entries = segment_updater
.purge_deletes(opstamp)
.expect("Failed purge deletes");
segment_updater.0.segment_manager.commit(segment_entries);
segment_updater.save_metas(opstamp, payload);
segment_updater.garbage_collect_files_exec();
segment_updater.consider_merge_options();
}
pub fn schedule_commit(
&self,
opstamp: Opstamp,
payload: Option<String>,
) -> impl Future<Output = crate::Result<()>> {
let segment_updater: SegmentUpdater = self.clone();
self.schedule_future(async move {
let segment_entries = segment_updater.purge_deletes(opstamp)?;
segment_updater.segment_manager.commit(segment_entries);
segment_updater.save_metas(opstamp, payload)?;
let _ = garbage_collect_files(segment_updater.clone()).await;
segment_updater.consider_merge_options().await;
Ok(())
})
.wait()
}
pub fn start_merge(&self, segment_ids: &[SegmentId]) -> Result<Receiver<SegmentMeta>> {
let commit_opstamp = self.load_metas().opstamp;
let merge_operation = MergeOperation::new(
&self.0.merge_operations,
commit_opstamp,
segment_ids.to_vec(),
);
self.run_async(move |segment_updater| segment_updater.start_merge_impl(merge_operation))
.wait()?
}
fn store_meta(&self, index_meta: &IndexMeta) {
*self.0.active_metas.write().unwrap() = Arc::new(index_meta.clone());
}
fn load_metas(&self) -> Arc<IndexMeta> {
self.0.active_metas.read().unwrap().clone()
*self.active_metas.write().unwrap() = Arc::new(index_meta.clone());
}
fn load_metas(&self) -> Arc<IndexMeta> {
self.active_metas.read().unwrap().clone()
}
pub(crate) fn make_merge_operation(&self, segment_ids: &[SegmentId]) -> MergeOperation {
let commit_opstamp = self.load_metas().opstamp;
MergeOperation::new(&self.merge_operations, commit_opstamp, segment_ids.to_vec())
}
// Starts a merge operation. This function will block until the merge operation is effectively
// started. Note that it does not wait for the merge to terminate.
// The calling thread should not be block for a long time, as this only involve waiting for the
// `SegmentUpdater` queue which in turns only contains lightweight operations.
//
// The merge itself happens on a different thread.
//
// When successful, this function returns a `Future` for a `Result<SegmentMeta>` that represents
// the actual outcome of the merge operation.
//
// It returns an error if for some reason the merge operation could not be started.
//
// At this point an error is not necessarily the sign of a malfunction.
// (e.g. A rollback could have happened, between the instant when the merge operaiton was
// suggested and the moment when it ended up being executed.)
//
// `segment_ids` is required to be non-empty.
fn start_merge_impl(&self, merge_operation: MergeOperation) -> Result<Receiver<SegmentMeta>> {
pub fn start_merge(
&self,
merge_operation: MergeOperation,
) -> crate::Result<impl Future<Output = crate::Result<SegmentMeta>>> {
assert!(
!merge_operation.segment_ids().is_empty(),
"Segment_ids cannot be empty."
);
let segment_updater_clone = self.clone();
let segment_updater = self.clone();
let segment_entries: Vec<SegmentEntry> = self
.0
.segment_manager
.start_merge(merge_operation.segment_ids())?;
// let segment_ids_vec = merge_operation.segment_ids.to_vec();
info!("Starting merge - {:?}", merge_operation.segment_ids());
let merging_thread_id = self.get_merging_thread_id();
info!(
"Starting merge thread #{} - {:?}",
merging_thread_id,
merge_operation.segment_ids()
);
let (merging_future_send, merging_future_recv) = oneshot();
let (merging_future_send, merging_future_recv) =
oneshot::channel::<crate::Result<SegmentMeta>>();
// first we need to apply deletes to our segment.
let merging_join_handle = thread::Builder::new()
.name(format!("mergingthread-{}", merging_thread_id))
.spawn(move || {
// first we need to apply deletes to our segment.
let merge_result = perform_merge(
&merge_operation,
&segment_updater_clone.0.index,
segment_entries,
);
match merge_result {
Ok(after_merge_segment_entry) => {
let merged_segment_meta = after_merge_segment_entry.meta().clone();
segment_updater_clone
.end_merge(merge_operation, after_merge_segment_entry)
.expect("Segment updater thread is corrupted.");
// the future may fail if the listener of the oneshot future
// has been destroyed.
//
// This is not a problem here, so we just ignore any
// possible error.
let _merging_future_res = merging_future_send.send(merged_segment_meta);
}
Err(e) => {
warn!(
"Merge of {:?} was cancelled: {:?}",
merge_operation.segment_ids(),
e
);
// ... cancel merge
if cfg!(test) {
panic!("Merge failed.");
}
// As `merge_operation` will be dropped, the segment in merge state will
// be available for merge again.
// `merging_future_send` will be dropped, sending an error to the future.
self.merge_thread_pool.spawn_ok(async move {
// The fact that `merge_operation` is moved here is important.
// Its lifetime is used to track how many merging thread are currently running,
// as well as which segment is currently in merge and therefore should not be
// candidate for another merge.
match merge(
&segment_updater.index,
segment_entries,
merge_operation.target_opstamp(),
) {
Ok(after_merge_segment_entry) => {
let segment_meta = segment_updater
.end_merge(merge_operation, after_merge_segment_entry)
.await;
let _send_result = merging_future_send.send(segment_meta);
}
Err(e) => {
warn!(
"Merge of {:?} was cancelled: {:?}",
merge_operation.segment_ids().to_vec(),
e
);
// ... cancel merge
if cfg!(test) {
panic!("Merge failed.");
}
}
segment_updater_clone
.0
.merging_threads
.write()
.unwrap()
.remove(&merging_thread_id);
Ok(())
})
.expect("Failed to spawn a thread.");
self.0
.merging_threads
.write()
.unwrap()
.insert(merging_thread_id, merging_join_handle);
Ok(merging_future_recv)
}
});
Ok(merging_future_recv
.unwrap_or_else(|_| Err(crate::TantivyError::SystemError("Merge failed".to_string()))))
}
fn consider_merge_options(&self) {
let merge_segment_ids: HashSet<SegmentId> = self.0.merge_operations.segment_in_merge();
async fn consider_merge_options(&self) {
let merge_segment_ids: HashSet<SegmentId> = self.merge_operations.segment_in_merge();
let (committed_segments, uncommitted_segments) =
get_mergeable_segments(&merge_segment_ids, &self.0.segment_manager);
get_mergeable_segments(&merge_segment_ids, &self.segment_manager);
// Committed segments cannot be merged with uncommitted_segments.
// We therefore consider merges using these two sets of segments independently.
let merge_policy = self.get_merge_policy();
let current_opstamp = self.0.stamper.stamp();
let current_opstamp = self.stamper.stamp();
let mut merge_candidates: Vec<MergeOperation> = merge_policy
.compute_merge_candidates(&uncommitted_segments)
.into_iter()
.map(|merge_candidate| {
MergeOperation::new(&self.0.merge_operations, current_opstamp, merge_candidate.0)
MergeOperation::new(&self.merge_operations, current_opstamp, merge_candidate.0)
})
.collect();
@@ -427,25 +448,17 @@ impl SegmentUpdater {
let committed_merge_candidates = merge_policy
.compute_merge_candidates(&committed_segments)
.into_iter()
.map(|merge_candidate| {
MergeOperation::new(&self.0.merge_operations, commit_opstamp, merge_candidate.0)
})
.collect::<Vec<_>>();
merge_candidates.extend(committed_merge_candidates.into_iter());
.map(|merge_candidate: MergeCandidate| {
MergeOperation::new(&self.merge_operations, commit_opstamp, merge_candidate.0)
});
merge_candidates.extend(committed_merge_candidates);
for merge_operation in merge_candidates {
match self.start_merge_impl(merge_operation) {
Ok(merge_future) => {
if let Err(e) = merge_future.fuse().poll() {
error!("The merge task failed quickly after starting: {:?}", e);
}
}
Err(err) => {
warn!(
"Starting the merge failed for the following reason. This is not fatal. {}",
err
);
}
if let Err(err) = self.start_merge(merge_operation) {
warn!(
"Starting the merge failed for the following reason. This is not fatal. {}",
err
);
}
}
}
@@ -454,15 +467,17 @@ impl SegmentUpdater {
&self,
merge_operation: MergeOperation,
mut after_merge_segment_entry: SegmentEntry,
) -> Result<()> {
self.run_async(move |segment_updater| {
) -> impl Future<Output = crate::Result<SegmentMeta>> {
let segment_updater = self.clone();
let after_merge_segment_meta = after_merge_segment_entry.meta().clone();
let end_merge_future = self.schedule_future(async move {
info!("End merge {:?}", after_merge_segment_entry.meta());
{
let mut delete_cursor = after_merge_segment_entry.delete_cursor().clone();
if let Some(delete_operation) = delete_cursor.get() {
let committed_opstamp = segment_updater.load_metas().opstamp;
if delete_operation.opstamp < committed_opstamp {
let index = &segment_updater.0.index;
let index = &segment_updater.index;
let segment = index.segment(after_merge_segment_entry.meta().clone());
if let Err(e) = advance_deletes(
segment,
@@ -480,28 +495,33 @@ impl SegmentUpdater {
// ... cancel merge
// `merge_operations` are tracked. As it is dropped, the
// the segment_ids will be available again for merge.
return;
return Err(e);
}
}
}
let previous_metas = segment_updater.load_metas();
segment_updater
.0
let segments_status = segment_updater
.segment_manager
.end_merge(merge_operation.segment_ids(), after_merge_segment_entry);
segment_updater.consider_merge_options();
segment_updater.save_metas(previous_metas.opstamp, previous_metas.payload.clone());
.end_merge(merge_operation.segment_ids(), after_merge_segment_entry)?;
if segments_status == SegmentsStatus::Committed {
segment_updater
.save_metas(previous_metas.opstamp, previous_metas.payload.clone())?;
}
segment_updater.consider_merge_options().await;
} // we drop all possible handle to a now useless `SegmentMeta`.
segment_updater.garbage_collect_files_exec();
})
.wait()
let _ = garbage_collect_files(segment_updater).await;
Ok(())
});
end_merge_future.map_ok(|_| after_merge_segment_meta)
}
/// Wait for current merging threads.
///
/// Upon termination of the current merging threads,
/// merge opportunity may appear.
//
///
/// We keep waiting until the merge policy judges that
/// no opportunity is available.
///
@@ -512,26 +532,9 @@ impl SegmentUpdater {
///
/// Obsolete files will eventually be cleaned up
/// by the directory garbage collector.
pub fn wait_merging_thread(&self) -> Result<()> {
loop {
let merging_threads: HashMap<usize, JoinHandle<Result<()>>> = {
let mut merging_threads = self.0.merging_threads.write().unwrap();
mem::replace(merging_threads.deref_mut(), HashMap::new())
};
if merging_threads.is_empty() {
return Ok(());
}
debug!("wait merging thread {}", merging_threads.len());
for (_, merging_thread_handle) in merging_threads {
merging_thread_handle
.join()
.map(|_| ())
.map_err(|_| TantivyError::ErrorInThread("Merging thread failed.".into()))?;
}
// Our merging thread may have queued their completed merged segment.
// Let's wait for that too.
self.run_async(move |_| {}).wait()?;
}
pub fn wait_merging_thread(&self) -> crate::Result<()> {
self.merge_operations.wait_until_empty();
Ok(())
}
}
@@ -551,7 +554,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(MergeWheneverPossible));
{
@@ -604,7 +607,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
for _ in 0..100 {
@@ -675,7 +678,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
for _ in 0..100 {
@@ -687,7 +690,6 @@ mod tests {
index_writer.segment_updater().remove_all_segments();
let seg_vec = index_writer
.segment_updater()
.0
.segment_manager
.segment_entries();
assert!(seg_vec.is_empty());

223
src/indexer/segment_writer.rs
View File

@@ -2,7 +2,7 @@ use super::operation::AddOperation;
use crate::core::Segment;
use crate::core::SerializableSegment;
use crate::fastfield::FastFieldsWriter;
use crate::fieldnorm::FieldNormsWriter;
use crate::fieldnorm::{FieldNormReaders, FieldNormsWriter};
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::postings::compute_table_size;
use crate::postings::MultiFieldPostingsWriter;
@@ -11,20 +11,16 @@ use crate::schema::Schema;
use crate::schema::Term;
use crate::schema::Value;
use crate::schema::{Field, FieldEntry};
use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::FacetTokenizer;
use crate::tokenizer::{TokenStream, Tokenizer};
use crate::DocId;
use crate::tokenizer::{BoxTokenStream, PreTokenizedStream};
use crate::tokenizer::{FacetTokenizer, TextAnalyzer};
use crate::tokenizer::{TokenStreamChain, Tokenizer};
use crate::Opstamp;
use crate::Result;
use crate::TantivyError;
use std::io;
use std::str;
use crate::{DocId, SegmentComponent};
/// Computes the initial size of the hash table.
///
/// Returns a number of bit `b`, such that the recommended initial table size is 2^b.
fn initial_table_size(per_thread_memory_budget: usize) -> Result<usize> {
fn initial_table_size(per_thread_memory_budget: usize) -> crate::Result<usize> {
let table_memory_upper_bound = per_thread_memory_budget / 3;
if let Some(limit) = (10..)
.take_while(|num_bits: &usize| compute_table_size(*num_bits) < table_memory_upper_bound)
@@ -32,7 +28,7 @@ fn initial_table_size(per_thread_memory_budget: usize) -> Result<usize> {
{
Ok(limit.min(19)) // we cap it at 2^19 = 512K.
} else {
Err(TantivyError::InvalidArgument(
Err(crate::TantivyError::InvalidArgument(
format!("per thread memory budget (={}) is too small. Raise the memory budget or lower the number of threads.", per_thread_memory_budget)))
}
}
@@ -49,7 +45,8 @@ pub struct SegmentWriter {
fast_field_writers: FastFieldsWriter,
fieldnorms_writer: FieldNormsWriter,
doc_opstamps: Vec<Opstamp>,
tokenizers: Vec<Option<BoxedTokenizer>>,
tokenizers: Vec<Option<TextAnalyzer>>,
term_buffer: Term,
}
impl SegmentWriter {
@@ -64,11 +61,12 @@ impl SegmentWriter {
/// - schema
pub fn for_segment(
memory_budget: usize,
mut segment: Segment,
segment: Segment,
schema: &Schema,
) -> Result<SegmentWriter> {
) -> crate::Result<SegmentWriter> {
let tokenizer_manager = segment.index().tokenizers().clone();
let table_num_bits = initial_table_size(memory_budget)?;
let segment_serializer = SegmentSerializer::for_segment(&mut segment)?;
let segment_serializer = SegmentSerializer::for_segment(segment)?;
let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits);
let tokenizers = schema
.fields()
@@ -78,7 +76,7 @@ impl SegmentWriter {
.get_indexing_options()
.and_then(|text_index_option| {
let tokenizer_name = &text_index_option.tokenizer();
segment.index().tokenizers().get(tokenizer_name)
tokenizer_manager.get(tokenizer_name)
}),
_ => None,
},
@@ -92,6 +90,7 @@ impl SegmentWriter {
fast_field_writers: FastFieldsWriter::from_schema(schema),
doc_opstamps: Vec::with_capacity(1_000),
tokenizers,
term_buffer: Term::new(),
})
}
@@ -99,7 +98,7 @@ impl SegmentWriter {
///
/// Finalize consumes the `SegmentWriter`, so that it cannot
/// be used afterwards.
pub fn finalize(mut self) -> Result<Vec<u64>> {
pub fn finalize(mut self) -> crate::Result<Vec<u64>> {
self.fieldnorms_writer.fill_up_to_max_doc(self.max_doc);
write(
&self.multifield_postings,
@@ -117,7 +116,11 @@ impl SegmentWriter {
/// Indexes a new document
///
/// As a user, you should rather use `IndexWriter`'s add_document.
pub fn add_document(&mut self, add_operation: AddOperation, schema: &Schema) -> io::Result<()> {
pub fn add_document(
&mut self,
add_operation: AddOperation,
schema: &Schema,
) -> crate::Result<()> {
let doc_id = self.max_doc;
let mut doc = add_operation.document;
self.doc_opstamps.push(add_operation.opstamp);
@@ -125,111 +128,160 @@ impl SegmentWriter {
self.fast_field_writers.add_document(&doc);
for (field, field_values) in doc.get_sorted_field_values() {
let field_options = schema.get_field_entry(field);
if !field_options.is_indexed() {
let field_entry = schema.get_field_entry(field);
let make_schema_error = || {
crate::TantivyError::SchemaError(format!(
"Expected a {:?} for field {:?}",
field_entry.field_type().value_type(),
field_entry.name()
))
};
if !field_entry.is_indexed() {
continue;
}
match *field_options.field_type() {
let (term_buffer, multifield_postings) =
(&mut self.term_buffer, &mut self.multifield_postings);
match *field_entry.field_type() {
FieldType::HierarchicalFacet => {
let facets: Vec<&str> = field_values
.iter()
.flat_map(|field_value| match *field_value.value() {
Value::Facet(ref facet) => Some(facet.encoded_str()),
_ => {
panic!("Expected hierarchical facet");
}
})
.collect();
let mut term = Term::for_field(field); // we set the Term
for fake_str in facets {
term_buffer.set_field(field);
let facets =
field_values
.iter()
.flat_map(|field_value| match *field_value.value() {
Value::Facet(ref facet) => Some(facet.encoded_str()),
_ => {
panic!("Expected hierarchical facet");
}
});
for facet_str in facets {
let mut unordered_term_id_opt = None;
FacetTokenizer.token_stream(fake_str).process(&mut |token| {
term.set_text(&token.text);
let unordered_term_id =
self.multifield_postings.subscribe(doc_id, &term);
unordered_term_id_opt = Some(unordered_term_id);
});
FacetTokenizer
.token_stream(facet_str)
.process(&mut |token| {
term_buffer.set_text(&token.text);
let unordered_term_id =
multifield_postings.subscribe(doc_id, &term_buffer);
unordered_term_id_opt = Some(unordered_term_id);
});
if let Some(unordered_term_id) = unordered_term_id_opt {
self.fast_field_writers
.get_multivalue_writer(field)
.expect("multified writer for facet missing")
.expect("writer for facet missing")
.add_val(unordered_term_id);
}
}
}
FieldType::Str(_) => {
let num_tokens = if let Some(ref mut tokenizer) =
self.tokenizers[field.field_id() as usize]
{
let texts: Vec<&str> = field_values
.iter()
.flat_map(|field_value| match *field_value.value() {
Value::Str(ref text) => Some(text.as_str()),
_ => None,
})
.collect();
if texts.is_empty() {
0
} else {
let mut token_stream = tokenizer.token_stream_texts(&texts[..]);
self.multifield_postings
.index_text(doc_id, field, &mut token_stream)
let mut token_streams: Vec<BoxTokenStream> = vec![];
let mut offsets = vec![];
let mut total_offset = 0;
for field_value in field_values {
match field_value.value() {
Value::PreTokStr(tok_str) => {
offsets.push(total_offset);
if let Some(last_token) = tok_str.tokens.last() {
total_offset += last_token.offset_to;
}
token_streams
.push(PreTokenizedStream::from(tok_str.clone()).into());
}
Value::Str(ref text) => {
if let Some(ref mut tokenizer) =
self.tokenizers[field.field_id() as usize]
{
offsets.push(total_offset);
total_offset += text.len();
token_streams.push(tokenizer.token_stream(text));
}
}
_ => (),
}
} else {
}
let num_tokens = if token_streams.is_empty() {
0
} else {
let mut token_stream = TokenStreamChain::new(offsets, token_streams);
multifield_postings.index_text(
doc_id,
field,
&mut token_stream,
term_buffer,
)
};
self.fieldnorms_writer.record(doc_id, field, num_tokens);
}
FieldType::U64(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
let term = Term::from_field_u64(
field_value.field(),
field_value.value().u64_value(),
);
self.multifield_postings.subscribe(doc_id, &term);
term_buffer.set_field(field_value.field());
let u64_val = field_value
.value()
.u64_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_u64(u64_val);
multifield_postings.subscribe(doc_id, &term_buffer);
}
}
}
FieldType::Date(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
let term = Term::from_field_i64(
field_value.field(),
field_value.value().date_value().timestamp(),
);
self.multifield_postings.subscribe(doc_id, &term);
term_buffer.set_field(field_value.field());
let date_val = field_value
.value()
.date_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_i64(date_val.timestamp());
multifield_postings.subscribe(doc_id, &term_buffer);
}
}
}
FieldType::I64(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
let term = Term::from_field_i64(
field_value.field(),
field_value.value().i64_value(),
);
self.multifield_postings.subscribe(doc_id, &term);
term_buffer.set_field(field_value.field());
let i64_val = field_value
.value()
.i64_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_i64(i64_val);
multifield_postings.subscribe(doc_id, &term_buffer);
}
}
}
FieldType::F64(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
let term = Term::from_field_f64(
field_value.field(),
field_value.value().f64_value(),
);
self.multifield_postings.subscribe(doc_id, &term);
term_buffer.set_field(field_value.field());
let f64_val = field_value
.value()
.f64_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_f64(f64_val);
multifield_postings.subscribe(doc_id, &term_buffer);
}
}
}
FieldType::Bytes => {
// Do nothing. Bytes only supports fast fields.
FieldType::Bytes(ref option) => {
if option.is_indexed() {
for field_value in field_values {
term_buffer.set_field(field_value.field());
let bytes = field_value
.value()
.bytes_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_bytes(bytes);
self.multifield_postings.subscribe(doc_id, &term_buffer);
}
}
}
}
}
doc.filter_fields(|field| schema.get_field_entry(field).is_stored());
doc.prepare_for_store();
let doc_writer = self.segment_serializer.get_store_writer();
doc_writer.store(&doc)?;
self.max_doc += 1;
@@ -263,16 +315,23 @@ fn write(
fast_field_writers: &FastFieldsWriter,
fieldnorms_writer: &FieldNormsWriter,
mut serializer: SegmentSerializer,
) -> Result<()> {
let term_ord_map = multifield_postings.serialize(serializer.get_postings_serializer())?;
) -> crate::Result<()> {
if let Some(fieldnorms_serializer) = serializer.extract_fieldnorms_serializer() {
fieldnorms_writer.serialize(fieldnorms_serializer)?;
}
let fieldnorm_data = serializer
.segment()
.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
let term_ord_map =
multifield_postings.serialize(serializer.get_postings_serializer(), fieldnorm_readers)?;
fast_field_writers.serialize(serializer.get_fast_field_serializer(), &term_ord_map)?;
fieldnorms_writer.serialize(serializer.get_fieldnorms_serializer())?;
serializer.close()?;
Ok(())
}
impl SerializableSegment for SegmentWriter {
fn write(&self, serializer: SegmentSerializer) -> Result<u32> {
fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32> {
let max_doc = self.max_doc;
write(
&self.multifield_postings,

67
src/indexer/stamper.rs
View File

@@ -1,18 +1,76 @@
use crate::Opstamp;
use std::ops::Range;
use std::sync::atomic::{AtomicU64, Ordering};
use std::sync::atomic::Ordering;
use std::sync::Arc;
#[cfg(not(target_arch = "arm"))]
mod atomic_impl {
use crate::Opstamp;
use std::sync::atomic::{AtomicU64, Ordering};
#[derive(Default)]
pub struct AtomicU64Wrapper(AtomicU64);
impl AtomicU64Wrapper {
pub fn new(first_opstamp: Opstamp) -> AtomicU64Wrapper {
AtomicU64Wrapper(AtomicU64::new(first_opstamp as u64))
}
pub fn fetch_add(&self, val: u64, order: Ordering) -> u64 {
self.0.fetch_add(val as u64, order) as u64
}
pub fn revert(&self, val: u64, order: Ordering) -> u64 {
self.0.store(val, order);
val
}
}
}
#[cfg(target_arch = "arm")]
mod atomic_impl {
use crate::Opstamp;
/// Under other architecture, we rely on a mutex.
use std::sync::atomic::Ordering;
use std::sync::RwLock;
#[derive(Default)]
pub struct AtomicU64Wrapper(RwLock<u64>);
impl AtomicU64Wrapper {
pub fn new(first_opstamp: Opstamp) -> AtomicU64Wrapper {
AtomicU64Wrapper(RwLock::new(first_opstamp))
}
pub fn fetch_add(&self, incr: u64, _order: Ordering) -> u64 {
let mut lock = self.0.write().unwrap();
let previous_val = *lock;
*lock = previous_val + incr;
previous_val
}
pub fn revert(&self, val: u64, _order: Ordering) -> u64 {
let mut lock = self.0.write().unwrap();
*lock = val;
val
}
}
}
use self::atomic_impl::AtomicU64Wrapper;
/// Stamper provides Opstamps, which is just an auto-increment id to label
/// an operation.
///
/// Cloning does not "fork" the stamp generation. The stamper actually wraps an `Arc`.
#[derive(Clone, Default)]
pub struct Stamper(Arc<AtomicU64>);
pub struct Stamper(Arc<AtomicU64Wrapper>);
impl Stamper {
pub fn new(first_opstamp: Opstamp) -> Stamper {
Stamper(Arc::new(AtomicU64::new(first_opstamp)))
Stamper(Arc::new(AtomicU64Wrapper::new(first_opstamp)))
}
pub fn stamp(&self) -> Opstamp {
@@ -31,8 +89,7 @@ impl Stamper {
/// Reverts the stamper to a given `Opstamp` value and returns it
pub fn revert(&self, to_opstamp: Opstamp) -> Opstamp {
self.0.store(to_opstamp, Ordering::SeqCst);
to_opstamp
self.0.revert(to_opstamp, Ordering::SeqCst)
}
}

671
src/lib.rs Executable file → Normal file
View File

File diff suppressed because it is too large Load Diff

6
src/macros.rs
View File

@@ -35,9 +35,9 @@
/// let likes = schema_builder.add_u64_field("num_u64", FAST);
/// let schema = schema_builder.build();
/// let doc = doc!(
/// title => "Life Aquatic",
/// author => "Wes Anderson",
/// likes => 4u64
/// title => "Life Aquatic",
/// author => "Wes Anderson",
/// likes => 4u64
/// );
/// # }
/// ```

110
src/positions/mod.rs
View File

@@ -37,12 +37,12 @@ const LONG_SKIP_INTERVAL: u64 = (LONG_SKIP_IN_BLOCKS * COMPRESSION_BLOCK_SIZE) a
#[cfg(test)]
pub mod tests {
use super::{PositionReader, PositionSerializer};
use crate::directory::ReadOnlySource;
use crate::positions::COMPRESSION_BLOCK_SIZE;
use super::PositionSerializer;
use crate::positions::reader::PositionReader;
use crate::{common::HasLen, directory::FileSlice};
use std::iter;
fn create_stream_buffer(vals: &[u32]) -> (ReadOnlySource, ReadOnlySource) {
fn create_stream_buffer(vals: &[u32]) -> (FileSlice, FileSlice) {
let mut skip_buffer = vec![];
let mut stream_buffer = vec![];
{
@@ -53,10 +53,7 @@ pub mod tests {
}
serializer.close().unwrap();
}
(
ReadOnlySource::from(stream_buffer),
ReadOnlySource::from(skip_buffer),
)
(FileSlice::from(stream_buffer), FileSlice::from(skip_buffer))
}
#[test]
@@ -65,10 +62,10 @@ pub mod tests {
let (stream, skip) = create_stream_buffer(&v[..]);
assert_eq!(skip.len(), 12);
assert_eq!(stream.len(), 1168);
let mut position_reader = PositionReader::new(stream, skip, 0u64);
let mut position_reader = PositionReader::new(stream, skip, 0u64).unwrap();
for &n in &[1, 10, 127, 128, 130, 312] {
let mut v = vec![0u32; n];
position_reader.read(&mut v[..n]);
position_reader.read(0, &mut v[..]);
for i in 0..n {
assert_eq!(v[i], i as u32);
}
@@ -76,19 +73,19 @@ pub mod tests {
}
#[test]
fn test_position_skip() {
let v: Vec<u32> = (0..1_000).collect();
fn test_position_read_with_offset() {
let v: Vec<u32> = (0..1000).collect();
let (stream, skip) = create_stream_buffer(&v[..]);
assert_eq!(skip.len(), 12);
assert_eq!(stream.len(), 1168);
let mut position_reader = PositionReader::new(stream, skip, 0u64);
position_reader.skip(10);
for &n in &[10, 127, COMPRESSION_BLOCK_SIZE, 130, 312] {
let mut v = vec![0u32; n];
position_reader.read(&mut v[..n]);
for i in 0..n {
assert_eq!(v[i], 10u32 + i as u32);
let mut position_reader = PositionReader::new(stream, skip, 0u64).unwrap();
for &offset in &[1u64, 10u64, 127u64, 128u64, 130u64, 312u64] {
for &len in &[1, 10, 130, 500] {
let mut v = vec![0u32; len];
position_reader.read(offset, &mut v[..]);
for i in 0..len {
assert_eq!(v[i], i as u32 + offset as u32);
}
}
}
}
@@ -100,14 +97,15 @@ pub mod tests {
assert_eq!(skip.len(), 12);
assert_eq!(stream.len(), 1168);
let mut position_reader = PositionReader::new(stream, skip, 0u64);
let mut position_reader = PositionReader::new(stream, skip, 0u64).unwrap();
let mut buf = [0u32; 7];
let mut c = 0;
let mut offset = 0;
for _ in 0..100 {
position_reader.read(&mut buf);
position_reader.read(&mut buf);
position_reader.skip(4);
position_reader.skip(3);
position_reader.read(offset, &mut buf);
position_reader.read(offset, &mut buf);
offset += 7;
for &el in &buf {
assert_eq!(c, el);
c += 1;
@@ -115,6 +113,59 @@ pub mod tests {
}
}
#[test]
fn test_position_reread_anchor_different_than_block() {
let v: Vec<u32> = (0..2_000_000).collect();
let (stream, skip) = create_stream_buffer(&v[..]);
assert_eq!(skip.len(), 15_749);
assert_eq!(stream.len(), 4_987_872);
let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 0).unwrap();
let mut buf = [0u32; 256];
position_reader.read(128, &mut buf);
for i in 0..256 {
assert_eq!(buf[i], (128 + i) as u32);
}
position_reader.read(128, &mut buf);
for i in 0..256 {
assert_eq!(buf[i], (128 + i) as u32);
}
}
#[test]
#[should_panic(expected = "offset arguments should be increasing.")]
fn test_position_panic_if_called_previous_anchor() {
let v: Vec<u32> = (0..2_000_000).collect();
let (stream, skip) = create_stream_buffer(&v[..]);
assert_eq!(skip.len(), 15_749);
assert_eq!(stream.len(), 4_987_872);
let mut buf = [0u32; 1];
let mut position_reader =
PositionReader::new(stream.clone(), skip.clone(), 200_000).unwrap();
position_reader.read(230, &mut buf);
position_reader.read(9, &mut buf);
}
#[test]
fn test_positions_bug() {
let mut v: Vec<u32> = vec![];
for i in 1..200 {
for j in 0..i {
v.push(j);
}
}
let (stream, skip) = create_stream_buffer(&v[..]);
let mut buf = Vec::new();
let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), 0).unwrap();
let mut offset = 0;
for i in 1..24 {
buf.resize(i, 0);
position_reader.read(offset, &mut buf[..]);
offset += i as u64;
let r: Vec<u32> = (0..i).map(|el| el as u32).collect();
assert_eq!(buf, &r[..]);
}
}
#[test]
fn test_position_long_skip_const() {
const CONST_VAL: u32 = 9u32;
@@ -122,9 +173,9 @@ pub mod tests {
let (stream, skip) = create_stream_buffer(&v[..]);
assert_eq!(skip.len(), 15_749);
assert_eq!(stream.len(), 1_000_000);
let mut position_reader = PositionReader::new(stream, skip, 128 * 1024);
let mut position_reader = PositionReader::new(stream, skip, 128 * 1024).unwrap();
let mut buf = [0u32; 1];
position_reader.read(&mut buf);
position_reader.read(0, &mut buf);
assert_eq!(buf[0], CONST_VAL);
}
@@ -141,9 +192,10 @@ pub mod tests {
128 * 1024 + 7,
128 * 10 * 1024 + 10,
] {
let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), offset);
let mut position_reader =
PositionReader::new(stream.clone(), skip.clone(), offset).unwrap();
let mut buf = [0u32; 1];
position_reader.read(&mut buf);
position_reader.read(0, &mut buf);
assert_eq!(buf[0], offset as u32);
}
}

236
src/positions/reader.rs
View File

@@ -1,9 +1,13 @@
use std::io;
use crate::common::{BinarySerializable, FixedSize};
use crate::directory::ReadOnlySource;
use crate::directory::FileSlice;
use crate::directory::OwnedBytes;
use crate::positions::COMPRESSION_BLOCK_SIZE;
use crate::positions::LONG_SKIP_INTERVAL;
use crate::positions::LONG_SKIP_IN_BLOCKS;
use crate::postings::compression::compressed_block_size;
use bitpacking::{BitPacker, BitPacker4x};
/// Positions works as a long sequence of compressed block.
/// All terms are chained one after the other.
///
@@ -24,29 +28,28 @@ use crate::postings::compression::compressed_block_size;
/// A given block obviously takes `(128 x num_bit_for_the_block / num_bits_in_a_byte)`,
/// so skipping a block without decompressing it is just a matter of advancing that many
/// bytes.
use bitpacking::{BitPacker, BitPacker4x};
use owned_read::OwnedRead;
struct Positions {
bit_packer: BitPacker4x,
skip_source: ReadOnlySource,
position_source: ReadOnlySource,
long_skip_source: ReadOnlySource,
skip_file: FileSlice,
position_file: FileSlice,
long_skip_data: OwnedBytes,
}
impl Positions {
pub fn new(position_source: ReadOnlySource, skip_source: ReadOnlySource) -> Positions {
let skip_len = skip_source.len();
let (body, footer) = skip_source.split(skip_len - u32::SIZE_IN_BYTES);
let num_long_skips = u32::deserialize(&mut footer.as_slice()).expect("Index corrupted");
let body_split = body.len() - u64::SIZE_IN_BYTES * (num_long_skips as usize);
let (skip_source, long_skip_source) = body.split(body_split);
Positions {
pub fn new(position_file: FileSlice, skip_file: FileSlice) -> io::Result<Positions> {
let (body, footer) = skip_file.split_from_end(u32::SIZE_IN_BYTES);
let footer_data = footer.read_bytes()?;
let num_long_skips = u32::deserialize(&mut footer_data.as_slice())?;
let (skip_file, long_skip_file) =
body.split_from_end(u64::SIZE_IN_BYTES * (num_long_skips as usize));
let long_skip_data = long_skip_file.read_bytes()?;
Ok(Positions {
bit_packer: BitPacker4x::new(),
skip_source,
long_skip_source,
position_source,
}
skip_file,
long_skip_data,
position_file,
})
}
/// Returns the offset of the block associated to the given `long_skip_id`.
@@ -56,143 +59,116 @@ impl Positions {
if long_skip_id == 0 {
return 0;
}
let long_skip_slice = self.long_skip_source.as_slice();
let long_skip_slice = self.long_skip_data.as_slice();
let mut long_skip_blocks: &[u8] = &long_skip_slice[(long_skip_id - 1) * 8..][..8];
u64::deserialize(&mut long_skip_blocks).expect("Index corrupted")
}
fn reader(&self, offset: u64) -> PositionReader {
fn reader(&self, offset: u64) -> io::Result<PositionReader> {
let long_skip_id = (offset / LONG_SKIP_INTERVAL) as usize;
let small_skip = (offset % LONG_SKIP_INTERVAL) as usize;
let offset_num_bytes: u64 = self.long_skip(long_skip_id);
let mut position_read = OwnedRead::new(self.position_source.clone());
position_read.advance(offset_num_bytes as usize);
let mut skip_read = OwnedRead::new(self.skip_source.clone());
skip_read.advance(long_skip_id * LONG_SKIP_IN_BLOCKS);
let mut position_reader = PositionReader {
let position_read = self
.position_file
.slice_from(offset_num_bytes as usize)
.read_bytes()?;
let skip_read = self
.skip_file
.slice_from(long_skip_id * LONG_SKIP_IN_BLOCKS)
.read_bytes()?;
Ok(PositionReader {
bit_packer: self.bit_packer,
skip_read,
position_read,
inner_offset: 0,
buffer: Box::new([0u32; 128]),
ahead: None,
};
position_reader.skip(small_skip);
position_reader
block_offset: std::i64::MAX as u64,
anchor_offset: (long_skip_id as u64) * LONG_SKIP_INTERVAL,
abs_offset: offset,
})
}
}
#[derive(Clone)]
pub struct PositionReader {
skip_read: OwnedRead,
position_read: OwnedRead,
skip_read: OwnedBytes,
position_read: OwnedBytes,
bit_packer: BitPacker4x,
inner_offset: usize,
buffer: Box<[u32; 128]>,
ahead: Option<usize>, // if None, no block is loaded.
// if Some(num_blocks), the block currently loaded is num_blocks ahead
// of the block of the next int to read.
}
buffer: Box<[u32; COMPRESSION_BLOCK_SIZE]>,
// `ahead` represents the offset of the block currently loaded
// compared to the cursor of the actual stream.
//
// By contract, when this function is called, the current block has to be
// decompressed.
//
// If the requested number of els ends exactly at a given block, the next
// block is not decompressed.
fn read_impl(
bit_packer: BitPacker4x,
mut position: &[u8],
buffer: &mut [u32; 128],
mut inner_offset: usize,
num_bits: &[u8],
output: &mut [u32],
) -> usize {
let mut output_start = 0;
let mut output_len = output.len();
let mut ahead = 0;
loop {
let available_len = COMPRESSION_BLOCK_SIZE - inner_offset;
// We have enough elements in the current block.
// Let's copy the requested elements in the output buffer,
// and return.
if output_len <= available_len {
output[output_start..].copy_from_slice(&buffer[inner_offset..][..output_len]);
return ahead;
}
output[output_start..][..available_len].copy_from_slice(&buffer[inner_offset..]);
output_len -= available_len;
output_start += available_len;
inner_offset = 0;
let num_bits = num_bits[ahead];
bit_packer.decompress(position, &mut buffer[..], num_bits);
let block_len = compressed_block_size(num_bits);
position = &position[block_len..];
ahead += 1;
}
block_offset: u64,
anchor_offset: u64,
abs_offset: u64,
}
impl PositionReader {
pub fn new(
position_source: ReadOnlySource,
skip_source: ReadOnlySource,
position_file: FileSlice,
skip_file: FileSlice,
offset: u64,
) -> PositionReader {
Positions::new(position_source, skip_source).reader(offset)
) -> io::Result<PositionReader> {
let positions = Positions::new(position_file, skip_file)?;
positions.reader(offset)
}
/// Fills a buffer with the next `output.len()` integers.
/// This does not consume / advance the stream.
pub fn read(&mut self, output: &mut [u32]) {
let skip_data = self.skip_read.as_ref();
let position_data = self.position_read.as_ref();
let num_bits = self.skip_read.get(0);
if self.ahead != Some(0) {
// the block currently available is not the block
// for the current position
fn advance_num_blocks(&mut self, num_blocks: usize) {
let num_bits: usize = self.skip_read.as_ref()[..num_blocks]
.iter()
.cloned()
.map(|num_bits| num_bits as usize)
.sum();
let num_bytes_to_skip = num_bits * COMPRESSION_BLOCK_SIZE / 8;
self.skip_read.advance(num_blocks as usize);
self.position_read.advance(num_bytes_to_skip);
}
/// Fills a buffer with the positions `[offset..offset+output.len())` integers.
///
/// `offset` is required to have a value >= to the offsets given in previous calls
/// for the given `PositionReaderAbsolute` instance.
pub fn read(&mut self, mut offset: u64, mut output: &mut [u32]) {
offset += self.abs_offset;
assert!(
offset >= self.anchor_offset,
"offset arguments should be increasing."
);
let delta_to_block_offset = offset as i64 - self.block_offset as i64;
if !(0..128).contains(&delta_to_block_offset) {
// The first position is not within the first block.
// We need to decompress the first block.
let delta_to_anchor_offset = offset - self.anchor_offset;
let num_blocks_to_skip =
(delta_to_anchor_offset / (COMPRESSION_BLOCK_SIZE as u64)) as usize;
self.advance_num_blocks(num_blocks_to_skip);
self.anchor_offset = offset - (offset % COMPRESSION_BLOCK_SIZE as u64);
self.block_offset = self.anchor_offset;
let num_bits = self.skip_read.as_slice()[0];
self.bit_packer
.decompress(self.position_read.as_ref(), self.buffer.as_mut(), num_bits);
} else {
let num_blocks_to_skip =
((self.block_offset - self.anchor_offset) / COMPRESSION_BLOCK_SIZE as u64) as usize;
self.advance_num_blocks(num_blocks_to_skip);
self.anchor_offset = self.block_offset;
}
let mut num_bits = self.skip_read.as_slice()[0];
let mut position_data = self.position_read.as_ref();
for i in 1.. {
let offset_in_block = (offset as usize) % COMPRESSION_BLOCK_SIZE;
let remaining_in_block = COMPRESSION_BLOCK_SIZE - offset_in_block;
if remaining_in_block >= output.len() {
output.copy_from_slice(&self.buffer[offset_in_block..][..output.len()]);
break;
}
output[..remaining_in_block].copy_from_slice(&self.buffer[offset_in_block..]);
output = &mut output[remaining_in_block..];
offset += remaining_in_block as u64;
position_data = &position_data[(num_bits as usize * COMPRESSION_BLOCK_SIZE / 8)..];
num_bits = self.skip_read.as_slice()[i];
self.bit_packer
.decompress(position_data, self.buffer.as_mut(), num_bits);
self.ahead = Some(0);
self.block_offset += COMPRESSION_BLOCK_SIZE as u64;
}
let block_len = compressed_block_size(num_bits);
self.ahead = Some(read_impl(
self.bit_packer,
&position_data[block_len..],
self.buffer.as_mut(),
self.inner_offset,
&skip_data[1..],
output,
));
}
/// Skip the next `skip_len` integer.
///
/// If a full block is skipped, calling
/// `.skip(...)` will avoid decompressing it.
///
/// May panic if the end of the stream is reached.
pub fn skip(&mut self, skip_len: usize) {
let skip_len_plus_inner_offset = skip_len + self.inner_offset;
let num_blocks_to_advance = skip_len_plus_inner_offset / COMPRESSION_BLOCK_SIZE;
self.inner_offset = skip_len_plus_inner_offset % COMPRESSION_BLOCK_SIZE;
self.ahead = self.ahead.and_then(|num_blocks| {
if num_blocks >= num_blocks_to_advance {
Some(num_blocks - num_blocks_to_advance)
} else {
None
}
});
let skip_len_in_bits = self.skip_read.as_ref()[..num_blocks_to_advance]
.iter()
.map(|num_bits| *num_bits as usize)
.sum::<usize>()
* COMPRESSION_BLOCK_SIZE;
let skip_len_in_bytes = skip_len_in_bits / 8;
self.skip_read.advance(num_blocks_to_advance);
self.position_read.advance(skip_len_in_bytes);
}
}

14
src/positions/serializer.rs
View File

@@ -8,7 +8,7 @@ use std::io::{self, Write};
pub struct PositionSerializer<W: io::Write> {
bit_packer: BitPacker4x,
write_stream: CountingWriter<W>,
write_skiplist: W,
write_skip_index: W,
block: Vec<u32>,
buffer: Vec<u8>,
num_ints: u64,
@@ -16,11 +16,11 @@ pub struct PositionSerializer<W: io::Write> {
}
impl<W: io::Write> PositionSerializer<W> {
pub fn new(write_stream: W, write_skiplist: W) -> PositionSerializer<W> {
pub fn new(write_stream: W, write_skip_index: W) -> PositionSerializer<W> {
PositionSerializer {
bit_packer: BitPacker4x::new(),
write_stream: CountingWriter::wrap(write_stream),
write_skiplist,
write_skip_index,
block: Vec::with_capacity(128),
buffer: vec![0u8; 128 * 4],
num_ints: 0u64,
@@ -52,7 +52,7 @@ impl<W: io::Write> PositionSerializer<W> {
fn flush_block(&mut self) -> io::Result<()> {
let num_bits = self.bit_packer.num_bits(&self.block[..]);
self.write_skiplist.write_all(&[num_bits])?;
self.write_skip_index.write_all(&[num_bits])?;
let written_len = self
.bit_packer
.compress(&self.block[..], &mut self.buffer, num_bits);
@@ -70,10 +70,10 @@ impl<W: io::Write> PositionSerializer<W> {
self.flush_block()?;
}
for &long_skip in &self.long_skips {
long_skip.serialize(&mut self.write_skiplist)?;
long_skip.serialize(&mut self.write_skip_index)?;
}
(self.long_skips.len() as u32).serialize(&mut self.write_skiplist)?;
self.write_skiplist.flush()?;
(self.long_skips.len() as u32).serialize(&mut self.write_skip_index)?;
self.write_skip_index.flush()?;
self.write_stream.flush()?;
Ok(())
}

Some files were not shown because too many files have changed in this diff Show More