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

Compare commits

base: rust:criterion
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:race-condition-in-tests
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

52 Commits
criterion ... race-condi

Author SHA1 Message Date
Paul Masurel
72bd0cfd4a Closes #708 
Fixes a race condition in the test.
 2019-11-21 10:30:10 +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
116 changed files with 2949 additions and 1290 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
.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

19
CHANGELOG.md
View File

@@ -5,7 +5,26 @@ Tantivy 0.11.0
- 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)
- 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?
- `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 0.10.2
=====================
- Closes #656. Solving memory leak.
Tantivy 0.10.1
=====================

30
Cargo.toml
View File

@@ -13,10 +13,11 @@ keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
base64 = "0.10.0"
base64 = "0.11.0"
byteorder = "1.0"
once_cell = "0.2"
regex = "1.0"
crc32fast = "1.2.0"
once_cell = "1.0"
regex ={version = "1.3.0", default-features = false, features = ["std"]}
tantivy-fst = "0.1"
memmap = {version = "0.7", optional=true}
lz4 = {version="1.20", optional=true}
@@ -24,7 +25,6 @@ snap = {version="0.2"}
atomicwrites = {version="0.2.2", optional=true}
tempfile = "3.0"
log = "0.4"
combine = ">=3.6.0,<4.0.0"
serde = "1.0"
serde_derive = "1.0"
serde_json = "1.0"
@@ -34,25 +34,25 @@ itertools = "0.8"
levenshtein_automata = {version="0.1", features=["fst_automaton"]}
notify = {version="4", optional=true}
bit-set = "0.5"
uuid = { version = "0.7.2", features = ["v4", "serde"] }
uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.7"
futures = "0.1"
futures-cpupool = "0.1"
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 = { path="./query-grammar" }
bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
census = "0.2"
census = "0.3"
fnv = "1.0.6"
owned-read = "0.4"
failure = "0.1"
htmlescape = "0.3.1"
fail = "0.3"
scoped-pool = "1.0"
murmurhash32 = "0.2"
chrono = "0.4"
smallvec = "0.6"
smallvec = "1.0"
rayon = "1"
[target.'cfg(windows)'.dependencies]
winapi = "0.3"
@@ -63,6 +63,10 @@ maplit = "1"
matches = "0.1.8"
time = "0.1.42"
[dev-dependencies.fail]
version = "0.3"
features = ["failpoints"]
[profile.release]
opt-level = 3
debug = false
@@ -80,12 +84,12 @@ 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.

3
Makefile Normal file
View File

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

57
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.
@@ -31,7 +31,7 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark
Tantivy is typically faster than Lucene, but the results will depend on
Tantivy is typically faster than Lucene, but the results depend on
the nature of the queries in your workload.
The following [benchmark](https://tantivy-search.github.io/bench/) break downs
@@ -40,19 +40,19 @@ performance for different type of queries / collection.
# 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)) and [Japanese](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter))
- 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
@@ -61,43 +61,42 @@ performance for different type of queries / collection.
# 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.
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'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 +107,7 @@ 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 +115,13 @@ 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 +129,7 @@ $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

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

36
examples/basic_search.rs
View File

@@ -5,20 +5,17 @@
//
// 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 tantivy::{doc, Index, ReloadPolicy};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
@@ -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.
@@ -149,8 +145,8 @@ 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 +158,14 @@ 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 +181,7 @@ 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 +201,7 @@ 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 +217,7 @@ 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))?;

5
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, SegmentReader, TantivyError};
#[derive(Default)]
struct Stats {

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.

4
examples/faceted_search.rs
View File

@@ -12,12 +12,10 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::FacetCollector;
use tantivy::query::AllQuery;
use tantivy::schema::*;
use tantivy::Index;
use tantivy::{doc, Index};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {

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

5
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, DocId, DocSet, Index, Postings};
fn main() -> tantivy::Result<()> {
// We first create a schema for the sake of the

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));
}

138
examples/pre_tokenized_text.rs Normal file
View File

@@ -0,0 +1,138 @@
// # 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::tokenizer::{PreTokenizedString, SimpleTokenizer, Token, TokenStream, Tokenizer};
use tantivy::collector::{Count, TopDocs};
use tantivy::query::TermQuery;
use tantivy::schema::*;
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` using
// `add_pre_tokenized_text` method of `Document`
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);
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(())
}

5
examples/snippet.rs
View File

@@ -7,13 +7,10 @@
// ---
// 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 tantivy::{doc, Index, Snippet, SnippetGenerator};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {

4
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`

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

@@ -0,0 +1,16 @@
[package]
name = "tantivy-query-grammar"
version = "0.11.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
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 = ">=3.6.0,<4.0.0"

17
query-grammar/src/lib.rs Normal file
View File

@@ -0,0 +1,17 @@
#![recursion_limit = "100"]
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)
}

45
src/query/occur.rs → query-grammar/src/occur.rs
View File

@@ -1,5 +1,8 @@
use std::fmt;
use std::fmt::Write;
/// Defines whether a term in a query must be present,
/// should be present or must not 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,
@@ -18,32 +21,38 @@ impl Occur {
/// - `Should` => '?',
/// - `Must` => '+'
/// - `Not` => '-'
pub fn to_char(self) -> char {
fn to_char(self) -> char {
match self {
Occur::Should => '?',
Occur::Must => '+',
Occur::MustNot => '-',
}
}
}
/// Compose two occur values.
pub fn compose_occur(left: Occur, right: Occur) -> Occur {
match left {
Occur::Should => right,
Occur::Must => {
if right == Occur::MustNot {
Occur::MustNot
} else {
Occur::Must
/// Compose two occur values.
pub fn compose(left: Occur, right: Occur) -> Occur {
match left {
Occur::Should => right,
Occur::Must => {
if right == Occur::MustNot {
Occur::MustNot
} else {
Occur::Must
}
}
}
Occur::MustNot => {
if right == Occur::MustNot {
Occur::Must
} else {
Occur::MustNot
Occur::MustNot => {
if right == Occur::MustNot {
Occur::Must
} else {
Occur::MustNot
}
}
}
}
}
impl fmt::Display for Occur {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
f.write_char(self.to_char())
}
}

113
src/query/query_parser/query_grammar.rs → query-grammar/src/query_grammar.rs
View File

@@ -1,6 +1,5 @@
use super::user_input_ast::*;
use crate::query::occur::Occur;
use crate::query::query_parser::user_input_ast::UserInputBound;
use crate::Occur;
use combine::char::*;
use combine::error::StreamError;
use combine::stream::StreamErrorFor;
@@ -83,28 +82,67 @@ parser! {
}
parser! {
/// Function that parses a range out of a Stream
/// Supports ranges like:
/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
/// [a TO *], [a TO c], [abc TO bcd}
fn range[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>] {
let range_term_val = || {
word().or(negative_number()).or(char('*').with(value("*".to_string())))
};
// check for unbounded range in the form of <5, <=10, >5, >=5
let elastic_unbounded_range = (choice([attempt(string(">=")),
attempt(string("<=")),
attempt(string("<")),
attempt(string(">"))])
.skip(spaces()),
range_term_val()).
map(|(comparison_sign, bound): (&str, String)|
match comparison_sign {
">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
"<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
"<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
// default case
_ => (UserInputBound::Unbounded, UserInputBound::Unbounded)
});
let lower_bound = (one_of("{[".chars()), range_term_val())
.map(|(boundary_char, lower_bound): (char, String)|
if boundary_char == '{' { UserInputBound::Exclusive(lower_bound) }
else { UserInputBound::Inclusive(lower_bound) });
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 boundary_char == '}' { UserInputBound::Exclusive(higher_bound) }
else { UserInputBound::Inclusive(higher_bound) });
(
optional(field()),
lower_bound
.skip((spaces(), string("TO"), spaces())),
upper_bound,
).map(|(field, lower, upper)| UserInputLeaf::Range {
field,
lower,
upper
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
})
}
}
@@ -258,6 +296,49 @@ mod test {
);
}
#[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_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\"");
@@ -291,7 +372,7 @@ mod test {
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:[* 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 + ");

11
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, "\"*\"}}"),
}
}
@@ -73,6 +79,7 @@ impl UserInputBound {
match *self {
UserInputBound::Inclusive(ref contents) => contents,
UserInputBound::Exclusive(ref contents) => contents,
UserInputBound::Unbounded => &"*",
}
}
}
@@ -144,7 +151,7 @@ impl fmt::Debug for UserInputAST {
Ok(())
}
UserInputAST::Unary(ref occur, ref subquery) => {
write!(formatter, "{}({:?})", occur.to_char(), subquery)
write!(formatter, "{}({:?})", occur, subquery)
}
UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
}

7
src/collector/count_collector.rs
View File

@@ -10,12 +10,10 @@ 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, Result};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
@@ -125,5 +123,4 @@ mod tests {
assert_eq!(count_collector.harvest(), 2);
}
}
}

27
src/collector/facet_collector.rs
View File

@@ -81,12 +81,10 @@ 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, Result};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
@@ -517,7 +515,7 @@ 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"));
}
@@ -548,7 +546,7 @@ mod tests {
#[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"));
}
@@ -601,19 +599,18 @@ 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) {
@@ -630,7 +627,7 @@ 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();
for doc in docs {
@@ -639,7 +636,7 @@ mod bench {
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();
});

1
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::*;

6
src/collector/multi_collector.rs
View File

@@ -105,12 +105,10 @@ 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, Result};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {

113
src/collector/top_collector.rs
View File

@@ -12,6 +12,9 @@ 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
@@ -21,29 +24,37 @@ struct ComparableDoc<T, D> {
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,
@@ -214,4 +225,94 @@ 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(),
);
}
}
#[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()
});
}
}

55
src/collector/top_score_collector.rs
View File

@@ -15,21 +15,21 @@ use crate::SegmentLocalId;
use crate::SegmentReader;
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, Result};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
@@ -87,10 +87,8 @@ impl TopDocs {
/// 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, Result, DocAddress};
/// # use tantivy::query::{Query, QueryParser};
/// use tantivy::Searcher;
/// use tantivy::collector::TopDocs;
@@ -128,7 +126,7 @@ 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)>> {
///
@@ -197,10 +195,8 @@ 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;
@@ -302,10 +298,8 @@ 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;
@@ -437,12 +431,13 @@ 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 itertools::Itertools;
fn make_index() -> Index {
let mut schema_builder = Schema::builder();
@@ -503,6 +498,29 @@ mod tests {
);
}
#[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().map(|result| result.0).all_equal());
assert!(page_2.iter().map(|result| result.0).all_equal());
// 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() {
@@ -560,7 +578,7 @@ 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)
@@ -601,5 +619,4 @@ mod tests {
let query = query_parser.parse_query(query).unwrap();
(index, query)
}
}

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 {

5
src/common/serialize.rs
View File

@@ -199,10 +199,7 @@ 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]

20
src/core/executor.rs
View File

@@ -1,6 +1,6 @@
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.
///
@@ -11,7 +11,7 @@ use scoped_pool::{Pool, ThreadConfig};
/// used by the client. Second, we may stop using rayon in the future.
pub enum Executor {
SingleThread,
ThreadPool(Pool),
ThreadPool(ThreadPool),
}
impl Executor {
@@ -21,10 +21,12 @@ impl Executor {
}
// 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)
pub fn multi_thread(num_threads: usize, prefix: &'static str) -> 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.
@@ -48,9 +50,9 @@ impl Executor {
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 +105,7 @@ 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 +129,7 @@ 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);

131
src/core/index.rs
View File

@@ -26,9 +26,10 @@ 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::{Path, PathBuf};
use std::sync::Arc;
fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> {
@@ -72,15 +73,16 @@ 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) -> 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) -> 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`.
@@ -102,23 +104,21 @@ impl Index {
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(),
))
}
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(),
))
}
}
@@ -173,11 +173,11 @@ 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) -> Result<BoxedTokenizer> {
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<BoxedTokenizer> = match field_type {
FieldType::Str(text_options) => text_options
.get_indexing_options()
.map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -216,8 +216,22 @@ impl Index {
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
@@ -354,6 +368,11 @@ impl Index {
.map(SegmentMeta::id)
.collect())
}
/// Returns the set of corrupted files
pub fn validate_checksum(&self) -> Result<HashSet<PathBuf>> {
self.directory.list_damaged().map_err(Into::into)
}
}
impl fmt::Debug for Index {
@@ -367,12 +386,9 @@ 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() {
@@ -450,14 +466,14 @@ mod tests {
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
}
#[cfg(feature = "mmap")]
mod mmap_specific {
use super::*;
use crate::Directory;
use std::path::PathBuf;
use tempfile::TempDir;
@@ -468,22 +484,20 @@ mod tests {
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
}
#[test]
fn test_index_manual_policy_mmap() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let index = Index::create_from_tempdir(schema).unwrap();
let mut index = Index::create_from_tempdir(schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let reader = index
@@ -493,8 +507,12 @@ 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);
@@ -514,39 +532,26 @@ 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_with_num_threads(1, 3_000_000).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 {
break;
}
thread::sleep(Duration::from_millis(100));
}
assert_eq!(count, 1);
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 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 {
break;
}
thread::sleep(Duration::from_millis(100));
}
assert_eq!(count, 2);
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 2);
}
// This test will not pass on windows, because windows
@@ -563,9 +568,13 @@ 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 +588,11 @@ 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
);
}
}

21
src/core/index_meta.rs
View File

@@ -30,7 +30,6 @@ impl SegmentMetaInventory {
.collect::<Vec<_>>()
}
#[doc(hidden)]
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
let inner = InnerSegmentMeta {
segment_id,
@@ -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 {
@@ -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}"#
);
}
}

11
src/core/segment.rs
View File

@@ -50,6 +50,17 @@ 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 {

55
src/core/segment_id.rs
View File

@@ -4,6 +4,8 @@ use uuid::Uuid;
#[cfg(test)]
use once_cell::sync::Lazy;
use std::error::Error;
use std::str::FromStr;
#[cfg(test)]
use std::sync::atomic;
@@ -52,15 +54,51 @@ 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 +118,18 @@ 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());
}
}

4
src/directory/directory.rs
View File

@@ -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 [`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 [`atomic_write`]
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
/// Atomically replace the content of a file with data.

277
src/directory/footer.rs Normal file
View File

@@ -0,0 +1,277 @@
use crate::directory::read_only_source::ReadOnlySource;
use crate::directory::{AntiCallToken, TerminatingWrite};
use byteorder::{ByteOrder, LittleEndian};
use crc32fast::Hasher;
use std::io;
use std::io::Write;
const COMMON_FOOTER_SIZE: usize = 4 * 5;
type CrcHashU32 = u32;
#[derive(Debug, Clone, PartialEq)]
pub struct Footer {
pub tantivy_version: (u32, u32, u32),
pub meta: String,
pub versioned_footer: VersionedFooter,
}
impl Footer {
pub fn new(versioned_footer: VersionedFooter) -> Self {
let tantivy_version = (
env!("CARGO_PKG_VERSION_MAJOR").parse().unwrap(),
env!("CARGO_PKG_VERSION_MINOR").parse().unwrap(),
env!("CARGO_PKG_VERSION_PATCH").parse().unwrap(),
);
Footer {
tantivy_version,
meta: format!(
"tantivy v{}.{}.{}, index_format v{}",
tantivy_version.0,
tantivy_version.1,
tantivy_version.2,
versioned_footer.version()
),
versioned_footer,
}
}
/// Serialises the footer to a byte-array
/// [ versioned_footer | meta | common_footer ]
/// [ 0..8 | 8..32 | 32..52 ]
pub fn to_bytes(&self) -> Vec<u8> {
let mut res = self.versioned_footer.to_bytes();
res.extend_from_slice(self.meta.as_bytes());
let len = res.len();
res.resize(len + COMMON_FOOTER_SIZE, 0);
let mut common_footer = &mut res[len..];
LittleEndian::write_u32(&mut common_footer, self.meta.len() as u32);
LittleEndian::write_u32(&mut common_footer[4..], self.tantivy_version.0);
LittleEndian::write_u32(&mut common_footer[8..], self.tantivy_version.1);
LittleEndian::write_u32(&mut common_footer[12..], self.tantivy_version.2);
LittleEndian::write_u32(&mut common_footer[16..], (len + COMMON_FOOTER_SIZE) as u32);
res
}
pub fn from_bytes(data: &[u8]) -> Result<Self, io::Error> {
let len = data.len();
if len < COMMON_FOOTER_SIZE + 4 {
// 4 bytes for index version, stored in versioned footer
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!("File corrupted. The footer len must be over 24, while the entire file len is {}", len)
)
);
}
let size = LittleEndian::read_u32(&data[len - 4..]) as usize;
if len < size as usize {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"The footer len is {}, while the entire file len is {}. \
Your index is either corrupted or was built using a tantivy version\
anterior to 0.11.",
size, len
),
));
}
let footer = &data[len - size as usize..];
let meta_len = LittleEndian::read_u32(&footer[size - COMMON_FOOTER_SIZE..]) as usize;
let tantivy_major = LittleEndian::read_u32(&footer[size - 16..]);
let tantivy_minor = LittleEndian::read_u32(&footer[size - 12..]);
let tantivy_patch = LittleEndian::read_u32(&footer[size - 8..]);
Ok(Footer {
tantivy_version: (tantivy_major, tantivy_minor, tantivy_patch),
meta: String::from_utf8_lossy(
&footer[size - meta_len - COMMON_FOOTER_SIZE..size - COMMON_FOOTER_SIZE],
)
.into_owned(),
versioned_footer: VersionedFooter::from_bytes(
&footer[..size - meta_len - COMMON_FOOTER_SIZE],
)?,
})
}
pub fn extract_footer(source: ReadOnlySource) -> Result<(Footer, ReadOnlySource), io::Error> {
let footer = Footer::from_bytes(source.as_slice())?;
let reader = source.slice_to(source.as_slice().len() - footer.size());
Ok((footer, reader))
}
pub fn size(&self) -> usize {
self.versioned_footer.size() as usize + self.meta.len() + COMMON_FOOTER_SIZE
}
}
/// Footer that includes a crc32 hash that enables us to checksum files in the index
#[derive(Debug, Clone, PartialEq)]
pub enum VersionedFooter {
UnknownVersion { version: u32, size: u32 },
V0(CrcHashU32), // crc
}
impl VersionedFooter {
/// Serializes a valid `VersionedFooter` or panics if the version is unknown
/// [ version | crc_hash ]
/// [ 0..4 | 4..8 ]
pub fn to_bytes(&self) -> Vec<u8> {
match self {
VersionedFooter::V0(crc) => {
let mut buf = [0u8; 8];
LittleEndian::write_u32(&mut buf[0..4], 0);
LittleEndian::write_u32(&mut buf[4..8], *crc);
buf.to_vec()
}
VersionedFooter::UnknownVersion { .. } => {
panic!("Unsupported index should never get serialized");
}
}
}
pub fn from_bytes(footer: &[u8]) -> Result<Self, io::Error> {
assert!(footer.len() >= 4);
if footer.len() < 4 {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
"Footer should be more than 4 bytes.",
));
}
let version = LittleEndian::read_u32(footer);
match version {
// the first 4 bytes should be zeroed out thus returning a `0`
0 => {
if footer.len() != 8 {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The versioned footer len is {}, while it should be 8",
footer.len()
),
));
}
Ok(VersionedFooter::V0(LittleEndian::read_u32(&footer[4..])))
}
version => Ok(VersionedFooter::UnknownVersion {
version,
size: footer.len() as u32,
}),
}
}
pub fn size(&self) -> u32 {
match self {
VersionedFooter::V0(_) => 8,
VersionedFooter::UnknownVersion { size, .. } => *size,
}
}
pub fn version(&self) -> u32 {
match self {
VersionedFooter::V0(_) => 0,
VersionedFooter::UnknownVersion { version, .. } => *version,
}
}
pub fn crc(&self) -> Option<CrcHashU32> {
match self {
VersionedFooter::V0(crc) => Some(*crc),
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 crc = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V0(crc)).to_bytes();
let mut writer = self.writer.take().unwrap();
writer.write_all(&footer)?;
writer.terminate()
}
}
#[cfg(test)]
mod tests {
use crate::directory::footer::{Footer, VersionedFooter};
use regex::Regex;
#[test]
fn test_serialize_deserialize_footer() {
let crc = 123456;
let footer = Footer::new(VersionedFooter::V0(crc));
let footer_bytes = footer.to_bytes();
assert_eq!(Footer::from_bytes(&footer_bytes).unwrap(), footer);
}
#[test]
fn footer_length() {
// test to make sure the ascii art in the doc-strings is correct
let crc = 1111111 as u32;
let versioned_footer = VersionedFooter::V0(crc);
assert_eq!(versioned_footer.size(), 8);
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.find(&footer.meta).is_some());
}
#[test]
fn versioned_footer_from_bytes() {
use byteorder::{ByteOrder, LittleEndian};
let v_footer_bytes = vec![0, 0, 0, 0, 12, 35, 89, 18];
let versioned_footer = VersionedFooter::from_bytes(&v_footer_bytes).unwrap();
let expected_versioned_footer =
VersionedFooter::V0(LittleEndian::read_u32(&[12, 35, 89, 18]));
assert_eq!(versioned_footer, expected_versioned_footer);
assert_eq!(versioned_footer.to_bytes(), v_footer_bytes);
}
#[should_panic(expected = "Unsupported index should never get serialized")]
#[test]
fn versioned_footer_panic() {
use byteorder::{ByteOrder, LittleEndian};
let v_footer_bytes = vec![1; 8];
let versioned_footer = VersionedFooter::from_bytes(&v_footer_bytes).unwrap();
let expected_version = LittleEndian::read_u32(&[1, 1, 1, 1]);
let expected_versioned_footer = VersionedFooter::UnknownVersion {
version: expected_version,
size: v_footer_bytes.len() as u32,
};
assert_eq!(versioned_footer, expected_versioned_footer);
versioned_footer.to_bytes();
}
}

146
src/directory/managed_directory.rs
View File

@@ -1,6 +1,8 @@
use crate::core::MANAGED_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};
@@ -8,6 +10,7 @@ use crate::directory::{WatchCallback, WatchHandle};
use crate::error::DataCorruption;
use crate::Directory;
use crate::Result;
use crc32fast::Hasher;
use serde_json;
use std::collections::HashSet;
use std::io;
@@ -102,7 +105,10 @@ 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 +134,25 @@ 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::Error::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 +162,10 @@ 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 +188,13 @@ 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 +223,59 @@ 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 managed_paths = self
.meta_informations
.read()
.expect("Managed directory rlock poisoned in list damaged.")
.managed_paths
.clone();
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))?;
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<()> {
@@ -259,8 +317,9 @@ 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 tempfile::TempDir;
@@ -275,16 +334,15 @@ 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 +352,7 @@ 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));
}
@@ -310,13 +368,15 @@ mod tests_mmap_specific {
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 +384,45 @@ 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();
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));
}
}

101
src/directory/mmap_directory.rs
View File

@@ -11,6 +11,7 @@ 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;
@@ -18,7 +19,7 @@ use crate::directory::ReadOnlySource;
use crate::directory::WatchCallback;
use crate::directory::WatchCallbackList;
use crate::directory::WatchHandle;
use crate::directory::WritePtr;
use crate::directory::{TerminatingWrite, WritePtr};
use atomicwrites;
use memmap::Mmap;
use std::collections::HashMap;
@@ -141,42 +142,28 @@ impl MmapCache {
}
}
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 +174,7 @@ 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 +187,15 @@ 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)
}
}
@@ -265,7 +254,7 @@ 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");
}
@@ -412,6 +401,12 @@ 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);
@@ -543,16 +538,15 @@ 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());
}
@@ -645,13 +639,18 @@ mod tests {
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 +659,42 @@ 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 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());
}
}

51
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;
@@ -24,18 +25,64 @@ 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};
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
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)
}
}
/// 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;

11
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>,
@@ -188,7 +195,7 @@ impl Directory for RAMDirectory {
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(())
}

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_eq!(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_eq!(i + 1, counter.load(SeqCst));
}
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_eq!(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());
}

69
src/directory/watch_event_router.rs
View File

@@ -1,3 +1,5 @@
use futures::channel::oneshot;
use futures::{Future, TryFutureExt};
use std::sync::Arc;
use std::sync::RwLock;
use std::sync::Weak;
@@ -47,14 +49,21 @@ 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 +71,17 @@ 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 +91,22 @@ 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 +122,20 @@ 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 +149,15 @@ 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));
}
}

6
src/error.rs
View File

@@ -170,3 +170,9 @@ 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())
}
}

20
src/fastfield/delete.rs
View File

@@ -10,11 +10,14 @@ 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();
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 {
for doc in 0..(max_doc as usize) {
if delete_bitset.contains(doc) {
byte |= 1 << shift;
}
@@ -86,18 +89,17 @@ mod tests {
use bit_set::BitSet;
use std::path::PathBuf;
fn test_delete_bitset_helper(bitset: &BitSet) {
fn test_delete_bitset_helper(bitset: &BitSet, max_doc: u32) {
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();
write_delete_bitset(bitset, max_doc, &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 {
for doc in 0..max_doc as usize {
assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId));
}
assert_eq!(delete_bitset.len(), bitset.len());
@@ -110,7 +112,7 @@ mod tests {
let mut bitset = BitSet::with_capacity(10);
bitset.insert(1);
bitset.insert(9);
test_delete_bitset_helper(&bitset);
test_delete_bitset_helper(&bitset, 10);
}
{
let mut bitset = BitSet::with_capacity(8);
@@ -119,7 +121,7 @@ mod tests {
bitset.insert(3);
bitset.insert(5);
bitset.insert(7);
test_delete_bitset_helper(&bitset);
test_delete_bitset_helper(&bitset, 8);
}
}
}

8
src/fastfield/mod.rs
View File

@@ -429,7 +429,6 @@ mod tests {
}
}
}
}
#[cfg(all(test, feature = "unstable"))]
@@ -437,9 +436,9 @@ 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 +536,4 @@ mod bench {
});
}
}
}

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

@@ -5,8 +5,8 @@ use crate::postings::UnorderedTermId;
use crate::schema::{Document, Field};
use crate::termdict::TermOrdinal;
use crate::DocId;
use fnv::FnvHashMap;
use itertools::Itertools;
use std::collections::HashMap;
use std::io;
/// Writer for multi-valued (as in, more than one value per document)
@@ -102,7 +102,7 @@ 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

3
src/fastfield/readers.rs
View File

@@ -59,8 +59,7 @@ impl FastFieldReaders {
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

6
src/fastfield/writer.rs
View File

@@ -6,6 +6,7 @@ use crate::fastfield::{BytesFastFieldWriter, FastFieldSerializer};
use crate::postings::UnorderedTermId;
use crate::schema::{Cardinality, Document, Field, FieldType, Schema};
use crate::termdict::TermOrdinal;
use fnv::FnvHashMap;
use std::collections::HashMap;
use std::io;
@@ -23,8 +24,7 @@ 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);
for (field, field_entry) in schema.fields() {
let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
@@ -116,7 +116,7 @@ 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)?;

23
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"
@@ -77,7 +80,7 @@ impl FieldNormsWriter {
/// Serialize the seen fieldnorm values to the serializer for all fields.
pub fn serialize(&self, fieldnorms_serializer: &mut 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)?;
}
Ok(())

2
src/indexer/delete_queue.rs
View File

@@ -258,7 +258,7 @@ 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),

114
src/indexer/index_writer.rs
View File

@@ -7,7 +7,8 @@ use crate::core::SegmentComponent;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SegmentReader;
use crate::directory::DirectoryLock;
use crate::directory::TerminatingWrite;
use crate::directory::{DirectoryLock, GarbageCollectionResult};
use crate::docset::DocSet;
use crate::error::TantivyError;
use crate::fastfield::write_delete_bitset;
@@ -22,10 +23,10 @@ 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 {
@@ -131,7 +132,7 @@ pub(crate) fn advance_deletes(
mut segment: Segment,
segment_entry: &mut SegmentEntry,
target_opstamp: Opstamp,
) -> Result<()> {
) -> crate::Result<()> {
{
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
@@ -147,7 +148,6 @@ pub(crate) fn advance_deletes(
};
let delete_cursor = segment_entry.delete_cursor();
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
@@ -167,7 +167,8 @@ pub(crate) fn advance_deletes(
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)?;
write_delete_bitset(&delete_bitset, max_doc, &mut delete_file)?;
delete_file.terminate()?;
}
}
segment_entry.set_meta(segment.meta().clone());
@@ -176,13 +177,13 @@ pub(crate) fn advance_deletes(
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 +203,32 @@ 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 +236,7 @@ fn apply_deletes(
mut delete_cursor: &mut DeleteCursor,
doc_opstamps: &[Opstamp],
last_docstamp: Opstamp,
) -> Result<Option<BitSet<u32>>> {
) -> crate::Result<Option<BitSet<u32>>> {
if delete_cursor.get().is_none() {
// if there are no delete operation in the queue, no need
// to even open the segment.
@@ -236,7 +244,9 @@ 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_capacity(max_doc as usize);
let may_have_deletes = compute_deleted_bitset(
&mut deleted_bitset,
&segment_reader,
@@ -271,7 +281,7 @@ 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 {}.",
@@ -322,7 +332,7 @@ impl IndexWriter {
/// 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);
@@ -351,10 +361,10 @@ 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 +381,7 @@ 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 +389,7 @@ 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 +418,7 @@ impl IndexWriter {
let segment = index.new_segment();
index_documents(
mem_budget,
&segment,
segment,
&mut document_iterator,
&mut segment_updater,
delete_cursor.clone(),
@@ -425,22 +435,23 @@ 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 +461,10 @@ 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 +490,7 @@ impl IndexWriter {
/// Ok(())
/// }
/// ```
pub fn delete_all_documents(&mut self) -> Result<Opstamp> {
pub fn delete_all_documents(&self) -> crate::Result<Opstamp> {
// Delete segments
self.segment_updater.remove_all_segments();
// Return new stamp - reverted stamp
@@ -492,11 +501,9 @@ impl IndexWriter {
/// Merges a given list of segments
///
/// `segment_ids` is required to be non-empty.
pub fn merge(
&mut self,
segment_ids: &[SegmentId],
) -> Result<impl Future<Item = SegmentMeta, Error = Canceled>> {
self.segment_updater.start_merge(segment_ids)
pub async fn merge(&mut self, segment_ids: &[SegmentId]) -> crate::Result<SegmentMeta> {
let merge_operation = self.segment_updater.make_merge_operation(segment_ids);
self.segment_updater.start_merge(merge_operation)?.await
}
/// Closes the current document channel send.
@@ -522,13 +529,8 @@ 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();
@@ -584,7 +586,7 @@ 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 +633,7 @@ 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 +674,6 @@ 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 };
@@ -1182,5 +1181,4 @@ mod tests {
assert!(clear_again.is_ok());
assert!(commit_again.is_ok());
}
}

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),
}
}

95
src/indexer/merger.rs
View File

@@ -190,8 +190,7 @@ impl IndexMerger {
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);
for (field, field_entry) in self.schema.fields() {
let field_type = field_entry.field_type();
match *field_type {
FieldType::HierarchicalFacet => {
@@ -649,15 +648,12 @@ impl IndexMerger {
serializer: &mut InvertedIndexSerializer,
) -> 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() {
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_entry.field_type(),
serializer,
)? {
term_ordinal_mappings.insert(indexed_field, term_ordinal_mapping);
if let Some(term_ordinal_mapping) =
self.write_postings_for_field(field, field_entry.field_type(), serializer)?
{
term_ordinal_mappings.insert(field, term_ordinal_mapping);
}
}
}
@@ -713,7 +709,7 @@ mod tests {
use crate::IndexWriter;
use crate::Searcher;
use byteorder::{BigEndian, ReadBytesExt, WriteBytesExt};
use futures::Future;
use futures::executor::block_on;
use std::io::Cursor;
#[test]
@@ -796,11 +792,7 @@ mod tests {
.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");
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
index_writer.wait_merging_threads().unwrap();
}
{
@@ -1044,11 +1036,7 @@ 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 +1131,7 @@ 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();
@@ -1281,11 +1265,7 @@ mod tests {
.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");
block_on(index_writer.merge(&segment_ids)).expect("Merging failed");
index_writer.wait_merging_threads().unwrap();
reader.reload().unwrap();
test_searcher(
@@ -1340,11 +1320,7 @@ 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.
@@ -1365,22 +1341,18 @@ mod tests {
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);
@@ -1419,12 +1391,12 @@ 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 +1428,6 @@ 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();
@@ -1488,27 +1451,13 @@ mod tests {
.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");
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();

24
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 +28,25 @@ pub use self::segment_writer::SegmentWriter;
/// Alias for the default merge policy, which is the `LogMergePolicy`.
pub type DefaultMergePolicy = LogMergePolicy;
#[cfg(test)]
mod tests {
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_with_num_threads(1, 3_000_000).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();
}
}

9
src/indexer/prepared_commit.rs
View File

@@ -1,6 +1,7 @@
use super::IndexWriter;
use crate::Opstamp;
use crate::Result;
use futures::executor::block_on;
/// A prepared commit
pub struct PreparedCommit<'a> {
@@ -32,9 +33,11 @@ impl<'a> PreparedCommit<'a> {
pub fn commit(self) -> 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)
}
}

58
src/indexer/segment_manager.rs
View File

@@ -16,6 +16,28 @@ 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.
///
@@ -153,33 +175,35 @@ 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::Error::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]);
}
}

449
src/indexer/segment_updater.rs
View File

@@ -6,39 +6,34 @@ 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 futures::channel::oneshot;
use futures::executor::{ThreadPool, ThreadPoolBuilder};
use futures::future::Future;
use futures::future::TryFutureExt;
use serde_json;
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 +44,7 @@ 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 +65,7 @@ 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 +84,38 @@ 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();
// 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 +129,19 @@ fn perform_merge(
.collect();
// An IndexMerger is like a "view" of our merged segments.
let merger: IndexMerger = IndexMerger::open(schema, &segments[..])?;
// ... we just serialize this index merger in our new segment
// to merge the two 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)?;
let num_docs = merger.write(segment_serializer)?;
let segment_meta = index
.inventory()
.new_segment_meta(merged_segment.id(), num_docs);
let segment_meta = index.new_segment_meta(merged_segment.id(), num_docs);
let after_merge_segment_entry = SegmentEntry::new(segment_meta.clone(), delete_cursor, None);
Ok(after_merge_segment_entry)
Ok(SegmentEntry::new(segment_meta.clone(), 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 +165,31 @@ 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::Error::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::Error::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 +197,76 @@ 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();
self.pool.spawn_ok(async move {
let _ = sender.send(f.await);
});
receiver.unwrap_or_else(|_| {
let err_msg =
"A segment_updater future did not success. This should never happen.".to_string();
Err(crate::Error::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 +288,18 @@ 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 +307,132 @@ 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| {
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 {
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();
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::Error::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 +440,18 @@ 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 +460,17 @@ 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,
@@ -482,21 +488,26 @@ 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.
@@ -514,26 +525,13 @@ 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(());
pub fn wait_merging_thread(&self) -> crate::Result<()> {
for merge_operation in self.merge_operations.changes_iter() {
if merge_operation.is_empty() {
break;
}
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()?;
}
Ok(())
}
}
@@ -689,7 +687,6 @@ 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());

75
src/indexer/segment_writer.rs
View File

@@ -6,14 +6,15 @@ use crate::fieldnorm::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::schema::{Field, FieldEntry};
use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::FacetTokenizer;
use crate::tokenizer::{TokenStream, Tokenizer};
use crate::tokenizer::PreTokenizedStream;
use crate::tokenizer::{TokenStream, TokenStreamChain, Tokenizer};
use crate::DocId;
use crate::Opstamp;
use crate::Result;
@@ -49,7 +50,7 @@ pub struct SegmentWriter {
fast_field_writers: FastFieldsWriter,
fieldnorms_writer: FieldNormsWriter,
doc_opstamps: Vec<Opstamp>,
tokenizers: Vec<Option<Box<dyn BoxedTokenizer>>>,
tokenizers: Vec<Option<BoxedTokenizer>>,
}
impl SegmentWriter {
@@ -70,12 +71,10 @@ impl SegmentWriter {
let table_num_bits = initial_table_size(memory_budget)?;
let segment_serializer = SegmentSerializer::for_segment(&mut 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| {
@@ -83,8 +82,9 @@ impl SegmentWriter {
segment.index().tokenizers().get(tokenizer_name)
}),
_ => None,
})
.collect();
},
)
.collect();
Ok(SegmentWriter {
max_doc: 0,
multifield_postings,
@@ -159,26 +159,44 @@ 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<Box<dyn TokenStream>> = 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(Box::new(PreTokenizedStream::from(tok_str.clone())));
}
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: Box<dyn TokenStream> =
Box::new(TokenStreamChain::new(offsets, token_streams));
self.multifield_postings
.index_text(doc_id, field, &mut token_stream)
};
self.fieldnorms_writer.record(doc_id, field, num_tokens);
}
FieldType::U64(ref int_option) => {
@@ -296,5 +314,4 @@ mod tests {
assert_eq!(initial_table_size(10_000_000).unwrap(), 17);
assert_eq!(initial_table_size(1_000_000_000).unwrap(), 19);
}
}

28
src/lib.rs
View File

@@ -1,5 +1,4 @@
#![doc(html_logo_url = "http://fulmicoton.com/tantivy-logo/tantivy-logo.png")]
#![recursion_limit = "100"]
#![cfg_attr(all(feature = "unstable", test), feature(test))]
#![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
#![doc(test(attr(allow(unused_variables), deny(warnings))))]
@@ -11,21 +10,12 @@
//! Think `Lucene`, but in Rust.
//!
//! ```rust
//! # extern crate tempfile;
//! #
//! #[macro_use]
//! extern crate tantivy;
//!
//! // ...
//!
//! # use std::path::Path;
//! # use tempfile::TempDir;
//! # use tantivy::Index;
//! # use tantivy::schema::*;
//! # use tantivy::{Score, DocAddress};
//! # 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
@@ -222,15 +212,13 @@ 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
}
@@ -239,11 +227,11 @@ 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);

6
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;
///
/// //...
///

8
src/postings/compression/mod.rs
View File

@@ -274,13 +274,15 @@ pub mod tests {
mod bench {
use super::*;
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()
}

37
src/postings/mod.rs
View File

@@ -356,9 +356,9 @@ 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;
@@ -511,19 +511,19 @@ 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")
});
@@ -622,23 +622,23 @@ pub mod tests {
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::SkipResult;
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(|| {
@@ -652,7 +652,8 @@ mod bench {
#[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
@@ -682,7 +683,8 @@ mod bench {
}
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);
@@ -737,7 +739,8 @@ 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);

24
src/postings/postings_writer.rs
View File

@@ -12,6 +12,7 @@ use crate::tokenizer::TokenStream;
use crate::tokenizer::{Token, MAX_TOKEN_LEN};
use crate::DocId;
use crate::Result;
use fnv::FnvHashMap;
use std::collections::HashMap;
use std::io;
use std::marker::PhantomData;
@@ -60,12 +61,12 @@ fn make_field_partition(
.iter()
.map(|(key, _, _)| Term::wrap(key).field())
.enumerate();
let mut prev_field = Field(u32::max_value());
let mut prev_field_opt = None;
let mut fields = vec![];
let mut offsets = vec![];
for (offset, field) in term_offsets_it {
if field != prev_field {
prev_field = field;
if Some(field) != prev_field_opt {
prev_field_opt = Some(field);
fields.push(field);
offsets.push(offset);
}
@@ -85,8 +86,7 @@ impl MultiFieldPostingsWriter {
let term_index = TermHashMap::new(table_bits);
let per_field_postings_writers: Vec<_> = schema
.fields()
.iter()
.map(|field_entry| posting_from_field_entry(field_entry))
.map(|(_, field_entry)| posting_from_field_entry(field_entry))
.collect();
MultiFieldPostingsWriter {
heap: MemoryArena::new(),
@@ -106,7 +106,8 @@ impl MultiFieldPostingsWriter {
field: Field,
token_stream: &mut dyn TokenStream,
) -> u32 {
let postings_writer = self.per_field_postings_writers[field.0 as usize].deref_mut();
let postings_writer =
self.per_field_postings_writers[field.field_id() as usize].deref_mut();
postings_writer.index_text(
&mut self.term_index,
doc,
@@ -117,7 +118,8 @@ impl MultiFieldPostingsWriter {
}
pub fn subscribe(&mut self, doc: DocId, term: &Term) -> UnorderedTermId {
let postings_writer = self.per_field_postings_writers[term.field().0 as usize].deref_mut();
let postings_writer =
self.per_field_postings_writers[term.field().field_id() as usize].deref_mut();
postings_writer.subscribe(&mut self.term_index, doc, 0u32, term, &mut self.heap)
}
@@ -127,12 +129,12 @@ impl MultiFieldPostingsWriter {
pub fn serialize(
&self,
serializer: &mut InvertedIndexSerializer,
) -> Result<HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>>> {
) -> Result<HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>> {
let mut term_offsets: Vec<(&[u8], Addr, UnorderedTermId)> =
self.term_index.iter().collect();
term_offsets.sort_unstable_by_key(|&(k, _, _)| k);
let mut unordered_term_mappings: HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>> =
let mut unordered_term_mappings: HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>> =
HashMap::new();
let field_offsets = make_field_partition(&term_offsets);
@@ -147,7 +149,7 @@ impl MultiFieldPostingsWriter {
let unordered_term_ids = term_offsets[start..stop]
.iter()
.map(|&(_, _, bucket)| bucket);
let mapping: HashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids
let mapping: FnvHashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids
.enumerate()
.map(|(term_ord, unord_term_id)| {
(unord_term_id as UnorderedTermId, term_ord as TermOrdinal)
@@ -159,7 +161,7 @@ impl MultiFieldPostingsWriter {
FieldType::Bytes => {}
}
let postings_writer = &self.per_field_postings_writers[field.0 as usize];
let postings_writer = &self.per_field_postings_writers[field.field_id() as usize];
let mut field_serializer =
serializer.new_field(field, postings_writer.total_num_tokens())?;
postings_writer.serialize(

5
src/postings/serializer.rs
View File

@@ -141,10 +141,7 @@ impl<'a> FieldSerializer<'a> {
FieldType::Str(ref text_options) => {
if let Some(text_indexing_options) = text_options.get_indexing_options() {
let index_option = text_indexing_options.index_option();
(
index_option.is_termfreq_enabled(),
index_option.is_position_enabled(),
)
(index_option.has_freq(), index_option.has_positions())
} else {
(false, false)
}

10
src/postings/stacker/expull.rs
View File

@@ -310,6 +310,7 @@ mod bench {
use super::super::MemoryArena;
use super::ExpUnrolledLinkedList;
use byteorder::{NativeEndian, WriteBytesExt};
use std::iter;
use test::Bencher;
const NUM_STACK: usize = 10_000;
@@ -335,11 +336,10 @@ mod bench {
fn bench_push_stack(bench: &mut Bencher) {
bench.iter(|| {
let mut heap = MemoryArena::new();
let mut stacks = Vec::with_capacity(100);
for _ in 0..NUM_STACK {
let mut stack = ExpUnrolledLinkedList::new();
stacks.push(stack);
}
let mut stacks: Vec<ExpUnrolledLinkedList> =
iter::repeat_with(ExpUnrolledLinkedList::new)
.take(NUM_STACK)
.collect();
for s in 0..NUM_STACK {
for i in 0u32..STACK_SIZE {
let t = s * 392017 % NUM_STACK;

1
src/query/all_query.rs
View File

@@ -130,5 +130,4 @@ mod tests {
assert!(!scorer.advance());
}
}
}

18
src/query/automaton_weight.rs
View File

@@ -8,15 +8,13 @@ use crate::termdict::{TermDictionary, TermStreamer};
use crate::DocId;
use crate::TantivyError;
use crate::{Result, SkipResult};
use std::sync::Arc;
use tantivy_fst::Automaton;
/// A weight struct for Fuzzy Term and Regex Queries
pub struct AutomatonWeight<A>
where
A: Automaton + Send + Sync + 'static,
{
pub struct AutomatonWeight<A> {
field: Field,
automaton: A,
automaton: Arc<A>,
}
impl<A> AutomatonWeight<A>
@@ -24,12 +22,16 @@ where
A: Automaton + Send + Sync + 'static,
{
/// Create a new AutomationWeight
pub fn new(field: Field, automaton: A) -> AutomatonWeight<A> {
AutomatonWeight { field, automaton }
pub fn new<IntoArcA: Into<Arc<A>>>(field: Field, automaton: IntoArcA) -> AutomatonWeight<A> {
AutomatonWeight {
field,
automaton: automaton.into(),
}
}
fn automaton_stream<'a>(&'a self, term_dict: &'a TermDictionary) -> TermStreamer<'a, &'a A> {
let term_stream_builder = term_dict.search(&self.automaton);
let automaton: &A = &*self.automaton;
let term_stream_builder = term_dict.search(automaton);
term_stream_builder.into_stream()
}
}

9
src/query/bitset/mod.rs
View File

@@ -216,7 +216,6 @@ mod tests {
assert!(!docset.advance());
}
}
}
#[cfg(all(test, feature = "unstable"))]
@@ -224,13 +223,12 @@ mod bench {
use super::BitSet;
use super::BitSetDocSet;
use test;
use tests;
use DocSet;
use crate::test;
use crate::tests;
use crate::DocSet;
#[bench]
fn bench_bitset_1pct_insert(b: &mut test::Bencher) {
use tests;
let els = tests::generate_nonunique_unsorted(1_000_000u32, 10_000);
b.iter(|| {
let mut bitset = BitSet::with_max_value(1_000_000);
@@ -242,7 +240,6 @@ mod bench {
#[bench]
fn bench_bitset_1pct_clone(b: &mut test::Bencher) {
use tests;
let els = tests::generate_nonunique_unsorted(1_000_000u32, 10_000);
let mut bitset = BitSet::with_max_value(1_000_000);
for el in els {

1
src/query/bm25.rs
View File

@@ -137,5 +137,4 @@ mod tests {
fn test_idf() {
assert_nearly_equals(idf(1, 2), 0.6931472);
}
}

110
src/query/boolean_query/boolean_query.rs
View File

@@ -9,7 +9,8 @@ use crate::Result;
use crate::Searcher;
use std::collections::BTreeSet;
/// The boolean query combines a set of queries
/// The boolean query returns a set of documents
/// that matches the Boolean combination of constituent subqueries.
///
/// The documents matched by the boolean query are
/// those which
@@ -19,6 +20,113 @@ use std::collections::BTreeSet;
/// `MustNot` occurence.
/// * match at least one of the subqueries that is not
/// a `MustNot` occurence.
///
///
/// You can combine other query types and their `Occur`ances into one `BooleanQuery`
///
/// ```rust
///use tantivy::collector::Count;
///use tantivy::doc;
///use tantivy::query::{BooleanQuery, Occur, PhraseQuery, Query, TermQuery};
///use tantivy::schema::{IndexRecordOption, Schema, TEXT};
///use tantivy::Term;
///use tantivy::{Index, Result};
///
///fn main() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let body = schema_builder.add_text_field("body", 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",
/// body => "hidden",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// body => "found",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
///
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
///
/// // Make TermQuery's for "girl" and "diary" in the title
/// let girl_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(title, "girl"),
/// IndexRecordOption::Basic,
/// ));
/// let diary_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(title, "diary"),
/// IndexRecordOption::Basic,
/// ));
/// // A TermQuery with "found" in the body
/// let body_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(body, "found"),
/// IndexRecordOption::Basic,
/// ));
/// // TermQuery "diary" must and "girl" must not be present
/// let queries_with_occurs1 = vec![
/// (Occur::Must, diary_term_query.box_clone()),
/// (Occur::MustNot, girl_term_query),
/// ];
/// // Make a BooleanQuery equivalent to
/// // title:+diary title:-girl
/// let diary_must_and_girl_mustnot = BooleanQuery::from(queries_with_occurs1);
/// let count1 = searcher.search(&diary_must_and_girl_mustnot, &Count)?;
/// assert_eq!(count1, 1);
///
/// // TermQuery for "cow" in the title
/// let cow_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(title, "cow"),
/// IndexRecordOption::Basic,
/// ));
/// // "title:diary OR title:cow"
/// let title_diary_or_cow = BooleanQuery::from(vec![
/// (Occur::Should, diary_term_query.box_clone()),
/// (Occur::Should, cow_term_query),
/// ]);
/// let count2 = searcher.search(&title_diary_or_cow, &Count)?;
/// assert_eq!(count2, 4);
///
/// // Make a `PhraseQuery` from a vector of `Term`s
/// let phrase_query: Box<dyn Query> = Box::new(PhraseQuery::new(vec![
/// Term::from_field_text(title, "dairy"),
/// Term::from_field_text(title, "cow"),
/// ]));
/// // You can combine subqueries of different types into 1 BooleanQuery:
/// // `TermQuery` and `PhraseQuery`
/// // "title:diary OR "dairy cow"
/// let term_of_phrase_query = BooleanQuery::from(vec![
/// (Occur::Should, diary_term_query.box_clone()),
/// (Occur::Should, phrase_query.box_clone()),
/// ]);
/// let count3 = searcher.search(&term_of_phrase_query, &Count)?;
/// assert_eq!(count3, 4);
///
/// // You can nest one BooleanQuery inside another
/// // body:found AND ("title:diary OR "dairy cow")
/// let nested_query = BooleanQuery::from(vec![
/// (Occur::Must, body_term_query),
/// (Occur::Must, Box::new(term_of_phrase_query))
/// ]);
/// let count4 = searcher.search(&nested_query, &Count)?;
/// assert_eq!(count4, 1);
/// Ok(())
///}
/// ```
#[derive(Debug)]
pub struct BooleanQuery {
subqueries: Vec<(Occur, Box<dyn Query>)>,

4
src/query/boolean_query/mod.rs
View File

@@ -247,9 +247,7 @@ mod tests {
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let query_parser = QueryParser::for_index(&index, vec![title, text]);
let query = query_parser
.parse_query("Оксана Лифенко")
.unwrap();
let query = query_parser.parse_query("Оксана Лифенко").unwrap();
let weight = query.weight(&searcher, true).unwrap();
let mut scorer = weight.scorer(searcher.segment_reader(0u32)).unwrap();
scorer.advance();

1
src/query/exclude.rs
View File

@@ -175,5 +175,4 @@ mod tests {
sample_skip,
);
}
}

6
src/query/fuzzy_query.rs
View File

@@ -28,12 +28,10 @@ static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Laz
/// containing a specific term that is within
/// Levenshtein distance
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result, Term};
/// use tantivy::collector::{Count, TopDocs};
/// use tantivy::query::FuzzyTermQuery;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result, Term};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {

2
src/query/intersection.rs
View File

@@ -45,7 +45,7 @@ pub fn intersect_scorers(mut scorers: Vec<Box<dyn Scorer>>) -> Box<dyn Scorer> {
})
}
/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
/// Creates a `DocSet` that iterate through the intersection of two or more `DocSet`s.
pub struct Intersection<TDocSet: DocSet, TOtherDocSet: DocSet = Box<dyn Scorer>> {
left: TDocSet,
right: TDocSet,

2
src/query/intersection_two.rs
View File

@@ -5,7 +5,7 @@ use Score;
use SkipResult;
/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
/// Creates a `DocSet` that iterate through the intersection of two `DocSet`s.
pub struct IntersectionTwoTerms<TDocSet> {
left: TDocSet,
right: TDocSet

3
src/query/mod.rs
View File

@@ -12,7 +12,6 @@ mod exclude;
mod explanation;
mod fuzzy_query;
mod intersection;
mod occur;
mod phrase_query;
mod query;
mod query_parser;
@@ -43,7 +42,6 @@ pub use self::exclude::Exclude;
pub use self::explanation::Explanation;
pub use self::fuzzy_query::FuzzyTermQuery;
pub use self::intersection::intersect_scorers;
pub use self::occur::Occur;
pub use self::phrase_query::PhraseQuery;
pub use self::query::Query;
pub use self::query_parser::QueryParser;
@@ -55,6 +53,7 @@ pub use self::scorer::ConstScorer;
pub use self::scorer::Scorer;
pub use self::term_query::TermQuery;
pub use self::weight::Weight;
pub use tantivy_query_grammar::Occur;
#[cfg(test)]
mod tests {

4
src/query/phrase_query/phrase_query.rs
View File

@@ -40,7 +40,7 @@ impl PhraseQuery {
PhraseQuery::new_with_offset(terms_with_offset)
}
/// Creates a new `PhraseQuery` given a list of terms and there offsets.
/// Creates a new `PhraseQuery` given a list of terms and their offsets.
///
/// Can be used to provide custom offset for each term.
pub fn new_with_offset(mut terms: Vec<(usize, Term)>) -> PhraseQuery {
@@ -73,7 +73,7 @@ impl PhraseQuery {
.collect::<Vec<Term>>()
}
/// Returns the `PhraseWeight` for the given phrase query given a specific `searcher`.
/// Returns the `PhraseWeight` for the given phrase query given a specific `searcher`.
///
/// This function is the same as `.weight(...)` except it returns
/// a specialized type `PhraseWeight` instead of a Boxed trait.

2
src/query/query_parser/mod.rs
View File

@@ -1,6 +1,4 @@
mod query_grammar;
mod query_parser;
mod user_input_ast;
pub mod logical_ast;
pub use self::query_parser::QueryParser;

101
src/query/query_parser/query_parser.rs
View File

@@ -1,9 +1,5 @@
use super::logical_ast::*;
use super::query_grammar::parse_to_ast;
use super::user_input_ast::*;
use crate::core::Index;
use crate::query::occur::compose_occur;
use crate::query::query_parser::logical_ast::LogicalAST;
use crate::query::AllQuery;
use crate::query::BooleanQuery;
use crate::query::EmptyQuery;
@@ -16,11 +12,11 @@ use crate::schema::IndexRecordOption;
use crate::schema::{Field, Schema};
use crate::schema::{FieldType, Term};
use crate::tokenizer::TokenizerManager;
use combine::Parser;
use std::borrow::Cow;
use std::num::{ParseFloatError, ParseIntError};
use std::ops::Bound;
use std::str::FromStr;
use tantivy_query_grammar::{UserInputAST, UserInputBound, UserInputLeaf};
/// Possible error that may happen when parsing a query.
#[derive(Debug, PartialEq, Eq, Fail)]
@@ -222,9 +218,8 @@ impl QueryParser {
/// Parse the user query into an AST.
fn parse_query_to_logical_ast(&self, query: &str) -> Result<LogicalAST, QueryParserError> {
let (user_input_ast, _remaining) = parse_to_ast()
.parse(query)
.map_err(|_| QueryParserError::SyntaxError)?;
let user_input_ast =
tantivy_query_grammar::parse_query(query).map_err(|_| QueryParserError::SyntaxError)?;
self.compute_logical_ast(user_input_ast)
}
@@ -369,6 +364,7 @@ impl QueryParser {
match *bound {
UserInputBound::Inclusive(_) => Ok(Bound::Included(term)),
UserInputBound::Exclusive(_) => Ok(Bound::Excluded(term)),
UserInputBound::Unbounded => Ok(Bound::Unbounded),
}
}
@@ -398,7 +394,7 @@ impl QueryParser {
let mut logical_sub_queries: Vec<(Occur, LogicalAST)> = Vec::new();
for sub_query in sub_queries {
let (occur, sub_ast) = self.compute_logical_ast_with_occur(sub_query)?;
let new_occur = compose_occur(default_occur, occur);
let new_occur = Occur::compose(default_occur, occur);
logical_sub_queries.push((new_occur, sub_ast));
}
Ok((Occur::Should, LogicalAST::Clause(logical_sub_queries)))
@@ -406,7 +402,7 @@ impl QueryParser {
UserInputAST::Unary(left_occur, subquery) => {
let (right_occur, logical_sub_queries) =
self.compute_logical_ast_with_occur(*subquery)?;
Ok((compose_occur(left_occur, right_occur), logical_sub_queries))
Ok((Occur::compose(left_occur, right_occur), logical_sub_queries))
}
UserInputAST::Leaf(leaf) => {
let result_ast = self.compute_logical_ast_from_leaf(*leaf)?;
@@ -628,7 +624,7 @@ mod test {
pub fn test_parse_query_untokenized() {
test_parse_query_to_logical_ast_helper(
"nottokenized:\"wordone wordtwo\"",
"Term([0, 0, 0, 7, 119, 111, 114, 100, 111, 110, \
"Term(field=7,bytes=[119, 111, 114, 100, 111, 110, \
101, 32, 119, 111, 114, 100, 116, 119, 111])",
false,
);
@@ -672,19 +668,25 @@ mod test {
.is_ok());
test_parse_query_to_logical_ast_helper(
"unsigned:2324",
"Term([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 9, 20])",
"Term(field=3,bytes=[0, 0, 0, 0, 0, 0, 9, 20])",
false,
);
test_parse_query_to_logical_ast_helper(
"signed:-2324",
&format!("{:?}", Term::from_field_i64(Field(2u32), -2324)),
&format!(
"{:?}",
Term::from_field_i64(Field::from_field_id(2u32), -2324)
),
false,
);
test_parse_query_to_logical_ast_helper(
"float:2.5",
&format!("{:?}", Term::from_field_f64(Field(10u32), 2.5)),
&format!(
"{:?}",
Term::from_field_f64(Field::from_field_id(10u32), 2.5)
),
false,
);
}
@@ -693,19 +695,19 @@ mod test {
pub fn test_parse_query_to_ast_single_term() {
test_parse_query_to_logical_ast_helper(
"title:toto",
"Term([0, 0, 0, 0, 116, 111, 116, 111])",
"Term(field=0,bytes=[116, 111, 116, 111])",
false,
);
test_parse_query_to_logical_ast_helper(
"+title:toto",
"Term([0, 0, 0, 0, 116, 111, 116, 111])",
"Term(field=0,bytes=[116, 111, 116, 111])",
false,
);
test_parse_query_to_logical_ast_helper(
"+title:toto -titi",
"(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
Term([0, 0, 0, 1, 116, 105, 116, 105])))",
"(+Term(field=0,bytes=[116, 111, 116, 111]) \
-(Term(field=0,bytes=[116, 105, 116, 105]) \
Term(field=1,bytes=[116, 105, 116, 105])))",
false,
);
assert_eq!(
@@ -720,14 +722,13 @@ mod test {
pub fn test_parse_query_to_ast_two_terms() {
test_parse_query_to_logical_ast_helper(
"title:a b",
"(Term([0, 0, 0, 0, 97]) (Term([0, 0, 0, 0, 98]) \
Term([0, 0, 0, 1, 98])))",
"(Term(field=0,bytes=[97]) (Term(field=0,bytes=[98]) Term(field=1,bytes=[98])))",
false,
);
test_parse_query_to_logical_ast_helper(
"title:\"a b\"",
"\"[(0, Term([0, 0, 0, 0, 97])), \
(1, Term([0, 0, 0, 0, 98]))]\"",
"\"[(0, Term(field=0,bytes=[97])), \
(1, Term(field=0,bytes=[98]))]\"",
false,
);
}
@@ -736,45 +737,43 @@ mod test {
pub fn test_parse_query_to_ast_ranges() {
test_parse_query_to_logical_ast_helper(
"title:[a TO b]",
"(Included(Term([0, 0, 0, 0, 97])) TO \
Included(Term([0, 0, 0, 0, 98])))",
"(Included(Term(field=0,bytes=[97])) TO Included(Term(field=0,bytes=[98])))",
false,
);
test_parse_query_to_logical_ast_helper(
"[a TO b]",
"((Included(Term([0, 0, 0, 0, 97])) TO \
Included(Term([0, 0, 0, 0, 98]))) \
(Included(Term([0, 0, 0, 1, 97])) TO \
Included(Term([0, 0, 0, 1, 98]))))",
"((Included(Term(field=0,bytes=[97])) TO \
Included(Term(field=0,bytes=[98]))) \
(Included(Term(field=1,bytes=[97])) TO \
Included(Term(field=1,bytes=[98]))))",
false,
);
test_parse_query_to_logical_ast_helper(
"title:{titi TO toto}",
"(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO \
Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
"(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO \
Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
false,
);
test_parse_query_to_logical_ast_helper(
"title:{* TO toto}",
"(Unbounded TO \
Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
"(Unbounded TO Excluded(Term(field=0,bytes=[116, 111, 116, 111])))",
false,
);
test_parse_query_to_logical_ast_helper(
"title:{titi TO *}",
"(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO Unbounded)",
"(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO Unbounded)",
false,
);
test_parse_query_to_logical_ast_helper(
"signed:{-5 TO 3}",
"(Excluded(Term([0, 0, 0, 2, 127, 255, 255, 255, 255, 255, 255, 251])) TO \
Excluded(Term([0, 0, 0, 2, 128, 0, 0, 0, 0, 0, 0, 3])))",
"(Excluded(Term(field=2,bytes=[127, 255, 255, 255, 255, 255, 255, 251])) TO \
Excluded(Term(field=2,bytes=[128, 0, 0, 0, 0, 0, 0, 3])))",
false,
);
test_parse_query_to_logical_ast_helper(
"float:{-1.5 TO 1.5}",
"(Excluded(Term([0, 0, 0, 10, 64, 7, 255, 255, 255, 255, 255, 255])) TO \
Excluded(Term([0, 0, 0, 10, 191, 248, 0, 0, 0, 0, 0, 0])))",
"(Excluded(Term(field=10,bytes=[64, 7, 255, 255, 255, 255, 255, 255])) TO \
Excluded(Term(field=10,bytes=[191, 248, 0, 0, 0, 0, 0, 0])))",
false,
);
@@ -879,19 +878,19 @@ mod test {
pub fn test_parse_query_to_ast_conjunction() {
test_parse_query_to_logical_ast_helper(
"title:toto",
"Term([0, 0, 0, 0, 116, 111, 116, 111])",
"Term(field=0,bytes=[116, 111, 116, 111])",
true,
);
test_parse_query_to_logical_ast_helper(
"+title:toto",
"Term([0, 0, 0, 0, 116, 111, 116, 111])",
"Term(field=0,bytes=[116, 111, 116, 111])",
true,
);
test_parse_query_to_logical_ast_helper(
"+title:toto -titi",
"(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
Term([0, 0, 0, 1, 116, 105, 116, 105])))",
"(+Term(field=0,bytes=[116, 111, 116, 111]) \
-(Term(field=0,bytes=[116, 105, 116, 105]) \
Term(field=1,bytes=[116, 105, 116, 105])))",
true,
);
assert_eq!(
@@ -902,15 +901,15 @@ mod test {
);
test_parse_query_to_logical_ast_helper(
"title:a b",
"(+Term([0, 0, 0, 0, 97]) \
+(Term([0, 0, 0, 0, 98]) \
Term([0, 0, 0, 1, 98])))",
"(+Term(field=0,bytes=[97]) \
+(Term(field=0,bytes=[98]) \
Term(field=1,bytes=[98])))",
true,
);
test_parse_query_to_logical_ast_helper(
"title:\"a b\"",
"\"[(0, Term([0, 0, 0, 0, 97])), \
(1, Term([0, 0, 0, 0, 98]))]\"",
"\"[(0, Term(field=0,bytes=[97])), \
(1, Term(field=0,bytes=[98]))]\"",
true,
);
}
@@ -919,10 +918,8 @@ mod test {
pub fn test_query_parser_hyphen() {
test_parse_query_to_logical_ast_helper(
"title:www-form-encoded",
"\"[(0, Term([0, 0, 0, 0, 119, 119, 119])), \
(1, Term([0, 0, 0, 0, 102, 111, 114, 109])), \
(2, Term([0, 0, 0, 0, 101, 110, 99, 111, 100, 101, 100]))]\"",
false,
"\"[(0, Term(field=0,bytes=[119, 119, 119])), (1, Term(field=0,bytes=[102, 111, 114, 109])), (2, Term(field=0,bytes=[101, 110, 99, 111, 100, 101, 100]))]\"",
false
);
}
}

51
src/query/range_query.rs
View File

@@ -38,14 +38,10 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
/// # Example
///
/// ```rust
///
/// # #[macro_use]
/// # extern crate tantivy;
/// # use tantivy::Index;
/// # use tantivy::schema::{Schema, INDEXED};
/// # use tantivy::collector::Count;
/// # use tantivy::Result;
/// # use tantivy::query::RangeQuery;
/// # use tantivy::schema::{Schema, INDEXED};
/// # use tantivy::{doc, Index, Result};
/// #
/// # fn run() -> Result<()> {
/// # let mut schema_builder = Schema::builder();
@@ -338,39 +334,33 @@ mod tests {
use crate::collector::Count;
use crate::schema::{Document, Field, Schema, INDEXED};
use crate::Index;
use crate::Result;
use std::collections::Bound;
#[test]
fn test_range_query_simple() {
fn run() -> Result<()> {
let mut schema_builder = Schema::builder();
let year_field = schema_builder.add_u64_field("year", INDEXED);
let schema = schema_builder.build();
let mut schema_builder = Schema::builder();
let year_field = schema_builder.add_u64_field("year", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
for year in 1950u64..2017u64 {
let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
for _ in 0..num_docs_within_year {
index_writer.add_document(doc!(year_field => year));
}
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
for year in 1950u64..2017u64 {
let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
for _ in 0..num_docs_within_year {
index_writer.add_document(doc!(year_field => year));
}
index_writer.commit().unwrap();
}
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
// ... or `1960..=1969` if inclusive range is enabled.
let count = searcher.search(&docs_in_the_sixties, &Count)?;
assert_eq!(count, 2285);
Ok(())
index_writer.commit().unwrap();
}
let reader = index.reader().unwrap();
let searcher = reader.searcher();
run().unwrap();
let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
// ... or `1960..=1969` if inclusive range is enabled.
let count = searcher.search(&docs_in_the_sixties, &Count).unwrap();
assert_eq!(count, 2285);
}
#[test]
@@ -489,5 +479,4 @@ mod tests {
91
);
}
}

102
src/query/regex_query.rs
View File

@@ -4,22 +4,18 @@ use crate::schema::Field;
use crate::Result;
use crate::Searcher;
use std::clone::Clone;
use std::sync::Arc;
use tantivy_fst::Regex;
// A Regex Query matches all of the documents
/// A Regex Query matches all of the documents
/// containing a specific term that matches
/// a regex pattern
/// A Fuzzy Query matches all of the documents
/// containing a specific term that is within
/// Levenshtein distance
/// a regex pattern.
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result, Term};
/// use tantivy::collector::Count;
/// use tantivy::query::RegexQuery;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result, Term};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
@@ -48,7 +44,7 @@ use tantivy_fst::Regex;
/// let searcher = reader.searcher();
///
/// let term = Term::from_field_text(title, "Diary");
/// let query = RegexQuery::new("d[ai]{2}ry".to_string(), title);
/// let query = RegexQuery::from_pattern("d[ai]{2}ry", title)?;
/// let count = searcher.search(&query, &Count)?;
/// assert_eq!(count, 3);
/// Ok(())
@@ -56,30 +52,34 @@ use tantivy_fst::Regex;
/// ```
#[derive(Debug, Clone)]
pub struct RegexQuery {
regex_pattern: String,
regex: Arc<Regex>,
field: Field,
}
impl RegexQuery {
/// Creates a new Fuzzy Query
pub fn new(regex_pattern: String, field: Field) -> RegexQuery {
/// Creates a new RegexQuery from a given pattern
pub fn from_pattern(regex_pattern: &str, field: Field) -> Result<Self> {
let regex = Regex::new(&regex_pattern)
.map_err(|_| TantivyError::InvalidArgument(regex_pattern.to_string()))?;
Ok(RegexQuery::from_regex(regex, field))
}
/// Creates a new RegexQuery from a fully built Regex
pub fn from_regex<T: Into<Arc<Regex>>>(regex: T, field: Field) -> Self {
RegexQuery {
regex_pattern,
regex: regex.into(),
field,
}
}
fn specialized_weight(&self) -> Result<AutomatonWeight<Regex>> {
let automaton = Regex::new(&self.regex_pattern)
.map_err(|_| TantivyError::InvalidArgument(self.regex_pattern.clone()))?;
Ok(AutomatonWeight::new(self.field, automaton))
fn specialized_weight(&self) -> AutomatonWeight<Regex> {
AutomatonWeight::new(self.field, self.regex.clone())
}
}
impl Query for RegexQuery {
fn weight(&self, _searcher: &Searcher, _scoring_enabled: bool) -> Result<Box<dyn Weight>> {
Ok(Box::new(self.specialized_weight()?))
Ok(Box::new(self.specialized_weight()))
}
}
@@ -87,13 +87,14 @@ impl Query for RegexQuery {
mod test {
use super::RegexQuery;
use crate::collector::TopDocs;
use crate::schema::Schema;
use crate::schema::TEXT;
use crate::schema::{Field, Schema};
use crate::tests::assert_nearly_equals;
use crate::Index;
use crate::{Index, IndexReader};
use std::sync::Arc;
use tantivy_fst::Regex;
#[test]
pub fn test_regex_query() {
fn build_test_index() -> (IndexReader, Field) {
let mut schema_builder = Schema::builder();
let country_field = schema_builder.add_text_field("country", TEXT);
let schema = schema_builder.build();
@@ -109,20 +110,65 @@ mod test {
index_writer.commit().unwrap();
}
let reader = index.reader().unwrap();
(reader, country_field)
}
fn verify_regex_query(
query_matching_one: RegexQuery,
query_matching_zero: RegexQuery,
reader: IndexReader,
) {
let searcher = reader.searcher();
{
let regex_query = RegexQuery::new("jap[ao]n".to_string(), country_field);
let scored_docs = searcher
.search(&regex_query, &TopDocs::with_limit(2))
.search(&query_matching_one, &TopDocs::with_limit(2))
.unwrap();
assert_eq!(scored_docs.len(), 1, "Expected only 1 document");
let (score, _) = scored_docs[0];
assert_nearly_equals(1f32, score);
}
let regex_query = RegexQuery::new("jap[A-Z]n".to_string(), country_field);
let top_docs = searcher
.search(&regex_query, &TopDocs::with_limit(2))
.search(&query_matching_zero, &TopDocs::with_limit(2))
.unwrap();
assert!(top_docs.is_empty(), "Expected ZERO document");
}
#[test]
pub fn test_regex_query() {
let (reader, field) = build_test_index();
let matching_one = RegexQuery::from_pattern("jap[ao]n", field).unwrap();
let matching_zero = RegexQuery::from_pattern("jap[A-Z]n", field).unwrap();
verify_regex_query(matching_one, matching_zero, reader);
}
#[test]
pub fn test_construct_from_regex() {
let (reader, field) = build_test_index();
let matching_one = RegexQuery::from_regex(Regex::new("jap[ao]n").unwrap(), field);
let matching_zero = RegexQuery::from_regex(Regex::new("jap[A-Z]n").unwrap(), field);
verify_regex_query(matching_one, matching_zero, reader);
}
#[test]
pub fn test_construct_from_reused_regex() {
let r1 = Arc::new(Regex::new("jap[ao]n").unwrap());
let r2 = Arc::new(Regex::new("jap[A-Z]n").unwrap());
let (reader, field) = build_test_index();
let matching_one = RegexQuery::from_regex(r1.clone(), field);
let matching_zero = RegexQuery::from_regex(r2.clone(), field);
verify_regex_query(matching_one, matching_zero, reader.clone());
let matching_one = RegexQuery::from_regex(r1.clone(), field);
let matching_zero = RegexQuery::from_regex(r2.clone(), field);
verify_regex_query(matching_one, matching_zero, reader.clone());
}
}

1
src/query/reqopt_scorer.rs
View File

@@ -190,5 +190,4 @@ mod tests {
skip_docs,
);
}
}

14
src/query/term_query/mod.rs
View File

@@ -12,7 +12,7 @@ mod tests {
use crate::collector::TopDocs;
use crate::docset::DocSet;
use crate::query::{Query, QueryParser, Scorer, TermQuery};
use crate::schema::{IndexRecordOption, Schema, STRING, TEXT};
use crate::schema::{Field, IndexRecordOption, Schema, STRING, TEXT};
use crate::tests::assert_nearly_equals;
use crate::Index;
use crate::Term;
@@ -114,4 +114,16 @@ mod tests {
let reader = index.reader().unwrap();
assert_eq!(term_query.count(&*reader.searcher()).unwrap(), 1);
}
#[test]
fn test_term_query_debug() {
let term_query = TermQuery::new(
Term::from_field_text(Field::from_field_id(1), "hello"),
IndexRecordOption::WithFreqs,
);
assert_eq!(
format!("{:?}", term_query),
"TermQuery(Term(field=1,bytes=[104, 101, 108, 108, 111]))"
);
}
}

15
src/query/term_query/term_query.rs
View File

@@ -7,6 +7,7 @@ use crate::Result;
use crate::Searcher;
use crate::Term;
use std::collections::BTreeSet;
use std::fmt;
/// A Term query matches all of the documents
/// containing a specific term.
@@ -19,12 +20,10 @@ use std::collections::BTreeSet;
/// * `field norm` - number of tokens in the field.
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
/// use tantivy::{Index, Result, Term};
/// use tantivy::collector::{Count, TopDocs};
/// use tantivy::query::TermQuery;
/// use tantivy::schema::{Schema, TEXT, IndexRecordOption};
/// use tantivy::{doc, Index, Result, Term};
///
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
@@ -61,12 +60,18 @@ use std::collections::BTreeSet;
/// Ok(())
/// }
/// ```
#[derive(Clone, Debug)]
#[derive(Clone)]
pub struct TermQuery {
term: Term,
index_record_option: IndexRecordOption,
}
impl fmt::Debug for TermQuery {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "TermQuery({:?})", self.term)
}
}
impl TermQuery {
/// Creates a new term query.
pub fn new(term: Term, segment_postings_options: IndexRecordOption) -> TermQuery {

15
src/query/union.rs
View File

@@ -28,7 +28,7 @@ where
}
}
/// Creates a `DocSet` that iterator through the intersection of two `DocSet`s.
/// Creates a `DocSet` that iterate through the union of two or more `DocSet`s.
pub struct Union<TScorer, TScoreCombiner = DoNothingCombiner> {
docsets: Vec<TScorer>,
bitsets: Box<[TinySet; HORIZON_NUM_TINYBITSETS]>,
@@ -409,20 +409,17 @@ mod tests {
vec![1, 2, 3, 7, 8, 9, 99, 100, 101, 500, 20000],
);
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use query::score_combiner::DoNothingCombiner;
use query::ConstScorer;
use query::Union;
use query::VecDocSet;
use crate::query::score_combiner::DoNothingCombiner;
use crate::query::{ConstScorer, Union, VecDocSet};
use crate::tests;
use crate::DocId;
use crate::DocSet;
use test::Bencher;
use tests;
use DocId;
use DocSet;
#[bench]
fn bench_union_3_high(bench: &mut Bencher) {

1
src/query/vec_docset.rs
View File

@@ -82,5 +82,4 @@ pub mod tests {
}
assert_eq!(postings.fill_buffer(&mut buffer[..]), 9);
}
}

5
src/reader/mod.rs
View File

@@ -162,6 +162,11 @@ pub struct IndexReader {
}
impl IndexReader {
#[cfg(test)]
pub(crate) fn index(&self) -> Index {
self.inner.index.clone()
}
/// Update searchers so that they reflect the state of the last
/// `.commit()`.
///

66
src/reader/pool.rs
View File

@@ -167,7 +167,7 @@ mod tests {
use super::Pool;
use super::Queue;
use std::iter;
use std::{iter, mem};
#[test]
fn test_pool() {
@@ -197,33 +197,67 @@ mod tests {
fn test_pool_dont_panic_on_empty_pop() {
// When the object pool is exhausted, it shouldn't panic on pop()
use std::sync::Arc;
use std::{thread, time};
use std::thread;
// Wrap the pool in an Arc, same way as its used in `core/index.rs`
let pool = Arc::new(Pool::new());
let pool1 = Arc::new(Pool::new());
// clone pools outside the move scope of each new thread
let pool1 = Arc::clone(&pool);
let pool2 = Arc::clone(&pool);
let pool2 = Arc::clone(&pool1);
let pool3 = Arc::clone(&pool1);
let elements_for_pool = vec![1, 2];
pool.publish_new_generation(elements_for_pool);
pool1.publish_new_generation(elements_for_pool);
let mut threads = vec![];
let sleep_dur = time::Duration::from_millis(10);
// spawn one more thread than there are elements in the pool
let (start_1_send, start_1_recv) = crossbeam::bounded(0);
let (start_2_send, start_2_recv) = crossbeam::bounded(0);
let (start_3_send, start_3_recv) = crossbeam::bounded(0);
let (event_send1, event_recv) = crossbeam::unbounded();
let event_send2 = event_send1.clone();
let event_send3 = event_send1.clone();
threads.push(thread::spawn(move || {
// leasing to make sure it's not dropped before sleep is called
let _leased_searcher = &pool.acquire();
thread::sleep(sleep_dur);
}));
threads.push(thread::spawn(move || {
// leasing to make sure it's not dropped before sleep is called
assert_eq!(start_1_recv.recv(), Ok("start"));
let _leased_searcher = &pool1.acquire();
thread::sleep(sleep_dur);
assert!(event_send1.send("1 acquired").is_ok());
assert_eq!(start_1_recv.recv(), Ok("stop"));
assert!(event_send1.send("1 stopped").is_ok());
mem::drop(_leased_searcher);
}));
threads.push(thread::spawn(move || {
// leasing to make sure it's not dropped before sleep is called
assert_eq!(start_2_recv.recv(), Ok("start"));
let _leased_searcher = &pool2.acquire();
thread::sleep(sleep_dur);
assert!(event_send2.send("2 acquired").is_ok());
assert_eq!(start_2_recv.recv(), Ok("stop"));
mem::drop(_leased_searcher);
assert!(event_send2.send("2 stopped").is_ok());
}));
threads.push(thread::spawn(move || {
assert_eq!(start_3_recv.recv(), Ok("start"));
let _leased_searcher = &pool3.acquire();
assert!(event_send3.send("3 acquired").is_ok());
assert_eq!(start_3_recv.recv(), Ok("stop"));
mem::drop(_leased_searcher);
assert!(event_send3.send("3 stopped").is_ok());
}));
assert!(start_1_send.send("start").is_ok());
assert_eq!(event_recv.recv(), Ok("1 acquired"));
assert!(start_2_send.send("start").is_ok());
assert_eq!(event_recv.recv(), Ok("2 acquired"));
assert!(start_3_send.send("start").is_ok());
assert!(event_recv.try_recv().is_err());
assert!(start_1_send.send("stop").is_ok());
assert_eq!(event_recv.recv(), Ok("1 stopped"));
assert_eq!(event_recv.recv(), Ok("3 acquired"));
assert!(start_3_send.send("stop").is_ok());
assert_eq!(event_recv.recv(), Ok("3 stopped"));
assert!(start_2_send.send("stop").is_ok());
assert_eq!(event_recv.recv(), Ok("2 stopped"));
}
}

16
src/schema/document.rs
View File

@@ -1,6 +1,7 @@
use super::*;
use crate::common::BinarySerializable;
use crate::common::VInt;
use crate::tokenizer::PreTokenizedString;
use crate::DateTime;
use itertools::Itertools;
use std::io::{self, Read, Write};
@@ -29,8 +30,8 @@ impl From<Vec<FieldValue>> for Document {
impl PartialEq for Document {
fn eq(&self, other: &Document) -> bool {
// super slow, but only here for tests
let mut self_field_values = self.field_values.clone();
let mut other_field_values = other.field_values.clone();
let mut self_field_values: Vec<&_> = self.field_values.iter().collect();
let mut other_field_values: Vec<&_> = other.field_values.iter().collect();
self_field_values.sort();
other_field_values.sort();
self_field_values.eq(&other_field_values)
@@ -78,6 +79,16 @@ impl Document {
self.add(FieldValue::new(field, value));
}
/// Add a pre-tokenized text field.
pub fn add_pre_tokenized_text(
&mut self,
field: Field,
pre_tokenized_text: &PreTokenizedString,
) {
let value = Value::PreTokStr(pre_tokenized_text.clone());
self.add(FieldValue::new(field, value));
}
/// Add a u64 field
pub fn add_u64(&mut self, field: Field, value: u64) {
self.add(FieldValue::new(field, Value::U64(value)));
@@ -178,5 +189,4 @@ mod tests {
doc.add_text(text_field, "My title");
assert_eq!(doc.field_values().len(), 1);
}
}

23
src/schema/field.rs
View File

@@ -3,14 +3,23 @@ use std::io;
use std::io::Read;
use std::io::Write;
/// `Field` is actually a `u8` identifying a `Field`
/// The schema is in charge of holding mapping between field names
/// to `Field` objects.
///
/// Because the field id is a `u8`, tantivy can only have at most `255` fields.
/// Value 255 is reserved.
/// `Field` is represented by an unsigned 32-bit integer type
/// The schema holds the mapping between field names and `Field` objects.
#[derive(Copy, Clone, Debug, PartialEq, PartialOrd, Eq, Ord, Hash, Serialize, Deserialize)]
pub struct Field(pub u32);
pub struct Field(u32);
impl Field {
/// Create a new field object for the given FieldId.
pub fn from_field_id(field_id: u32) -> Field {
Field(field_id)
}
/// Returns a u32 identifying uniquely a field within a schema.
#[allow(clippy::trivially_copy_pass_by_ref)]
pub fn field_id(&self) -> u32 {
self.0
}
}
impl BinarySerializable for Field {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {

97
src/schema/field_type.rs
View File

@@ -1,16 +1,16 @@
use base64::decode;
use crate::schema::{IntOptions, TextOptions};
use crate::schema::Facet;
use crate::schema::IndexRecordOption;
use crate::schema::TextFieldIndexing;
use crate::schema::Value;
use crate::schema::{IntOptions, TextOptions};
use crate::tokenizer::PreTokenizedString;
use serde_json::Value as JsonValue;
/// Possible error that may occur while parsing a field value
/// At this point the JSON is known to be valid.
#[derive(Debug)]
#[derive(Debug, PartialEq)]
pub enum ValueParsingError {
/// Encountered a numerical value that overflows or underflow its integer type.
OverflowError(String),
@@ -169,6 +169,28 @@ impl FieldType {
Err(ValueParsingError::TypeError(msg))
}
},
JsonValue::Object(_) => match *self {
FieldType::Str(_) => {
if let Ok(tok_str_val) =
serde_json::from_value::<PreTokenizedString>(json.clone())
{
Ok(Value::PreTokStr(tok_str_val))
} else {
let msg = format!(
"Json value {:?} cannot be translated to PreTokenizedString.",
json
);
Err(ValueParsingError::TypeError(msg))
}
}
_ => {
let msg = format!(
"Json value not supported error {:?}. Expected {:?}",
json, self
);
Err(ValueParsingError::TypeError(msg))
}
},
_ => {
let msg = format!(
"Json value not supported error {:?}. Expected {:?}",
@@ -184,7 +206,9 @@ impl FieldType {
mod tests {
use super::FieldType;
use crate::schema::field_type::ValueParsingError;
use crate::schema::TextOptions;
use crate::schema::Value;
use crate::tokenizer::{PreTokenizedString, Token};
#[test]
fn test_bytes_value_from_json() {
@@ -205,4 +229,71 @@ mod tests {
_ => panic!("Expected parse failure for invalid base64"),
}
}
#[test]
fn test_pre_tok_str_value_from_json() {
let pre_tokenized_string_json = r#"{
"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 expected_value = Value::PreTokStr(PreTokenizedString {
text: String::from("The Old Man"),
tokens: vec![
Token {
offset_from: 0,
offset_to: 3,
position: 0,
text: String::from("The"),
position_length: 1,
},
Token {
offset_from: 4,
offset_to: 7,
position: 1,
text: String::from("Old"),
position_length: 1,
},
Token {
offset_from: 8,
offset_to: 11,
position: 2,
text: String::from("Man"),
position_length: 1,
},
],
});
let deserialized_value = FieldType::Str(TextOptions::default())
.value_from_json(&serde_json::from_str(pre_tokenized_string_json).unwrap())
.unwrap();
assert_eq!(deserialized_value, expected_value);
let serialized_value_json = serde_json::to_string_pretty(&expected_value).unwrap();
assert_eq!(serialized_value_json, pre_tokenized_string_json);
}
}

16
src/schema/index_record_option.rs
View File

@@ -29,22 +29,6 @@ pub enum IndexRecordOption {
}
impl IndexRecordOption {
/// Returns true iff the term frequency will be encoded.
pub fn is_termfreq_enabled(self) -> bool {
match self {
IndexRecordOption::WithFreqsAndPositions | IndexRecordOption::WithFreqs => true,
_ => false,
}
}
/// Returns true iff the term positions within the document are stored as well.
pub fn is_position_enabled(self) -> bool {
match self {
IndexRecordOption::WithFreqsAndPositions => true,
_ => false,
}
}
/// Returns true iff this option includes encoding
/// term frequencies.
pub fn has_freq(self) -> bool {

1
src/schema/mod.rs
View File

@@ -174,5 +174,4 @@ mod tests {
assert!(!is_valid_field_name("シャボン玉"));
assert!(is_valid_field_name("my_text_field"));
}
}

158
src/schema/schema.rs
View File

@@ -167,7 +167,7 @@ impl SchemaBuilder {
/// Adds a field entry to the schema in build.
fn add_field(&mut self, field_entry: FieldEntry) -> Field {
let field = Field(self.fields.len() as u32);
let field = Field::from_field_id(self.fields.len() as u32);
let field_name = field_entry.name().to_string();
self.fields.push(field_entry);
self.fields_map.insert(field_name, field);
@@ -223,7 +223,7 @@ pub struct Schema(Arc<InnerSchema>);
impl Schema {
/// Return the `FieldEntry` associated to a `Field`.
pub fn get_field_entry(&self, field: Field) -> &FieldEntry {
&self.0.fields[field.0 as usize]
&self.0.fields[field.field_id() as usize]
}
/// Return the field name for a given `Field`.
@@ -232,8 +232,12 @@ impl Schema {
}
/// Return the list of all the `Field`s.
pub fn fields(&self) -> &[FieldEntry] {
&self.0.fields
pub fn fields(&self) -> impl Iterator<Item = (Field, &FieldEntry)> {
self.0
.fields
.iter()
.enumerate()
.map(|(field_id, field_entry)| (Field::from_field_id(field_id as u32), field_entry))
}
/// Creates a new builder.
@@ -246,6 +250,25 @@ impl Schema {
self.0.fields_map.get(field_name).cloned()
}
/// Create a named document off the doc.
pub fn convert_named_doc(
&self,
named_doc: NamedFieldDocument,
) -> Result<Document, DocParsingError> {
let mut document = Document::new();
for (field_name, values) in named_doc.0 {
if let Some(field) = self.get_field(&field_name) {
for value in values {
let field_value = FieldValue::new(field, value);
document.add(field_value);
}
} else {
return Err(DocParsingError::NoSuchFieldInSchema(field_name));
}
}
Ok(document)
}
/// Create a named document off the doc.
pub fn to_named_doc(&self, doc: &Document) -> NamedFieldDocument {
let mut field_map = BTreeMap::new();
@@ -282,28 +305,26 @@ impl Schema {
let mut doc = Document::default();
for (field_name, json_value) in json_obj.iter() {
match self.get_field(field_name) {
Some(field) => {
let field_entry = self.get_field_entry(field);
let field_type = field_entry.field_type();
match *json_value {
JsonValue::Array(ref json_items) => {
for json_item in json_items {
let value = field_type.value_from_json(json_item).map_err(|e| {
DocParsingError::ValueError(field_name.clone(), e)
})?;
doc.add(FieldValue::new(field, value));
}
}
_ => {
let value = field_type
.value_from_json(json_value)
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
doc.add(FieldValue::new(field, value));
}
let field = self
.get_field(field_name)
.ok_or_else(|| DocParsingError::NoSuchFieldInSchema(field_name.clone()))?;
let field_entry = self.get_field_entry(field);
let field_type = field_entry.field_type();
match *json_value {
JsonValue::Array(ref json_items) => {
for json_item in json_items {
let value = field_type
.value_from_json(json_item)
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
doc.add(FieldValue::new(field, value));
}
}
None => return Err(DocParsingError::NoSuchFieldInSchema(field_name.clone())),
_ => {
let value = field_type
.value_from_json(json_value)
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
doc.add(FieldValue::new(field, value));
}
}
}
Ok(doc)
@@ -360,7 +381,7 @@ impl<'de> Deserialize<'de> for Schema {
/// Error that may happen when deserializing
/// a document from JSON.
#[derive(Debug, Fail)]
#[derive(Debug, Fail, PartialEq)]
pub enum DocParsingError {
/// The payload given is not valid JSON.
#[fail(display = "The provided string is not valid JSON")]
@@ -369,7 +390,10 @@ pub enum DocParsingError {
#[fail(display = "The field '{:?}' could not be parsed: {:?}", _0, _1)]
ValueError(String, ValueParsingError),
/// The json-document contains a field that is not declared in the schema.
#[fail(display = "The json-document contains an unknown field: {:?}", _0)]
#[fail(
display = "The document contains a field that is not declared in the schema: {:?}",
_0
)]
NoSuchFieldInSchema(String),
}
@@ -381,6 +405,7 @@ mod tests {
use crate::schema::*;
use matches::{assert_matches, matches};
use serde_json;
use std::collections::BTreeMap;
#[test]
pub fn is_indexed_test() {
@@ -464,13 +489,32 @@ mod tests {
let schema: Schema = serde_json::from_str(expected).unwrap();
let mut fields = schema.fields().iter();
assert_eq!("title", fields.next().unwrap().name());
assert_eq!("author", fields.next().unwrap().name());
assert_eq!("count", fields.next().unwrap().name());
assert_eq!("popularity", fields.next().unwrap().name());
assert_eq!("score", fields.next().unwrap().name());
let mut fields = schema.fields();
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("title", field_entry.name());
assert_eq!(0, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("author", field_entry.name());
assert_eq!(1, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("count", field_entry.name());
assert_eq!(2, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("popularity", field_entry.name());
assert_eq!(3, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("score", field_entry.name());
assert_eq!(4, field.field_id());
}
assert!(fields.next().is_none());
}
@@ -495,6 +539,54 @@ mod tests {
assert_eq!(doc, doc_serdeser);
}
#[test]
pub fn test_document_from_nameddoc() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field("title", TEXT);
let val = schema_builder.add_i64_field("val", INDEXED);
let schema = schema_builder.build();
let mut named_doc_map = BTreeMap::default();
named_doc_map.insert(
"title".to_string(),
vec![Value::from("title1"), Value::from("title2")],
);
named_doc_map.insert(
"val".to_string(),
vec![Value::from(14u64), Value::from(-1i64)],
);
let doc = schema
.convert_named_doc(NamedFieldDocument(named_doc_map))
.unwrap();
assert_eq!(
doc.get_all(title),
vec![
&Value::from("title1".to_string()),
&Value::from("title2".to_string())
]
);
assert_eq!(
doc.get_all(val),
vec![&Value::from(14u64), &Value::from(-1i64)]
);
}
#[test]
pub fn test_document_from_nameddoc_error() {
let schema = Schema::builder().build();
let mut named_doc_map = BTreeMap::default();
named_doc_map.insert(
"title".to_string(),
vec![Value::from("title1"), Value::from("title2")],
);
let err = schema
.convert_named_doc(NamedFieldDocument(named_doc_map))
.unwrap_err();
assert_eq!(
err,
DocParsingError::NoSuchFieldInSchema("title".to_string())
);
}
#[test]
pub fn test_parse_document() {
let mut schema_builder = Schema::builder();

31
src/schema/term.rs
View File

@@ -22,10 +22,10 @@ impl Term {
/// Builds a term given a field, and a i64-value
///
/// Assuming the term has a field id of 1, and a i64 value of 3234,
/// the Term will have 8 bytes.
/// the Term will have 12 bytes.
///
/// The first four byte are dedicated to storing the field id as a u64.
/// The 4 following bytes are encoding the u64 value.
/// The 8 following bytes are encoding the u64 value.
pub fn from_field_i64(field: Field, val: i64) -> Term {
let val_u64: u64 = common::i64_to_u64(val);
Term::from_field_u64(field, val_u64)
@@ -33,11 +33,11 @@ impl Term {
/// Builds a term given a field, and a f64-value
///
/// Assuming the term has a field id of 1, and a u64 value of 3234,
/// the Term will have 8 bytes. <= this is wrong
/// Assuming the term has a field id of 1, and a f64 value of 1.5,
/// the Term will have 12 bytes.
///
/// The first four byte are dedicated to storing the field id as a u64.
/// The 4 following bytes are encoding the u64 value.
/// The 8 following bytes are encoding the f64 as a u64 value.
pub fn from_field_f64(field: Field, val: f64) -> Term {
let val_u64: u64 = common::f64_to_u64(val);
Term::from_field_u64(field, val_u64)
@@ -46,10 +46,10 @@ impl Term {
/// Builds a term given a field, and a DateTime value
///
/// Assuming the term has a field id of 1, and a timestamp i64 value of 3234,
/// the Term will have 8 bytes.
/// the Term will have 12 bytes.
///
/// The first four byte are dedicated to storing the field id as a u64.
/// The 4 following bytes are encoding the DateTime as i64 timestamp value.
/// The 8 following bytes are encoding the DateTime as i64 timestamp value.
pub fn from_field_date(field: Field, val: &DateTime) -> Term {
let val_timestamp = val.timestamp();
Term::from_field_i64(field, val_timestamp)
@@ -82,10 +82,10 @@ impl Term {
/// Builds a term given a field, and a u64-value
///
/// Assuming the term has a field id of 1, and a u64 value of 3234,
/// the Term will have 8 bytes.
/// the Term will have 12 bytes.
///
/// The first four byte are dedicated to storing the field id as a u64.
/// The 4 following bytes are encoding the u64 value.
/// The 8 following bytes are encoding the u64 value.
pub fn from_field_u64(field: Field, val: u64) -> Term {
let mut term = Term(vec![0u8; INT_TERM_LEN]);
term.set_field(field);
@@ -105,7 +105,7 @@ impl Term {
if self.0.len() < 4 {
self.0.resize(4, 0u8);
}
BigEndian::write_u32(&mut self.0[0..4], field.0);
BigEndian::write_u32(&mut self.0[0..4], field.field_id());
}
/// Sets a u64 value in the term.
@@ -157,7 +157,7 @@ where
/// Returns the field.
pub fn field(&self) -> Field {
Field(BigEndian::read_u32(&self.0.as_ref()[..4]))
Field::from_field_id(BigEndian::read_u32(&self.0.as_ref()[..4]))
}
/// Returns the `u64` value stored in a term.
@@ -182,7 +182,7 @@ where
///
/// # Panics
/// ... or returns an invalid value
/// if the term is not a `i64` field.
/// if the term is not a `f64` field.
pub fn get_f64(&self) -> f64 {
common::u64_to_f64(BigEndian::read_u64(&self.0.as_ref()[4..]))
}
@@ -224,7 +224,12 @@ where
impl fmt::Debug for Term {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "Term({:?})", &self.0[..])
write!(
f,
"Term(field={},bytes={:?})",
self.field().field_id(),
self.value_bytes()
)
}
}

64
src/schema/value.rs
View File

@@ -1,4 +1,5 @@
use crate::schema::Facet;
use crate::tokenizer::PreTokenizedString;
use crate::DateTime;
use serde::de::Visitor;
use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -10,6 +11,8 @@ use std::{cmp::Ordering, fmt};
pub enum Value {
/// The str type is used for any text information.
Str(String),
/// Pre-tokenized str type,
PreTokStr(PreTokenizedString),
/// Unsigned 64-bits Integer `u64`
U64(u64),
/// Signed 64-bits Integer `i64`
@@ -29,6 +32,7 @@ impl Ord for Value {
fn cmp(&self, other: &Self) -> Ordering {
match (self, other) {
(Value::Str(l), Value::Str(r)) => l.cmp(r),
(Value::PreTokStr(l), Value::PreTokStr(r)) => l.cmp(r),
(Value::U64(l), Value::U64(r)) => l.cmp(r),
(Value::I64(l), Value::I64(r)) => l.cmp(r),
(Value::Date(l), Value::Date(r)) => l.cmp(r),
@@ -44,6 +48,8 @@ impl Ord for Value {
}
(Value::Str(_), _) => Ordering::Less,
(_, Value::Str(_)) => Ordering::Greater,
(Value::PreTokStr(_), _) => Ordering::Less,
(_, Value::PreTokStr(_)) => Ordering::Greater,
(Value::U64(_), _) => Ordering::Less,
(_, Value::U64(_)) => Ordering::Greater,
(Value::I64(_), _) => Ordering::Less,
@@ -65,6 +71,7 @@ impl Serialize for Value {
{
match *self {
Value::Str(ref v) => serializer.serialize_str(v),
Value::PreTokStr(ref v) => v.serialize(serializer),
Value::U64(u) => serializer.serialize_u64(u),
Value::I64(u) => serializer.serialize_i64(u),
Value::F64(u) => serializer.serialize_f64(u),
@@ -124,6 +131,15 @@ impl Value {
}
}
/// Returns the tokenized text, provided the value is of the `PreTokStr` type.
/// (Returns None if the value is not of the `PreTokStr` type).
pub fn tokenized_text(&self) -> Option<&PreTokenizedString> {
match *self {
Value::PreTokStr(ref tok_text) => Some(tok_text),
_ => None,
}
}
/// Returns the u64-value, provided the value is of the `U64` type.
///
/// # Panics
@@ -217,10 +233,17 @@ impl From<Vec<u8>> for Value {
}
}
impl From<PreTokenizedString> for Value {
fn from(pretokenized_string: PreTokenizedString) -> Value {
Value::PreTokStr(pretokenized_string)
}
}
mod binary_serialize {
use super::Value;
use crate::common::{f64_to_u64, u64_to_f64, BinarySerializable};
use crate::schema::Facet;
use crate::tokenizer::PreTokenizedString;
use chrono::{TimeZone, Utc};
use std::io::{self, Read, Write};
@@ -231,6 +254,11 @@ mod binary_serialize {
const BYTES_CODE: u8 = 4;
const DATE_CODE: u8 = 5;
const F64_CODE: u8 = 6;
const EXT_CODE: u8 = 7;
// extended types
const TOK_STR_CODE: u8 = 0;
impl BinarySerializable for Value {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
@@ -239,6 +267,18 @@ mod binary_serialize {
TEXT_CODE.serialize(writer)?;
text.serialize(writer)
}
Value::PreTokStr(ref tok_str) => {
EXT_CODE.serialize(writer)?;
TOK_STR_CODE.serialize(writer)?;
if let Ok(text) = serde_json::to_string(tok_str) {
text.serialize(writer)
} else {
Err(io::Error::new(
io::ErrorKind::Other,
"Failed to dump Value::PreTokStr(_) to json.",
))
}
}
Value::U64(ref val) => {
U64_CODE.serialize(writer)?;
val.serialize(writer)
@@ -290,6 +330,30 @@ mod binary_serialize {
}
HIERARCHICAL_FACET_CODE => Ok(Value::Facet(Facet::deserialize(reader)?)),
BYTES_CODE => Ok(Value::Bytes(Vec::<u8>::deserialize(reader)?)),
EXT_CODE => {
let ext_type_code = u8::deserialize(reader)?;
match ext_type_code {
TOK_STR_CODE => {
let str_val = String::deserialize(reader)?;
if let Ok(value) = serde_json::from_str::<PreTokenizedString>(&str_val)
{
Ok(Value::PreTokStr(value))
} else {
Err(io::Error::new(
io::ErrorKind::Other,
"Failed to parse string data as Value::PreTokStr(_).",
))
}
}
_ => Err(io::Error::new(
io::ErrorKind::InvalidData,
format!(
"No extened field type is associated with code {:?}",
ext_type_code
),
)),
}
}
_ => Err(io::Error::new(
io::ErrorKind::InvalidData,
format!("No field type is associated with code {:?}", type_code),

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