rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2025-12-28 04:52:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: rust:python-binding-changes
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:limit-random-seeks
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

199 Commits
python-bin ... limit-rand

Author SHA1 Message Date
Paul Masurel
9eb87e91cc TermInfo contain the end_offset of the postings. 
We slice the ReadOnlySource tightly.
 2020-09-21 00:42:15 +09:00
Paul Masurel
36f43da4d8 Added Field stats to remove total num tokens from the beginning of posting list files 2020-09-19 23:23:03 +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
Mathias Svensson
6a8a8557d2 Use slice::iter instead of into_iter to avoid future breakage (#679) 
* Use `slice::iter` instead of `into_iter` to avoid future breakage

`an_array.into_iter()` currently just works because of the autoref
feature, which then calls `<[T] as IntoIterator>::into_iter`. But
in the future, arrays will implement `IntoIterator`, too. In order
to avoid problems in the future, the call is replaced by `iter()`
which is shorter and more explicit.

* cargo fmt
 2019-10-31 20:59:50 +09:00
Alberto Piai
3a65dc84c8 TopDocs: ensure stable sorting on equal score (#675) 
* TopDocs: ensure stable sorting on equal score

When selecting the top K documents by score, we need to ensure stable
sorting. Until now, for documents with the same score, we were relying
on the (arbitrary) order returned by the BinaryHeap used to implement
the collectors.

This patch fixes the problem by explicitly using the doc address when
harvesting the `TopSegmentCollector` and when merging the results in
`TopCollector::merge_fruits()`.

This is important (for example) to implement pagination correctly using
the TopDocs collector. If sorting isn't stable, documents that have the
same score might be ranked in different positions depending on the
specific K that was used, thus appearing in two different pages, or in
none at all.

Fixes gh-671

* TMP: alternative solution (see previous commit)

If we add the constrait that D is also PartialOrd in ComparableDoc<T,
D>, then we can move the comparison by doc address directly in the cmp
implementation of ComparableDoc.

* TMP rebase as first commit: add benchmarks for TopSegmentCollector

* fixup! TMP: alternative solution (see previous commit)

* TMP add changelog entry

* TMP run cargo fmt
 2019-10-26 15:27:25 +09:00
dependabot-preview[bot]
ce42bbf5c9 Update base64 requirement from 0.10.0 to 0.11.0 (#676) 
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/v0.10.0...v0.11.0)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>
 2019-10-26 15:24:47 +09:00
Paul Masurel
7b21b3f25a Refactoring around Field (#673) 
* Refactoring around Field

Removing the contract about the order of the field, and the
field id allocation.

* Update delete_queue.rs

* Update field.rs
 2019-10-25 09:06:44 +09:00
Paul Masurel
46caec1040 Updating uuid to 0.8 (#674) 2019-10-25 09:02:00 +09:00
petr-tik
1187a02a3e Fixed #664 (#667) 
Removed references to u8 and old documentation
 2019-10-22 09:34:10 +09:00
Andrew Banchich
f6c525b19e Fix grammar / punctuation (#668) 2019-10-21 10:50:53 +09:00
petr-tik
4a8f7712f3 Add a doctest to BooleanQuery (#630) 
* Add a doctest to BooleanQuery

Closes #446

Mark a function that is only used in tests to be compiled for tests only

Fix doc-comments in a couple of related files

* Minor corrections

remove whitespace, fix typos, add explicit dyn marker

* WIP: BooleanQuery doc test

Trying to nest several BooleanQueries together

* Addressed old review

rust 2018 edition + make function available to everyone

* Box the previous query to resolve the type error

* Rework wording in DocAdress document strings

* Reworded and restructured the docstring
 2019-10-07 10:05:12 +09:00
Paul Masurel
2f867aad17 Fix bench (#663) 
* fmt

* Fixing bench compilation
 2019-10-04 17:07:49 +09:00
Paul Masurel
5c6580eb15 fmt (#661) 2019-10-04 12:10:01 +09:00
Paul Masurel
4c3941750b Waiting potentially longer on watch 2019-10-01 09:50:46 +09:00
Paul Masurel
2ea8e618f2 Merge branch 'hotfix-656' 2019-10-01 09:44:56 +09:00
Paul Masurel
94f27f990b Address #656 
Broke the reference loop to make sure that the watch_router can
be dropped, and the thread exits.
 2019-10-01 09:34:22 +09:00
Paul Masurel
349e8aa348 Removed enum variants on type alias 2019-09-26 18:43:29 +09:00
Paul Masurel
cde9b78b8d Fixing the issue associated with the Regex performance change 2019-09-18 18:29:27 +09:00
fdb-hiroshima
d8894f0bd2 add checksum check in ManagedDirectory (#605) 
* add checksum check in ManagedDirectory

fix #400

* flush after writing checksum

* don't checksum atomic file access and clone managed_paths

* implement a footer storing metadata about a file

this is more of a poc, it require some refactoring into multiple files
`terminate(self)` is implemented, but not used anywhere yet

* address comments and simplify things with new contract

use BitOrder for integer to raw byte conversion
consider atomic write imply atomic read, which might not actually be true
use some indirection to have a boxable terminating writer

* implement TerminatingWrite and make terminate() be called where it should

add dependancy to drop_bomb to help find where terminate() should be called
implement TerminatingWrite for wrapper writers
make tests pass
/!\ some tests seems to pass where they shouldn't

* remove usage of drop_bomb

* fmt

* add test for checksum

* address some review comments

* update changelog

* fmt
 2019-09-18 18:26:25 +09:00
fdb-hiroshima
7e08e0047b fix Term documentation (#655) 
u64-based fields are actually 4+8=12 bytes long
 2019-09-11 18:49:35 +09:00
fdb-hiroshima
1a817f117f fix documentation error (#654) 
Union missdocumented as doing an intersection
Union and Intersection can hold more than 2 DocSets
 2019-09-11 17:12:08 +09:00
petr-tik
2ec19b21ae Remove unnecessary duplicate methods (#650) 
Closes #649

Spotted by @imor
 2019-09-09 06:36:04 +09:00
Raminder Singh
141f5a93f7 Using FnvHashMap for mapping UnorderedTermId to TermOrdinal. Fixes #507 (#647) 
* Using FnvHashMap for mapping UnorderedTermId to TermOrdinal. Fixes #507

* Fixed cargo fmt errors
 2019-09-07 19:40:21 +09:00
Paul Masurel
df47d55cd2 Occur debug interface (#648) 2019-09-07 15:08:45 +09:00
Raminder Singh
5e579fd6b7 Fixed clippy warning: unneeded return statement (#646) 2019-09-07 10:14:37 +09:00
Paul Masurel
4b9c1dce69 Moving queyr grammar to a different crate. (#645) 2019-09-05 09:37:28 +09:00
Paul Masurel
d74f71bbef Lighter regex dependency. (#644) 
Detail on https://github.com/rust-lang/regex/pull/613
 2019-09-04 13:10:12 +09:00
Paul Masurel
5196ca41d8 Small code clean up 2019-09-03 09:22:32 +09:00
dependabot-preview[bot]
4959e06151 Update once_cell requirement from 0.2 to 1.0 (#643) 
Updates the requirements on [once_cell](https://github.com/matklad/once_cell) to permit the latest version.
- [Release notes](https://github.com/matklad/once_cell/releases)
- [Changelog](https://github.com/matklad/once_cell/blob/master/CHANGELOG.md)
- [Commits](https://github.com/matklad/once_cell/compare/v0.2.0...v1.0.2)

Signed-off-by: dependabot-preview[bot] <support@dependabot.com>
 2019-09-03 07:00:45 +09:00
Paul Masurel
c1635c13f6 RegexQuery performance: make it possible to cache Regexes - remastered by fulmicoton (Closes #639) (#641) 
* small docs cleanup

* only compile a regex once per RegexQuery

Building a `Regex` is an expensive operation. Users of `RegexQuery`
need to cache and reuse regexes when searching across multiple fields.

This is the first step towards allowing that: we can store the `Regex`
directly in the `RegexQuery`, instead of the string pattern.

* RegexQuery: account for possible failure in the constructor

When building a regex from a str pattern, we have to account for the
possibility that the pattern is invalid. Before the previous commit, the
failure would happen in the `specialized_weight` method. Now that we
store a compiled `Regex` in `RegexQuery`, `specialized_weight` doesn't
fail anymore, and we can fail early while constructing `RegexQuery` if
the pattern is invalid.

This is a breaking change for users of `RegexQuery::new`.

* add RegexQuery::from_regex method

This builds a `RegexQuery` from an already compiled `Regex`. The use of
`Into<Arc<Regex>>` is to allow the caller to either simply pass a
`Regex`, or an `Arc<Regex>`, in case it needs to be cached and shared on
the caller's side.

* Using an Arc in AutomatonWeight

Closes #639
 2019-08-22 16:14:01 +09:00
Paul Masurel
135e0ea2e9 Expose new segment meta from Index (#637) 2019-08-19 10:39:15 +09:00
Paul Masurel
f283bfd7ab Added segmentid_from_string (#636) 2019-08-19 10:37:30 +09:00
Joshua Dutton
9f74786db2 Update import statements in examples, doctests (#633) 
Update import statements to edition 2018, including removing
`extern crate` and  `#[macro_use]`. Alphabetize the statements.
 2019-08-19 07:26:35 +09:00
Joshua Dutton
32e5d7a0c7 Fix trait object in doctest (#635) 2019-08-19 07:25:00 +09:00
Joshua Dutton
84c615cff1 Fixing typos (#634) 2019-08-19 07:24:05 +09:00
Paul Masurel
039c0a0863 Introducing a wrapper struct instead of Boxed<BoxableTokenizer> (#631) 
Closes #629
 2019-08-15 16:37:04 +09:00
Paul Masurel
b3b0138b82 Change for tantivy-py 
Schema.convert_named_doc
Better Debug string for Terms and TermQueries
 2019-08-14 17:44:25 +09:00
petr-tik
ea56160cdc Added cargo-fmt to CI runs (#627) 
* Added cargo-fmt to CI runs

Closes #625

* Remove fmt from appveyor builds

Windows seems to have issues with install components through rustup.

Formatting should be equally informative regardless of the OS,
so best to keep it in Linux on Travis
 2019-08-12 08:25:47 +09:00
petr-tik
028b0a749c Elastic unbounded range query (#624) 
* Tidy up

fmt

remove unneccessary -> Result<()> followed by run.unwrap() in a test

* Adding support for elasticsearch-style unbounded queries

Extend the UserInputBound to include Unbounded, so we can reuse formatting and
internal query format

* Still working on elastic-style range queries

Fixes #498

Merge the elastic_range into range

Reformat to make code easier to follow, use optional() macro to return Some

* Fixed bugs

Made the range parser insensitive to whitespace between the ":" and the range.

Removed optional parsing of field.

Added a unit test for the range parser.

Derived PartialEq to compare the results of parsing as structs, instead of
strings. Found a bug with that unit test - "*}" was parsed as an
UserInputBound::Exclusive, instead of UserInputBound::Unbounded. Added an early
detection-and-return for * in the original range parser

* Correct failing test

Assume that we will use "{*" for Unbounded ranges

* Add a note in the changelog

cargo-fmt

* Moved parenthesis to a newline to make nested if-else more visible
 2019-08-12 08:24:47 +09:00
Paul Masurel
941f06eb9f Added Schema.from_named_doc 2019-08-11 16:50:32 +09:00
Paul Masurel
04832a86eb WTF is this file doing here (#622) 2019-08-08 21:54:10 +09:00
fdb-hiroshima
beb8e990cd fix parsing neg float in range query (#621) 
fix #620
 2019-08-08 20:41:04 +09:00
Paul Masurel
001af3876f cargo fmt 2019-08-08 18:07:19 +09:00
Paul Masurel
f428f344da Various bugfix in the query parser (#619) 2019-08-08 17:48:21 +09:00
Paul Masurel
143f78eced Trying to fix #609 (#616) 2019-08-06 20:33:30 +09:00
Kornel
754b55eee5 Bump deps (#613) 
* Bump crossbeam

* Warnings--

* Remove outdated tempdir
 2019-08-05 22:21:22 +09:00
Paul Masurel
280ea1209c Changes required for python binding (#610) 2019-08-01 17:26:21 +09:00
petr-tik
0154dbe477 Replace unwrap with match and proper Error handling (#606) 
* Replace unwrap with match and proper Error handling

* Replaced 'magic' values with a documented variable

Didn't like the unexplained 0..3 range, thought it was best as a variable

Calculating Levenshtein distance is expensive, so best explain why we should
keep it low
 2019-07-31 08:16:02 +09:00
192 changed files with 11089 additions and 5821 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*

2
.travis.yml
View File

@@ -47,6 +47,7 @@ matrix:
before_install:
- set -e
- rustup self update
- rustup component add rustfmt
install:
- sh ci/install.sh
@@ -60,6 +61,7 @@ before_script:
script:
- bash ci/script.sh
- cargo fmt --all -- --check
before_deploy:
- sh ci/before_deploy.sh

92
CHANGELOG.md
View File

@@ -1,7 +1,99 @@
Tantivy 0.14.0
=========================
- Remove dependency to atomicwrites #833 .Implemented by @pmasurel upon suggestion and research from @asafigan).
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/master/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
=====================
- Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima)
- Various bugfixes in the query parser.
- Better handling of hyphens in query parser. (#609)
- Better handling of whitespaces.
- Closes #498 - add support for Elastic-style unbounded range queries for alphanumeric types eg. "title:>hello", "weight:>=70.5", "height:<200" (@petr-tik)
- 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
=====================
- Closes #656. Solving memory leak.
Tantivy 0.10.1
=====================

78
Cargo.toml
View File

@@ -1,11 +1,11 @@
[package]
name = "tantivy"
version = "0.10.1"
version = "0.14.0-dev"
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"
@@ -13,47 +13,42 @@ keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
base64 = "0.10.0"
byteorder = "1.0"
once_cell = "0.2"
regex = "1.0"
tantivy-fst = "0.1"
base64 = "0.12"
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}
snap = "1"
tempfile = {version="3", optional=true}
log = "0.4"
combine = ">=3.6.0,<4.0.0"
tempdir = "0.3"
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"]}
levenshtein_automata = "0.2"
notify = {version="4", optional=true}
bit-set = "0.5"
uuid = { version = "0.7.2", features = ["v4", "serde"] }
crossbeam = "0.5"
futures = "0.1"
futures-cpupool = "0.1"
uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.7"
futures = {version = "0.3", features=["thread-pool"] }
owning_ref = "0.4"
stable_deref_trait = "1.0.0"
rust-stemmers = "1.1"
downcast-rs = { version="1.0" }
tantivy-query-grammar = { version="0.14.0-dev", 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"
census = "0.4"
fnv = "1"
owned-read = "0.4"
failure = "0.1"
htmlescape = "0.3.1"
fail = "0.3"
scoped-pool = "1.0"
htmlescape = "0.3"
fail = "0.4"
murmurhash32 = "0.2"
chrono = "0.4"
smallvec = "0.6"
smallvec = "1"
rayon = "1"
[target.'cfg(windows)'.dependencies]
winapi = "0.3"
@@ -62,7 +57,11 @@ winapi = "0.3"
rand = "0.7"
maplit = "1"
matches = "0.1.8"
time = "0.1.42"
proptest = "0.10"
[dev-dependencies.fail]
version = "0.4"
features = ["failpoints"]
[profile.release]
opt-level = 3
@@ -75,19 +74,18 @@ overflow-checks = true
[features]
default = ["mmap"]
mmap = ["atomicwrites", "fs2", "memmap", "notify"]
mmap = ["fs2", "tempfile", "memmap", "notify"]
lz4-compression = ["lz4"]
failpoints = ["fail/failpoints"]
unstable = [] # useful for benches.
wasm-bindgen = ["uuid/wasm-bindgen"]
[workspace]
members = ["query-grammar"]
[badges]
travis-ci = { repository = "tantivy-search/tantivy" }
[dev-dependencies.fail]
features = ["failpoints"]
# Following the "fail" crate best practises, we isolate
# tests that define specific behavior in fail check points
# in a different binary.
@@ -98,4 +96,4 @@ features = ["failpoints"]
[[test]]
name = "failpoints"
path = "tests/failpoints/mod.rs"
required-features = ["fail/failpoints"]
required-features = ["fail/failpoints"]

3
Makefile Normal file
View File

@@ -0,0 +1,3 @@
test:
echo "Run test only... No examples."
cargo test --tests --lib

65
README.md
View File

@@ -21,9 +21,9 @@
[![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
**Tantivy** is a **full text search engine library** written in rust.
**Tantivy** is a **full text search engine library** written in Rust.
It is closer to [Apache Lucene](https://lucene.apache.org/) than to [Elasticsearch](https://www.elastic.co/products/elasticsearch) and [Apache Solr](https://lucene.apache.org/solr/) in the sense it is not
It is closer to [Apache Lucene](https://lucene.apache.org/) than to [Elasticsearch](https://www.elastic.co/products/elasticsearch) or [Apache Solr](https://lucene.apache.org/solr/) in the sense it is not
an off-the-shelf search engine server, but rather a crate that can be used
to build such a search engine.
@@ -31,73 +31,70 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark
Tantivy is typically faster than Lucene, but the results will 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. 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)
- Natural query language `(michael AND jackson) OR "king of pop"`
- Phrase queries search (`"michael jackson"`)
- BM25 scoring (the same as Lucene)
- Natural query language (e.g. `(michael AND jackson) OR "king of pop"`)
- Phrase queries search (e.g. `"michael jackson"`)
- Incremental indexing
- Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop)
- Mmap directory
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set.
- Single valued and multivalued u64, i64 and f64 fast fields (equivalent of doc values in Lucene)
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set
- Single valued and multivalued u64, i64, and f64 fast fields (equivalent of doc values in Lucene)
- `&[u8]` fast fields
- Text, i64, u64, f64, dates and hierarchical facet fields
- Text, i64, u64, f64, dates, and hierarchical facet fields
- LZ4 compressed document store
- Range queries
- Faceted search
- 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 meant as a
- 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.
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'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.
It will walk you through getting a wikipedia search engine up and running in a few minutes.
- [reference doc for the last released version](https://docs.rs/tantivy/)
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.
It walks you through getting a wikipedia search engine up and running in a few minutes.
- [Reference doc for the last released version](https://docs.rs/tantivy/)
# How can I support this project?
There are many ways to support this project.
- Use tantivy and tell us about your experience on [gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
- Use Tantivy and tell us about your experience on [Gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
- Report bugs
- Write a blog post
- 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
- 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)
# Contributing code
We use the GitHub Pull Request workflow - reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
We use the GitHub Pull Request workflow: reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
## Clone and build locally
Tantivy compiles on stable rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run :
Tantivy compiles on stable Rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run:
```bash
git clone https://github.com/tantivy-search/tantivy.git
@@ -108,7 +105,7 @@ To check out and run tests, you can simply run :
## Run tests
Some tests will not run with just `cargo test` because of `fail-rs`.
To run the tests exhaustively, run `./run-tests.sh`
To run the tests exhaustively, run `./run-tests.sh`.
## Debug
@@ -116,13 +113,13 @@ You might find it useful to step through the programme with a debugger.
### A failing test
Make sure you haven't run `cargo clean` after the most recent `cargo test` or `cargo build` to guarantee that `target/` dir exists. Use this bash script to find the most name of the most recent debug build of tantivy and run it under rust-gdb.
Make sure you haven't run `cargo clean` after the most recent `cargo test` or `cargo build` to guarantee that the `target/` directory exists. Use this bash script to find the name of the most recent debug build of Tantivy and run it under `rust-gdb`:
```bash
find target/debug/ -maxdepth 1 -executable -type f -name "tantivy*" -printf '%TY-%Tm-%Td %TT %p\n' | sort -r | cut -d " " -f 3 | xargs -I RECENT_DBG_TANTIVY rust-gdb RECENT_DBG_TANTIVY
```
Now that you are in rust-gdb, you can set breakpoints on lines and methods that match your source-code and run the debug executable with flags that you normally pass to `cargo test` to like this
Now that you are in `rust-gdb`, you can set breakpoints on lines and methods that match your source code and run the debug executable with flags that you normally pass to `cargo test` like this:
```bash
$gdb run --test-threads 1 --test $NAME_OF_TEST
@@ -130,7 +127,7 @@ $gdb run --test-threads 1 --test $NAME_OF_TEST
### An example
By default, rustc compiles everything in the `examples/` dir in debug mode. This makes it easy for you to make examples to reproduce bugs.
By default, `rustc` compiles everything in the `examples/` directory in debug mode. This makes it easy for you to make examples to reproduce bugs:
```bash
rust-gdb target/debug/examples/$EXAMPLE_NAME

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

5
ci/script.sh
View File

@@ -7,7 +7,7 @@ set -ex
main() {
if [ ! -z $CODECOV ]; then
echo "Codecov"
cargo build --verbose && cargo coverage --verbose && bash <(curl -s https://codecov.io/bash) -s target/kcov
cargo build --verbose && cargo coverage --verbose --all && bash <(curl -s https://codecov.io/bash) -s target/kcov
else
echo "Build"
cross build --target $TARGET
@@ -15,7 +15,8 @@ main() {
return
fi
echo "Test"
cross test --target $TARGET --no-default-features --features mmap -- --test-threads 1
cross test --target $TARGET --no-default-features --features mmap
cross test --target $TARGET --no-default-features --features mmap query-grammar
fi
for example in $(ls examples/*.rs)
do

50
doc/src/index-format.md Normal file
View File

@@ -0,0 +1,50 @@
# Managed files
+----------+-----------+-------------------+
| content | footer | footer_len: u32 |
+----------+-----------+-------------------+
# Term Dictionary (Composite File)
+---------+---------------------------+------------------------+
| fst | term_info_store | footer_len: u64 |
+---------+---------------------------+------------------------+
During a merge the term info store need to fit in memory.
It has a cost of n bytes per term.
# term_info_store
+-------------------+---------------------------+------------------------+
| len_block_meta | block_meta | term_infos |
+-------------------+---------------------------+------------------------+
# inverted_index
+------------------------+---------------------------+------------------------+
| total_num_tokens: u64 | posting_lists.. | term_infos |
+------------------------+---------------------------+------------------------+
# postings lists
+------------------------+---------------------------+------------------------+
|
+
# composite file
+----------------+-----+----------------+----------------------+----------------+
| field file 1 | ... | field field n |composite file footer | footer len: u32|
+----------------+-----+----------------+----------------------+----------------+
# composite file footer
+-----------------+---------------------------------------+
|num fields: vint | (file_addr, offset_delta: vint) []... |
+-----------------+---------------------------------------+
# FileAddr
+--------------+--------------+
| field: u32 | idx: VInt |
+--------------+--------------+
# Posting lists
+-----------------------------------------+
| skip_reader
+-----------------------------------------+

52
examples/basic_search.rs
View File

@@ -5,26 +5,23 @@
//
// We will :
// - define our schema
// = create an index in a directory
// - index few documents in our index
// - search for the best document matchings "sea whale"
// - retrieve the best document original content.
// - create an index in a directory
// - index a few documents into our index
// - search for the best document matching a basic query
// - retrieve the best document's original content.
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::Index;
use tantivy::ReloadPolicy;
use tempdir::TempDir;
use tantivy::{doc, Index, ReloadPolicy};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new("tantivy_example_dir")?;
let index_path = TempDir::new()?;
// # Defining the schema
//
@@ -33,7 +30,7 @@ fn main() -> tantivy::Result<()> {
// and for each field, its type and "the way it should
// be indexed".
// first we need to define a schema ...
// First we need to define a schema ...
let mut schema_builder = Schema::builder();
// Our first field is title.
@@ -48,7 +45,7 @@ fn main() -> tantivy::Result<()> {
//
// `STORED` means that the field will also be saved
// in a compressed, row-oriented key-value store.
// This store is useful to reconstruct the
// This store is useful for reconstructing the
// documents that were selected during the search phase.
schema_builder.add_text_field("title", TEXT | STORED);
@@ -57,8 +54,7 @@ fn main() -> tantivy::Result<()> {
// need to be able to be able to retrieve it
// for our application.
//
// We can make our index lighter and
// by omitting `STORED` flag.
// We can make our index lighter by omitting the `STORED` flag.
schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
@@ -71,7 +67,7 @@ fn main() -> tantivy::Result<()> {
// with our schema in the directory.
let index = Index::create_in_dir(&index_path, schema.clone())?;
// To insert document we need an index writer.
// To insert a document we will need an index writer.
// There must be only one writer at a time.
// This single `IndexWriter` is already
// multithreaded.
@@ -116,18 +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",
@@ -149,8 +133,8 @@ fn main() -> tantivy::Result<()> {
// At this point our documents are not searchable.
//
//
// We need to call .commit() explicitly to force the
// index_writer to finish processing the documents in the queue,
// We need to call `.commit()` explicitly to force the
// `index_writer` to finish processing the documents in the queue,
// flush the current index to the disk, and advertise
// the existence of new documents.
//
@@ -162,14 +146,14 @@ fn main() -> tantivy::Result<()> {
// persistently indexed.
//
// In the scenario of a crash or a power failure,
// tantivy behaves as if has rolled back to its last
// tantivy behaves as if it has rolled back to its last
// commit.
// # Searching
//
// ### Searcher
//
// A reader is required to get search the index.
// A reader is required first in order to search an index.
// It acts as a `Searcher` pool that reloads itself,
// depending on a `ReloadPolicy`.
//
@@ -185,7 +169,7 @@ fn main() -> tantivy::Result<()> {
// We now need to acquire a searcher.
//
// A searcher points to snapshotted, immutable version of the index.
// A searcher points to a snapshotted, immutable version of the index.
//
// Some search experience might require more than
// one query. Using the same searcher ensures that all of these queries will run on the
@@ -205,7 +189,7 @@ fn main() -> tantivy::Result<()> {
// in both title and body.
let query_parser = QueryParser::for_index(&index, vec![title, body]);
// QueryParser may fail if the query is not in the right
// `QueryParser` may fail if the query is not in the right
// format. For user facing applications, this can be a problem.
// A ticket has been opened regarding this problem.
let query = query_parser.parse_query("sea whale")?;
@@ -221,7 +205,7 @@ fn main() -> tantivy::Result<()> {
//
// We are not interested in all of the documents but
// only in the top 10. Keeping track of our top 10 best documents
// is the role of the TopDocs.
// is the role of the `TopDocs` collector.
// We can now perform our query.
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

7
examples/custom_collector.rs
View File

@@ -9,15 +9,12 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::{Collector, SegmentCollector};
use tantivy::fastfield::FastFieldReader;
use tantivy::query::QueryParser;
use tantivy::schema::Field;
use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
use tantivy::SegmentReader;
use tantivy::{Index, TantivyError};
use tantivy::{doc, Index, Score, SegmentReader, TantivyError};
#[derive(Default)]
struct Stats {
@@ -117,7 +114,7 @@ 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;

5
examples/custom_tokenizer.rs
View File

@@ -2,14 +2,11 @@
//
// In this example, we'll see how to define a tokenizer pipeline
// by aligning a bunch of `TokenFilter`.
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::tokenizer::NgramTokenizer;
use tantivy::Index;
use tantivy::{doc, Index};
fn main() -> tantivy::Result<()> {
// # Defining the schema

5
examples/deleting_updating_documents.rs
View File

@@ -8,13 +8,10 @@
//
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::TermQuery;
use tantivy::schema::*;
use tantivy::Index;
use tantivy::IndexReader;
use tantivy::{doc, Index, IndexReader};
// A simple helper function to fetch a single document
// given its id from our index.

112
examples/faceted_search.rs
View File

@@ -12,67 +12,101 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::FacetCollector;
use tantivy::query::AllQuery;
use tantivy::query::{AllQuery, TermQuery};
use tantivy::schema::*;
use tantivy::Index;
use tantivy::{doc, Index};
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new("tantivy_facet_example_dir")?;
// 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(())
}
use tempdir::TempDir;

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 mut 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()))
.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(())
}

6
examples/integer_range_search.rs
View File

@@ -2,14 +2,10 @@
//
// Below is an example of creating an indexed integer field in your schema
// You can use RangeQuery to get a Count of all occurrences in a given range.
#[macro_use]
extern crate tantivy;
use tantivy::collector::Count;
use tantivy::query::RangeQuery;
use tantivy::schema::{Schema, INDEXED};
use tantivy::Index;
use tantivy::Result;
use tantivy::{doc, Index, Result};
fn run() -> Result<()> {
// For the sake of simplicity, this schema will only have 1 field

20
examples/iterating_docs_and_positions.rs
View File

@@ -9,11 +9,8 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::schema::*;
use tantivy::Index;
use tantivy::{DocId, DocSet, Postings};
use tantivy::{doc, DocSet, Index, Postings, TERMINATED};
fn main() -> tantivy::Result<()> {
// We first create a schema for the sake of the
@@ -65,12 +62,11 @@ fn main() -> tantivy::Result<()> {
{
// 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;
}
@@ -89,6 +85,7 @@ fn main() -> tantivy::Result<()> {
// Doc 2: TermFreq 1: [0]
// ```
println!("Doc {}: TermFreq {}: {:?}", doc_id, term_freq, positions);
doc_id = segment_postings.advance();
}
}
}
@@ -120,11 +117,16 @@ fn main() -> tantivy::Result<()> {
if let Some(mut block_segment_postings) =
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();
}
}
}

15
examples/multiple_producer.rs
View File

@@ -25,14 +25,11 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use std::sync::{Arc, RwLock};
use std::thread;
use std::time::Duration;
use tantivy::schema::{Schema, STORED, TEXT};
use tantivy::Opstamp;
use tantivy::{Index, IndexWriter};
use tantivy::{doc, Index, IndexWriter, Opstamp};
fn main() -> tantivy::Result<()> {
// # Defining the schema
@@ -49,10 +46,9 @@ fn main() -> tantivy::Result<()> {
thread::spawn(move || {
// we index 100 times the document... for the sake of the example.
for i in 0..100 {
let opstamp = {
// A read lock is sufficient here.
let index_writer_rlock = index_writer_clone_1.read().unwrap();
index_writer_rlock.add_document(
let opstamp = index_writer_clone_1
.read().unwrap() //< A read lock is sufficient here.
.add_document(
doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
@@ -63,8 +59,7 @@ fn main() -> tantivy::Result<()> {
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"
))
};
));
println!("add doc {} from thread 1 - opstamp {}", i, opstamp);
thread::sleep(Duration::from_millis(20));
}

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(())
}

9
examples/snippet.rs
View File

@@ -7,19 +7,16 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::Index;
use tantivy::{Snippet, SnippetGenerator};
use tempdir::TempDir;
use tantivy::{doc, Index, Snippet, SnippetGenerator};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new("tantivy_example_dir")?;
let index_path = TempDir::new()?;
// # Defining the schema
let mut schema_builder = Schema::builder();

6
examples/stop_words.rs
View File

@@ -11,13 +11,11 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::tokenizer::*;
use tantivy::Index;
use tantivy::{doc, Index};
fn main() -> tantivy::Result<()> {
// this example assumes you understand the content in `basic_search`
@@ -52,7 +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(),

16
query-grammar/Cargo.toml Normal file
View File

@@ -0,0 +1,16 @@
[package]
name = "tantivy-query-grammar"
version = "0.14.0-dev"
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"
homepage = "https://github.com/tantivy-search/tantivy"
repository = "https://github.com/tantivy-search/tantivy"
readme = "README.md"
keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
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.

15
query-grammar/src/lib.rs Normal file
View File

@@ -0,0 +1,15 @@
mod occur;
mod query_grammar;
mod user_input_ast;
use combine::parser::Parser;
pub use crate::occur::Occur;
use crate::query_grammar::parse_to_ast;
pub use crate::user_input_ast::{UserInputAST, UserInputBound, UserInputLeaf, UserInputLiteral};
pub struct Error;
pub fn parse_query(query: &str) -> Result<UserInputAST, Error> {
let (user_input_ast, _remaining) = parse_to_ast().parse(query).map_err(|_| Error)?;
Ok(user_input_ast)
}

72
query-grammar/src/occur.rs Normal file
View File

@@ -0,0 +1,72 @@
use std::fmt;
use std::fmt::Write;
/// Defines whether a term in a query must be present,
/// should be present or must be not present.
#[derive(Debug, Clone, Hash, Copy, Eq, PartialEq)]
pub enum Occur {
/// For a given document to be considered for scoring,
/// at least one of the document with the Should or the Must
/// Occur constraint must be within the document.
Should,
/// Document without the term are excluded from the search.
Must,
/// Document that contain the term are excluded from the
/// search.
MustNot,
}
impl Occur {
/// Returns the one-char prefix symbol for this `Occur`.
/// - `Should` => '?',
/// - `Must` => '+'
/// - `Not` => '-'
fn to_char(self) -> char {
match self {
Occur::Should => '?',
Occur::Must => '+',
Occur::MustNot => '-',
}
}
/// Compose two occur values.
pub fn compose(left: Occur, right: Occur) -> Occur {
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,
}
}
}
impl fmt::Display for Occur {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
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);
}
}

534
query-grammar/src/query_grammar.rs Normal file
View File

@@ -0,0 +1,534 @@
use super::user_input_ast::{UserInputAST, UserInputBound, UserInputLeaf, UserInputLiteral};
use crate::Occur;
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,
};
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))
}
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 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()
})
}
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)]
enum BinaryOperand {
Or,
And,
}
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(
left: UserInputAST,
others: Vec<(BinaryOperand, UserInputAST)>,
) -> UserInputAST {
let mut dnf: Vec<Vec<UserInputAST>> = vec![vec![left]];
for (operator, operand_ast) in others {
match operator {
BinaryOperand::And => {
if let Some(last) = dnf.last_mut() {
last.push(operand_ast);
}
}
BinaryOperand::Or => {
dnf.push(vec![operand_ast]);
}
}
}
if dnf.len() == 1 {
UserInputAST::and(dnf.into_iter().next().unwrap()) //< safe
} else {
let conjunctions = dnf.into_iter().map(UserInputAST::and).collect();
UserInputAST::or(conjunctions)
}
}
fn operand_leaf<'a>() -> impl Parser<&'a str, Output = (BinaryOperand, UserInputAST)> {
(
binary_operand().skip(spaces()),
boosted_leaf().skip(spaces()),
)
}
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;
let query_str = format!("{:?}", query);
assert_eq!(query_str, expected);
}
fn test_is_parse_err(query: &str) {
assert!(parse_to_ast().parse(query).is_err());
}
#[test]
fn test_parse_empty_to_ast() {
test_parse_query_to_ast_helper("", "<emptyclause>");
}
#[test]
fn test_parse_query_to_ast_hyphen() {
test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
}
#[test]
fn test_parse_query_to_ast_not_op() {
assert_eq!(
format!("{:?}", parse_to_ast().parse("NOT")),
"Err(UnexpectedParse)"
);
test_parse_query_to_ast_helper("NOTa", "\"NOTa\"");
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\")");
assert_eq!(
format!("{:?}", parse_to_ast().parse("a OR b aaa")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("a AND b aaa")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("aaa a OR b ")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("aaa ccc a OR b ")),
"Err(UnexpectedParse)"
);
}
#[test]
fn test_parse_elastic_query_ranges() {
test_parse_query_to_ast_helper("title: >a", "title:{\"a\" TO \"*\"}");
test_parse_query_to_ast_helper("title:>=a", "title:[\"a\" TO \"*\"}");
test_parse_query_to_ast_helper("title: <a", "title:{\"*\" TO \"a\"}");
test_parse_query_to_ast_helper("title:<=a", "title:{\"*\" TO \"a\"]");
test_parse_query_to_ast_helper("title:<=bsd", "title:{\"*\" TO \"bsd\"]");
test_parse_query_to_ast_helper("weight: >70", "weight:{\"70\" TO \"*\"}");
test_parse_query_to_ast_helper("weight:>=70", "weight:[\"70\" TO \"*\"}");
test_parse_query_to_ast_helper("weight: <70", "weight:{\"*\" TO \"70\"}");
test_parse_query_to_ast_helper("weight:<=70", "weight:{\"*\" TO \"70\"]");
test_parse_query_to_ast_helper("weight: >60.7", "weight:{\"60.7\" TO \"*\"}");
test_parse_query_to_ast_helper("weight: <= 70", "weight:{\"*\" TO \"70\"]");
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
let res = range().parse("title: <hello").unwrap().0;
let expected = UserInputLeaf::Range {
field: Some("title".to_string()),
lower: UserInputBound::Unbounded,
upper: UserInputBound::Exclusive("hello".to_string()),
};
let res2 = range().parse("title:{* TO hello}").unwrap().0;
assert_eq!(res, expected);
assert_eq!(res2, expected);
let expected_weight = UserInputLeaf::Range {
field: Some("weight".to_string()),
lower: UserInputBound::Inclusive("71.2".to_string()),
upper: UserInputBound::Unbounded,
};
let res3 = range().parse("weight: >=71.2").unwrap().0;
let res4 = range().parse("weight:[71.2 TO *}").unwrap().0;
assert_eq!(res3, expected_weight);
assert_eq!(res4, expected_weight);
}
#[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]
fn test_parse_query_single_term() {
test_parse_query_to_ast_helper("abc", "\"abc\"");
}
#[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]
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\"}");
test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:{\"*\" TO \"toto\"}");
test_parse_query_to_ast_helper("foo:[1 TO *}", "foo:[\"1\" TO \"*\"}");
test_parse_query_to_ast_helper("foo:[1.1 TO *}", "foo:[\"1.1\" TO \"*\"}");
test_is_parse_err("abc + ");
}
}

86
src/query/query_parser/user_input_ast.rs → query-grammar/src/user_input_ast.rs
View File

@@ -1,8 +1,9 @@
use std::fmt;
use std::fmt::{Debug, Formatter};
use crate::query::Occur;
use crate::Occur;
#[derive(PartialEq)]
pub enum UserInputLeaf {
Literal(UserInputLiteral),
All,
@@ -35,6 +36,7 @@ impl Debug for UserInputLeaf {
}
}
#[derive(PartialEq)]
pub struct UserInputLiteral {
pub field_name: Option<String>,
pub phrase: String,
@@ -49,9 +51,11 @@ impl fmt::Debug for UserInputLiteral {
}
}
#[derive(PartialEq)]
pub enum UserInputBound {
Inclusive(String),
Exclusive(String),
Unbounded,
}
impl UserInputBound {
@@ -59,6 +63,7 @@ impl UserInputBound {
match *self {
UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word),
UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word),
UserInputBound::Unbounded => write!(formatter, "{{\"*\""),
}
}
@@ -66,6 +71,7 @@ impl UserInputBound {
match *self {
UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word),
UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word),
UserInputBound::Unbounded => write!(formatter, "\"*\"}}"),
}
}
@@ -73,38 +79,40 @@ impl UserInputBound {
match *self {
UserInputBound::Inclusive(ref contents) => contents,
UserInputBound::Exclusive(ref contents) => contents,
UserInputBound::Unbounded => &"*",
}
}
}
pub enum UserInputAST {
Clause(Vec<UserInputAST>),
Unary(Occur, Box<UserInputAST>),
// Not(Box<UserInputAST>),
// Should(Box<UserInputAST>),
// Must(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 {
assert!(occur != Occur::MustNot);
assert_ne!(occur, Occur::MustNot);
assert!(!asts.is_empty());
if asts.len() == 1 {
asts.into_iter().next().unwrap() //< safe
} else {
UserInputAST::Clause(
asts.into_iter()
.map(|ast: UserInputAST| ast.unary(occur))
.map(|ast: UserInputAST| (Some(occur), ast))
.collect::<Vec<_>>(),
)
}
}
pub fn empty_query() -> UserInputAST {
UserInputAST::Clause(Vec::default())
}
pub fn and(asts: Vec<UserInputAST>) -> UserInputAST {
UserInputAST::compose(Occur::Must, asts)
}
@@ -114,42 +122,6 @@ impl UserInputAST {
}
}
/*
impl UserInputAST {
fn compose_occur(self, occur: Occur) -> UserInputAST {
match self {
UserInputAST::Not(other) => {
let new_occur = compose_occur(Occur::MustNot, occur);
other.simplify()
}
_ => {
self
}
}
}
pub fn simplify(self) -> UserInputAST {
match self {
UserInputAST::Clause(els) => {
if els.len() == 1 {
return els.into_iter().next().unwrap();
} else {
return self;
}
}
UserInputAST::Not(els) => {
if els.len() == 1 {
return els.into_iter().next().unwrap();
} else {
return self;
}
}
}
}
}
*/
impl From<UserInputLiteral> for UserInputLeaf {
fn from(literal: UserInputLiteral) -> UserInputLeaf {
UserInputLeaf::Literal(literal)
@@ -162,26 +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.to_char(), subquery)
}
UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
UserInputAST::Boost(ref leaf, boost) => write!(formatter, "({:?})^{}", leaf, boost),
}
}
}

73
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;
@@ -10,49 +9,32 @@ use crate::SegmentReader;
/// documents match the query.
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::Count;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// 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;
@@ -61,7 +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())
}
@@ -69,7 +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())
}
}
@@ -110,20 +96,19 @@ 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);
}
}
}

23
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)>;
@@ -58,7 +57,7 @@ where
&self,
segment_local_id: u32,
segment_reader: &SegmentReader,
) -> Result<Self::Child> {
) -> crate::Result<Self::Child> {
let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
let segment_collector = self
.collector
@@ -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)
}
}

124
src/collector/facet_collector.rs
View File

@@ -1,11 +1,9 @@
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;
@@ -81,15 +79,12 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::FacetCollector;
/// use tantivy::query::AllQuery;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// 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.
@@ -129,7 +124,7 @@ 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)?;
@@ -145,7 +140,7 @@ 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)?;
///
@@ -160,8 +155,8 @@ 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)?;
///
@@ -174,6 +169,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
/// Ok(())
/// }
/// # assert!(example().is_ok());
/// ```
pub struct FacetCollector {
field: Field,
@@ -191,6 +187,11 @@ 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>,
@@ -200,14 +201,14 @@ 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();
@@ -264,7 +265,7 @@ impl Collector for FacetCollector {
&self,
_: SegmentLocalId,
reader: &SegmentReader,
) -> Result<FacetSegmentCollector> {
) -> crate::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))
@@ -284,7 +285,7 @@ impl Collector for FacetCollector {
// 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;
@@ -304,7 +305,7 @@ impl Collector for FacetCollector {
}
break;
}
SkipResult::End | SkipResult::OverStep => {
SkipResult::NotFound => {
collapse_mapping.push(0);
if !facet_streamer.advance() {
break;
@@ -330,7 +331,7 @@ 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 {
@@ -454,9 +455,11 @@ 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};
@@ -469,7 +472,7 @@ 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| {
@@ -517,7 +520,7 @@ mod tests {
#[should_panic(expected = "Tried to add a facet which is a descendant of \
an already added facet.")]
fn test_misused_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field(0));
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
facet_collector.add_facet(Facet::from("/country"));
facet_collector.add_facet(Facet::from("/country/europe"));
}
@@ -528,7 +531,7 @@ 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"),
@@ -546,9 +549,59 @@ 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(0));
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
facet_collector.add_facet(Facet::from("/country"));
facet_collector.add_facet(Facet::from("/countryeurope"));
}
@@ -578,7 +631,7 @@ 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);
}
@@ -601,19 +654,18 @@ mod tests {
);
}
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use collector::FacetCollector;
use query::AllQuery;
use rand::{thread_rng, Rng};
use schema::Facet;
use schema::Schema;
use crate::collector::FacetCollector;
use crate::query::AllQuery;
use crate::schema::{Facet, Schema};
use crate::Index;
use rand::seq::SliceRandom;
use rand::thread_rng;
use test::Bencher;
use Index;
#[bench]
fn bench_facet_collector(b: &mut Bencher) {
@@ -630,16 +682,16 @@ mod bench {
}
}
// 40425 docs
thread_rng().shuffle(&mut 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);
}
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
b.iter(|| {
let searcher = index.searcher();
let searcher = reader.searcher();
let facet_collector = FacetCollector::for_field(facet_field);
searcher.search(&AllQuery, &facet_collector).unwrap();
});

2
src/collector/int_facet_collector.rs
View File

@@ -89,7 +89,7 @@ mod tests {
let index = Index::create_in_ram(schema.clone());
{
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 0u64..10u64 {
index_writer.add_document(doc!(

56
src/collector/mod.rs
View File

@@ -35,7 +35,6 @@ The resulting `Fruit` will then be a typed tuple with each collector's original
in their respective position.
```rust
# extern crate tantivy;
# use tantivy::schema::*;
# use tantivy::*;
# use tantivy::query::*;
@@ -86,7 +85,6 @@ See the `custom_collector` example.
*/
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -111,6 +109,7 @@ pub use self::tweak_score_top_collector::{ScoreSegmentTweaker, ScoreTweaker};
mod facet_collector;
pub use self::facet_collector::FacetCollector;
use crate::query::Weight;
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
@@ -134,7 +133,7 @@ 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;
@@ -148,14 +147,37 @@ 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::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
@@ -186,7 +208,11 @@ 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))
@@ -199,7 +225,7 @@ where
fn merge_fruits(
&self,
children: Vec<(Left::Fruit, Right::Fruit)>,
) -> Result<(Left::Fruit, Right::Fruit)> {
) -> crate::Result<(Left::Fruit, Right::Fruit)> {
let mut left_fruits = vec![];
let mut right_fruits = vec![];
for (left_fruit, right_fruit) in children {
@@ -241,7 +267,11 @@ 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)?;
@@ -252,7 +282,7 @@ 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::Fruit>) -> crate::Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];
@@ -300,7 +330,11 @@ 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)?;
@@ -315,7 +349,7 @@ where
|| self.3.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
fn merge_fruits(&self, children: Vec<Self::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)))
}
@@ -33,7 +32,10 @@ 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>> {
fn merge_fruits(
&self,
children: Vec<<Self as Collector>::Fruit>,
) -> crate::Result<Box<dyn Fruit>> {
let typed_fruit: Vec<TCollector::Fruit> = children
.into_iter()
.map(|untyped_fruit| {
@@ -44,7 +46,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
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);
}
@@ -105,54 +107,38 @@ impl<TFruit: Fruit> FruitHandle<TFruit> {
/// [Combining several collectors section of the collector documentation](./index.html#combining-several-collectors).
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::{Count, TopDocs, MultiCollector};
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// 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)]
@@ -191,12 +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 })
}
@@ -207,7 +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<_>>();
@@ -225,7 +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 })
}
}
@@ -273,7 +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"));

14
src/collector/tests.rs
View File

@@ -55,7 +55,7 @@ impl Collector for TestCollector {
&self,
segment_id: SegmentLocalId,
_reader: &SegmentReader,
) -> Result<TestSegmentCollector> {
) -> crate::Result<TestSegmentCollector> {
Ok(TestSegmentCollector {
segment_id,
fruit: TestFruit::default(),
@@ -66,7 +66,7 @@ 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 +124,7 @@ 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 +139,7 @@ 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())
}
}
@@ -184,7 +184,7 @@ impl Collector for BytesFastFieldTestCollector {
&self,
_segment_local_id: u32,
segment_reader: &SegmentReader,
) -> Result<BytesFastFieldSegmentCollector> {
) -> crate::Result<BytesFastFieldSegmentCollector> {
Ok(BytesFastFieldSegmentCollector {
vals: Vec::new(),
reader: segment_reader
@@ -198,7 +198,7 @@ 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 +206,7 @@ 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);
}

204
src/collector/top_collector.rs
View File

@@ -1,6 +1,5 @@
use crate::DocAddress;
use crate::DocId;
use crate::Result;
use crate::SegmentLocalId;
use crate::SegmentReader;
use serde::export::PhantomData;
@@ -12,41 +11,53 @@ use std::collections::BinaryHeap;
/// It has a custom implementation of `PartialOrd` that reverses the order. This is because the
/// default Rust heap is a max heap, whereas a min heap is needed.
///
/// Additionally, it guarantees stable sorting: in case of a tie on the feature, the document
/// address is used.
///
/// WARNING: equality is not what you would expect here.
/// 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 for ComparableDoc<T, D> {
impl<T: PartialOrd, D: PartialOrd> PartialOrd for ComparableDoc<T, D> {
fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other))
}
}
impl<T: PartialOrd, D> Ord for ComparableDoc<T, D> {
impl<T: PartialOrd, D: PartialOrd> Ord for ComparableDoc<T, D> {
#[inline]
fn cmp(&self, other: &Self) -> Ordering {
other
// Reversed to make BinaryHeap work as a min-heap
let by_feature = other
.feature
.partial_cmp(&self.feature)
.unwrap_or_else(|| Ordering::Equal)
.unwrap_or(Ordering::Equal);
let lazy_by_doc_address = || self.doc.partial_cmp(&other.doc).unwrap_or(Ordering::Equal);
// In case of a tie on the feature, we sort by ascending
// `DocAddress` in order to ensure a stable sorting of the
// documents.
by_feature.then_with(lazy_by_doc_address)
}
}
impl<T: PartialOrd, D> PartialEq for ComparableDoc<T, D> {
impl<T: PartialOrd, D: PartialOrd> PartialEq for ComparableDoc<T, D> {
fn eq(&self, other: &Self) -> bool {
self.cmp(other) == Ordering::Equal
}
}
impl<T: PartialOrd, D> Eq 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>,
}
@@ -62,27 +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 {
@@ -94,6 +111,7 @@ where
Ok(top_collector
.into_sorted_vec()
.into_iter()
.skip(self.offset)
.map(|cdoc| (cdoc.feature, cdoc.doc))
.collect())
}
@@ -102,8 +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,
}
}
}
@@ -177,7 +211,7 @@ impl<T: PartialOrd + Clone> TopSegmentCollector<T> {
#[cfg(test)]
mod tests {
use super::TopSegmentCollector;
use super::{TopCollector, TopSegmentCollector};
use crate::DocAddress;
#[test]
@@ -214,4 +248,136 @@ mod tests {
]
);
}
#[test]
fn test_top_segment_collector_stable_ordering_for_equal_feature() {
// given that the documents are collected in ascending doc id order,
// when harvesting we have to guarantee stable sorting in case of a tie
// on the score
let doc_ids_collection = [4, 5, 6];
let score = 3.14;
let mut top_collector_limit_2 = TopSegmentCollector::new(0, 2);
for id in &doc_ids_collection {
top_collector_limit_2.collect(*id, score);
}
let mut top_collector_limit_3 = TopSegmentCollector::new(0, 3);
for id in &doc_ids_collection {
top_collector_limit_3.collect(*id, score);
}
assert_eq!(
top_collector_limit_2.harvest(),
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"))]
mod bench {
use super::TopSegmentCollector;
use test::Bencher;
#[bench]
fn bench_top_segment_collector_collect_not_at_capacity(b: &mut Bencher) {
let mut top_collector = TopSegmentCollector::new(0, 400);
b.iter(|| {
for i in 0..100 {
top_collector.collect(i, 0.8);
}
});
}
#[bench]
fn bench_top_segment_collector_collect_at_capacity(b: &mut Bencher) {
let mut top_collector = TopSegmentCollector::new(0, 100);
for i in 0..100 {
top_collector.collect(i, 0.8);
}
b.iter(|| {
for i in 0..100 {
top_collector.collect(i, 0.8);
}
});
}
#[bench]
fn bench_top_segment_collector_collect_and_harvest_many_ties(b: &mut Bencher) {
b.iter(|| {
let mut top_collector = TopSegmentCollector::new(0, 100);
for i in 0..100 {
top_collector.collect(i, 0.8);
}
// it would be nice to be able to do the setup N times but still
// measure only harvest(). We can't since harvest() consumes
// the top_collector.
top_collector.harvest()
});
}
#[bench]
fn bench_top_segment_collector_collect_and_harvest_no_tie(b: &mut Bencher) {
b.iter(|| {
let mut top_collector = TopSegmentCollector::new(0, 100);
let mut score = 1.0;
for i in 0..100 {
score += 1.0;
top_collector.collect(i, score);
}
// it would be nice to be able to do the setup N times but still
// measure only harvest(). We can't since harvest() consumes
// the top_collector.
top_collector.harvest()
});
}
}

473
src/collector/top_score_collector.rs
View File

@@ -1,73 +1,103 @@
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 std::collections::BinaryHeap;
use std::fmt;
/// The Top Score Collector keeps track of the K documents
/// The `TopDocs` collector keeps track of the top `K` documents
/// sorted by their score.
///
/// The implementation is based on a `BinaryHeap`.
/// The theorical complexity for collecting the top `K` out of `n` documents
/// is `O(n log K)`.
///
/// This collector guarantees a stable sorting in case of a tie on the
/// document score. As such, it is suitable to implement pagination.
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::DocAddress;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// 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(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_u64(u64::from(doc))
}
}
struct ScorerByField {
field: Field,
}
impl CustomScorer<u64> for ScorerByField {
type Child = ScorerByFastFieldReader;
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
let ff_reader = segment_reader
.fast_fields()
.u64(self.field)
.ok_or_else(|| {
crate::TantivyError::SchemaError(format!(
"Field requested ({:?}) is not a i64/u64 fast field.",
self.field
))
})?;
Ok(ScorerByFastFieldReader { ff_reader })
}
}
impl TopDocs {
/// Creates a top score collector, with a number of documents equal to "limit".
///
@@ -77,13 +107,50 @@ 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.
///
/// ```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.
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{Index, Result, DocAddress};
/// # use tantivy::{doc, Index, DocAddress};
/// # use tantivy::query::{Query, QueryParser};
/// use tantivy::Searcher;
/// use tantivy::collector::TopDocs;
@@ -96,16 +163,13 @@ impl TopDocs {
/// # 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()?;
/// # let reader = index.reader()?;
/// # assert!(index_writer.commit().is_ok());
/// # let reader = index.reader().unwrap();
/// # let query = QueryParser::for_index(&index, vec![title]).parse_query("diary")?;
/// # let top_docs = docs_sorted_by_rating(&reader.searcher(), &query, rating)?;
/// # assert_eq!(top_docs,
@@ -121,9 +185,9 @@ impl TopDocs {
/// ///
/// /// `field` is required to be a FAST field.
/// fn docs_sorted_by_rating(searcher: &Searcher,
/// query: &Query,
/// query: &dyn Query,
/// sort_by_field: Field)
/// -> Result<Vec<(u64, DocAddress)>> {
/// -> tantivy::Result<Vec<(u64, DocAddress)>> {
///
/// // This is where we build our topdocs collector
/// //
@@ -155,14 +219,7 @@ impl TopDocs {
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)
})
self.custom_score(ScorerByField { field })
}
/// Ranks the documents using a custom score.
@@ -190,36 +247,40 @@ impl TopDocs {
/// learning-to-rank model over various features
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{Index, DocAddress, DocId, Score};
/// # use tantivy::{doc, Index, DocAddress, DocId, Score};
/// # use tantivy::query::QueryParser;
/// use tantivy::SegmentReader;
/// 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
@@ -242,19 +303,16 @@ 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
@@ -266,9 +324,9 @@ 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.
@@ -295,10 +353,8 @@ impl TopDocs {
/// # Example
///
/// ```rust
/// # #[macro_use]
/// # extern crate tantivy;
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{Index, DocAddress, DocId};
/// # use tantivy::{doc, Index, DocAddress, DocId};
/// # use tantivy::query::QueryParser;
/// use tantivy::SegmentReader;
/// use tantivy::collector::TopDocs;
@@ -315,7 +371,7 @@ 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();
@@ -382,9 +438,9 @@ 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())
}
}
@@ -397,7 +453,7 @@ 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))
}
@@ -406,9 +462,70 @@ 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`.
@@ -418,7 +535,7 @@ 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)> {
@@ -430,12 +547,12 @@ impl SegmentCollector for TopScoreSegmentCollector {
mod tests {
use super::TopDocs;
use crate::collector::Collector;
use crate::query::{Query, QueryParser};
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 crate::{DocAddress, DocId, SegmentReader};
fn make_index() -> Index {
let mut schema_builder = Schema::builder();
@@ -444,7 +561,7 @@ 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"));
@@ -453,6 +570,13 @@ 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() {
let index = make_index();
@@ -465,16 +589,31 @@ 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();
@@ -487,15 +626,59 @@ 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)),
],
);
}
#[test]
fn test_top_collector_stable_sorting() {
let index = make_index();
// using AllQuery to get a constant score
let searcher = index.reader().unwrap().searcher();
let page_1 = searcher.search(&AllQuery, &TopDocs::with_limit(2)).unwrap();
let page_2 = searcher.search(&AllQuery, &TopDocs::with_limit(3)).unwrap();
// precondition for the test to be meaningful: we did get documents
// with the same score
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);
assert_eq!(page_2.len(), 3);
assert_eq!(page_1, &page_2[..page_1.len()]);
}
#[test]
#[should_panic]
fn test_top_0() {
@@ -530,8 +713,8 @@ 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))
@@ -553,7 +736,7 @@ mod tests {
));
});
let searcher = index.reader().unwrap().searcher();
let top_collector = TopDocs::with_limit(4).order_by_u64_field(Field(2));
let top_collector = TopDocs::with_limit(4).order_by_u64_field(Field::from_field_id(2));
let segment_reader = searcher.segment_reader(0u32);
top_collector
.for_segment(0, segment_reader)
@@ -561,7 +744,6 @@ mod tests {
}
#[test]
#[should_panic(expected = "Field requested is not a i64/u64 fast field")]
fn test_field_not_fast_field() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field(TITLE, TEXT);
@@ -576,7 +758,59 @@ mod tests {
let searcher = index.reader().unwrap().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);
if let Err(crate::TantivyError::SchemaError(msg)) = err {
assert_eq!(
msg,
"Field requested (Field(1)) is not a i64/u64 fast field."
);
} else {
assert!(false);
}
}
#[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(
@@ -584,15 +818,14 @@ mod tests {
query_field: Field,
schema: Schema,
mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
) -> (Index, Box<Query>) {
) -> (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]);
let query = query_parser.parse_query(query).unwrap();
(index, query)
}
}

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)
}
}

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]

20
src/common/composite_file.rs
View File

@@ -2,7 +2,7 @@ use crate::common::BinarySerializable;
use crate::common::CountingWriter;
use crate::common::VInt;
use crate::directory::ReadOnlySource;
use crate::directory::WritePtr;
use crate::directory::{TerminatingWrite, WritePtr};
use crate::schema::Field;
use crate::space_usage::FieldUsage;
use crate::space_usage::PerFieldSpaceUsage;
@@ -42,7 +42,7 @@ pub struct CompositeWrite<W = WritePtr> {
offsets: HashMap<FileAddr, u64>,
}
impl<W: Write> CompositeWrite<W> {
impl<W: TerminatingWrite + Write> CompositeWrite<W> {
/// Crate a new API writer that writes a composite file
/// in a given write.
pub fn wrap(w: W) -> CompositeWrite<W> {
@@ -91,8 +91,7 @@ impl<W: Write> CompositeWrite<W> {
let footer_len = (self.write.written_bytes() - footer_offset) as u32;
footer_len.serialize(&mut self.write)?;
self.write.flush()?;
Ok(())
self.write.terminate()
}
}
@@ -200,13 +199,13 @@ mod test {
let w = directory.open_write(path).unwrap();
let mut composite_write = CompositeWrite::wrap(w);
{
let mut write_0 = composite_write.for_field(Field(0u32));
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(4u32));
let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
VInt(2).serialize(&mut write_4).unwrap();
write_4.flush().unwrap();
}
@@ -216,14 +215,18 @@ mod test {
let r = directory.open_read(path).unwrap();
let composite_file = CompositeFile::open(&r).unwrap();
{
let file0 = composite_file.open_read(Field(0u32)).unwrap();
let file0 = composite_file
.open_read(Field::from_field_id(0u32))
.unwrap();
let mut file0_buf = file0.as_slice();
let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0;
assert_eq!(file0_buf.len(), 0);
assert_eq!(payload_0, 32431123u64);
}
{
let file4 = composite_file.open_read(Field(4u32)).unwrap();
let file4 = composite_file
.open_read(Field::from_field_id(4u32))
.unwrap();
let mut file4_buf = file4.as_slice();
let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
assert_eq!(file4_buf.len(), 0);
@@ -231,5 +234,4 @@ mod test {
}
}
}
}

9
src/common/counting_writer.rs
View File

@@ -1,3 +1,5 @@
use crate::directory::AntiCallToken;
use crate::directory::TerminatingWrite;
use std::io;
use std::io::Write;
@@ -42,6 +44,13 @@ 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)
}
}
#[cfg(test)]
mod test {

54
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
@@ -124,26 +139,25 @@ pub fn f64_to_u64(val: f64) -> u64 {
/// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html).
#[inline(always)]
pub fn u64_to_f64(val: u64) -> f64 {
f64::from_bits(
if val & HIGHEST_BIT != 0 {
val ^ HIGHEST_BIT
} else {
!val
}
)
f64::from_bits(if val & HIGHEST_BIT != 0 {
val ^ HIGHEST_BIT
} else {
!val
})
}
#[cfg(test)]
pub(crate) mod test {
pub use super::minmax;
pub use super::serialize::test::fixed_size_test;
use super::{compute_num_bits, i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
use std::f64;
fn test_i64_converter_helper(val: i64) {
assert_eq!(u64_to_i64(i64_to_u64(val)), val);
}
fn test_f64_converter_helper(val: f64) {
assert_eq!(u64_to_f64(f64_to_u64(val)), val);
}
@@ -172,7 +186,8 @@ pub(crate) mod test {
#[test]
fn test_f64_order() {
assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY)).contains(&f64_to_u64(f64::NAN))); //nan is not a number
assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
.contains(&f64_to_u64(f64::NAN))); //nan is not a number
assert!(f64_to_u64(1.5) > f64_to_u64(1.0)); //same exponent, different mantissa
assert!(f64_to_u64(2.0) > f64_to_u64(1.0)); //same mantissa, different exponent
assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa
@@ -200,4 +215,21 @@ 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)));
}
}

18
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)
@@ -199,10 +212,7 @@ pub mod test {
fn test_serialize_string() {
assert_eq!(serialize_test(String::from("")), 1);
assert_eq!(serialize_test(String::from("ぽよぽよ")), 1 + 3 * 4);
assert_eq!(
serialize_test(String::from("富士さん見える。")),
1 + 3 * 8
);
assert_eq!(serialize_test(String::from("富士さん見える。")), 1 + 3 * 8);
}
#[test]

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);

196
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;
@@ -20,18 +19,21 @@ 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;
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);
IndexMeta::deserialize(&meta_string, &inventory)
@@ -72,15 +74,16 @@ 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`.
@@ -97,28 +100,29 @@ 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) {
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(),
))
}
}
@@ -131,13 +135,13 @@ 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> {
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
let directory = ManagedDirectory::wrap(dir)?;
Index::from_directory(directory, schema)
}
@@ -145,7 +149,7 @@ 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> {
fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
save_new_metas(schema.clone(), directory.borrow_mut())?;
let metas = IndexMeta::with_schema(schema);
Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
@@ -156,7 +160,7 @@ impl Index {
directory: ManagedDirectory,
metas: &IndexMeta,
inventory: SegmentMetaInventory,
) -> Result<Index> {
) -> crate::Result<Index> {
let schema = metas.schema.clone();
Ok(Index {
directory,
@@ -173,11 +177,11 @@ impl Index {
}
/// Helper to access the tokenizer associated to a specific field.
pub fn tokenizer_for_field(&self, field: Field) -> Result<Box<dyn 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<Box<dyn 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())
@@ -196,7 +200,7 @@ 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()
}
@@ -211,17 +215,31 @@ 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)
}
pub(crate) fn inventory(&self) -> &SegmentMetaInventory {
&self.inventory
/// Returns the list of the segment metas tracked by the index.
///
/// Such segments can of course be part of the index,
/// but also they could be segments being currently built or in the middle of a merge
/// operation.
pub fn list_all_segment_metas(&self) -> Vec<SegmentMeta> {
self.inventory.all()
}
/// Creates a new segment_meta (Advanced user only).
///
/// As long as the `SegmentMeta` lives, the files associated with the
/// `SegmentMeta` are guaranteed to not be garbage collected, regardless of
/// whether the segment is recorded as part of the index or not.
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
self.inventory.new_segment_meta(segment_id, max_doc)
}
/// 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)?;
@@ -229,7 +247,7 @@ 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)
}
@@ -257,7 +275,7 @@ 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)
@@ -265,7 +283,7 @@ 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."
@@ -282,6 +300,15 @@ 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.
@@ -292,7 +319,7 @@ 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 {
@@ -309,7 +336,7 @@ 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()
@@ -319,7 +346,7 @@ 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.
@@ -342,18 +369,23 @@ 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()
.map(SegmentMeta::id)
.collect())
}
/// Returns the set of corrupted files
pub fn validate_checksum(&self) -> crate::Result<HashSet<PathBuf>> {
self.directory.list_damaged().map_err(Into::into)
}
}
impl fmt::Debug for Index {
@@ -367,12 +399,9 @@ mod tests {
use crate::directory::RAMDirectory;
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() {
@@ -450,41 +479,39 @@ 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 tempdir::TempDir;
use tempfile::TempDir;
#[test]
fn test_index_on_commit_reload_policy_mmap() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let tempdir = TempDir::new("index").unwrap();
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() {
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();
let mut index = Index::create_from_tempdir(schema).unwrap();
let mut writer = index.writer_for_tests().unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
@@ -493,8 +520,12 @@ mod tests {
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = index.directory_mut().watch(Box::new(move || {
let _ = sender.send(());
}));
writer.commit().unwrap();
thread::sleep(Duration::from_millis(500));
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 0);
reader.reload().unwrap();
assert_eq!(reader.searcher().num_docs(), 1);
@@ -504,7 +535,7 @@ mod tests {
fn test_index_on_commit_reload_policy_different_directories() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let tempdir = TempDir::new("index").unwrap();
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let read_index = Index::open_in_dir(&tempdir_path).unwrap();
@@ -514,39 +545,36 @@ 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(Box::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
@@ -563,9 +591,13 @@ mod tests {
for i in 0u64..8_000u64 {
writer.add_document(doc!(field => i));
}
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = directory.watch(Box::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)
@@ -579,7 +611,11 @@ 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
);
}
}

27
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;
@@ -30,7 +29,6 @@ impl SegmentMetaInventory {
.collect::<Vec<_>>()
}
#[doc(hidden)]
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
let inner = InnerSegmentMeta {
segment_id,
@@ -118,6 +116,7 @@ impl SegmentMeta {
SegmentComponent::FASTFIELDS => ".fast".to_string(),
SegmentComponent::FIELDNORMS => ".fieldnorm".to_string(),
SegmentComponent::DELETE => format!(".{}.del", self.delete_opstamp().unwrap_or(0)),
SegmentComponent::FIELDSTATS => ".fieldstats".to_string(),
});
PathBuf::from(path)
}
@@ -151,6 +150,21 @@ 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 {
@@ -200,7 +214,7 @@ 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>,
@@ -286,6 +300,9 @@ 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}"#
);
}
}

29
src/core/inverted_index_reader.rs
View File

@@ -1,13 +1,10 @@
use crate::common::BinarySerializable;
use crate::directory::ReadOnlySource;
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.
@@ -38,14 +35,12 @@ impl InvertedIndexReader {
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
total_num_tokens: u64,
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 {
termdict,
postings_source: postings_source.slice_from(8),
postings_source,
positions_source,
positions_idx_source,
record_option,
@@ -55,12 +50,9 @@ impl InvertedIndexReader {
/// 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),
termdict: TermDictionary::empty(),
postings_source: ReadOnlySource::empty(),
positions_source: ReadOnlySource::empty(),
positions_idx_source: ReadOnlySource::empty(),
@@ -94,11 +86,10 @@ impl InvertedIndexReader {
term_info: &TermInfo,
block_postings: &mut BlockSegmentPostings,
) {
let offset = term_info.postings_offset as usize;
let offset = term_info.postings_start_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);
block_postings.reset(term_info.doc_freq, postings_slice);
}
/// Returns a block postings given a `Term`.
@@ -123,11 +114,13 @@ impl InvertedIndexReader {
term_info: &TermInfo,
requested_option: IndexRecordOption,
) -> BlockSegmentPostings {
let offset = term_info.postings_offset as usize;
let postings_data = self.postings_source.slice_from(offset);
let postings_data = self.postings_source.slice(
term_info.postings_start_offset as usize,
term_info.postings_end_offset as usize,
);
BlockSegmentPostings::from_data(
term_info.doc_freq,
OwnedRead::new(postings_data),
postings_data,
self.record_option,
requested_option,
)

41
src/core/searcher.rs
View File

@@ -1,11 +1,8 @@
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};
@@ -14,30 +11,9 @@ 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())
}
/// Holds a list of `SegmentReader`s ready for search.
///
/// It guarantees that the `Segment` will not be removed before
@@ -78,7 +54,7 @@ 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)
@@ -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)
}
@@ -154,18 +134,13 @@ 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(),
)?;

38
src/core/segment.rs
View File

@@ -8,10 +8,8 @@ use crate::directory::{ReadOnlySource, 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 +78,14 @@ 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<ReadOnlySource, OpenReadError> {
let path = self.relative_path(component);
let source = self.index.directory().open_read(&path)?;
Ok(source)
}
/// 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 +98,5 @@ 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>;
}

6
src/core/segment_component.rs
View File

@@ -24,14 +24,17 @@ pub enum SegmentComponent {
/// Accessing a document from the store is relatively slow, as it
/// requires to decompress the entire block it belongs to.
STORE,
/// Bitset describing which document of the segment is deleted.
DELETE,
FIELDSTATS,
}
impl SegmentComponent {
/// Iterates through the components.
pub fn iterator() -> slice::Iter<'static, SegmentComponent> {
static SEGMENT_COMPONENTS: [SegmentComponent; 8] = [
static SEGMENT_COMPONENTS: [SegmentComponent; 9] = [
SegmentComponent::POSTINGS,
SegmentComponent::POSITIONS,
SegmentComponent::POSITIONSSKIP,
@@ -40,6 +43,7 @@ impl SegmentComponent {
SegmentComponent::TERMS,
SegmentComponent::STORE,
SegmentComponent::DELETE,
SegmentComponent::FIELDSTATS,
];
SEGMENT_COMPONENTS.iter()
}

56
src/core/segment_id.rs
View File

@@ -4,6 +4,9 @@ use uuid::Uuid;
#[cfg(test)]
use once_cell::sync::Lazy;
use serde::{Deserialize, Serialize};
use std::error::Error;
use std::str::FromStr;
#[cfg(test)]
use std::sync::atomic;
@@ -52,15 +55,51 @@ impl SegmentId {
/// and the rest is random.
///
/// Picking the first 8 chars is ok to identify
/// segments in a display message.
/// segments in a display message (e.g. a5c4dfcb).
pub fn short_uuid_string(&self) -> String {
(&self.0.to_simple_ref().to_string()[..8]).to_string()
}
/// Returns a segment uuid string.
///
/// It consists in 32 lowercase hexadecimal chars
/// (e.g. a5c4dfcbdfe645089129e308e26d5523)
pub fn uuid_string(&self) -> String {
self.0.to_simple_ref().to_string()
}
/// Build a `SegmentId` string from the full uuid string.
///
/// E.g. "a5c4dfcbdfe645089129e308e26d5523"
pub fn from_uuid_string(uuid_string: &str) -> Result<SegmentId, SegmentIdParseError> {
FromStr::from_str(uuid_string)
}
}
/// Error type used when parsing a `SegmentId` from a string fails.
pub struct SegmentIdParseError(uuid::Error);
impl Error for SegmentIdParseError {}
impl fmt::Debug for SegmentIdParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.0.fmt(f)
}
}
impl fmt::Display for SegmentIdParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.0.fmt(f)
}
}
impl FromStr for SegmentId {
type Err = SegmentIdParseError;
fn from_str(uuid_string: &str) -> Result<Self, SegmentIdParseError> {
let uuid = Uuid::parse_str(uuid_string).map_err(SegmentIdParseError)?;
Ok(SegmentId(uuid))
}
}
impl fmt::Debug for SegmentId {
@@ -80,3 +119,18 @@ impl Ord for SegmentId {
self.0.as_bytes().cmp(other.0.as_bytes())
}
}
#[cfg(test)]
mod tests {
use super::SegmentId;
#[test]
fn test_to_uuid_string() {
let full_uuid = "a5c4dfcbdfe645089129e308e26d5523";
let segment_id = SegmentId::from_uuid_string(full_uuid).unwrap();
assert_eq!(segment_id.uuid_string(), full_uuid);
assert_eq!(segment_id.short_uuid_string(), "a5c4dfcb");
// one extra char
assert!(SegmentId::from_uuid_string("a5c4dfcbdfe645089129e308e26d5523b").is_err());
}
}

107
src/core/segment_reader.rs
View File

@@ -1,4 +1,3 @@
use crate::common::CompositeFile;
use crate::common::HasLen;
use crate::core::InvertedIndexReader;
use crate::core::Segment;
@@ -8,15 +7,15 @@ use crate::directory::ReadOnlySource;
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, postings::FieldStats};
use fail::fail_point;
use std::collections::HashMap;
use std::fmt;
@@ -49,7 +48,8 @@ pub struct SegmentReader {
positions_composite: CompositeFile,
positions_idx_composite: CompositeFile,
fast_fields_readers: Arc<FastFieldReaders>,
fieldnorms_composite: CompositeFile,
fieldnorm_readers: FieldNormReaders,
field_stats: FieldStats,
store_source: ReadOnlySource,
delete_bitset_opt: Option<DeleteBitSet>,
@@ -126,17 +126,15 @@ 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_name
);
panic!(err_msg);
}
crate::TantivyError::SchemaError(err_msg)
})
}
/// Accessor to the segment's `StoreReader`.
@@ -145,7 +143,7 @@ impl SegmentReader {
}
/// Open a new segment for reading.
pub fn open(segment: &Segment) -> Result<SegmentReader> {
pub fn open(segment: &Segment) -> crate::Result<SegmentReader> {
let termdict_source = segment.open_read(SegmentComponent::TERMS)?;
let termdict_composite = CompositeFile::open(&termdict_source)?;
@@ -179,8 +177,11 @@ impl SegmentReader {
let fast_field_readers =
Arc::new(FastFieldReaders::load_all(&schema, &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 field_stats_data = segment.open_read(SegmentComponent::FIELDSTATS)?;
let field_stats = FieldStats::from_source(field_stats_data.as_slice())?;
let delete_bitset_opt = if segment.meta().has_deletes() {
let delete_data = segment.open_read(SegmentComponent::DELETE)?;
@@ -196,7 +197,8 @@ impl SegmentReader {
termdict_composite,
postings_composite,
fast_fields_readers: fast_field_readers,
fieldnorms_composite,
fieldnorm_readers,
field_stats,
segment_id: segment.id(),
store_source,
delete_bitset_opt,
@@ -213,6 +215,11 @@ 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.
///
/// 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) -> Arc<InvertedIndexReader> {
if let Some(inv_idx_reader) = self
.inv_idx_reader_cache
@@ -227,21 +234,21 @@ impl SegmentReader {
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_source_opt = self.postings_composite.open_read(field);
if postings_source_opt.is_none() {
if postings_source_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 Arc::new(InvertedIndexReader::empty(record_option));
}
let record_option = record_option_opt.unwrap();
let postings_source = postings_source_opt.unwrap();
let termdict_source = self.termdict_composite.open_read(field).expect(
@@ -258,11 +265,17 @@ impl SegmentReader {
.open_read(field)
.expect("Index corrupted. Failed to open field positions in composite file.");
let total_num_tokens = self
.field_stats
.get(field)
.map(|field_stat| field_stat.num_tokens())
.unwrap_or(0u64);
let inv_idx_reader = Arc::new(InvertedIndexReader::new(
TermDictionary::from_source(&termdict_source),
postings_source,
positions_source,
positions_idx_source,
total_num_tokens,
record_option,
));
@@ -296,8 +309,8 @@ 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<'a>(&'a self) -> impl Iterator<Item = DocId> + 'a {
(0u32..self.max_doc).filter(move |doc| !self.is_deleted(*doc))
}
/// Summarize total space usage of this segment.
@@ -309,7 +322,7 @@ impl SegmentReader {
self.positions_composite.space_usage(),
self.positions_idx_composite.space_usage(),
self.fast_fields_readers.space_usage(),
self.fieldnorms_composite.space_usage(),
self.fieldnorm_readers.space_usage(),
self.get_store_reader().space_usage(),
self.delete_bitset_opt
.as_ref()
@@ -325,52 +338,6 @@ 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;
@@ -386,7 +353,7 @@ 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().unwrap();
index_writer.add_document(doc!(name => "tantivy"));
index_writer.add_document(doc!(name => "horse"));
index_writer.add_document(doc!(name => "jockey"));

10
src/directory/directory.rs
View File

@@ -48,14 +48,14 @@ impl RetryPolicy {
///
/// It is transparently associated to a lock file, that gets deleted
/// on `Drop.` The lock is released automatically on `Drop`.
pub struct DirectoryLock(Box<dyn Drop + Send + Sync + 'static>);
pub struct DirectoryLock(Box<dyn Send + Sync + 'static>);
struct DirectoryLockGuard {
directory: Box<dyn Directory>,
path: PathBuf,
}
impl<T: Drop + Send + Sync + 'static> From<Box<T>> for DirectoryLock {
impl<T: Send + Sync + 'static> From<Box<T>> for DirectoryLock {
fn from(underlying: Box<T>) -> Self {
DirectoryLock(underlying)
}
@@ -118,6 +118,8 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
///
/// Specifically, subsequent writes or flushes should
/// have no effect on the returned `ReadOnlySource` object.
///
/// You should only use this to read files create with [Directory::open_write].
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
/// Removes a file
@@ -157,6 +159,8 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// atomic_write.
///
/// This should only be used for small files.
///
/// 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.
@@ -193,7 +197,7 @@ 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

84
src/directory/error.rs
View File

@@ -1,3 +1,4 @@
use crate::Version;
use std::error::Error as StdError;
use std::fmt;
use std::io;
@@ -156,6 +157,65 @@ impl StdError for OpenWriteError {
}
}
/// 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::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)?;
}
}
Ok(())
}
}
/// Error that may occur when accessing a file read
#[derive(Debug)]
pub enum OpenReadError {
@@ -164,6 +224,8 @@ pub enum OpenReadError {
/// Any kind of IO error that happens when
/// interacting with the underlying IO device.
IOError(IOError),
/// This library doesn't support the index version found on disk
IncompatibleIndex(Incompatibility),
}
impl From<IOError> for OpenReadError {
@@ -183,19 +245,9 @@ impl fmt::Display for OpenReadError {
"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),
OpenReadError::IncompatibleIndex(ref footer) => {
write!(f, "Incompatible index format: {:?}", footer)
}
}
}
}
@@ -216,6 +268,12 @@ impl From<IOError> for DeleteError {
}
}
impl From<Incompatibility> for OpenReadError {
fn from(incompatibility: Incompatibility) -> Self {
OpenReadError::IncompatibleIndex(incompatibility)
}
}
impl fmt::Display for DeleteError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {

394
src/directory/footer.rs Normal file
View File

@@ -0,0 +1,394 @@
use crate::common::{BinarySerializable, CountingWriter, FixedSize, VInt};
use crate::directory::error::Incompatibility;
use crate::directory::read_only_source::ReadOnlySource;
use crate::directory::{AntiCallToken, TerminatingWrite};
use crate::Version;
use byteorder::{ByteOrder, LittleEndian, WriteBytesExt};
use crc32fast::Hasher;
use std::io;
use std::io::Write;
const FOOTER_MAX_LEN: usize = 10_000;
type CrcHashU32 = u32;
#[derive(Debug, Clone, PartialEq)]
pub struct Footer {
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 version = crate::VERSION.clone();
let meta = version.to_string();
Footer {
version,
meta,
versioned_footer,
}
}
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();
write.write_u32::<LittleEndian>(written_len as u32)?;
Ok(())
}
pub fn extract_footer(source: ReadOnlySource) -> Result<(Footer, ReadOnlySource), io::Error> {
if source.len() < 4 {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The file is smaller than 4 bytes (len={}).",
source.len()
),
));
}
let (body_footer, footer_len_bytes) = source.split_from_end(u32::SIZE_IN_BYTES);
let footer_len = LittleEndian::read_u32(footer_len_bytes.as_slice()) as usize;
let body_len = body_footer.len() - footer_len;
let (body, footer_data) = body_footer.split(body_len);
let mut cursor = footer_data.as_slice();
let footer = Footer::deserialize(&mut cursor)?;
Ok((footer, body))
}
/// 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(())
}
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::UnknownVersion => Err(Incompatibility::IndexMismatch {
library_version: library_version.clone(),
index_version: self.version.clone(),
}),
}
}
}
/// 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,
},
}
impl BinarySerializable for VersionedFooter {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
let mut buf = Vec::new();
match self {
VersionedFooter::V2 {
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(&2u32, &mut buf)?;
BinarySerializable::serialize(crc32, &mut buf)?;
BinarySerializable::serialize(compression, &mut buf)?;
}
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(())
}
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 != 1 && version != 2 {
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 {
assert_eq!(version, 2);
VersionedFooter::V2 {
crc32,
store_compression,
}
})
}
}
impl VersionedFooter {
pub fn crc(&self) -> Option<CrcHashU32> {
match self {
VersionedFooter::V2 { crc32, .. } => Some(*crc32),
VersionedFooter::V1 { crc32, .. } => Some(*crc32),
VersionedFooter::UnknownVersion { .. } => None,
}
}
}
pub(crate) struct FooterProxy<W: TerminatingWrite> {
/// always Some except after terminate call
hasher: Option<Hasher>,
/// always Some except after terminate call
writer: Option<W>,
}
impl<W: TerminatingWrite> FooterProxy<W> {
pub fn new(writer: W) -> Self {
FooterProxy {
hasher: Some(Hasher::new()),
writer: Some(writer),
}
}
}
impl<W: TerminatingWrite> Write for FooterProxy<W> {
fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
let count = self.writer.as_mut().unwrap().write(buf)?;
self.hasher.as_mut().unwrap().update(&buf[..count]);
Ok(count)
}
fn flush(&mut self) -> io::Result<()> {
self.writer.as_mut().unwrap().flush()
}
}
impl<W: TerminatingWrite> TerminatingWrite for FooterProxy<W> {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
let crc32 = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V2 {
crc32,
store_compression: crate::store::COMPRESSION.to_string(),
});
let mut writer = self.writer.take().unwrap();
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::V2 { store_compression, .. }
if store_compression == crate::store::COMPRESSION
));
assert_eq!(&footer.version, crate::version());
}
#[test]
fn test_serialize_deserialize_footer() {
let mut buffer = Vec::new();
let crc32 = 123456u32;
let footer: Footer = Footer::new(VersionedFooter::V2 {
crc32,
store_compression: "lz4".to_string(),
});
footer.serialize(&mut buffer).unwrap();
let footer_deser = Footer::deserialize(&mut &buffer[..]).unwrap();
assert_eq!(footer_deser, footer);
}
#[test]
fn footer_length() {
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V2 {
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
2,
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::V2 {
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."
);
}
}

169
src/directory/managed_directory.rs
View File

@@ -1,14 +1,16 @@
use crate::core::MANAGED_FILEPATH;
use crate::core::{MANAGED_FILEPATH, META_FILEPATH};
use crate::directory::error::{DeleteError, IOError, 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::{WatchCallback, WatchHandle};
use crate::error::DataCorruption;
use crate::Directory;
use crate::Result;
use serde_json;
use crc32fast::Hasher;
use std::collections::HashSet;
use std::io;
use std::io::Write;
@@ -62,7 +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);
@@ -85,6 +87,11 @@ impl ManagedDirectory {
meta_informations: Arc::default(),
}),
Err(OpenReadError::IOError(e)) => Err(From::from(e)),
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))
}
}
}
@@ -102,7 +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![];
@@ -128,19 +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(_) => {
@@ -150,9 +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(_) => {
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.
@@ -175,10 +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
@@ -207,17 +227,62 @@ impl ManagedDirectory {
}
Ok(())
}
/// 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 mut hasher = Hasher::new();
hasher.update(data.as_slice());
let crc = hasher.finalize();
Ok(footer
.versioned_footer
.crc()
.map(|v| v == crc)
.unwrap_or(false))
}
/// 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 mut managed_paths = self
.meta_informations
.read()
.expect("Managed directory rlock poisoned in list damaged.")
.managed_paths
.clone();
managed_paths.remove(*META_FILEPATH);
for path in managed_paths.into_iter() {
if !self.validate_checksum(&path)? {
hashset.insert(path);
}
}
Ok(hashset)
}
}
impl Directory for ManagedDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
self.directory.open_read(path)
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))?;
footer.is_compatible()?;
Ok(reader)
}
fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
self.register_file_as_managed(path)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
self.directory.open_write(path)
Ok(io::BufWriter::new(Box::new(FooterProxy::new(
self.directory
.open_write(path)?
.into_inner()
.map_err(|_| ())
.expect("buffer should be empty"),
))))
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
@@ -259,15 +324,16 @@ impl Clone for ManagedDirectory {
#[cfg(test)]
mod tests_mmap_specific {
use crate::directory::{Directory, ManagedDirectory, MmapDirectory};
use crate::directory::{Directory, ManagedDirectory, MmapDirectory, TerminatingWrite};
use std::collections::HashSet;
use std::fs::OpenOptions;
use std::io::Write;
use std::path::{Path, PathBuf};
use tempdir::TempDir;
use tempfile::TempDir;
#[test]
fn test_managed_directory() {
let tempdir = TempDir::new("tantivy-test").unwrap();
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let test_path1: &'static Path = Path::new("some_path_for_test");
@@ -275,16 +341,15 @@ mod tests_mmap_specific {
{
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let mut write_file = managed_directory.open_write(test_path1).unwrap();
write_file.flush().unwrap();
let write_file = managed_directory.open_write(test_path1).unwrap();
write_file.terminate().unwrap();
managed_directory
.atomic_write(test_path2, &[0u8, 1u8])
.unwrap();
assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path2));
let living_files: HashSet<PathBuf> =
[test_path1.to_owned()].into_iter().cloned().collect();
managed_directory.garbage_collect(|| living_files);
let living_files: HashSet<PathBuf> = [test_path1.to_owned()].iter().cloned().collect();
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
}
@@ -294,7 +359,7 @@ mod tests_mmap_specific {
assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
let living_files: HashSet<PathBuf> = HashSet::new();
managed_directory.garbage_collect(|| living_files);
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(!managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
}
@@ -304,19 +369,21 @@ mod tests_mmap_specific {
fn test_managed_directory_gc_while_mmapped() {
let test_path1: &'static Path = Path::new("some_path_for_test");
let tempdir = TempDir::new("index").unwrap();
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let living_files = HashSet::new();
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
managed_directory
.atomic_write(test_path1, &vec![0u8, 1u8])
.unwrap();
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));
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));
@@ -324,11 +391,47 @@ mod tests_mmap_specific {
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.garbage_collect(|| living_files).is_ok());
assert!(!managed_directory.exists(test_path1));
} else {
assert!(!managed_directory.exists(test_path1));
}
}
#[test]
fn test_checksum() {
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 mut write = managed_directory.open_write(test_path2).unwrap();
write.write_all(&[3u8, 4u8, 5u8]).unwrap();
write.terminate().unwrap();
let read_source = managed_directory.open_read(test_path2).unwrap();
assert_eq!(read_source.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();
drop(file);
let damaged = managed_directory.list_damaged().unwrap();
assert_eq!(damaged.len(), 1);
assert!(damaged.contains(test_path2));
}
}

164
src/directory/mmap_directory.rs
View File

@@ -1,16 +1,10 @@
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::Directory;
use crate::directory::DirectoryLock;
use crate::directory::Lock;
@@ -18,9 +12,13 @@ use crate::directory::ReadOnlySource;
use crate::directory::WatchCallback;
use crate::directory::WatchCallbackList;
use crate::directory::WatchHandle;
use crate::directory::WritePtr;
use atomicwrites;
use crate::directory::{TerminatingWrite, WritePtr};
use fs2::FileExt;
use memmap::Mmap;
use notify::RawEvent;
use notify::RecursiveMode;
use notify::Watcher;
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
use std::convert::From;
use std::fmt;
@@ -36,7 +34,7 @@ use std::sync::Mutex;
use std::sync::RwLock;
use std::sync::Weak;
use std::thread;
use tempdir::TempDir;
use tempfile::TempDir;
/// Create a default io error given a string.
pub(crate) fn make_io_err(msg: String) -> io::Error {
@@ -130,53 +128,38 @@ impl MmapCache {
}
self.cache.remove(full_path);
self.counters.miss += 1;
Ok(if let Some(mmap) = open_mmap(full_path)? {
let mmap_opt = open_mmap(full_path)?;
Ok(mmap_opt.map(|mmap| {
let mmap_arc: Arc<BoxedData> = Arc::new(Box::new(mmap));
let mmap_weak = Arc::downgrade(&mmap_arc);
self.cache.insert(full_path.to_owned(), mmap_weak);
Some(mmap_arc)
} else {
None
})
mmap_arc
}))
}
}
struct InnerWatcherWrapper {
_watcher: Mutex<notify::RecommendedWatcher>,
watcher_router: WatchCallbackList,
}
impl InnerWatcherWrapper {
pub fn new(path: &Path) -> Result<(Self, Receiver<notify::RawEvent>), notify::Error> {
let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
// We need to initialize the
let mut watcher = notify::raw_watcher(tx)?;
watcher.watch(path, RecursiveMode::Recursive)?;
let inner = InnerWatcherWrapper {
_watcher: Mutex::new(watcher),
watcher_router: Default::default(),
};
Ok((inner, watcher_recv))
}
}
#[derive(Clone)]
struct WatcherWrapper {
inner: Arc<InnerWatcherWrapper>,
_watcher: Mutex<notify::RecommendedWatcher>,
watcher_router: Arc<WatchCallbackList>,
}
impl WatcherWrapper {
pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
let (inner, watcher_recv) = InnerWatcherWrapper::new(path).map_err(|err| match err {
notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()),
_ => {
panic!("Unknown error while starting watching directory {:?}", path);
}
})?;
let watcher_wrapper = WatcherWrapper {
inner: Arc::new(inner),
};
let watcher_wrapper_clone = watcher_wrapper.clone();
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 || {
@@ -187,7 +170,7 @@ impl WatcherWrapper {
// 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_wrapper_clone.inner.watcher_router.broadcast();
let _ = watcher_router_clone.broadcast();
}
}
}
@@ -200,13 +183,15 @@ impl WatcherWrapper {
}
}
}
})
.expect("Failed to spawn thread to watch meta.json");
Ok(watcher_wrapper)
})?;
Ok(WatcherWrapper {
_watcher: Mutex::new(watcher),
watcher_router,
})
}
pub fn watch(&mut self, watch_callback: WatchCallback) -> WatchHandle {
self.inner.watcher_router.subscribe(watch_callback)
self.watcher_router.subscribe(watch_callback)
}
}
@@ -235,17 +220,13 @@ struct MmapDirectoryInner {
}
impl MmapDirectoryInner {
fn new(
root_path: PathBuf,
temp_directory: Option<TempDir>,
) -> Result<MmapDirectoryInner, OpenDirectoryError> {
let mmap_directory_inner = MmapDirectoryInner {
fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectoryInner {
MmapDirectoryInner {
root_path,
mmap_cache: Default::default(),
_temp_directory: temp_directory,
watcher: RwLock::new(None),
};
Ok(mmap_directory_inner)
}
}
fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle> {
@@ -265,7 +246,7 @@ impl MmapDirectoryInner {
}
}
if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() {
return Ok(watch_wrapper.watch(watch_callback));
Ok(watch_wrapper.watch(watch_callback))
} else {
unreachable!("At this point, watch wrapper is supposed to be initialized");
}
@@ -279,14 +260,11 @@ 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.
@@ -294,9 +272,9 @@ 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("index").map_err(OpenDirectoryError::IoError)?;
let tempdir = TempDir::new().map_err(OpenDirectoryError::IoError)?;
let tempdir_path = PathBuf::from(tempdir.path());
MmapDirectory::new(tempdir_path, Some(tempdir))
Ok(MmapDirectory::new(tempdir_path, Some(tempdir)))
}
/// Opens a MmapDirectory in a directory.
@@ -314,7 +292,7 @@ impl MmapDirectory {
directory_path,
)))
} else {
Ok(MmapDirectory::new(PathBuf::from(directory_path), None)?)
Ok(MmapDirectory::new(PathBuf::from(directory_path), None))
}
}
@@ -412,6 +390,12 @@ impl Seek for SafeFileWriter {
}
}
impl TerminatingWrite for SafeFileWriter {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
impl Directory for MmapDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
debug!("Open Read {:?}", path);
@@ -503,11 +487,13 @@ impl Directory for MmapDirectory {
}
}
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fn atomic_write(&mut self, path: &Path, content: &[u8]) -> io::Result<()> {
debug!("Atomic Write {:?}", path);
let mut tempfile = tempfile::Builder::new().tempfile_in(&self.inner.root_path)?;
tempfile.write_all(content)?;
tempfile.flush()?;
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))?;
tempfile.into_temp_path().persist(full_path)?;
Ok(())
}
@@ -543,16 +529,15 @@ mod tests {
// The following tests are specific to the MmapDirectory
use super::*;
use crate::indexer::LogMergePolicy;
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;
#[test]
fn test_open_non_existant_path() {
fn test_open_non_existent_path() {
assert!(MmapDirectory::open(PathBuf::from("./nowhere")).is_err());
}
@@ -642,16 +627,21 @@ mod tests {
fn test_watch_wrapper() {
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let tmp_dir: TempDir = tempdir::TempDir::new("test_watch_wrapper").unwrap();
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 tmp_file = tmp_dirpath.join(*META_FILEPATH);
let _handle = watch_wrapper.watch(Box::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
}));
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle2 = watch_wrapper.watch(Box::new(move || {
let _ = sender.send(());
}));
assert_eq!(counter.load(Ordering::SeqCst), 0);
fs::write(&tmp_file, b"whateverwilldo").unwrap();
thread::sleep(Duration::new(0, 1_000u32));
assert!(receiver.recv().is_ok());
assert!(counter.load(Ordering::SeqCst) >= 1);
}
#[test]
@@ -660,34 +650,42 @@ mod tests {
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());
}
}

63
src/directory/mod.rs
View File

@@ -9,6 +9,7 @@ mod mmap_directory;
mod directory;
mod directory_lock;
mod footer;
mod managed_directory;
mod ram_directory;
mod read_only_source;
@@ -22,20 +23,74 @@ pub use self::directory::{Directory, DirectoryClone};
pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
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};
use std::io::{BufWriter, Write};
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;
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
pub trait TerminatingWrite: Write {
/// Indicate that the writer will no longer be used. Internally call terminate_ref.
fn terminate(mut self) -> io::Result<()>
where
Self: Sized,
{
self.terminate_ref(AntiCallToken(()))
}
/// You should implement this function to define custom behavior.
/// This function should flush any buffer it may hold.
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()>;
}
impl<W: TerminatingWrite + ?Sized> TerminatingWrite for Box<W> {
fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
self.as_mut().terminate_ref(token)
}
}
impl<W: TerminatingWrite> TerminatingWrite for BufWriter<W> {
fn terminate_ref(&mut self, a: AntiCallToken) -> io::Result<()> {
self.flush()?;
self.get_mut().terminate_ref(a)
}
}
#[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
/// and Seek.
pub type WritePtr = BufWriter<Box<dyn Write>>;
pub type WritePtr = BufWriter<Box<dyn TerminatingWrite>>;
#[cfg(test)]
mod tests;

56
src/directory/ram_directory.rs
View File

@@ -1,8 +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::WritePtr;
use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
use crate::directory::{TerminatingWrite, WritePtr};
use fail::fail_point;
use std::collections::HashMap;
use std::fmt;
@@ -71,6 +72,12 @@ impl Write for VecWriter {
}
}
impl TerminatingWrite for VecWriter {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
#[derive(Default)]
struct InnerDirectory {
fs: HashMap<PathBuf, ReadOnlySource>,
@@ -137,6 +144,22 @@ 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: &mut dyn Directory) -> crate::Result<()> {
let wlock = self.fs.write().unwrap();
for (path, source) in wlock.fs.iter() {
let mut dest_wrt = dest.open_write(path)?;
dest_wrt.write_all(source.as_slice())?;
dest_wrt.terminate()?;
}
Ok(())
}
}
impl Directory for RAMDirectory {
@@ -177,18 +200,18 @@ impl Directory for RAMDirectory {
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
io::ErrorKind::Other,
msg.unwrap_or("Undefined".to_string())
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(), &[]);
let mut vec_writer = VecWriter::new(path_buf.clone(), self.clone());
let mut vec_writer = VecWriter::new(path_buf, self.clone());
vec_writer.write_all(data)?;
vec_writer.flush()?;
if path == Path::new(&*META_FILEPATH) {
self.fs.write().unwrap().watch_router.broadcast();
let _ = self.fs.write().unwrap().watch_router.broadcast();
}
Ok(())
}
@@ -197,3 +220,28 @@ 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 mut 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 mut directory_copy = RAMDirectory::create();
assert!(directory.persist(&mut 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);
}
}

6
src/directory/read_only_source.rs
View File

@@ -70,6 +70,12 @@ impl ReadOnlySource {
(left, right)
}
/// Splits into 2 `ReadOnlySource`, at the offset `end - right_len`.
pub fn split_from_end(self, right_len: usize) -> (ReadOnlySource, ReadOnlySource) {
let left_len = self.len() - right_len;
self.split(left_len)
}
/// Creates a ReadOnlySource that is just a
/// view over a slice of the data.
///

185
src/directory/tests.rs
View File

@@ -1,25 +1,117 @@
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() {
let mut directory = make_directory();
super::test_simple(&mut directory);
}
#[test]
fn test_write_create_the_file() {
let mut directory = make_directory();
super::test_write_create_the_file(&mut directory);
}
#[test]
fn test_rewrite_forbidden() {
let mut directory = make_directory();
super::test_rewrite_forbidden(&mut directory);
}
#[test]
fn test_directory_delete() {
let mut directory = make_directory();
super::test_directory_delete(&mut directory);
}
#[test]
fn test_lock_non_blocking() {
let mut directory = make_directory();
super::test_lock_non_blocking(&mut directory);
}
#[test]
fn test_lock_blocking() {
let mut directory = make_directory();
super::test_lock_blocking(&mut directory);
}
#[test]
fn test_watch() {
let mut directory = make_directory();
super::test_watch(&mut 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() {
let mut directory = make_directory();
super::test_simple(&mut directory);
}
#[test]
fn test_write_create_the_file() {
let mut directory = make_directory();
super::test_write_create_the_file(&mut directory);
}
#[test]
fn test_rewrite_forbidden() {
let mut directory = make_directory();
super::test_rewrite_forbidden(&mut directory);
}
#[test]
fn test_directory_delete() {
let mut directory = make_directory();
super::test_directory_delete(&mut directory);
}
#[test]
fn test_lock_non_blocking() {
let mut directory = make_directory();
super::test_lock_non_blocking(&mut directory);
}
#[test]
fn test_lock_blocking() {
let mut directory = make_directory();
super::test_lock_blocking(&mut directory);
}
#[test]
fn test_watch() {
let mut directory = make_directory();
super::test_watch(&mut directory);
}
}
#[test]
@@ -99,48 +191,39 @@ fn test_directory_delete(directory: &mut dyn Directory) {
assert!(directory.delete(&test_path).is_err());
}
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) {
let num_progress: Arc<AtomicUsize> = Default::default();
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let (sender, receiver) = crossbeam::channel::unbounded();
let watch_callback = Box::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
counter_clone.fetch_add(1, 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));
// This callback is used to synchronize watching in our unit test.
// We bind it to a variable because the callback is removed when that
// handle is dropped.
let watch_handle = directory.watch(watch_callback).unwrap();
let _progress_listener = directory
.watch(Box::new(move || {
let val = num_progress.fetch_add(1, SeqCst);
let _ = sender.send(val);
}))
.unwrap();
for i in 0..10 {
assert_eq!(i, counter.load(Ordering::SeqCst));
assert!(i <= counter.load(SeqCst));
assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data_2")
.is_ok());
for _ in 0..100 {
if counter.load(Ordering::SeqCst) > i {
break;
}
thread::sleep(Duration::from_millis(10));
}
assert_eq!(i + 1, counter.load(Ordering::SeqCst));
assert_eq!(receiver.recv_timeout(Duration::from_millis(500)), Ok(i));
assert!(i + 1 <= counter.load(SeqCst)); // notify can trigger more than once.
}
mem::drop(watch_handle);
assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data")
.is_ok());
thread::sleep(Duration::from_millis(200));
assert_eq!(10, counter.load(Ordering::SeqCst));
assert!(receiver.recv_timeout(Duration::from_millis(500)).is_ok());
assert!(10 <= counter.load(SeqCst));
}
fn test_lock_non_blocking(directory: &mut dyn Directory) {
@@ -174,9 +257,13 @@ fn test_lock_blocking(directory: &mut dyn Directory) {
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 +276,18 @@ 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());
}

82
src/directory/watch_event_router.rs
View File

@@ -1,9 +1,11 @@
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>;
pub type WatchCallback = Box<dyn Fn() + Sync + Send>;
/// Helper struct to implement the watch method in `Directory` implementations.
///
@@ -22,13 +24,20 @@ 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)
}
}
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>> {
@@ -47,14 +56,21 @@ 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();
}
let _ = sender.send(());
});
if let Err(err) = spawn_res {
error!(
@@ -62,19 +78,17 @@ impl WatchCallbackList {
err
);
}
result
}
}
#[cfg(test)]
mod tests {
use crate::directory::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() {
@@ -84,22 +98,22 @@ mod tests {
let inc_callback = Box::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));
}
@@ -115,20 +129,20 @@ mod tests {
};
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));
}
@@ -142,15 +156,15 @@ mod tests {
});
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));
}
}

131
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 {
/// 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 +104,42 @@ 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()
}
}
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 +161,4 @@ 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);
}
}

15
src/error.rs
View File

@@ -2,12 +2,11 @@
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 std::fmt;
use std::path::PathBuf;
use std::sync::PoisonError;
@@ -80,6 +79,9 @@ pub enum TantivyError {
/// System error. (e.g.: We failed spawning a new thread)
#[fail(display = "System error.'{}'", _0)]
SystemError(String),
/// Index incompatible with current version of tantivy
#[fail(display = "{:?}", _0)]
IncompatibleIndex(Incompatibility),
}
impl From<DataCorruption> for TantivyError {
@@ -129,6 +131,9 @@ impl From<OpenReadError> for TantivyError {
match error {
OpenReadError::FileDoesNotExist(filepath) => TantivyError::PathDoesNotExist(filepath),
OpenReadError::IOError(io_error) => TantivyError::IOError(io_error),
OpenReadError::IncompatibleIndex(incompatibility) => {
TantivyError::IncompatibleIndex(incompatibility)
}
}
}
}
@@ -170,3 +175,9 @@ impl From<serde_json::Error> for TantivyError {
TantivyError::IOError(io_err.into())
}
}
impl From<rayon::ThreadPoolBuildError> for TantivyError {
fn from(error: rayon::ThreadPoolBuildError) -> TantivyError {
TantivyError::SystemError(error.to_string())
}
}

2
src/fastfield/bytes/mod.rs
View File

@@ -15,7 +15,7 @@ mod tests {
let field = schema_builder.add_bytes_field("bytesfield");
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=>vec![0u8, 1, 2, 3]));
index_writer.add_document(doc!(field=>vec![]));
index_writer.add_document(doc!(field=>vec![255u8]));

88
src/fastfield/delete.rs
View File

@@ -1,17 +1,21 @@
use crate::common::HasLen;
use crate::common::{BitSet, HasLen};
use crate::directory::ReadOnlySource;
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 {
@@ -29,7 +33,7 @@ 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.
@@ -40,6 +44,24 @@ pub struct DeleteBitSet {
}
impl DeleteBitSet {
#[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 mut 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 source = directory.open_read(path).unwrap();
Self::open(source)
}
/// Opens a delete bitset given its data source.
pub fn open(data: ReadOnlySource) -> DeleteBitSet {
let num_deleted: usize = data
@@ -81,45 +103,35 @@ 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);
}
}

135
src/fastfield/mod.rs
View File

@@ -33,6 +33,7 @@ pub use self::reader::FastFieldReader;
pub use self::readers::FastFieldReaders;
pub use self::serializer::FastFieldSerializer;
pub use self::writer::{FastFieldsWriter, IntFastFieldWriter};
use crate::chrono::{NaiveDateTime, Utc};
use crate::common;
use crate::schema::Cardinality;
use crate::schema::FieldType;
@@ -49,7 +50,7 @@ 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 +70,12 @@ 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())
}
}
impl FastValue for u64 {
@@ -135,11 +142,34 @@ impl FastValue for 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 value_to_u64(value: &Value) -> u64 {
match *value {
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 +181,12 @@ 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 once_cell::sync::Lazy;
use rand::prelude::SliceRandom;
use rand::rngs::StdRng;
@@ -178,6 +210,12 @@ mod tests {
assert_eq!(test_fastfield.get(2), 300);
}
#[test]
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() {
let path = Path::new("test");
@@ -430,6 +468,92 @@ mod tests {
}
}
#[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);
}
}
}
#[cfg(all(test, feature = "unstable"))]
@@ -437,9 +561,9 @@ mod bench {
use super::tests::FIELD;
use super::tests::{generate_permutation, SCHEMA};
use super::*;
use common::CompositeFile;
use directory::{Directory, RAMDirectory, WritePtr};
use fastfield::FastFieldReader;
use crate::common::CompositeFile;
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::FastFieldReader;
use std::collections::HashMap;
use std::path::Path;
use test::{self, Bencher};
@@ -537,5 +661,4 @@ mod bench {
});
}
}
}

12
src/fastfield/multivalued/mod.rs
View File

@@ -7,9 +7,6 @@ pub use self::writer::MultiValueIntFastFieldWriter;
#[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),
@@ -188,7 +186,7 @@ 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));
@@ -223,7 +221,7 @@ 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())));
}

4
src/fastfield/multivalued/reader.rs
View File

@@ -45,7 +45,7 @@ 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 +74,7 @@ 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"),

9
src/fastfield/multivalued/writer.rs
View File

@@ -5,8 +5,7 @@ use crate::postings::UnorderedTermId;
use crate::schema::{Document, Field};
use crate::termdict::TermOrdinal;
use crate::DocId;
use itertools::Itertools;
use std::collections::HashMap;
use fnv::FnvHashMap;
use std::io;
/// Writer for multi-valued (as in, more than one value per document)
@@ -102,7 +101,7 @@ impl MultiValueIntFastFieldWriter {
pub fn serialize(
&self,
serializer: &mut FastFieldSerializer,
mapping_opt: Option<&HashMap<UnorderedTermId, TermOrdinal>>,
mapping_opt: Option<&FnvHashMap<UnorderedTermId, TermOrdinal>>,
) -> io::Result<()> {
{
// writing the offset index
@@ -151,8 +150,8 @@ impl MultiValueIntFastFieldWriter {
}
}
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 {

53
src/fastfield/readers.rs
View File

@@ -4,7 +4,6 @@ use crate::fastfield::MultiValueIntFastFieldReader;
use crate::fastfield::{FastFieldNotAvailableError, FastFieldReader};
use crate::schema::{Cardinality, Field, FieldType, Schema};
use crate::space_usage::PerFieldSpaceUsage;
use crate::Result;
use std::collections::HashMap;
/// Provides access to all of the FastFieldReader.
@@ -15,9 +14,11 @@ 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_date: HashMap<Field, FastFieldReader<crate::DateTime>>,
fast_field_i64s: HashMap<Field, MultiValueIntFastFieldReader<i64>>,
fast_field_u64s: HashMap<Field, MultiValueIntFastFieldReader<u64>>,
fast_field_f64s: HashMap<Field, MultiValueIntFastFieldReader<f64>>,
fast_field_dates: HashMap<Field, MultiValueIntFastFieldReader<crate::DateTime>>,
fast_bytes: HashMap<Field, BytesFastFieldReader>,
fast_fields_composite: CompositeFile,
}
@@ -26,6 +27,7 @@ enum FastType {
I64,
U64,
F64,
Date,
}
fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality)> {
@@ -39,6 +41,9 @@ 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,
}
@@ -48,19 +53,20 @@ impl FastFieldReaders {
pub(crate) fn load_all(
schema: &Schema,
fast_fields_composite: &CompositeFile,
) -> Result<FastFieldReaders> {
) -> crate::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_date: Default::default(),
fast_field_i64s: Default::default(),
fast_field_u64s: Default::default(),
fast_field_f64s: Default::default(),
fast_field_dates: Default::default(),
fast_bytes: Default::default(),
fast_fields_composite: fast_fields_composite.clone(),
};
for (field_id, field_entry) in schema.fields().iter().enumerate() {
let field = Field(field_id as u32);
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
@@ -96,6 +102,12 @@ impl FastFieldReaders {
FastFieldReader::open(fast_field_data.clone()),
);
}
FastType::Date => {
fast_field_readers.fast_field_date.insert(
field,
FastFieldReader::open(fast_field_data.clone()),
);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
@@ -131,6 +143,14 @@ impl FastFieldReaders {
.fast_field_f64s
.insert(field, multivalued_int_fast_field);
}
FastType::Date => {
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_dates
.insert(field, multivalued_int_fast_field);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
@@ -157,8 +177,6 @@ impl FastFieldReaders {
/// 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) {
@@ -167,6 +185,12 @@ impl FastFieldReaders {
if let Some(i64_ff_reader) = self.i64(field) {
return Some(i64_ff_reader.into_u64_reader());
}
if let Some(f64_ff_reader) = self.f64(field) {
return Some(f64_ff_reader.into_u64_reader());
}
if let Some(date_ff_reader) = self.date(field) {
return Some(date_ff_reader.into_u64_reader());
}
None
}
@@ -177,6 +201,13 @@ impl FastFieldReaders {
self.fast_field_i64.get(&field).cloned()
}
/// 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) -> Option<FastFieldReader<crate::DateTime>> {
self.fast_field_date.get(&field).cloned()
}
/// Returns the `f64` fast field reader reader associated to `field`.
///
/// If `field` is not a f64 fast field, this method returns `None`.
@@ -203,6 +234,9 @@ impl FastFieldReaders {
if let Some(i64s_ff_reader) = self.i64s(field) {
return Some(i64s_ff_reader.into_u64s_reader());
}
if let Some(f64s_ff_reader) = self.f64s(field) {
return Some(f64s_ff_reader.into_u64s_reader());
}
None
}
@@ -220,6 +254,13 @@ impl FastFieldReaders {
self.fast_field_f64s.get(&field).cloned()
}
/// 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) -> Option<MultiValueIntFastFieldReader<crate::DateTime>> {
self.fast_field_dates.get(&field).cloned()
}
/// Returns the `bytes` fast field reader associated to `field`.
///
/// If `field` is not a bytes fast field, returns `None`.

27
src/fastfield/writer.rs
View File

@@ -4,8 +4,9 @@ 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;
use std::io;
@@ -16,6 +17,14 @@ pub struct FastFieldsWriter {
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 {
@@ -23,18 +32,16 @@ impl FastFieldsWriter {
let mut multi_values_writers = Vec::new();
let mut bytes_value_writers = Vec::new();
for (field_id, field_entry) in schema.fields().iter().enumerate() {
let field = Field(field_id as u32);
let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
};
for (field, field_entry) in schema.fields() {
match *field_entry.field_type() {
FieldType::I64(ref int_options) | FieldType::U64(ref int_options) | FieldType::F64(ref int_options) => {
FieldType::I64(ref int_options)
| FieldType::U64(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);
}
@@ -114,7 +121,7 @@ impl FastFieldsWriter {
pub fn serialize(
&self,
serializer: &mut FastFieldSerializer,
mapping: &HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>>,
mapping: &HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>,
) -> io::Result<()> {
for field_writer in &self.single_value_writers {
field_writer.serialize(serializer)?;

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;

67
src/fieldnorm/reader.rs
View File

@@ -1,6 +1,41 @@
use super::{fieldnorm_to_id, id_to_fieldnorm};
use crate::common::CompositeFile;
use crate::directory::ReadOnlySource;
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(source: ReadOnlySource) -> crate::Result<FieldNormReaders> {
let data = CompositeFile::open(&source)?;
Ok(FieldNormReaders {
data: Arc::new(data),
})
}
/// Returns the FieldNormReader for a specific field.
pub fn get_field(&self, field: Field) -> Option<FieldNormReader> {
self.data.open_read(field).map(FieldNormReader::open)
}
/// 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
@@ -19,6 +54,7 @@ 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.
#[derive(Clone)]
pub struct FieldNormReader {
data: ReadOnlySource,
}
@@ -29,6 +65,11 @@ impl FieldNormReader {
FieldNormReader { data }
}
/// Returns the number of documents in this segment.
pub fn num_docs(&self) -> u32 {
self.data.len() as u32
}
/// Returns the `fieldnorm` associated to a doc id.
/// The fieldnorm is a value approximating the number
/// of tokens in a given field of the `doc_id`.
@@ -62,13 +103,12 @@ impl FieldNormReader {
pub fn fieldnorm_to_id(fieldnorm: u32) -> u8 {
fieldnorm_to_id(fieldnorm)
}
}
#[cfg(test)]
impl From<Vec<u32>> for FieldNormReader {
fn from(field_norms: Vec<u32>) -> FieldNormReader {
#[cfg(test)]
pub fn for_test(field_norms: &[u32]) -> FieldNormReader {
let field_norms_id = field_norms
.into_iter()
.iter()
.cloned()
.map(FieldNormReader::fieldnorm_to_id)
.collect::<Vec<u8>>();
let field_norms_data = ReadOnlySource::from(field_norms_id);
@@ -77,3 +117,20 @@ impl From<Vec<u32>> for FieldNormReader {
}
}
}
#[cfg(test)]
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);
}
}

26
src/fieldnorm/writer.rs
View File

@@ -22,11 +22,14 @@ impl FieldNormsWriter {
pub(crate) fn fields_with_fieldnorm(schema: &Schema) -> Vec<Field> {
schema
.fields()
.iter()
.enumerate()
.filter(|&(_, field_entry)| field_entry.is_indexed())
.map(|(field, _)| Field(field as u32))
.collect::<Vec<Field>>()
.filter_map(|(field, field_entry)| {
if field_entry.is_indexed() {
Some(field)
} else {
None
}
})
.collect::<Vec<_>>()
}
/// Initialize with state for tracking the field norm fields
@@ -35,7 +38,7 @@ impl FieldNormsWriter {
let fields = FieldNormsWriter::fields_with_fieldnorm(schema);
let max_field = fields
.iter()
.map(|field| field.0)
.map(Field::field_id)
.max()
.map(|max_field_id| max_field_id as usize + 1)
.unwrap_or(0);
@@ -50,8 +53,8 @@ impl FieldNormsWriter {
///
/// Will extend with 0-bytes for documents that have not been seen.
pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) {
for &field in self.fields.iter() {
self.fieldnorms_buffer[field.0 as usize].resize(max_doc as usize, 0u8);
for field in self.fields.iter() {
self.fieldnorms_buffer[field.field_id() as usize].resize(max_doc as usize, 0u8);
}
}
@@ -64,7 +67,7 @@ impl FieldNormsWriter {
/// * field - the field being set
/// * fieldnorm - the number of terms present in document `doc` in field `field`
pub fn record(&mut self, doc: DocId, field: Field, fieldnorm: u32) {
let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.0 as usize];
let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.field_id() as usize];
assert!(
fieldnorm_buffer.len() <= doc as usize,
"Cannot register a given fieldnorm twice"
@@ -75,11 +78,12 @@ 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.0 as usize][..];
let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.field_id() as usize][..];
fieldnorms_serializer.serialize_field(field, fieldnorm_values)?;
}
fieldnorms_serializer.close()?;
Ok(())
}
}

83
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::default(),
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::new(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<Box<[DeleteOperation]>>,
next: NextBlock,
}
@@ -258,7 +255,7 @@ mod tests {
let delete_queue = DeleteQueue::new();
let make_op = |i: usize| {
let field = Field(1u32);
let field = Field::from_field_id(1u32);
DeleteOperation {
opstamp: i as u64,
term: Term::from_field_u64(field, i as u64),

280
src/indexer/index_writer.rs
View File

@@ -1,14 +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::docset::DocSet;
use crate::directory::TerminatingWrite;
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};
@@ -22,10 +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;
@@ -71,7 +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,
@@ -94,7 +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 {
@@ -111,78 +112,92 @@ fn compute_deleted_bitset(
if let Some(mut docset) =
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)?;
}
}
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 {
@@ -202,25 +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()
.inventory()
.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(
@@ -228,7 +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.
@@ -236,7 +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,
@@ -271,7 +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 {}.",
@@ -320,12 +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 {
@@ -336,7 +365,6 @@ impl IndexWriter {
TantivyError::ErrorInThread("Error in indexing worker thread.".into())
})?;
}
drop(self.workers_join_handle);
let result = self
.segment_updater
@@ -351,10 +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.
@@ -371,7 +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();
@@ -379,7 +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 {
@@ -408,7 +436,7 @@ impl IndexWriter {
let segment = index.new_segment();
index_documents(
mem_budget,
&segment,
segment,
&mut document_iterator,
&mut segment_updater,
delete_cursor.clone(),
@@ -425,22 +453,23 @@ impl IndexWriter {
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
@@ -450,12 +479,10 @@ impl IndexWriter {
/// by clearing and resubmitting necessary documents
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::query::QueryParser;
/// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::*;
/// use tantivy::Index;
/// use tantivy::{doc, Index};
///
/// fn main() -> tantivy::Result<()> {
/// let mut schema_builder = Schema::builder();
@@ -481,7 +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
@@ -495,8 +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.
@@ -507,6 +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);
@@ -522,13 +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();
@@ -551,7 +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.
@@ -584,7 +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.
@@ -631,7 +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()
}
@@ -672,9 +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 };
@@ -748,6 +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 {
@@ -757,11 +789,10 @@ 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;
use fail;
#[test]
fn test_operations_group() {
@@ -769,7 +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")),
@@ -778,6 +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")`
@@ -793,7 +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![
@@ -855,8 +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`"));
@@ -872,7 +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());
@@ -1184,4 +1255,15 @@ mod tests {
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());
}
}

88
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
/// 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),
}
}

436
src/indexer/merger.rs
View File

@@ -2,39 +2,37 @@ use crate::common::MAX_DOC_LIMIT;
use crate::core::Segment;
use crate::core::SegmentReader;
use crate::core::SerializableSegment;
use crate::docset::DocSet;
use crate::docset::{DocSet, TERMINATED};
use crate::fastfield::BytesFastFieldReader;
use crate::fastfield::DeleteBitSet;
use crate::fastfield::FastFieldReader;
use crate::fastfield::FastFieldSerializer;
use crate::fastfield::MultiValueIntFastFieldReader;
use crate::fieldnorm::FieldNormReader;
use crate::fieldnorm::FieldNormsSerializer;
use crate::fieldnorm::FieldNormsWriter;
use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
use crate::indexer::SegmentSerializer;
use crate::postings::InvertedIndexSerializer;
use crate::postings::Postings;
use crate::postings::{InvertedIndexSerializer, SegmentPostings};
use crate::schema::Cardinality;
use crate::schema::FieldType;
use crate::schema::{Field, Schema};
use crate::store::StoreWriter;
use crate::termdict::TermMerger;
use crate::termdict::TermOrdinal;
use crate::DocId;
use crate::Result;
use crate::TantivyError;
use itertools::Itertools;
use crate::{DocId, InvertedIndexReader, SegmentComponent};
use std::cmp;
use std::collections::HashMap;
use std::sync::Arc;
fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> crate::Result<u64> {
let mut total_tokens = 0u64;
let mut count: [usize; 256] = [0; 256];
for reader in readers {
if reader.has_deletes() {
// if there are deletes, then we use an approximation
// using the fieldnorm
let fieldnorms_reader = reader.get_fieldnorms_reader(field);
let fieldnorms_reader = reader.get_fieldnorms_reader(field)?;
for doc in reader.doc_ids_alive() {
let fieldnorm_id = fieldnorms_reader.fieldnorm_id(doc);
count[fieldnorm_id as usize] += 1;
@@ -43,7 +41,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
total_tokens += reader.inverted_index(field).total_num_tokens();
}
}
total_tokens
Ok(total_tokens
+ count
.iter()
.cloned()
@@ -51,7 +49,7 @@ fn compute_total_num_tokens(readers: &[SegmentReader], field: Field) -> u64 {
.map(|(fieldnorm_ord, count)| {
count as u64 * u64::from(FieldNormReader::id_to_fieldnorm(fieldnorm_ord as u8))
})
.sum::<u64>()
.sum::<u64>())
}
pub struct IndexMerger {
@@ -72,11 +70,11 @@ fn compute_min_max_val(
Some(delete_bitset) => {
// some deleted documents,
// we need to recompute the max / min
(0..max_doc)
.filter(|doc_id| delete_bitset.is_alive(*doc_id))
.map(|doc_id| u64_reader.get(doc_id))
.minmax()
.into_option()
crate::common::minmax(
(0..max_doc)
.filter(|doc_id| delete_bitset.is_alive(*doc_id))
.map(|doc_id| u64_reader.get(doc_id)),
)
}
None => {
// no deleted documents,
@@ -143,7 +141,7 @@ impl DeltaComputer {
}
impl IndexMerger {
pub fn open(schema: Schema, segments: &[Segment]) -> Result<IndexMerger> {
pub fn open(schema: Schema, segments: &[Segment]) -> crate::Result<IndexMerger> {
let mut readers = vec![];
let mut max_doc: u32 = 0u32;
for segment in segments {
@@ -159,7 +157,7 @@ impl IndexMerger {
which exceeds the limit {}.",
max_doc, MAX_DOC_LIMIT
);
return Err(TantivyError::InvalidArgument(err_msg));
return Err(crate::TantivyError::InvalidArgument(err_msg));
}
Ok(IndexMerger {
schema,
@@ -168,13 +166,16 @@ impl IndexMerger {
})
}
fn write_fieldnorms(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> Result<()> {
fn write_fieldnorms(
&self,
mut fieldnorms_serializer: FieldNormsSerializer,
) -> crate::Result<()> {
let fields = FieldNormsWriter::fields_with_fieldnorm(&self.schema);
let mut fieldnorms_data = Vec::with_capacity(self.max_doc as usize);
for field in fields {
fieldnorms_data.clear();
for reader in &self.readers {
let fieldnorms_reader = reader.get_fieldnorms_reader(field);
let fieldnorms_reader = reader.get_fieldnorms_reader(field)?;
for doc_id in reader.doc_ids_alive() {
let fieldnorm_id = fieldnorms_reader.fieldnorm_id(doc_id);
fieldnorms_data.push(fieldnorm_id);
@@ -182,6 +183,7 @@ impl IndexMerger {
}
fieldnorms_serializer.serialize_field(field, &fieldnorms_data[..])?;
}
fieldnorms_serializer.close()?;
Ok(())
}
@@ -189,9 +191,8 @@ impl IndexMerger {
&self,
fast_field_serializer: &mut FastFieldSerializer,
mut term_ord_mappings: HashMap<Field, TermOrdinalMapping>,
) -> Result<()> {
for (field_id, field_entry) in self.schema.fields().iter().enumerate() {
let field = Field(field_id as u32);
) -> crate::Result<()> {
for (field, field_entry) in self.schema.fields() {
let field_type = field_entry.field_type();
match *field_type {
FieldType::HierarchicalFacet => {
@@ -235,7 +236,7 @@ impl IndexMerger {
&self,
field: Field,
fast_field_serializer: &mut FastFieldSerializer,
) -> Result<()> {
) -> crate::Result<()> {
let mut u64_readers = vec![];
let mut min_value = u64::max_value();
let mut max_value = u64::min_value();
@@ -285,7 +286,7 @@ impl IndexMerger {
&self,
field: Field,
fast_field_serializer: &mut FastFieldSerializer,
) -> Result<()> {
) -> crate::Result<()> {
let mut total_num_vals = 0u64;
let mut u64s_readers: Vec<MultiValueIntFastFieldReader<u64>> = Vec::new();
@@ -332,7 +333,7 @@ impl IndexMerger {
field: Field,
term_ordinal_mappings: &TermOrdinalMapping,
fast_field_serializer: &mut FastFieldSerializer,
) -> Result<()> {
) -> crate::Result<()> {
// Multifastfield consists in 2 fastfields.
// The first serves as an index into the second one and is stricly increasing.
// The second contains the actual values.
@@ -372,7 +373,7 @@ impl IndexMerger {
&self,
field: Field,
fast_field_serializer: &mut FastFieldSerializer,
) -> Result<()> {
) -> crate::Result<()> {
// Multifastfield consists in 2 fastfields.
// The first serves as an index into the second one and is stricly increasing.
// The second contains the actual values.
@@ -437,7 +438,7 @@ impl IndexMerger {
&self,
field: Field,
fast_field_serializer: &mut FastFieldSerializer,
) -> Result<()> {
) -> crate::Result<()> {
let mut total_num_vals = 0u64;
let mut bytes_readers: Vec<BytesFastFieldReader> = Vec::new();
@@ -493,10 +494,11 @@ impl IndexMerger {
indexed_field: Field,
field_type: &FieldType,
serializer: &mut InvertedIndexSerializer,
) -> Result<Option<TermOrdinalMapping>> {
fieldnorm_reader: Option<FieldNormReader>,
) -> crate::Result<Option<TermOrdinalMapping>> {
let mut positions_buffer: Vec<u32> = Vec::with_capacity(1_000);
let mut delta_computer = DeltaComputer::new();
let field_readers = self
let field_readers: Vec<Arc<InvertedIndexReader>> = self
.readers
.iter()
.map(|reader| reader.inverted_index(indexed_field))
@@ -539,7 +541,7 @@ impl IndexMerger {
// The total number of tokens will only be exact when there has been no deletes.
//
// Otherwise, we approximate by removing deleted documents proportionally.
let total_num_tokens: u64 = compute_total_num_tokens(&self.readers, indexed_field);
let total_num_tokens: u64 = compute_total_num_tokens(&self.readers, indexed_field)?;
// Create the total list of doc ids
// by stacking the doc ids from the different segment.
@@ -551,7 +553,8 @@ impl IndexMerger {
// - Segment 2's doc ids become [seg0.max_doc + seg1.max_doc,
// seg0.max_doc + seg1.max_doc + seg2.max_doc]
// ...
let mut field_serializer = serializer.new_field(indexed_field, total_num_tokens)?;
let mut field_serializer =
serializer.new_field(indexed_field, total_num_tokens, fieldnorm_reader)?;
let field_entry = self.schema.get_field_entry(indexed_field);
@@ -561,84 +564,78 @@ impl IndexMerger {
indexed. Have you modified the schema?",
);
let mut segment_postings_containing_the_term: Vec<(usize, SegmentPostings)> = vec![];
while merged_terms.advance() {
segment_postings_containing_the_term.clear();
let term_bytes: &[u8] = merged_terms.key();
let mut total_doc_freq = 0;
// Let's compute the list of non-empty posting lists
let segment_postings: Vec<_> = merged_terms
.current_kvs()
.iter()
.flat_map(|heap_item| {
let segment_ord = heap_item.segment_ord;
let term_info = heap_item.streamer.value();
let segment_reader = &self.readers[heap_item.segment_ord];
let inverted_index = segment_reader.inverted_index(indexed_field);
let mut segment_postings = inverted_index
.read_postings_from_terminfo(term_info, segment_postings_option);
while segment_postings.advance() {
if !segment_reader.is_deleted(segment_postings.doc()) {
return Some((segment_ord, segment_postings));
}
}
None
})
.collect();
for heap_item in merged_terms.current_kvs() {
let segment_ord = heap_item.segment_ord;
let term_info = heap_item.streamer.value();
let segment_reader = &self.readers[heap_item.segment_ord];
let inverted_index: &InvertedIndexReader = &*field_readers[segment_ord];
let segment_postings =
inverted_index.read_postings_from_terminfo(term_info, segment_postings_option);
let delete_bitset_opt = segment_reader.delete_bitset();
let doc_freq = if let Some(delete_bitset) = delete_bitset_opt {
segment_postings.doc_freq_given_deletes(delete_bitset)
} else {
segment_postings.doc_freq()
};
if doc_freq > 0u32 {
total_doc_freq += doc_freq;
segment_postings_containing_the_term.push((segment_ord, segment_postings));
}
}
// At this point, `segment_postings` contains the posting list
// of all of the segments containing the given term.
// of all of the segments containing the given term (and that are non-empty)
//
// These segments are non-empty and advance has already been called.
if !segment_postings.is_empty() {
// If not, the `term` will be entirely removed.
// We know that there is at least one document containing
// the term, so we add it.
let to_term_ord = field_serializer.new_term(term_bytes)?;
if let Some(ref mut term_ord_mapping) = term_ord_mapping_opt {
for (segment_ord, from_term_ord) in merged_terms.matching_segments() {
term_ord_mapping.register_from_to(segment_ord, from_term_ord, to_term_ord);
}
}
// We can now serialize this postings, by pushing each document to the
// postings serializer.
for (segment_ord, mut segment_postings) in segment_postings {
let old_to_new_doc_id = &merged_doc_id_map[segment_ord];
loop {
let doc = segment_postings.doc();
// `.advance()` has been called once before the loop.
//
// It was required to make sure we only consider segments
// that effectively contain at least one non-deleted document
// and remove terms that do not have documents associated.
//
// For this reason, we cannot use a `while segment_postings.advance()` loop.
// deleted doc are skipped as they do not have a `remapped_doc_id`.
if let Some(remapped_doc_id) = old_to_new_doc_id[doc as usize] {
// we make sure to only write the term iff
// there is at least one document.
let term_freq = segment_postings.term_freq();
segment_postings.positions(&mut positions_buffer);
let delta_positions = delta_computer.compute_delta(&positions_buffer);
field_serializer.write_doc(
remapped_doc_id,
term_freq,
delta_positions,
)?;
}
if !segment_postings.advance() {
break;
}
}
}
// closing the term.
field_serializer.close_term()?;
if total_doc_freq == 0u32 {
// All docs that used to contain the term have been deleted. The `term` will be
// entirely removed.
continue;
}
let to_term_ord = field_serializer.new_term(term_bytes, total_doc_freq)?;
if let Some(ref mut term_ord_mapping) = term_ord_mapping_opt {
for (segment_ord, from_term_ord) in merged_terms.matching_segments() {
term_ord_mapping.register_from_to(segment_ord, from_term_ord, to_term_ord);
}
}
// We can now serialize this postings, by pushing each document to the
// postings serializer.
for (segment_ord, mut segment_postings) in
segment_postings_containing_the_term.drain(..)
{
let old_to_new_doc_id = &merged_doc_id_map[segment_ord];
let mut doc = segment_postings.doc();
while doc != TERMINATED {
// deleted doc are skipped as they do not have a `remapped_doc_id`.
if let Some(remapped_doc_id) = old_to_new_doc_id[doc as usize] {
// we make sure to only write the term iff
// there is at least one document.
let term_freq = segment_postings.term_freq();
segment_postings.positions(&mut positions_buffer);
let delta_positions = delta_computer.compute_delta(&positions_buffer);
field_serializer.write_doc(remapped_doc_id, term_freq, delta_positions)?;
}
doc = segment_postings.advance();
}
}
// closing the term.
field_serializer.close_term()?;
}
field_serializer.close()?;
Ok(term_ord_mapping_opt)
@@ -647,24 +644,26 @@ impl IndexMerger {
fn write_postings(
&self,
serializer: &mut InvertedIndexSerializer,
) -> Result<HashMap<Field, TermOrdinalMapping>> {
fieldnorm_readers: FieldNormReaders,
) -> crate::Result<HashMap<Field, TermOrdinalMapping>> {
let mut term_ordinal_mappings = HashMap::new();
for (field_ord, field_entry) in self.schema.fields().iter().enumerate() {
for (field, field_entry) in self.schema.fields() {
let fieldnorm_reader = fieldnorm_readers.get_field(field);
if field_entry.is_indexed() {
let indexed_field = Field(field_ord as u32);
if let Some(term_ordinal_mapping) = self.write_postings_for_field(
indexed_field,
field,
field_entry.field_type(),
serializer,
fieldnorm_reader,
)? {
term_ordinal_mappings.insert(indexed_field, term_ordinal_mapping);
term_ordinal_mappings.insert(field, term_ordinal_mapping);
}
}
}
Ok(term_ordinal_mappings)
}
fn write_storable_fields(&self, store_writer: &mut StoreWriter) -> Result<()> {
fn write_storable_fields(&self, store_writer: &mut StoreWriter) -> crate::Result<()> {
for reader in &self.readers {
let store_reader = reader.get_store_reader();
if reader.num_deleted_docs() > 0 {
@@ -681,9 +680,16 @@ impl IndexMerger {
}
impl SerializableSegment for IndexMerger {
fn write(&self, mut serializer: SegmentSerializer) -> Result<u32> {
let term_ord_mappings = self.write_postings(serializer.get_postings_serializer())?;
self.write_fieldnorms(serializer.get_fieldnorms_serializer())?;
fn write(&self, mut serializer: SegmentSerializer) -> crate::Result<u32> {
if let Some(fieldnorms_serializer) = serializer.extract_fieldnorms_serializer() {
self.write_fieldnorms(fieldnorms_serializer)?;
}
let fieldnorm_data = serializer
.segment()
.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
let term_ord_mappings =
self.write_postings(serializer.get_postings_serializer(), fieldnorm_readers)?;
self.write_fast_fields(serializer.get_fast_field_serializer(), term_ord_mappings)?;
self.write_storable_fields(serializer.get_store_writer())?;
serializer.close()?;
@@ -693,15 +699,15 @@ impl SerializableSegment for IndexMerger {
#[cfg(test)]
mod tests {
use crate::assert_nearly_equals;
use crate::collector::tests::TEST_COLLECTOR_WITH_SCORE;
use crate::collector::tests::{BytesFastFieldTestCollector, FastFieldTestCollector};
use crate::collector::{Count, FacetCollector};
use crate::core::Index;
use crate::query::AllQuery;
use crate::query::BooleanQuery;
use crate::query::Scorer;
use crate::query::TermQuery;
use crate::schema;
use crate::schema::Cardinality;
use crate::schema::Document;
use crate::schema::Facet;
use crate::schema::IndexRecordOption;
@@ -709,11 +715,13 @@ mod tests {
use crate::schema::Term;
use crate::schema::TextFieldIndexing;
use crate::schema::INDEXED;
use crate::schema::{Cardinality, TEXT};
use crate::DocAddress;
use crate::IndexWriter;
use crate::Searcher;
use crate::{schema, DocSet, SegmentId};
use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};
use futures::Future;
use futures::executor::block_on;
use std::io::Cursor;
#[test]
@@ -743,7 +751,7 @@ mod tests {
};
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
{
// writing the segment
{
@@ -795,12 +803,8 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
let mut index_writer = index.writer_for_tests().unwrap();
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
index_writer.wait_merging_threads().unwrap();
}
{
@@ -900,7 +904,7 @@ mod tests {
let score_field = schema_builder.add_u64_field("score", score_fieldtype);
let bytes_score_field = schema_builder.add_bytes_field("score_bytes");
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let reader = index.reader().unwrap();
let search_term = |searcher: &Searcher, term: Term| {
let collector = FastFieldTestCollector::for_field(score_field);
@@ -1044,11 +1048,7 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
reader.reload().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
@@ -1143,11 +1143,7 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
reader.reload().unwrap();
let searcher = reader.searcher();
@@ -1215,7 +1211,7 @@ mod tests {
let index = Index::create_in_ram(schema_builder.build());
let reader = index.reader().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 index_doc = |index_writer: &mut IndexWriter, doc_facets: &[&str]| {
let mut doc = Document::default();
for facet in doc_facets {
@@ -1280,12 +1276,8 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
let mut index_writer = index.writer_for_tests().unwrap();
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
index_writer.wait_merging_threads().unwrap();
reader.reload().unwrap();
test_searcher(
@@ -1303,7 +1295,7 @@ mod tests {
// Deleting one term
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let facet = Facet::from_path(vec!["top", "a", "firstdoc"]);
let facet_term = Term::from_facet(facet_field, &facet);
index_writer.delete_term(facet_term);
@@ -1328,7 +1320,7 @@ mod tests {
let mut schema_builder = schema::Schema::builder();
let int_field = schema_builder.add_u64_field("intvals", INDEXED);
let index = Index::create_in_ram(schema_builder.build());
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!(int_field => 1u64));
index_writer.commit().expect("commit failed");
index_writer.add_document(doc!(int_field => 1u64));
@@ -1340,11 +1332,7 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
reader.reload().unwrap();
// commit has not been called yet. The document should still be
// there.
@@ -1361,26 +1349,22 @@ mod tests {
let index = Index::create_in_ram(schema_builder.build());
let reader = index.reader().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 mut doc = Document::default();
doc.add_u64(int_field, 1);
index_writer.add_document(doc.clone());
index_writer.commit().expect("commit failed");
assert!(index_writer.commit().is_ok());
index_writer.add_document(doc);
index_writer.commit().expect("commit failed");
assert!(index_writer.commit().is_ok());
index_writer.delete_term(Term::from_field_u64(int_field, 1));
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
assert!(block_on(index_writer.merge(&segment_ids)).is_ok());
// assert delete has not been committed
reader.reload().expect("failed to load searcher 1");
assert!(reader.reload().is_ok());
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 2);
@@ -1404,7 +1388,7 @@ mod tests {
let index = Index::create_in_ram(schema_builder.build());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let index_doc = |index_writer: &mut IndexWriter, int_vals: &[u64]| {
let mut doc = Document::default();
for &val in int_vals {
@@ -1419,12 +1403,12 @@ mod tests {
index_doc(&mut index_writer, &[1, 5]);
index_doc(&mut index_writer, &[3]);
index_doc(&mut index_writer, &[17]);
index_writer.commit().expect("committed");
assert!(index_writer.commit().is_ok());
index_doc(&mut index_writer, &[20]);
index_writer.commit().expect("committed");
assert!(index_writer.commit().is_ok());
index_doc(&mut index_writer, &[28, 27]);
index_doc(&mut index_writer, &[1_000]);
index_writer.commit().expect("committed");
assert!(index_writer.commit().is_ok());
}
let reader = index.reader().unwrap();
let searcher = reader.searcher();
@@ -1456,15 +1440,6 @@ mod tests {
assert_eq!(&vals, &[17]);
}
println!(
"{:?}",
searcher
.segment_readers()
.iter()
.map(|reader| reader.max_doc())
.collect::<Vec<_>>()
);
{
let segment = searcher.segment_reader(1u32);
let ff_reader = segment.fast_fields().u64s(int_field).unwrap();
@@ -1487,28 +1462,14 @@ mod tests {
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer
.merge(&segment_ids)
.expect("Failed to initiate merge")
.wait()
.expect("Merging failed");
index_writer
.wait_merging_threads()
.expect("Wait for merging threads");
let mut index_writer = index.writer_for_tests().unwrap();
assert!(block_on(index_writer.merge(&segment_ids)).is_ok());
assert!(index_writer.wait_merging_threads().is_ok());
}
reader.reload().expect("Load searcher");
assert!(reader.reload().is_ok());
{
let searcher = reader.searcher();
println!(
"{:?}",
searcher
.segment_readers()
.iter()
.map(|reader| reader.max_doc())
.collect::<Vec<_>>()
);
let segment = searcher.segment_reader(0u32);
let ff_reader = segment.fast_fields().u64s(int_field).unwrap();
@@ -1543,4 +1504,109 @@ mod tests {
assert_eq!(&vals, &[20]);
}
}
#[test]
fn merges_f64_fast_fields_correctly() -> crate::Result<()> {
let mut builder = schema::SchemaBuilder::new();
let fast_multi = IntOptions::default().set_fast(Cardinality::MultiValues);
let field = builder.add_f64_field("f64", schema::FAST);
let multi_field = builder.add_f64_field("f64s", fast_multi);
let index = Index::create_in_ram(builder.build());
let mut writer = index.writer_for_tests()?;
// Make sure we'll attempt to merge every created segment
let mut policy = crate::indexer::LogMergePolicy::default();
policy.set_min_merge_size(2);
writer.set_merge_policy(Box::new(policy));
for i in 0..100 {
let mut doc = Document::new();
doc.add_f64(field, 42.0);
doc.add_f64(multi_field, 0.24);
doc.add_f64(multi_field, 0.27);
writer.add_document(doc);
if i % 5 == 0 {
writer.commit()?;
}
}
writer.commit()?;
writer.wait_merging_threads()?;
// If a merging thread fails, we should end up with more
// than one segment here
assert_eq!(1, index.searchable_segments()?.len());
Ok(())
}
#[test]
fn test_merged_index_has_blockwand() -> crate::Result<()> {
let mut builder = schema::SchemaBuilder::new();
let text = builder.add_text_field("text", TEXT);
let index = Index::create_in_ram(builder.build());
let mut writer = index.writer_for_tests()?;
let happy_term = Term::from_field_text(text, "happy");
let term_query = TermQuery::new(happy_term, IndexRecordOption::WithFreqs);
for _ in 0..62 {
writer.add_document(doc!(text=>"hello happy tax payer"));
}
writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let mut term_scorer = term_query
.specialized_weight(&searcher, true)
.specialized_scorer(searcher.segment_reader(0u32), 1.0)?;
assert_eq!(term_scorer.doc(), 0);
assert_nearly_equals!(term_scorer.block_max_score(), 0.0079681855);
assert_nearly_equals!(term_scorer.score(), 0.0079681855);
for _ in 0..81 {
writer.add_document(doc!(text=>"hello happy tax payer"));
}
writer.commit()?;
reader.reload()?;
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 2);
for segment_reader in searcher.segment_readers() {
let mut term_scorer = term_query
.specialized_weight(&searcher, true)
.specialized_scorer(segment_reader, 1.0)?;
// the difference compared to before is instrinsic to the bm25 formula. no worries there.
for doc in segment_reader.doc_ids_alive() {
assert_eq!(term_scorer.doc(), doc);
assert_nearly_equals!(term_scorer.block_max_score(), 0.003478312);
assert_nearly_equals!(term_scorer.score(), 0.003478312);
term_scorer.advance();
}
}
let segment_ids: Vec<SegmentId> = searcher
.segment_readers()
.iter()
.map(|reader| reader.segment_id())
.collect();
block_on(writer.merge(&segment_ids[..]))?;
reader.reload()?;
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
let segment_reader = searcher.segment_reader(0u32);
let mut term_scorer = term_query
.specialized_weight(&searcher, true)
.specialized_scorer(segment_reader, 1.0)?;
// the difference compared to before is instrinsic to the bm25 formula. no worries there.
for doc in segment_reader.doc_ids_alive() {
assert_eq!(term_scorer.doc(), doc);
assert_nearly_equals!(term_scorer.block_max_score(), 0.003478312);
assert_nearly_equals!(term_scorer.score(), 0.003478312);
term_scorer.advance();
}
Ok(())
}
}

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();
}
}

2
src/indexer/operation.rs
View File

@@ -19,6 +19,8 @@ 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> {

1
src/indexer/segment_register.rs
View File

@@ -134,5 +134,4 @@ mod tests {
}
assert_eq!(segment_ids(&segment_register), vec![segment_id_merged]);
}
}

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(())
}
}

475
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: &mut 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: &mut 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)?;
@@ -117,24 +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
.inventory()
.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`.
@@ -142,12 +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<()>>>>,
killed: AtomicBool,
stamper: Stamper,
merge_operations: MergeOperationInventory,
@@ -158,22 +165,35 @@ 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()),
killed: AtomicBool::new(false),
stamper,
merge_operations: Default::default(),
@@ -181,67 +201,82 @@ impl SegmentUpdater {
}
pub fn get_merge_policy(&self) -> Arc<Box<dyn MergePolicy>> {
self.0.merge_policy.read().unwrap().clone()
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;
*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.
@@ -263,16 +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.
@@ -280,148 +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.inventory().all() {
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();
@@ -429,25 +448,18 @@ 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)
.map(|merge_candidate: MergeCandidate| {
MergeOperation::new(&self.merge_operations, commit_opstamp, merge_candidate.0)
})
.collect::<Vec<_>>();
merge_candidates.extend(committed_merge_candidates.into_iter());
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
);
}
}
}
@@ -456,15 +468,17 @@ 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,
@@ -482,28 +496,33 @@ 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.
///
@@ -514,26 +533,9 @@ 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(())
}
}
@@ -553,7 +555,7 @@ 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));
{
@@ -606,7 +608,7 @@ 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 {
@@ -677,7 +679,7 @@ 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 {
@@ -689,7 +691,6 @@ 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());

177
src/indexer/segment_writer.rs
View File

@@ -2,29 +2,26 @@ 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;
use crate::schema::FieldEntry;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::schema::Term;
use crate::schema::Value;
use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::FacetTokenizer;
use crate::tokenizer::{TokenStream, Tokenizer};
use crate::DocId;
use crate::schema::{Field, FieldEntry};
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 crate::{DocId, SegmentComponent};
use std::io;
use std::str;
/// 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 +29,7 @@ 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 +46,8 @@ pub struct SegmentWriter {
fast_field_writers: FastFieldsWriter,
fieldnorms_writer: FieldNormsWriter,
doc_opstamps: Vec<Opstamp>,
tokenizers: Vec<Option<Box<dyn BoxedTokenizer>>>,
tokenizers: Vec<Option<TextAnalyzer>>,
term_buffer: Term,
}
impl SegmentWriter {
@@ -64,27 +62,27 @@ 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()
.iter()
.map(FieldEntry::field_type)
.map(|field_type| match *field_type {
let tokenizers = schema
.fields()
.map(
|(_, field_entry): (Field, &FieldEntry)| match field_entry.field_type() {
FieldType::Str(ref text_options) => text_options
.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,
})
.collect();
},
)
.collect();
Ok(SegmentWriter {
max_doc: 0,
multifield_postings,
@@ -93,6 +91,7 @@ impl SegmentWriter {
fast_field_writers: FastFieldsWriter::from_schema(schema),
doc_opstamps: Vec::with_capacity(1_000),
tokenizers,
term_buffer: Term::new(),
})
}
@@ -100,7 +99,7 @@ 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,
@@ -130,24 +129,26 @@ impl SegmentWriter {
if !field_options.is_indexed() {
continue;
}
let (term_buffer, multifield_postings) =
(&mut self.term_buffer, &mut self.multifield_postings);
match *field_options.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
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 fake_str in facets {
let mut unordered_term_id_opt = None;
FacetTokenizer.token_stream(fake_str).process(&mut |token| {
term.set_text(&token.text);
term_buffer.set_text(&token.text);
let unordered_term_id =
self.multifield_postings.subscribe(doc_id, &term);
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 {
@@ -159,69 +160,80 @@ impl SegmentWriter {
}
}
FieldType::Str(_) => {
let num_tokens = if let Some(ref mut tokenizer) =
self.tokenizers[field.0 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());
term_buffer.set_u64(field_value.value().u64_value());
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());
term_buffer.set_i64(field_value.value().date_value().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());
term_buffer.set_i64(field_value.value().i64_value());
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());
term_buffer.set_f64(field_value.value().f64_value());
multifield_postings.subscribe(doc_id, &term_buffer);
}
}
}
@@ -231,6 +243,7 @@ impl SegmentWriter {
}
}
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;
@@ -264,16 +277,23 @@ 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,
@@ -296,5 +316,4 @@ mod tests {
assert_eq!(initial_table_size(10_000_000).unwrap(), 17);
assert_eq!(initial_table_size(1_000_000_000).unwrap(), 19);
}
}

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)
}
}

599
src/lib.rs Executable file → Normal file
View File

@@ -3,7 +3,6 @@
#![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
#![doc(test(attr(allow(unused_variables), deny(warnings))))]
#![warn(missing_docs)]
#![recursion_limit = "80"]
//! # `tantivy`
//!
@@ -11,26 +10,17 @@
//! Think `Lucene`, but in Rust.
//!
//! ```rust
//! # extern crate tempdir;
//! #
//! #[macro_use]
//! extern crate tantivy;
//!
//! // ...
//!
//! # use std::path::Path;
//! # use tempdir::TempDir;
//! # use tantivy::Index;
//! # use tantivy::schema::*;
//! # use tantivy::{Score, DocAddress};
//! # use tempfile::TempDir;
//! # use tantivy::collector::TopDocs;
//! # use tantivy::query::QueryParser;
//! # use tantivy::schema::*;
//! # use tantivy::{doc, DocAddress, Index, Score};
//! #
//! # fn main() {
//! # // Let's create a temporary directory for the
//! # // sake of this example
//! # if let Ok(dir) = TempDir::new("tantivy_example_dir") {
//! # if let Ok(dir) = TempDir::new() {
//! # run_example(dir.path()).unwrap();
//! # dir.close().unwrap();
//! # }
@@ -108,9 +98,6 @@
//! [literate programming](https://tantivy-search.github.io/examples/basic_search.html) /
//! [source code](https://github.com/tantivy-search/tantivy/blob/master/examples/basic_search.rs))
#[macro_use]
extern crate serde_derive;
#[cfg_attr(test, macro_use)]
extern crate serde_json;
@@ -131,13 +118,13 @@ mod functional_test;
mod macros;
pub use crate::error::TantivyError;
#[deprecated(since = "0.7.0", note = "please use `tantivy::TantivyError` instead")]
pub use crate::error::TantivyError as Error;
pub use chrono;
/// Tantivy result.
pub type Result<T> = std::result::Result<T, error::TantivyError>;
///
/// Within tantivy, please avoid importing `Result` using `use crate::Result`
/// and instead, refer to this as `crate::Result<T>`.
pub type Result<T> = std::result::Result<T, TantivyError>;
/// Tantivy DateTime
pub type DateTime = chrono::DateTime<chrono::Utc>;
@@ -169,22 +156,70 @@ mod snippet;
pub use self::snippet::{Snippet, SnippetGenerator};
mod docset;
pub use self::docset::{DocSet, SkipResult};
pub use crate::core::SegmentComponent;
pub use self::docset::{DocSet, TERMINATED};
pub use crate::common::{f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
pub use crate::core::{Executor, SegmentComponent};
pub use crate::core::{Index, IndexMeta, Searcher, Segment, SegmentId, SegmentMeta};
pub use crate::core::{InvertedIndexReader, SegmentReader};
pub use crate::directory::Directory;
pub use crate::indexer::operation::UserOperation;
pub use crate::indexer::IndexWriter;
pub use crate::postings::Postings;
pub use crate::reader::LeasedItem;
pub use crate::schema::{Document, Term};
use std::fmt;
pub use crate::common::{i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
use once_cell::sync::Lazy;
use serde::{Deserialize, Serialize};
/// Expose the current version of tantivy, as well
/// whether it was compiled with the simd compression.
pub fn version() -> &'static str {
env!("CARGO_PKG_VERSION")
/// Index format version.
const INDEX_FORMAT_VERSION: u32 = 2;
/// Structure version for the index.
#[derive(Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct Version {
major: u32,
minor: u32,
patch: u32,
index_format_version: u32,
store_compression: String,
}
impl fmt::Debug for Version {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", self.to_string())
}
}
static VERSION: Lazy<Version> = Lazy::new(|| Version {
major: env!("CARGO_PKG_VERSION_MAJOR").parse().unwrap(),
minor: env!("CARGO_PKG_VERSION_MINOR").parse().unwrap(),
patch: env!("CARGO_PKG_VERSION_PATCH").parse().unwrap(),
index_format_version: INDEX_FORMAT_VERSION,
store_compression: crate::store::COMPRESSION.to_string(),
});
impl ToString for Version {
fn to_string(&self) -> String {
format!(
"tantivy v{}.{}.{}, index_format v{}, store_compression: {}",
self.major, self.minor, self.patch, self.index_format_version, self.store_compression
)
}
}
static VERSION_STRING: Lazy<String> = Lazy::new(|| VERSION.to_string());
/// Expose the current version of tantivy as found in Cargo.toml during compilation.
/// eg. "0.11.0" as well as the compression scheme used in the docstore.
pub fn version() -> &'static Version {
&VERSION
}
/// Exposes the complete version of tantivy as found in Cargo.toml during compilation as a string.
/// eg. "tantivy v0.11.0, index_format v1, store_compression: lz4".
pub fn version_string() -> &'static str {
VERSION_STRING.as_str()
}
/// Defines tantivy's merging strategy
@@ -210,11 +245,10 @@ pub type DocId = u32;
/// with opstamp `n+1`.
pub type Opstamp = u64;
/// A f32 that represents the relevance of the document to the query
/// A Score that represents the relevance of the document to the query
///
/// This is modelled internally as a `f32`. The
/// larger the number, the more relevant the document
/// to the search
/// This is modelled internally as a `f32`. The larger the number, the more relevant
/// the document to the search query.
pub type Score = f32;
/// A `SegmentLocalId` identifies a segment.
@@ -222,15 +256,13 @@ pub type Score = f32;
pub type SegmentLocalId = u32;
impl DocAddress {
/// Return the segment ordinal.
/// The segment ordinal is an id identifying the segment
/// hosting the document. It is only meaningful, in the context
/// of a searcher.
/// Return the segment ordinal id that identifies the segment
/// hosting the document in the `Searcher` it is called from.
pub fn segment_ord(self) -> SegmentLocalId {
self.0
}
/// Return the segment local `DocId`
/// Return the segment-local `DocId`
pub fn doc(self) -> DocId {
self.1
}
@@ -239,25 +271,23 @@ impl DocAddress {
/// `DocAddress` contains all the necessary information
/// to identify a document given a `Searcher` object.
///
/// It consists in an id identifying its segment, and
/// its segment-local `DocId`.
/// It consists of an id identifying its segment, and
/// a segment-local `DocId`.
///
/// The id used for the segment is actually an ordinal
/// in the list of segment hold by a `Searcher`.
/// in the list of `Segment`s held by a `Searcher`.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
pub struct DocAddress(pub SegmentLocalId, pub DocId);
#[cfg(test)]
mod tests {
use crate::collector::tests::TEST_COLLECTOR_WITH_SCORE;
use crate::core::SegmentReader;
use crate::docset::DocSet;
use crate::docset::{DocSet, TERMINATED};
use crate::query::BooleanQuery;
use crate::schema::*;
use crate::DocAddress;
use crate::Index;
use crate::IndexWriter;
use crate::Postings;
use crate::ReloadPolicy;
use rand::distributions::Bernoulli;
@@ -265,17 +295,26 @@ mod tests {
use rand::rngs::StdRng;
use rand::{Rng, SeedableRng};
pub fn assert_nearly_equals(expected: f32, val: f32) {
assert!(
nearly_equals(val, expected),
"Got {}, expected {}.",
val,
expected
);
}
pub fn nearly_equals(a: f32, b: f32) -> bool {
(a - b).abs() < 0.0005 * (a + b).abs()
/// Checks if left and right are close one to each other.
/// Panics if the two values are more than 0.5% apart.
#[macro_export]
macro_rules! assert_nearly_equals {
($left:expr, $right:expr) => {{
match (&$left, &$right) {
(left_val, right_val) => {
let diff = (left_val - right_val).abs();
let add = left_val.abs() + right_val.abs();
if diff > 0.0005 * add {
panic!(
r#"assertion failed: `(left ~= right)`
left: `{:?}`,
right: `{:?}`"#,
&*left_val, &*right_val
)
}
}
}
}};
}
pub fn generate_nonunique_unsorted(max_value: u32, n_elems: usize) -> Vec<u32> {
@@ -299,16 +338,28 @@ mod tests {
sample_with_seed(n, ratio, 4)
}
#[test]
#[cfg(not(feature = "lz4"))]
fn test_version_string() {
use regex::Regex;
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();
let version = super::version().to_string();
assert!(regex_ptn.find(&version).is_some());
}
#[test]
#[cfg(feature = "mmap")]
fn test_indexing() {
fn test_indexing() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_from_tempdir(schema).unwrap();
{
// 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()?;
{
let doc = doc!(text_field=>"af b");
index_writer.add_document(doc);
@@ -323,36 +374,30 @@ mod tests {
}
assert!(index_writer.commit().is_ok());
}
Ok(())
}
#[test]
fn test_docfreq1() {
fn test_docfreq1() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let index = Index::create_in_ram(schema_builder.build());
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!(text_field=>"a b c"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
{
let doc = doc!(text_field=>"a");
index_writer.add_document(doc);
}
{
let doc = doc!(text_field=>"a a");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
index_writer.add_document(doc!(text_field=>"a"));
index_writer.add_document(doc!(text_field=>"a a"));
index_writer.commit()?;
}
{
let doc = doc!(text_field=>"c");
index_writer.add_document(doc);
index_writer.commit().unwrap();
index_writer.add_document(doc!(text_field=>"c"));
index_writer.commit()?;
}
{
let reader = index.reader().unwrap();
let reader = index.reader()?;
let searcher = reader.searcher();
let term_a = Term::from_field_text(text_field, "a");
assert_eq!(searcher.doc_freq(&term_a), 3);
@@ -363,80 +408,65 @@ mod tests {
let term_d = Term::from_field_text(text_field, "d");
assert_eq!(searcher.doc_freq(&term_d), 0);
}
Ok(())
}
#[test]
fn test_fieldnorm_no_docs_with_field() {
fn test_fieldnorm_no_docs_with_field() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let title_field = schema_builder.add_text_field("title", TEXT);
let text_field = schema_builder.add_text_field("text", TEXT);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.commit()?;
let index_reader = index.reader()?;
let searcher = index_reader.searcher();
let reader = searcher.segment_reader(0);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
{
let doc = doc!(text_field=>"a b c");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let fieldnorm_reader = reader.get_fieldnorms_reader(text_field)?;
assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
}
{
let index_reader = index.reader().unwrap();
let searcher = index_reader.searcher();
let reader = searcher.segment_reader(0);
{
let fieldnorm_reader = reader.get_fieldnorms_reader(text_field);
assert_eq!(fieldnorm_reader.fieldnorm(0), 3);
}
{
let fieldnorm_reader = reader.get_fieldnorms_reader(title_field);
assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
}
let fieldnorm_reader = reader.get_fieldnorms_reader(title_field)?;
assert_eq!(fieldnorm_reader.fieldnorm_id(0), 0);
}
Ok(())
}
#[test]
fn test_fieldnorm() {
fn test_fieldnorm() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let index = Index::create_in_ram(schema_builder.build());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
{
let doc = doc!(text_field=>"a b c");
index_writer.add_document(doc);
}
{
let doc = doc!();
index_writer.add_document(doc);
}
{
let doc = doc!(text_field=>"a b");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
}
{
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let segment_reader: &SegmentReader = searcher.segment_reader(0);
let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field);
assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
}
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!());
index_writer.add_document(doc!(text_field=>"a b"));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let segment_reader: &SegmentReader = searcher.segment_reader(0);
let fieldnorms_reader = segment_reader.get_fieldnorms_reader(text_field)?;
assert_eq!(fieldnorms_reader.fieldnorm(0), 3);
assert_eq!(fieldnorms_reader.fieldnorm(1), 0);
assert_eq!(fieldnorms_reader.fieldnorm(2), 2);
Ok(())
}
fn advance_undeleted(docset: &mut dyn DocSet, reader: &SegmentReader) -> bool {
while docset.advance() {
if !reader.is_deleted(docset.doc()) {
let mut doc = docset.advance();
while doc != TERMINATED {
if !reader.is_deleted(doc) {
return true;
}
doc = docset.advance();
}
false
}
#[test]
fn test_delete_postings1() {
fn test_delete_postings1() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let term_abcd = Term::from_field_text(text_field, "abcd");
@@ -452,7 +482,7 @@ mod tests {
.unwrap();
{
// 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()?;
// 0
index_writer.add_document(doc!(text_field=>"a b"));
// 1
@@ -468,10 +498,10 @@ mod tests {
index_writer.add_document(doc!(text_field=>" b c"));
// 5
index_writer.add_document(doc!(text_field=>" a"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
let inverted_index = segment_reader.inverted_index(text_field);
@@ -499,15 +529,15 @@ mod tests {
}
{
// 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()?;
// 0
index_writer.add_document(doc!(text_field=>"a b"));
// 1
index_writer.delete_term(Term::from_field_text(text_field, "c"));
index_writer.rollback().unwrap();
index_writer.rollback()?;
}
{
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
let seg_reader = searcher.segment_reader(0);
let inverted_index = seg_reader.inverted_index(term_abcd.field());
@@ -536,15 +566,15 @@ mod tests {
}
{
// 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()?;
index_writer.add_document(doc!(text_field=>"a b"));
index_writer.delete_term(Term::from_field_text(text_field, "c"));
index_writer.rollback().unwrap();
index_writer.rollback()?;
index_writer.delete_term(Term::from_field_text(text_field, "a"));
index_writer.commit().unwrap();
index_writer.commit()?;
}
{
reader.reload().unwrap();
reader.reload()?;
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
let inverted_index = segment_reader.inverted_index(term_abcd.field());
@@ -576,19 +606,20 @@ mod tests {
assert!(!advance_undeleted(&mut postings, segment_reader));
}
}
Ok(())
}
#[test]
fn test_indexed_u64() {
fn test_indexed_u64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let field = schema_builder.add_u64_field("value", INDEXED);
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()?;
index_writer.add_document(doc!(field=>1u64));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let term = Term::from_field_u64(field, 1u64);
let mut postings = searcher
@@ -596,23 +627,23 @@ mod tests {
.inverted_index(term.field())
.read_postings(&term, IndexRecordOption::Basic)
.unwrap();
assert!(postings.advance());
assert_eq!(postings.doc(), 0);
assert!(!postings.advance());
assert_eq!(postings.advance(), TERMINATED);
Ok(())
}
#[test]
fn test_indexed_i64() {
fn test_indexed_i64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let value_field = schema_builder.add_i64_field("value", INDEXED);
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()?;
let negative_val = -1i64;
index_writer.add_document(doc!(value_field => negative_val));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let term = Term::from_field_i64(value_field, negative_val);
let mut postings = searcher
@@ -620,23 +651,23 @@ mod tests {
.inverted_index(term.field())
.read_postings(&term, IndexRecordOption::Basic)
.unwrap();
assert!(postings.advance());
assert_eq!(postings.doc(), 0);
assert!(!postings.advance());
assert_eq!(postings.advance(), TERMINATED);
Ok(())
}
#[test]
fn test_indexed_f64() {
fn test_indexed_f64() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let value_field = schema_builder.add_f64_field("value", INDEXED);
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()?;
let val = std::f64::consts::PI;
index_writer.add_document(doc!(value_field => val));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let term = Term::from_field_f64(value_field, val);
let mut postings = searcher
@@ -644,29 +675,31 @@ mod tests {
.inverted_index(term.field())
.read_postings(&term, IndexRecordOption::Basic)
.unwrap();
assert!(postings.advance());
assert_eq!(postings.doc(), 0);
assert!(!postings.advance());
assert_eq!(postings.advance(), TERMINATED);
Ok(())
}
#[test]
fn test_indexedfield_not_in_documents() {
fn test_indexedfield_not_in_documents() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let absent_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(2, 6_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"a"));
assert!(index_writer.commit().is_ok());
let reader = index.reader().unwrap();
let reader = index.reader()?;
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
segment_reader.inverted_index(absent_field); //< should not panic
let inverted_index = segment_reader.inverted_index(absent_field); //< should not panic
assert_eq!(inverted_index.terms().num_terms(), 0);
Ok(())
}
#[test]
fn test_delete_postings2() {
fn test_delete_postings2() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
@@ -674,55 +707,40 @@ mod tests {
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
.try_into()?;
// writing the segment
let mut index_writer = index.writer_with_num_threads(2, 6_000_000).unwrap();
let add_document = |index_writer: &mut IndexWriter, val: &'static str| {
let doc = doc!(text_field=>val);
index_writer.add_document(doc);
};
let remove_document = |index_writer: &mut IndexWriter, val: &'static str| {
let delterm = Term::from_field_text(text_field, val);
index_writer.delete_term(delterm);
};
add_document(&mut index_writer, "63");
add_document(&mut index_writer, "70");
add_document(&mut index_writer, "34");
add_document(&mut index_writer, "1");
add_document(&mut index_writer, "38");
add_document(&mut index_writer, "33");
add_document(&mut index_writer, "40");
add_document(&mut index_writer, "17");
remove_document(&mut index_writer, "38");
remove_document(&mut index_writer, "34");
index_writer.commit().unwrap();
reader.reload().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 6);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"63"));
index_writer.add_document(doc!(text_field=>"70"));
index_writer.add_document(doc!(text_field=>"34"));
index_writer.add_document(doc!(text_field=>"1"));
index_writer.add_document(doc!(text_field=>"38"));
index_writer.add_document(doc!(text_field=>"33"));
index_writer.add_document(doc!(text_field=>"40"));
index_writer.add_document(doc!(text_field=>"17"));
index_writer.delete_term(Term::from_field_text(text_field, "38"));
index_writer.delete_term(Term::from_field_text(text_field, "34"));
index_writer.commit()?;
reader.reload()?;
assert_eq!(reader.searcher().num_docs(), 6);
Ok(())
}
#[test]
fn test_termfreq() {
fn test_termfreq() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
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 doc = doc!(text_field=>"af af af bc bc");
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"af af af bc bc"));
index_writer.commit()?;
}
{
let index_reader = index.reader().unwrap();
let index_reader = index.reader()?;
let searcher = index_reader.searcher();
let reader = searcher.segment_reader(0);
let inverted_index = reader.inverted_index(text_field);
@@ -734,68 +752,67 @@ mod tests {
let mut postings = inverted_index
.read_postings(&term_af, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert!(postings.advance());
assert_eq!(postings.doc(), 0);
assert_eq!(postings.term_freq(), 3);
assert!(!postings.advance());
assert_eq!(postings.advance(), TERMINATED);
}
Ok(())
}
#[test]
fn test_searcher_1() {
fn test_searcher_1() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let reader = index.reader().unwrap();
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(text_field=>"af af af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit().unwrap();
}
{
reader.reload().unwrap();
let searcher = reader.searcher();
let get_doc_ids = |terms: Vec<Term>| {
let query = BooleanQuery::new_multiterms_query(terms);
let topdocs = searcher.search(&query, &TEST_COLLECTOR_WITH_SCORE).unwrap();
topdocs.docs().to_vec()
};
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "a")]),
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "af")]),
vec![DocAddress(0, 0)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "b")]),
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "c")]),
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "d")]),
vec![DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![
Term::from_field_text(text_field, "b"),
Term::from_field_text(text_field, "a"),
]),
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
}
let reader = index.reader()?;
// writing the segment
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"af af af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit()?;
reader.reload()?;
let searcher = reader.searcher();
let get_doc_ids = |terms: Vec<Term>| {
let query = BooleanQuery::new_multiterms_query(terms);
searcher
.search(&query, &TEST_COLLECTOR_WITH_SCORE)
.map(|topdocs| topdocs.docs().to_vec())
};
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "a")])?,
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "af")])?,
vec![DocAddress(0, 0)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "b")])?,
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "c")])?,
vec![DocAddress(0, 1), DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![Term::from_field_text(text_field, "d")])?,
vec![DocAddress(0, 2)]
);
assert_eq!(
get_doc_ids(vec![
Term::from_field_text(text_field, "b"),
Term::from_field_text(text_field, "a"),
])?,
vec![DocAddress(0, 0), DocAddress(0, 1), DocAddress(0, 2)]
);
Ok(())
}
#[test]
fn test_searcher_2() {
fn test_searcher_2() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
@@ -803,19 +820,17 @@ mod tests {
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
.try_into()?;
assert_eq!(reader.searcher().num_docs(), 0u64);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(text_field=>"af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit().unwrap();
}
reader.reload().unwrap();
// writing the segment
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(text_field=>"af b"));
index_writer.add_document(doc!(text_field=>"a b c"));
index_writer.add_document(doc!(text_field=>"a b c d"));
index_writer.commit()?;
reader.reload()?;
assert_eq!(reader.searcher().num_docs(), 3u64);
Ok(())
}
#[test]
@@ -837,7 +852,7 @@ mod tests {
}
#[test]
fn test_wrong_fast_field_type() {
fn test_wrong_fast_field_type() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let fast_field_unsigned = schema_builder.add_u64_field("unsigned", FAST);
let fast_field_signed = schema_builder.add_i64_field("signed", FAST);
@@ -847,13 +862,14 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 50_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
{
let document = doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
let document =
doc!(fast_field_unsigned => 4u64, fast_field_signed=>4i64, fast_field_float=>4f64);
index_writer.add_document(document);
index_writer.commit().unwrap();
index_writer.commit()?;
}
let reader = index.reader().unwrap();
let reader = index.reader()?;
let searcher = reader.searcher();
let segment_reader: &SegmentReader = searcher.segment_reader(0);
{
@@ -892,5 +908,80 @@ mod tests {
let fast_field_reader = fast_field_reader_opt.unwrap();
assert_eq!(fast_field_reader.get(0), 4f64)
}
Ok(())
}
// motivated by #729
#[test]
fn test_update_via_delete_insert() -> crate::Result<()> {
use crate::collector::Count;
use crate::indexer::NoMergePolicy;
use crate::query::AllQuery;
use crate::SegmentId;
use futures::executor::block_on;
const DOC_COUNT: u64 = 2u64;
let mut schema_builder = SchemaBuilder::default();
let id = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let index_reader = index.reader()?;
let mut index_writer = index.writer_for_tests()?;
index_writer.set_merge_policy(Box::new(NoMergePolicy));
for doc_id in 0u64..DOC_COUNT {
index_writer.add_document(doc!(id => doc_id));
}
index_writer.commit()?;
index_reader.reload()?;
let searcher = index_reader.searcher();
assert_eq!(
searcher.search(&AllQuery, &Count).unwrap(),
DOC_COUNT as usize
);
// update the 10 elements by deleting and re-adding
for doc_id in 0u64..DOC_COUNT {
index_writer.delete_term(Term::from_field_u64(id, doc_id));
index_writer.commit()?;
index_reader.reload()?;
index_writer.add_document(doc!(id => doc_id));
index_writer.commit()?;
index_reader.reload()?;
let searcher = index_reader.searcher();
// The number of document should be stable.
assert_eq!(
searcher.search(&AllQuery, &Count).unwrap(),
DOC_COUNT as usize
);
}
index_reader.reload()?;
let searcher = index_reader.searcher();
let segment_ids: Vec<SegmentId> = searcher
.segment_readers()
.into_iter()
.map(|reader| reader.segment_id())
.collect();
block_on(index_writer.merge(&segment_ids)).unwrap();
index_reader.reload()?;
let searcher = index_reader.searcher();
assert_eq!(searcher.search(&AllQuery, &Count)?, DOC_COUNT as usize);
Ok(())
}
#[test]
fn test_validate_checksum() -> crate::Result<()> {
let index_path = tempfile::tempdir().expect("dir");
let schema = Schema::builder().build();
let index = Index::create_in_dir(&index_path, schema)?;
assert!(index.validate_checksum()?.is_empty());
Ok(())
}
}

12
src/macros.rs
View File

@@ -22,11 +22,9 @@
///
/// # Example
///
/// ```
/// #[macro_use]
/// extern crate tantivy;
///
/// ```rust
/// use tantivy::schema::{Schema, TEXT, FAST};
/// use tantivy::doc;
///
/// //...
///
@@ -37,9 +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
/// );
/// # }
/// ```

89
src/positions/mod.rs
View File

@@ -37,9 +37,9 @@ const LONG_SKIP_INTERVAL: u64 = (LONG_SKIP_IN_BLOCKS * COMPRESSION_BLOCK_SIZE) a
#[cfg(test)]
pub mod tests {
use super::{PositionReader, PositionSerializer};
use super::PositionSerializer;
use crate::directory::ReadOnlySource;
use crate::positions::COMPRESSION_BLOCK_SIZE;
use crate::positions::reader::PositionReader;
use std::iter;
fn create_stream_buffer(vals: &[u32]) -> (ReadOnlySource, ReadOnlySource) {
@@ -68,7 +68,7 @@ pub mod tests {
let mut position_reader = PositionReader::new(stream, skip, 0u64);
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 +76,19 @@ 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);
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);
}
}
}
}
@@ -103,11 +103,12 @@ pub mod tests {
let mut position_reader = PositionReader::new(stream, skip, 0u64);
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 +116,58 @@ 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);
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);
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);
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;
@@ -124,7 +177,7 @@ pub mod tests {
assert_eq!(stream.len(), 1_000_000);
let mut position_reader = PositionReader::new(stream, skip, 128 * 1024);
let mut buf = [0u32; 1];
position_reader.read(&mut buf);
position_reader.read(0, &mut buf);
assert_eq!(buf[0], CONST_VAL);
}
@@ -143,7 +196,7 @@ pub mod tests {
] {
let mut position_reader = PositionReader::new(stream.clone(), skip.clone(), offset);
let mut buf = [0u32; 1];
position_reader.read(&mut buf);
position_reader.read(0, &mut buf);
assert_eq!(buf[0], offset as u32);
}
}

176
src/positions/reader.rs
View File

@@ -3,7 +3,6 @@ use crate::directory::ReadOnlySource;
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;
/// Positions works as a long sequence of compressed block.
/// All terms are chained one after the other.
///
@@ -36,11 +35,10 @@ struct Positions {
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 (body, footer) = skip_source.split_from_end(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);
let (skip_source, long_skip_source) =
body.split_from_end(u64::SIZE_IN_BYTES * (num_long_skips as usize));
Positions {
bit_packer: BitPacker4x::new(),
skip_source,
@@ -63,74 +61,34 @@ impl Positions {
fn reader(&self, offset: u64) -> 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 {
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,
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 {
@@ -142,57 +100,65 @@ impl PositionReader {
Positions::new(position_source, skip_source).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 delta_to_block_offset < 0 || delta_to_block_offset >= 128 {
// 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.get(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.get(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.get(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);
}
}

40
src/postings/block_search.rs
View File

@@ -87,6 +87,7 @@ fn exponential_search(arr: &[u32], target: u32) -> (usize, usize) {
(begin, end)
}
#[inline(never)]
fn galloping(block_docs: &[u32], target: u32) -> usize {
let (start, end) = exponential_search(&block_docs, target);
start + linear_search(&block_docs[start..end], target)
@@ -106,7 +107,7 @@ impl BlockSearcher {
/// the target.
///
/// The results should be equivalent to
/// ```ignore
/// ```compile_fail
/// block[..]
// .iter()
// .take_while(|&&val| val < target)
@@ -129,23 +130,18 @@ impl BlockSearcher {
///
/// If SSE2 instructions are available in the `(platform, running CPU)`,
/// then we use a different implementation that does an exhaustive linear search over
/// the full block whenever the block is full (`len == 128`). It is surprisingly faster, most likely because of the lack
/// of branch.
pub(crate) fn search_in_block(
self,
block_docs: &AlignedBuffer,
len: usize,
start: usize,
target: u32,
) -> usize {
/// the block regardless of whether the block is full or not.
///
/// Indeed, if the block is not full, the remaining items are TERMINATED.
/// It is surprisingly faster, most likely because of the lack of branch misprediction.
pub(crate) fn search_in_block(self, block_docs: &AlignedBuffer, target: u32) -> usize {
#[cfg(target_arch = "x86_64")]
{
use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
if self == BlockSearcher::SSE2 && len == COMPRESSION_BLOCK_SIZE {
if self == BlockSearcher::SSE2 {
return sse2::linear_search_sse2_128(block_docs, target);
}
}
start + galloping(&block_docs.0[start..len], target)
galloping(&block_docs.0[..], target)
}
}
@@ -166,6 +162,7 @@ mod tests {
use super::exponential_search;
use super::linear_search;
use super::BlockSearcher;
use crate::docset::TERMINATED;
use crate::postings::compression::{AlignedBuffer, COMPRESSION_BLOCK_SIZE};
#[test]
@@ -196,19 +193,12 @@ mod tests {
fn util_test_search_in_block(block_searcher: BlockSearcher, block: &[u32], target: u32) {
let cursor = search_in_block_trivial_but_slow(block, target);
assert!(block.len() < COMPRESSION_BLOCK_SIZE);
let mut output_buffer = [u32::max_value(); COMPRESSION_BLOCK_SIZE];
let mut output_buffer = [TERMINATED; COMPRESSION_BLOCK_SIZE];
output_buffer[..block.len()].copy_from_slice(block);
for i in 0..cursor {
assert_eq!(
block_searcher.search_in_block(
&AlignedBuffer(output_buffer),
block.len(),
i,
target
),
cursor
);
}
assert_eq!(
block_searcher.search_in_block(&AlignedBuffer(output_buffer), target),
cursor
);
}
fn util_test_search_in_block_all(block_searcher: BlockSearcher, block: &[u32]) {

527
src/postings/block_segment_postings.rs Normal file
View File

@@ -0,0 +1,527 @@
use crate::common::{BinarySerializable, VInt};
use crate::directory::ReadOnlySource;
use crate::fieldnorm::FieldNormReader;
use crate::postings::compression::{
AlignedBuffer, BlockDecoder, VIntDecoder, COMPRESSION_BLOCK_SIZE,
};
use crate::postings::{BlockInfo, FreqReadingOption, SkipReader};
use crate::query::BM25Weight;
use crate::schema::IndexRecordOption;
use crate::{DocId, Score, TERMINATED};
fn max_score<I: Iterator<Item = Score>>(mut it: I) -> Option<Score> {
if let Some(first) = it.next() {
Some(it.fold(first, Score::max))
} else {
None
}
}
/// `BlockSegmentPostings` is a cursor iterating over blocks
/// of documents.
///
/// # Warning
///
/// While it is useful for some very specific high-performance
/// use cases, you should prefer using `SegmentPostings` for most usage.
#[derive(Clone)]
pub struct BlockSegmentPostings {
pub(crate) doc_decoder: BlockDecoder,
loaded_offset: usize,
freq_decoder: BlockDecoder,
freq_reading_option: FreqReadingOption,
block_max_score_cache: Option<Score>,
doc_freq: u32,
data: ReadOnlySource,
pub(crate) skip_reader: SkipReader,
}
fn decode_bitpacked_block(
doc_decoder: &mut BlockDecoder,
freq_decoder_opt: Option<&mut BlockDecoder>,
data: &[u8],
doc_offset: DocId,
doc_num_bits: u8,
tf_num_bits: u8,
) {
let num_consumed_bytes = doc_decoder.uncompress_block_sorted(data, doc_offset, doc_num_bits);
if let Some(freq_decoder) = freq_decoder_opt {
freq_decoder.uncompress_block_unsorted(&data[num_consumed_bytes..], tf_num_bits);
}
}
fn decode_vint_block(
doc_decoder: &mut BlockDecoder,
freq_decoder_opt: Option<&mut BlockDecoder>,
data: &[u8],
doc_offset: DocId,
num_vint_docs: usize,
) {
let num_consumed_bytes =
doc_decoder.uncompress_vint_sorted(data, doc_offset, num_vint_docs, TERMINATED);
if let Some(freq_decoder) = freq_decoder_opt {
freq_decoder.uncompress_vint_unsorted(
&data[num_consumed_bytes..],
num_vint_docs,
TERMINATED,
);
}
}
fn split_into_skips_and_postings(
doc_freq: u32,
data: ReadOnlySource,
) -> (Option<ReadOnlySource>, ReadOnlySource) {
if doc_freq < COMPRESSION_BLOCK_SIZE as u32 {
return (None, data);
}
let mut data_byte_arr = data.as_slice();
let skip_len = VInt::deserialize(&mut data_byte_arr)
.expect("Data corrupted")
.0 as usize;
let vint_len = data.len() - data_byte_arr.len();
let (skip_data, postings_data) = data.slice_from(vint_len).split(skip_len);
(Some(skip_data), postings_data)
}
impl BlockSegmentPostings {
pub(crate) fn from_data(
doc_freq: u32,
data: ReadOnlySource,
record_option: IndexRecordOption,
requested_option: IndexRecordOption,
) -> BlockSegmentPostings {
let freq_reading_option = match (record_option, requested_option) {
(IndexRecordOption::Basic, _) => FreqReadingOption::NoFreq,
(_, IndexRecordOption::Basic) => FreqReadingOption::SkipFreq,
(_, _) => FreqReadingOption::ReadFreq,
};
let (skip_data_opt, postings_data) = split_into_skips_and_postings(doc_freq, data);
let skip_reader = match skip_data_opt {
Some(skip_data) => SkipReader::new(skip_data, doc_freq, record_option),
None => SkipReader::new(ReadOnlySource::empty(), doc_freq, record_option),
};
let mut block_segment_postings = BlockSegmentPostings {
doc_decoder: BlockDecoder::with_val(TERMINATED),
loaded_offset: std::usize::MAX,
freq_decoder: BlockDecoder::with_val(1),
freq_reading_option,
block_max_score_cache: None,
doc_freq,
data: postings_data,
skip_reader,
};
block_segment_postings.load_block();
block_segment_postings
}
/// Returns the block_max_score for the current block.
/// It does not require the block to be loaded. For instance, it is ok to call this method
/// after having called `.shallow_advance(..)`.
///
/// See `TermScorer::block_max_score(..)` for more information.
pub fn block_max_score(
&mut self,
fieldnorm_reader: &FieldNormReader,
bm25_weight: &BM25Weight,
) -> Score {
if let Some(score) = self.block_max_score_cache {
return score;
}
if let Some(skip_reader_max_score) = self.skip_reader.block_max_score(bm25_weight) {
// if we are on a full block, the skip reader should have the block max information
// for us
self.block_max_score_cache = Some(skip_reader_max_score);
return skip_reader_max_score;
}
// this is the last block of the segment posting list.
// If it is actually loaded, we can compute block max manually.
if self.block_is_loaded() {
let docs = self.doc_decoder.output_array().iter().cloned();
let freqs = self.freq_decoder.output_array().iter().cloned();
let bm25_scores = docs.zip(freqs).map(|(doc, term_freq)| {
let fieldnorm_id = fieldnorm_reader.fieldnorm_id(doc);
bm25_weight.score(fieldnorm_id, term_freq)
});
let block_max_score = max_score(bm25_scores).unwrap_or(0.0);
self.block_max_score_cache = Some(block_max_score);
return block_max_score;
}
// We do not have access to any good block max value. We return bm25_weight.max_score()
// as it is a valid upperbound.
//
// We do not cache it however, so that it gets computed when once block is loaded.
bm25_weight.max_score()
}
pub(crate) fn freq_reading_option(&self) -> FreqReadingOption {
self.freq_reading_option
}
// Resets the block segment postings on another position
// in the postings file.
//
// This is useful for enumerating through a list of terms,
// and consuming the associated posting lists while avoiding
// reallocating a `BlockSegmentPostings`.
//
// # Warning
//
// This does not reset the positions list.
pub(crate) fn reset(&mut self, doc_freq: u32, postings_data: ReadOnlySource) {
let (skip_data_opt, postings_data) = split_into_skips_and_postings(doc_freq, postings_data);
self.data = ReadOnlySource::new(postings_data);
self.block_max_score_cache = None;
self.loaded_offset = std::usize::MAX;
if let Some(skip_data) = skip_data_opt {
self.skip_reader.reset(skip_data, doc_freq);
} else {
self.skip_reader.reset(ReadOnlySource::empty(), doc_freq);
}
self.doc_freq = doc_freq;
self.load_block();
}
/// Returns the overall number of documents in the block postings.
/// It does not take in account whether documents are deleted or not.
///
/// This `doc_freq` is simply the sum of the length of all of the blocks
/// length, and it does not take in account deleted documents.
pub fn doc_freq(&self) -> u32 {
self.doc_freq
}
/// Returns the array of docs in the current block.
///
/// Before the first call to `.advance()`, the block
/// returned by `.docs()` is empty.
#[inline]
pub fn docs(&self) -> &[DocId] {
debug_assert!(self.block_is_loaded());
self.doc_decoder.output_array()
}
/// Returns a full block, regardless of whetehr the block is complete or incomplete (
/// as it happens for the last block of the posting list).
///
/// In the latter case, the block is guaranteed to be padded with the sentinel value:
/// `TERMINATED`. The array is also guaranteed to be aligned on 16 bytes = 128 bits.
///
/// This method is useful to run SSE2 linear search.
#[inline(always)]
pub(crate) fn docs_aligned(&self) -> &AlignedBuffer {
debug_assert!(self.block_is_loaded());
self.doc_decoder.output_aligned()
}
/// Return the document at index `idx` of the block.
#[inline(always)]
pub fn doc(&self, idx: usize) -> u32 {
self.doc_decoder.output(idx)
}
/// Return the array of `term freq` in the block.
#[inline]
pub fn freqs(&self) -> &[u32] {
debug_assert!(self.block_is_loaded());
self.freq_decoder.output_array()
}
/// Return the frequency at index `idx` of the block.
#[inline]
pub fn freq(&self, idx: usize) -> u32 {
debug_assert!(self.block_is_loaded());
self.freq_decoder.output(idx)
}
/// Returns the length of the current block.
///
/// All blocks have a length of `NUM_DOCS_PER_BLOCK`,
/// except the last block that may have a length
/// of any number between 1 and `NUM_DOCS_PER_BLOCK - 1`
#[inline]
pub fn block_len(&self) -> usize {
debug_assert!(self.block_is_loaded());
self.doc_decoder.output_len
}
/// Position on a block that may contains `target_doc`.
///
/// If all docs are smaller than target, the block loaded may be empty,
/// or be the last an incomplete VInt block.
pub fn seek(&mut self, target_doc: DocId) {
self.shallow_seek(target_doc);
self.load_block();
}
pub(crate) fn position_offset(&self) -> u64 {
self.skip_reader.position_offset()
}
/// Dangerous API! This calls seek on the skip list,
/// but does not `.load_block()` afterwards.
///
/// `.load_block()` needs to be called manually afterwards.
/// If all docs are smaller than target, the block loaded may be empty,
/// or be the last an incomplete VInt block.
pub(crate) fn shallow_seek(&mut self, target_doc: DocId) {
if self.skip_reader.seek(target_doc) {
self.block_max_score_cache = None;
}
}
pub(crate) fn block_is_loaded(&self) -> bool {
self.loaded_offset == self.skip_reader.byte_offset()
}
pub(crate) fn load_block(&mut self) {
let offset = self.skip_reader.byte_offset();
if self.loaded_offset == offset {
return;
}
self.loaded_offset = offset;
match self.skip_reader.block_info() {
BlockInfo::BitPacked {
doc_num_bits,
tf_num_bits,
..
} => {
decode_bitpacked_block(
&mut self.doc_decoder,
if let FreqReadingOption::ReadFreq = self.freq_reading_option {
Some(&mut self.freq_decoder)
} else {
None
},
&self.data.as_slice()[offset..],
self.skip_reader.last_doc_in_previous_block,
doc_num_bits,
tf_num_bits,
);
}
BlockInfo::VInt { num_docs } => {
let data = {
if num_docs == 0 {
&[]
} else {
&self.data.as_slice()[offset..]
}
};
decode_vint_block(
&mut self.doc_decoder,
if let FreqReadingOption::ReadFreq = self.freq_reading_option {
Some(&mut self.freq_decoder)
} else {
None
},
data,
self.skip_reader.last_doc_in_previous_block,
num_docs as usize,
);
}
}
}
/// Advance to the next block.
///
/// Returns false iff there was no remaining blocks.
pub fn advance(&mut self) {
self.skip_reader.advance();
self.block_max_score_cache = None;
self.load_block();
}
/// Returns an empty segment postings object
pub fn empty() -> BlockSegmentPostings {
BlockSegmentPostings {
doc_decoder: BlockDecoder::with_val(TERMINATED),
loaded_offset: 0,
freq_decoder: BlockDecoder::with_val(1),
freq_reading_option: FreqReadingOption::NoFreq,
block_max_score_cache: None,
doc_freq: 0,
data: ReadOnlySource::new(vec![]),
skip_reader: SkipReader::new(ReadOnlySource::new(vec![]), 0, IndexRecordOption::Basic),
}
}
}
#[cfg(test)]
mod tests {
use super::BlockSegmentPostings;
use crate::common::HasLen;
use crate::core::Index;
use crate::docset::{DocSet, TERMINATED};
use crate::postings::compression::COMPRESSION_BLOCK_SIZE;
use crate::postings::postings::Postings;
use crate::postings::SegmentPostings;
use crate::schema::IndexRecordOption;
use crate::schema::Schema;
use crate::schema::Term;
use crate::schema::INDEXED;
use crate::DocId;
#[test]
fn test_empty_segment_postings() {
let mut postings = SegmentPostings::empty();
assert_eq!(postings.doc(), TERMINATED);
assert_eq!(postings.advance(), TERMINATED);
assert_eq!(postings.advance(), TERMINATED);
assert_eq!(postings.doc_freq(), 0);
assert_eq!(postings.len(), 0);
}
#[test]
fn test_empty_postings_doc_returns_terminated() {
let mut postings = SegmentPostings::empty();
assert_eq!(postings.doc(), TERMINATED);
assert_eq!(postings.advance(), TERMINATED);
}
#[test]
fn test_empty_postings_doc_term_freq_returns_0() {
let postings = SegmentPostings::empty();
assert_eq!(postings.term_freq(), 1);
}
#[test]
fn test_empty_block_segment_postings() {
let mut postings = BlockSegmentPostings::empty();
assert!(postings.docs().is_empty());
assert_eq!(postings.doc_freq(), 0);
postings.advance();
assert!(postings.docs().is_empty());
assert_eq!(postings.doc_freq(), 0);
}
#[test]
fn test_block_segment_postings() {
let mut block_segments = build_block_postings(&(0..100_000).collect::<Vec<u32>>());
let mut offset: u32 = 0u32;
// checking that the `doc_freq` is correct
assert_eq!(block_segments.doc_freq(), 100_000);
loop {
let block = block_segments.docs();
if block.is_empty() {
break;
}
for (i, doc) in block.iter().cloned().enumerate() {
assert_eq!(offset + (i as u32), doc);
}
offset += block.len() as u32;
block_segments.advance();
}
}
#[test]
fn test_skip_right_at_new_block() {
let mut doc_ids = (0..128).collect::<Vec<u32>>();
// 128 is missing
doc_ids.push(129);
doc_ids.push(130);
{
let block_segments = build_block_postings(&doc_ids);
let mut docset = SegmentPostings::from_block_postings(block_segments, None);
assert_eq!(docset.seek(128), 129);
assert_eq!(docset.doc(), 129);
assert_eq!(docset.advance(), 130);
assert_eq!(docset.doc(), 130);
assert_eq!(docset.advance(), TERMINATED);
}
{
let block_segments = build_block_postings(&doc_ids);
let mut docset = SegmentPostings::from_block_postings(block_segments, None);
assert_eq!(docset.seek(129), 129);
assert_eq!(docset.doc(), 129);
assert_eq!(docset.advance(), 130);
assert_eq!(docset.doc(), 130);
assert_eq!(docset.advance(), TERMINATED);
}
{
let block_segments = build_block_postings(&doc_ids);
let mut docset = SegmentPostings::from_block_postings(block_segments, None);
assert_eq!(docset.doc(), 0);
assert_eq!(docset.seek(131), TERMINATED);
assert_eq!(docset.doc(), TERMINATED);
}
}
fn build_block_postings(docs: &[DocId]) -> BlockSegmentPostings {
let mut schema_builder = Schema::builder();
let int_field = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
let mut last_doc = 0u32;
for &doc in docs {
for _ in last_doc..doc {
index_writer.add_document(doc!(int_field=>1u64));
}
index_writer.add_document(doc!(int_field=>0u64));
last_doc = doc + 1;
}
index_writer.commit().unwrap();
let searcher = index.reader().unwrap().searcher();
let segment_reader = searcher.segment_reader(0);
let inverted_index = segment_reader.inverted_index(int_field);
let term = Term::from_field_u64(int_field, 0u64);
let term_info = inverted_index.get_term_info(&term).unwrap();
inverted_index.read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic)
}
#[test]
fn test_block_segment_postings_seek() {
let mut docs = vec![0];
for i in 0..1300 {
docs.push((i * i / 100) + i);
}
let mut block_postings = build_block_postings(&docs[..]);
for i in vec![0, 424, 10000] {
block_postings.seek(i);
let docs = block_postings.docs();
assert!(docs[0] <= i);
assert!(docs.last().cloned().unwrap_or(0u32) >= i);
}
block_postings.seek(100_000);
assert_eq!(block_postings.doc(COMPRESSION_BLOCK_SIZE - 1), TERMINATED);
}
#[test]
fn test_reset_block_segment_postings() {
let mut schema_builder = Schema::builder();
let int_field = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
// create two postings list, one containg even number,
// the other containing odd numbers.
for i in 0..6 {
let doc = doc!(int_field=> (i % 2) as u64);
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let searcher = index.reader().unwrap().searcher();
let segment_reader = searcher.segment_reader(0);
let mut block_segments;
{
let term = Term::from_field_u64(int_field, 0u64);
let inverted_index = segment_reader.inverted_index(int_field);
let term_info = inverted_index.get_term_info(&term).unwrap();
block_segments = inverted_index
.read_block_postings_from_terminfo(&term_info, IndexRecordOption::Basic);
}
assert_eq!(block_segments.docs(), &[0, 2, 4]);
{
let term = Term::from_field_u64(int_field, 1u64);
let inverted_index = segment_reader.inverted_index(int_field);
let term_info = inverted_index.get_term_info(&term).unwrap();
inverted_index.reset_block_postings_from_terminfo(&term_info, &mut block_segments);
}
assert_eq!(block_segments.docs(), &[1, 3, 5]);
}
}

109
src/postings/compression/mod.rs
View File

@@ -17,6 +17,12 @@ pub struct BlockEncoder {
pub output_len: usize,
}
impl Default for BlockEncoder {
fn default() -> Self {
BlockEncoder::new()
}
}
impl BlockEncoder {
pub fn new() -> BlockEncoder {
BlockEncoder {
@@ -46,19 +52,23 @@ impl BlockEncoder {
/// We ensure that the OutputBuffer is align on 128 bits
/// in order to run SSE2 linear search on it.
#[repr(align(128))]
#[derive(Clone)]
pub(crate) struct AlignedBuffer(pub [u32; COMPRESSION_BLOCK_SIZE]);
#[derive(Clone)]
pub struct BlockDecoder {
bitpacker: BitPacker4x,
output: AlignedBuffer,
pub output_len: usize,
}
impl BlockDecoder {
pub fn new() -> BlockDecoder {
impl Default for BlockDecoder {
fn default() -> Self {
BlockDecoder::with_val(0u32)
}
}
impl BlockDecoder {
pub fn with_val(val: u32) -> BlockDecoder {
BlockDecoder {
bitpacker: BitPacker4x::new(),
@@ -90,8 +100,8 @@ impl BlockDecoder {
}
#[inline]
pub(crate) fn output_aligned(&self) -> (&AlignedBuffer, usize) {
(&self.output, self.output_len)
pub(crate) fn output_aligned(&self) -> &AlignedBuffer {
&self.output
}
#[inline]
@@ -134,11 +144,14 @@ pub trait VIntDecoder {
/// For instance, if delta encoded are `1, 3, 9`, and the
/// `offset` is 5, then the output will be:
/// `5 + 1 = 6, 6 + 3= 9, 9 + 9 = 18`
fn uncompress_vint_sorted<'a>(
///
/// The value given in `padding` will be used to fill the remaining `128 - num_els` values.
fn uncompress_vint_sorted(
&mut self,
compressed_data: &'a [u8],
compressed_data: &[u8],
offset: u32,
num_els: usize,
padding: u32,
) -> usize;
/// Uncompress an array of `u32s`, compressed using variable
@@ -146,7 +159,14 @@ pub trait VIntDecoder {
///
/// The method takes a number of int to decompress, and returns
/// the amount of bytes that were read to decompress them.
fn uncompress_vint_unsorted<'a>(&mut self, compressed_data: &'a [u8], num_els: usize) -> usize;
///
/// The value given in `padding` will be used to fill the remaining `128 - num_els` values.
fn uncompress_vint_unsorted(
&mut self,
compressed_data: &[u8],
num_els: usize,
padding: u32,
) -> usize;
}
impl VIntEncoder for BlockEncoder {
@@ -160,18 +180,26 @@ impl VIntEncoder for BlockEncoder {
}
impl VIntDecoder for BlockDecoder {
fn uncompress_vint_sorted<'a>(
fn uncompress_vint_sorted(
&mut self,
compressed_data: &'a [u8],
compressed_data: &[u8],
offset: u32,
num_els: usize,
padding: u32,
) -> usize {
self.output_len = num_els;
self.output.0.iter_mut().for_each(|el| *el = padding);
vint::uncompress_sorted(compressed_data, &mut self.output.0[..num_els], offset)
}
fn uncompress_vint_unsorted<'a>(&mut self, compressed_data: &'a [u8], num_els: usize) -> usize {
fn uncompress_vint_unsorted(
&mut self,
compressed_data: &[u8],
num_els: usize,
padding: u32,
) -> usize {
self.output_len = num_els;
self.output.0.iter_mut().for_each(|el| *el = padding);
vint::uncompress_unsorted(compressed_data, &mut self.output.0[..num_els])
}
}
@@ -180,13 +208,14 @@ impl VIntDecoder for BlockDecoder {
pub mod tests {
use super::*;
use crate::TERMINATED;
#[test]
fn test_encode_sorted_block() {
let vals: Vec<u32> = (0u32..128u32).map(|i| i * 7).collect();
let mut encoder = BlockEncoder::new();
let (num_bits, compressed_data) = encoder.compress_block_sorted(&vals, 0);
let mut decoder = BlockDecoder::new();
let mut decoder = BlockDecoder::default();
{
let consumed_num_bytes = decoder.uncompress_block_sorted(compressed_data, 0, num_bits);
assert_eq!(consumed_num_bytes, compressed_data.len());
@@ -199,9 +228,9 @@ pub mod tests {
#[test]
fn test_encode_sorted_block_with_offset() {
let vals: Vec<u32> = (0u32..128u32).map(|i| 11 + i * 7).collect();
let mut encoder = BlockEncoder::new();
let mut encoder = BlockEncoder::default();
let (num_bits, compressed_data) = encoder.compress_block_sorted(&vals, 10);
let mut decoder = BlockDecoder::new();
let mut decoder = BlockDecoder::default();
{
let consumed_num_bytes = decoder.uncompress_block_sorted(compressed_data, 10, num_bits);
assert_eq!(consumed_num_bytes, compressed_data.len());
@@ -216,11 +245,11 @@ pub mod tests {
let mut compressed: Vec<u8> = Vec::new();
let n = 128;
let vals: Vec<u32> = (0..n).map(|i| 11u32 + (i as u32) * 7u32).collect();
let mut encoder = BlockEncoder::new();
let mut encoder = BlockEncoder::default();
let (num_bits, compressed_data) = encoder.compress_block_sorted(&vals, 10);
compressed.extend_from_slice(compressed_data);
compressed.push(173u8);
let mut decoder = BlockDecoder::new();
let mut decoder = BlockDecoder::default();
{
let consumed_num_bytes = decoder.uncompress_block_sorted(&compressed, 10, num_bits);
assert_eq!(consumed_num_bytes, compressed.len() - 1);
@@ -236,11 +265,11 @@ pub mod tests {
let mut compressed: Vec<u8> = Vec::new();
let n = 128;
let vals: Vec<u32> = (0..n).map(|i| 11u32 + (i as u32) * 7u32 % 12).collect();
let mut encoder = BlockEncoder::new();
let mut encoder = BlockEncoder::default();
let (num_bits, compressed_data) = encoder.compress_block_unsorted(&vals);
compressed.extend_from_slice(compressed_data);
compressed.push(173u8);
let mut decoder = BlockDecoder::new();
let mut decoder = BlockDecoder::default();
{
let consumed_num_bytes = decoder.uncompress_block_unsorted(&compressed, num_bits);
assert_eq!(consumed_num_bytes + 1, compressed.len());
@@ -251,20 +280,27 @@ pub mod tests {
}
}
#[test]
fn test_block_decoder_initialization() {
let block = BlockDecoder::with_val(TERMINATED);
assert_eq!(block.output(0), TERMINATED);
}
#[test]
fn test_encode_vint() {
{
let expected_length = 154;
let mut encoder = BlockEncoder::new();
let input: Vec<u32> = (0u32..123u32).map(|i| 4 + i * 7 / 2).into_iter().collect();
for offset in &[0u32, 1u32, 2u32] {
let encoded_data = encoder.compress_vint_sorted(&input, *offset);
assert!(encoded_data.len() <= expected_length);
let mut decoder = BlockDecoder::new();
let consumed_num_bytes =
decoder.uncompress_vint_sorted(&encoded_data, *offset, input.len());
assert_eq!(consumed_num_bytes, encoded_data.len());
assert_eq!(input, decoder.output_array());
const PADDING_VALUE: u32 = 234_234_345u32;
let expected_length = 154;
let mut encoder = BlockEncoder::new();
let input: Vec<u32> = (0u32..123u32).map(|i| 4 + i * 7 / 2).into_iter().collect();
for offset in &[0u32, 1u32, 2u32] {
let encoded_data = encoder.compress_vint_sorted(&input, *offset);
assert!(encoded_data.len() <= expected_length);
let mut decoder = BlockDecoder::default();
let consumed_num_bytes =
decoder.uncompress_vint_sorted(&encoded_data, *offset, input.len(), PADDING_VALUE);
assert_eq!(consumed_num_bytes, encoded_data.len());
assert_eq!(input, decoder.output_array());
for i in input.len()..COMPRESSION_BLOCK_SIZE {
assert_eq!(decoder.output(i), PADDING_VALUE);
}
}
}
@@ -274,13 +310,16 @@ pub mod tests {
mod bench {
use super::*;
use crate::TERMINATED;
use rand::rngs::StdRng;
use rand::Rng;
use rand::SeedableRng;
use rand::{Rng, XorShiftRng};
use test::Bencher;
fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> {
let seed: &[u8; 16] = &[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, seed_val];
let mut rng: XorShiftRng = XorShiftRng::from_seed(*seed);
let mut seed: [u8; 32] = [0; 32];
seed[31] = seed_val;
let mut rng = StdRng::from_seed(seed);
(0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect()
}
@@ -302,7 +341,7 @@ mod bench {
let mut encoder = BlockEncoder::new();
let data = generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
let (num_bits, compressed) = encoder.compress_block_sorted(&data, 0u32);
let mut decoder = BlockDecoder::new();
let mut decoder = BlockDecoder::default();
b.iter(|| {
decoder.uncompress_block_sorted(compressed, 0u32, num_bits);
});
@@ -337,9 +376,9 @@ mod bench {
let mut encoder = BlockEncoder::new();
let data = generate_array(NUM_INTS_BENCH_VINT, 0.001);
let compressed = encoder.compress_vint_sorted(&data, 0u32);
let mut decoder = BlockDecoder::new();
let mut decoder = BlockDecoder::default();
b.iter(|| {
decoder.uncompress_vint_sorted(compressed, 0u32, NUM_INTS_BENCH_VINT);
decoder.uncompress_vint_sorted(compressed, 0u32, NUM_INTS_BENCH_VINT, TERMINATED);
});
}
}

2
src/postings/compression/vint.rs
View File

@@ -42,7 +42,7 @@ pub(crate) fn compress_unsorted<'a>(input: &[u32], output: &'a mut [u8]) -> &'a
}
#[inline(always)]
pub fn uncompress_sorted<'a>(compressed_data: &'a [u8], output: &mut [u32], offset: u32) -> usize {
pub fn uncompress_sorted(compressed_data: &[u8], output: &mut [u32], offset: u32) -> usize {
let mut read_byte = 0;
let mut result = offset;
for output_mut in output.iter_mut() {

284
src/postings/mod.rs
View File

@@ -3,11 +3,9 @@ Postings module (also called inverted index)
*/
mod block_search;
mod block_segment_postings;
pub(crate) mod compression;
/// Postings module
///
/// Postings, also called inverted lists, is the key datastructure
/// to full-text search.
mod field_stats;
mod postings;
mod postings_writer;
mod recorder;
@@ -18,22 +16,22 @@ mod stacker;
mod term_info;
pub(crate) use self::block_search::BlockSearcher;
pub(crate) use self::field_stats::{FieldStat, FieldStats};
pub(crate) use self::postings_writer::MultiFieldPostingsWriter;
pub use self::serializer::{FieldSerializer, InvertedIndexSerializer};
use self::compression::COMPRESSION_BLOCK_SIZE;
pub use self::postings::Postings;
pub(crate) use self::skip::SkipReader;
pub(crate) use self::skip::{BlockInfo, SkipReader};
pub use self::term_info::TermInfo;
pub use self::segment_postings::{BlockSegmentPostings, SegmentPostings};
pub use self::block_segment_postings::BlockSegmentPostings;
pub use self::segment_postings::SegmentPostings;
pub(crate) use self::stacker::compute_table_size;
pub use crate::common::HasLen;
pub(crate) const USE_SKIP_INFO_LIMIT: u32 = COMPRESSION_BLOCK_SIZE as u32;
pub(crate) type UnorderedTermId = u64;
#[cfg_attr(feature = "cargo-clippy", allow(clippy::enum_variant_names))]
@@ -51,7 +49,7 @@ pub mod tests {
use crate::core::Index;
use crate::core::SegmentComponent;
use crate::core::SegmentReader;
use crate::docset::{DocSet, SkipResult};
use crate::docset::{DocSet, TERMINATED};
use crate::fieldnorm::FieldNormReader;
use crate::indexer::operation::AddOperation;
use crate::indexer::SegmentWriter;
@@ -69,45 +67,42 @@ pub mod tests {
use std::iter;
#[test]
pub fn test_position_write() {
pub fn test_position_write() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut segment = index.new_segment();
let mut posting_serializer = InvertedIndexSerializer::open(&mut segment).unwrap();
{
let mut field_serializer = posting_serializer.new_field(text_field, 120 * 4).unwrap();
field_serializer.new_term("abc".as_bytes()).unwrap();
for doc_id in 0u32..120u32 {
let delta_positions = vec![1, 2, 3, 2];
field_serializer
.write_doc(doc_id, 4, &delta_positions)
.unwrap();
}
field_serializer.close_term().unwrap();
let mut posting_serializer = InvertedIndexSerializer::open(&mut segment)?;
let mut field_serializer = posting_serializer.new_field(text_field, 120 * 4, None)?;
field_serializer.new_term("abc".as_bytes(), 12u32)?;
for doc_id in 0u32..120u32 {
let delta_positions = vec![1, 2, 3, 2];
field_serializer.write_doc(doc_id, 4, &delta_positions)?;
}
posting_serializer.close().unwrap();
let read = segment.open_read(SegmentComponent::POSITIONS).unwrap();
field_serializer.close_term()?;
posting_serializer.close()?;
let read = segment.open_read(SegmentComponent::POSITIONS)?;
assert!(read.len() <= 140);
Ok(())
}
#[test]
pub fn test_skip_positions() {
pub fn test_skip_positions() -> crate::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, 30_000_000).unwrap();
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(title => r#"abc abc abc"#));
index_writer.add_document(doc!(title => r#"abc be be be be abc"#));
for _ in 0..1_000 {
index_writer.add_document(doc!(title => r#"abc abc abc"#));
}
index_writer.add_document(doc!(title => r#"abc be be be be abc"#));
index_writer.commit().unwrap();
index_writer.commit()?;
let searcher = index.reader().unwrap().searcher();
let searcher = index.reader()?.searcher();
let inverted_index = searcher.segment_reader(0u32).inverted_index(title);
let term = Term::from_field_text(title, "abc");
let mut positions = Vec::new();
@@ -115,29 +110,12 @@ pub mod tests {
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
postings.advance();
assert_eq!(postings.doc(), 0);
postings.positions(&mut positions);
assert_eq!(&[0, 1, 2], &positions[..]);
postings.positions(&mut positions);
assert_eq!(&[0, 1, 2], &positions[..]);
postings.advance();
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
}
{
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
postings.advance();
postings.advance();
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
}
{
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert_eq!(postings.skip_next(1), SkipResult::Reached);
assert_eq!(postings.advance(), 1);
assert_eq!(postings.doc(), 1);
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
@@ -146,7 +124,25 @@ pub mod tests {
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert_eq!(postings.skip_next(1002), SkipResult::Reached);
assert_eq!(postings.doc(), 0);
assert_eq!(postings.advance(), 1);
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
}
{
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert_eq!(postings.seek(1), 1);
assert_eq!(postings.doc(), 1);
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
}
{
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert_eq!(postings.seek(1002), 1002);
assert_eq!(postings.doc(), 1002);
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
@@ -155,12 +151,13 @@ pub mod tests {
let mut postings = inverted_index
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert_eq!(postings.skip_next(100), SkipResult::Reached);
assert_eq!(postings.skip_next(1002), SkipResult::Reached);
assert_eq!(postings.seek(100), 100);
assert_eq!(postings.seek(1002), 1002);
assert_eq!(postings.doc(), 1002);
postings.positions(&mut positions);
assert_eq!(&[0, 5], &positions[..]);
}
Ok(())
}
#[test]
@@ -181,7 +178,7 @@ pub mod tests {
.tokenizers()
.register("simple_no_truncation", SimpleTokenizer);
let reader = index.reader().unwrap();
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(NoMergePolicy));
{
index_writer.add_document(doc!(text_field=>exceeding_token_text));
@@ -210,7 +207,7 @@ pub mod tests {
}
#[test]
pub fn test_position_and_fieldnorm1() {
pub fn test_position_and_fieldnorm1() -> crate::Result<()> {
let mut positions = Vec::new();
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
@@ -222,42 +219,38 @@ pub mod tests {
let mut segment_writer =
SegmentWriter::for_segment(3_000_000, segment.clone(), &schema).unwrap();
{
let mut doc = Document::default();
// checking that position works if the field has two values
doc.add_text(text_field, "a b a c a d a a.");
doc.add_text(text_field, "d d d d a");
let op = AddOperation {
opstamp: 0u64,
document: doc,
document: doc!(
text_field => "a b a c a d a a.",
text_field => "d d d d a"
),
};
segment_writer.add_document(op, &schema).unwrap();
segment_writer.add_document(op, &schema)?;
}
{
let mut doc = Document::default();
doc.add_text(text_field, "b a");
let op = AddOperation {
opstamp: 1u64,
document: doc,
document: doc!(text_field => "b a"),
};
segment_writer.add_document(op, &schema).unwrap();
}
for i in 2..1000 {
let mut doc = Document::default();
let mut text = iter::repeat("e ").take(i).collect::<String>();
let mut text: String = iter::repeat("e ").take(i).collect();
text.push_str(" a");
doc.add_text(text_field, &text);
let op = AddOperation {
opstamp: 2u64,
document: doc,
document: doc!(text_field => text),
};
segment_writer.add_document(op, &schema).unwrap();
}
segment_writer.finalize().unwrap();
segment_writer.finalize()?;
}
{
let segment_reader = SegmentReader::open(&segment).unwrap();
let segment_reader = SegmentReader::open(&segment)?;
{
let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field);
let fieldnorm_reader = segment_reader.get_fieldnorms_reader(text_field)?;
assert_eq!(fieldnorm_reader.fieldnorm(0), 8 + 5);
assert_eq!(fieldnorm_reader.fieldnorm(1), 2);
for i in 2..1000 {
@@ -281,22 +274,21 @@ pub mod tests {
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert_eq!(postings_a.len(), 1000);
assert!(postings_a.advance());
assert_eq!(postings_a.doc(), 0);
assert_eq!(postings_a.term_freq(), 6);
postings_a.positions(&mut positions);
assert_eq!(&positions[..], [0, 2, 4, 6, 7, 13]);
assert!(postings_a.advance());
assert_eq!(postings_a.advance(), 1u32);
assert_eq!(postings_a.doc(), 1u32);
assert_eq!(postings_a.term_freq(), 1);
for i in 2u32..1000u32 {
assert!(postings_a.advance());
assert_eq!(postings_a.advance(), i);
assert_eq!(postings_a.term_freq(), 1);
postings_a.positions(&mut positions);
assert_eq!(&positions[..], [i]);
assert_eq!(postings_a.doc(), i);
}
assert!(!postings_a.advance());
assert_eq!(postings_a.advance(), TERMINATED);
}
{
let term_e = Term::from_field_text(text_field, "e");
@@ -306,7 +298,6 @@ pub mod tests {
.unwrap();
assert_eq!(postings_e.len(), 1000 - 2);
for i in 2u32..1000u32 {
assert!(postings_e.advance());
assert_eq!(postings_e.term_freq(), i);
postings_e.positions(&mut positions);
assert_eq!(positions.len(), i as usize);
@@ -314,10 +305,12 @@ pub mod tests {
assert_eq!(positions[j], (j as u32));
}
assert_eq!(postings_e.doc(), i);
postings_e.advance();
}
assert!(!postings_e.advance());
assert_eq!(postings_e.doc(), TERMINATED);
}
}
Ok(())
}
#[test]
@@ -328,17 +321,9 @@ pub 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 doc = Document::default();
doc.add_text(text_field, "g b b d c g c");
index_writer.add_document(doc);
}
{
let mut doc = Document::default();
doc.add_text(text_field, "g a b b a d c g c");
index_writer.add_document(doc);
}
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "g b b d c g c"));
index_writer.add_document(doc!(text_field => "g a b b a d c g c"));
assert!(index_writer.commit().is_ok());
}
let term_a = Term::from_field_text(text_field, "a");
@@ -348,7 +333,6 @@ pub mod tests {
.inverted_index(text_field)
.read_postings(&term_a, IndexRecordOption::WithFreqsAndPositions)
.unwrap();
assert!(postings.advance());
assert_eq!(postings.doc(), 1u32);
postings.positions(&mut positions);
assert_eq!(&positions[..], &[1u32, 4]);
@@ -356,9 +340,9 @@ pub mod tests {
#[test]
fn test_skip_next() {
let term_0 = Term::from_field_u64(Field(0), 0);
let term_1 = Term::from_field_u64(Field(0), 1);
let term_2 = Term::from_field_u64(Field(0), 2);
let term_0 = Term::from_field_u64(Field::from_field_id(0), 0);
let term_1 = Term::from_field_u64(Field::from_field_id(0), 1);
let term_2 = Term::from_field_u64(Field::from_field_id(0), 2);
let num_docs = 300u32;
@@ -369,12 +353,9 @@ pub mod tests {
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for i in 0..num_docs {
let mut doc = Document::default();
doc.add_u64(value_field, 2);
doc.add_u64(value_field, (i % 2) as u64);
let mut index_writer = index.writer_for_tests().unwrap();
for i in 0u64..num_docs as u64 {
let doc = doc!(value_field => 2u64, value_field => i % 2u64);
index_writer.add_document(doc);
}
assert!(index_writer.commit().is_ok());
@@ -391,11 +372,10 @@ pub mod tests {
.inverted_index(term_2.field())
.read_postings(&term_2, IndexRecordOption::Basic)
.unwrap();
assert_eq!(segment_postings.skip_next(i), SkipResult::Reached);
assert_eq!(segment_postings.seek(i), i);
assert_eq!(segment_postings.doc(), i);
assert_eq!(segment_postings.skip_next(j), SkipResult::Reached);
assert_eq!(segment_postings.seek(j), j);
assert_eq!(segment_postings.doc(), j);
}
}
@@ -407,17 +387,16 @@ pub mod tests {
.unwrap();
// check that `skip_next` advances the iterator
assert!(segment_postings.advance());
assert_eq!(segment_postings.doc(), 0);
assert_eq!(segment_postings.skip_next(1), SkipResult::Reached);
assert_eq!(segment_postings.seek(1), 1);
assert_eq!(segment_postings.doc(), 1);
assert_eq!(segment_postings.skip_next(1), SkipResult::OverStep);
assert_eq!(segment_postings.doc(), 2);
assert_eq!(segment_postings.seek(1), 1);
assert_eq!(segment_postings.doc(), 1);
// check that going beyond the end is handled
assert_eq!(segment_postings.skip_next(num_docs), SkipResult::End);
assert_eq!(segment_postings.seek(num_docs), TERMINATED);
}
// check that filtering works
@@ -428,7 +407,7 @@ pub mod tests {
.unwrap();
for i in 0..num_docs / 2 {
assert_eq!(segment_postings.skip_next(i * 2), SkipResult::Reached);
assert_eq!(segment_postings.seek(i * 2), i * 2);
assert_eq!(segment_postings.doc(), i * 2);
}
@@ -438,18 +417,19 @@ pub mod tests {
.unwrap();
for i in 0..num_docs / 2 - 1 {
assert_eq!(segment_postings.skip_next(i * 2 + 1), SkipResult::OverStep);
assert!(segment_postings.seek(i * 2 + 1) > (i * 1) * 2);
assert_eq!(segment_postings.doc(), (i + 1) * 2);
}
}
// delete some of the documents
{
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.delete_term(term_0);
assert!(index_writer.commit().is_ok());
}
let searcher = index.reader().unwrap().searcher();
assert_eq!(searcher.segment_readers().len(), 1);
let segment_reader = searcher.segment_reader(0);
// make sure seeking still works
@@ -460,11 +440,11 @@ pub mod tests {
.unwrap();
if i % 2 == 0 {
assert_eq!(segment_postings.skip_next(i), SkipResult::Reached);
assert_eq!(segment_postings.seek(i), i);
assert_eq!(segment_postings.doc(), i);
assert!(segment_reader.is_deleted(i));
} else {
assert_eq!(segment_postings.skip_next(i), SkipResult::Reached);
assert_eq!(segment_postings.seek(i), i);
assert_eq!(segment_postings.doc(), i);
}
}
@@ -479,12 +459,16 @@ pub mod tests {
let mut last = 2; // start from 5 to avoid seeking to 3 twice
let mut cur = 3;
loop {
match segment_postings.skip_next(cur) {
SkipResult::End => break,
SkipResult::Reached => assert_eq!(segment_postings.doc(), cur),
SkipResult::OverStep => assert_eq!(segment_postings.doc(), cur + 1),
let seek = segment_postings.seek(cur);
if seek == TERMINATED {
break;
}
assert_eq!(seek, segment_postings.doc());
if seek == cur {
assert_eq!(segment_postings.doc(), cur);
} else {
assert_eq!(segment_postings.doc(), cur + 1);
}
let next = cur + last;
last = cur;
cur = next;
@@ -494,7 +478,7 @@ pub mod tests {
// delete everything else
{
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.delete_term(term_1);
assert!(index_writer.commit().is_ok());
}
@@ -511,19 +495,19 @@ pub mod tests {
}
pub static TERM_A: Lazy<Term> = Lazy::new(|| {
let field = Field(0);
let field = Field::from_field_id(0);
Term::from_field_text(field, "a")
});
pub static TERM_B: Lazy<Term> = Lazy::new(|| {
let field = Field(0);
let field = Field::from_field_id(0);
Term::from_field_text(field, "b")
});
pub static TERM_C: Lazy<Term> = Lazy::new(|| {
let field = Field(0);
let field = Field::from_field_id(0);
Term::from_field_text(field, "c")
});
pub static TERM_D: Lazy<Term> = Lazy::new(|| {
let field = Field(0);
let field = Field::from_field_id(0);
Term::from_field_text(field, "d")
});
@@ -537,7 +521,7 @@ pub mod tests {
let index = Index::create_in_ram(schema);
let posting_list_size = 1_000_000;
{
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..posting_list_size {
let mut doc = Document::default();
if rng.gen_bool(1f64 / 15f64) {
@@ -570,7 +554,7 @@ pub mod tests {
}
impl<TDocSet: DocSet> DocSet for UnoptimizedDocSet<TDocSet> {
fn advance(&mut self) -> bool {
fn advance(&mut self) -> DocId {
self.0.advance()
}
@@ -595,50 +579,45 @@ pub mod tests {
) {
for target in targets {
let mut postings_opt = postings_factory();
if target < postings_opt.doc() {
continue;
}
let mut postings_unopt = UnoptimizedDocSet::wrap(postings_factory());
let skip_result_opt = postings_opt.skip_next(target);
let skip_result_unopt = postings_unopt.skip_next(target);
let skip_result_opt = postings_opt.seek(target);
let skip_result_unopt = postings_unopt.seek(target);
assert_eq!(
skip_result_unopt, skip_result_opt,
"Failed while skipping to {}",
target
);
match skip_result_opt {
SkipResult::Reached => assert_eq!(postings_opt.doc(), target),
SkipResult::OverStep => assert!(postings_opt.doc() > target),
SkipResult::End => {
return;
}
assert!(skip_result_opt >= target);
assert_eq!(skip_result_opt, postings_opt.doc());
if skip_result_opt == TERMINATED {
return;
}
while postings_opt.advance() {
assert!(postings_unopt.advance());
assert_eq!(
postings_opt.doc(),
postings_unopt.doc(),
"Failed while skipping to {}",
target
);
while postings_opt.doc() != TERMINATED {
assert_eq!(postings_opt.doc(), postings_unopt.doc());
assert_eq!(postings_opt.advance(), postings_unopt.advance());
}
assert!(!postings_unopt.advance());
}
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use super::tests::*;
use docset::SkipResult;
use query::Intersection;
use schema::IndexRecordOption;
use crate::docset::TERMINATED;
use crate::query::Intersection;
use crate::schema::IndexRecordOption;
use crate::tests;
use crate::DocSet;
use test::{self, Bencher};
use tests;
use DocSet;
#[bench]
fn bench_segment_postings(b: &mut Bencher) {
let searcher = INDEX.searcher();
let reader = INDEX.reader().unwrap();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
b.iter(|| {
@@ -646,13 +625,14 @@ mod bench {
.inverted_index(TERM_A.field())
.read_postings(&*TERM_A, IndexRecordOption::Basic)
.unwrap();
while segment_postings.advance() {}
while segment_postings.advance() != TERMINATED {}
});
}
#[bench]
fn bench_segment_intersection(b: &mut Bencher) {
let searcher = INDEX.searcher();
let reader = INDEX.reader().unwrap();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
b.iter(|| {
let segment_postings_a = segment_reader
@@ -677,12 +657,13 @@ mod bench {
segment_postings_c,
segment_postings_d,
]);
while intersection.advance() {}
while intersection.advance() != TERMINATED {}
});
}
fn bench_skip_next(p: f64, b: &mut Bencher) {
let searcher = INDEX.searcher();
let reader = INDEX.reader().unwrap();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
let docs = tests::sample(segment_reader.num_docs(), p);
@@ -692,11 +673,10 @@ mod bench {
.unwrap();
let mut existing_docs = Vec::new();
segment_postings.advance();
for doc in &docs {
if *doc >= segment_postings.doc() {
existing_docs.push(*doc);
if segment_postings.skip_next(*doc) == SkipResult::End {
if segment_postings.seek(*doc) == TERMINATED {
break;
}
}
@@ -708,7 +688,7 @@ mod bench {
.read_postings(&*TERM_A, IndexRecordOption::Basic)
.unwrap();
for doc in &existing_docs {
if segment_postings.skip_next(*doc) == SkipResult::End {
if segment_postings.seek(*doc) == TERMINATED {
break;
}
}
@@ -737,7 +717,8 @@ mod bench {
#[bench]
fn bench_iterate_segment_postings(b: &mut Bencher) {
let searcher = INDEX.searcher();
let reader = INDEX.reader().unwrap();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0);
b.iter(|| {
let n: u32 = test::black_box(17);
@@ -746,8 +727,9 @@ mod bench {
.read_postings(&*TERM_A, IndexRecordOption::Basic)
.unwrap();
let mut s = 0u32;
while segment_postings.advance() {
while segment_postings.doc() != TERMINATED {
s += (segment_postings.doc() & n) % 1024;
segment_postings.advance();
}
s
});

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