rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-01-08 01:52:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

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

17 Commits
fix-bench ... 0.1

Author SHA1 Message Date
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
44 changed files with 1069 additions and 202 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']

4
CHANGELOG.md
View File

@@ -9,6 +9,10 @@ Tantivy 0.11.0
- API change around `Box<BoxableTokenizer>`. See detail in #629 - API change around `Box<BoxableTokenizer>`. See detail in #629
- Avoid rebuilding Regex automaton whenever a regex query is reused. #639 (@brainlock) - Avoid rebuilding Regex automaton whenever a regex query is reused. #639 (@brainlock)
- Add footer with some metadata to index files. #605 (@fdb-hiroshima) - 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? ## How to update?

16
Cargo.toml
View File

@@ -13,7 +13,7 @@ keywords = ["search", "information", "retrieval"]
edition = "2018" edition = "2018"
[dependencies] [dependencies]
base64 = "0.10.0" base64 = "0.11.0"
byteorder = "1.0" byteorder = "1.0"
crc32fast = "1.2.0" crc32fast = "1.2.0"
once_cell = "1.0" once_cell = "1.0"
@@ -34,7 +34,7 @@ itertools = "0.8"
levenshtein_automata = {version="0.1", features=["fst_automaton"]} levenshtein_automata = {version="0.1", features=["fst_automaton"]}
notify = {version="4", optional=true} notify = {version="4", optional=true}
bit-set = "0.5" bit-set = "0.5"
uuid = { version = "0.7.2", features = ["v4", "serde"] } uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.7" crossbeam = "0.7"
futures = "0.1" futures = "0.1"
futures-cpupool = "0.1" futures-cpupool = "0.1"
@@ -50,10 +50,10 @@ owned-read = "0.4"
failure = "0.1" failure = "0.1"
htmlescape = "0.3.1" htmlescape = "0.3.1"
fail = "0.3" fail = "0.3"
scoped-pool = "1.0"
murmurhash32 = "0.2" murmurhash32 = "0.2"
chrono = "0.4" chrono = "0.4"
smallvec = "0.6" smallvec = "1.0"
rayon = "1"
[target.'cfg(windows)'.dependencies] [target.'cfg(windows)'.dependencies]
winapi = "0.3" winapi = "0.3"
@@ -64,6 +64,10 @@ maplit = "1"
matches = "0.1.8" matches = "0.1.8"
time = "0.1.42" time = "0.1.42"
[dev-dependencies.fail]
version = "0.3"
features = ["failpoints"]
[profile.release] [profile.release]
opt-level = 3 opt-level = 3
debug = false debug = false
@@ -87,10 +91,6 @@ members = ["query-grammar"]
[badges] [badges]
travis-ci = { repository = "tantivy-search/tantivy" } travis-ci = { repository = "tantivy-search/tantivy" }
[dev-dependencies.fail]
version = "0.3"
features = ["failpoints"]
# Following the "fail" crate best practises, we isolate # Following the "fail" crate best practises, we isolate
# tests that define specific behavior in fail check points # tests that define specific behavior in fail check points
# in a different binary. # in a different binary.

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) [![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 an off-the-shelf search engine server, but rather a crate that can be used
to build such a search engine. to build such a search engine.
@@ -31,7 +31,7 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark # 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 nature of the queries in your workload.
The following [benchmark](https://tantivy-search.github.io/bench/) break downs The following [benchmark](https://tantivy-search.github.io/bench/) break downs
@@ -40,19 +40,19 @@ performance for different type of queries / collection.
# Features # Features
- Full-text search - 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:) - Fast (check out the :racehorse: :sparkles: [benchmark](https://tantivy-search.github.io/bench/) :sparkles: :racehorse:)
- Tiny startup time (<10ms), perfect for command line tools - Tiny startup time (<10ms), perfect for command line tools
- BM25 scoring (the same as lucene) - BM25 scoring (the same as Lucene)
- Natural query language `(michael AND jackson) OR "king of pop"` - Natural query language (e.g. `(michael AND jackson) OR "king of pop"`)
- Phrase queries search (`"michael jackson"`) - Phrase queries search (e.g. `"michael jackson"`)
- Incremental indexing - Incremental indexing
- Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop) - Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop)
- Mmap directory - Mmap directory
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set. - 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) - Single valued and multivalued u64, i64, and f64 fast fields (equivalent of doc values in Lucene)
- `&[u8]` fast fields - `&[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 - LZ4 compressed document store
- Range queries - Range queries
- Faceted search - Faceted search
@@ -61,43 +61,42 @@ performance for different type of queries / collection.
# Non-features # Non-features
- Distributed search is out of the scope of tantivy. That being said, tantivy is meant as a - Distributed search is out of the scope of Tantivy. That being said, Tantivy is a
library upon which one could build a distributed search. Serializable/mergeable collector state for instance, 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 # 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 # Getting started
- [tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html) - [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 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,
`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.
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.
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/)
- [reference doc for the last released version](https://docs.rs/tantivy/)
# How can I support this project? # How can I support this project?
There are many ways to 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 - Report bugs
- Write a blog post - Write a blog post
- Help with documentation by asking questions or submitting PRs - Help with documentation by asking questions or submitting PRs
- Contribute code (you can join [our gitter](https://gitter.im/tantivy-search/tantivy) ) - Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy))
- Talk about tantivy around you - 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) - 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 # 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 ## Clone and build locally
Tantivy compiles on stable rust but requires `Rust >= 1.27`. Tantivy compiles on stable Rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run : To check out and run tests, you can simply run:
```bash ```bash
git clone https://github.com/tantivy-search/tantivy.git 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 ## Run tests
Some tests will not run with just `cargo test` because of `fail-rs`. 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 ## Debug
@@ -116,13 +115,13 @@ You might find it useful to step through the programme with a debugger.
### A failing test ### 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 ```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 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 ```bash
$gdb run --test-threads 1 --test $NAME_OF_TEST $gdb run --test-threads 1 --test $NAME_OF_TEST
@@ -130,7 +129,7 @@ $gdb run --test-threads 1 --test $NAME_OF_TEST
### An example ### An example
By default, rustc compiles everything in the `examples/` dir in debug mode. This makes it easy for you to make examples to reproduce bugs. By default, `rustc` compiles everything in the `examples/` directory in debug mode. This makes it easy for you to make examples to reproduce bugs:
```bash ```bash
rust-gdb target/debug/examples/$EXAMPLE_NAME rust-gdb target/debug/examples/$EXAMPLE_NAME

140
examples/pre_tokenized_text.rs Normal file
View File

@@ -0,0 +1,140 @@
// # 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 mut old_man_doc = Document::default();
old_man_doc.add_pre_tokenized_text(title, &title_tok);
old_man_doc.add_pre_tokenized_text(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(())
}

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

@@ -2,7 +2,7 @@ use std::fmt;
use std::fmt::Write; use std::fmt::Write;
/// Defines whether a term in a query must be present, /// 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)] #[derive(Debug, Clone, Hash, Copy, Eq, PartialEq)]
pub enum Occur { pub enum Occur {
/// For a given document to be considered for scoring, /// For a given document to be considered for scoring,

4
src/collector/facet_collector.rs
View File

@@ -515,7 +515,7 @@ mod tests {
#[should_panic(expected = "Tried to add a facet which is a descendant of \ #[should_panic(expected = "Tried to add a facet which is a descendant of \
an already added facet.")] an already added facet.")]
fn test_misused_facet_collector() { 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"));
facet_collector.add_facet(Facet::from("/country/europe")); facet_collector.add_facet(Facet::from("/country/europe"));
} }
@@ -546,7 +546,7 @@ mod tests {
#[test] #[test]
fn test_non_used_facet_collector() { 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("/country"));
facet_collector.add_facet(Facet::from("/countryeurope")); facet_collector.add_facet(Facet::from("/countryeurope"));
} }

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 /// 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. /// 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. /// WARNING: equality is not what you would expect here.
/// Two elements are equal if their feature is equal, and regardless of whether `doc` /// 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 /// 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, 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> { fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other)) Some(self.cmp(other))
} }
} }
impl<T: PartialOrd, D> Ord for ComparableDoc<T, D> { impl<T: PartialOrd, D: PartialOrd> Ord for ComparableDoc<T, D> {
#[inline] #[inline]
fn cmp(&self, other: &Self) -> Ordering { fn cmp(&self, other: &Self) -> Ordering {
other // Reversed to make BinaryHeap work as a min-heap
let by_feature = other
.feature .feature
.partial_cmp(&self.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 { fn eq(&self, other: &Self) -> bool {
self.cmp(other) == Ordering::Equal 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> { pub(crate) struct TopCollector<T> {
limit: usize, 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()
});
}
} }

33
src/collector/top_score_collector.rs
View File

@@ -15,13 +15,16 @@ use crate::SegmentLocalId;
use crate::SegmentReader; use crate::SegmentReader;
use std::fmt; 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. /// sorted by their score.
/// ///
/// The implementation is based on a `BinaryHeap`. /// The implementation is based on a `BinaryHeap`.
/// The theorical complexity for collecting the top `K` out of `n` documents /// The theorical complexity for collecting the top `K` out of `n` documents
/// is `O(n log K)`. /// 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 /// ```rust
/// use tantivy::collector::TopDocs; /// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser; /// use tantivy::query::QueryParser;
@@ -428,12 +431,13 @@ impl SegmentCollector for TopScoreSegmentCollector {
mod tests { mod tests {
use super::TopDocs; use super::TopDocs;
use crate::collector::Collector; 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::schema::{Field, Schema, FAST, STORED, TEXT};
use crate::DocAddress; use crate::DocAddress;
use crate::Index; use crate::Index;
use crate::IndexWriter; use crate::IndexWriter;
use crate::Score; use crate::Score;
use itertools::Itertools;
fn make_index() -> Index { fn make_index() -> Index {
let mut schema_builder = Schema::builder(); let mut schema_builder = Schema::builder();
@@ -494,6 +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] #[test]
#[should_panic] #[should_panic]
fn test_top_0() { fn test_top_0() {
@@ -551,7 +578,7 @@ mod tests {
)); ));
}); });
let searcher = index.reader().unwrap().searcher(); 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); let segment_reader = searcher.segment_reader(0u32);
top_collector top_collector
.for_segment(0, segment_reader) .for_segment(0, segment_reader)

12
src/common/composite_file.rs
View File

@@ -199,13 +199,13 @@ mod test {
let w = directory.open_write(path).unwrap(); let w = directory.open_write(path).unwrap();
let mut composite_write = CompositeWrite::wrap(w); 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(); VInt(32431123u64).serialize(&mut write_0).unwrap();
write_0.flush().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(); VInt(2).serialize(&mut write_4).unwrap();
write_4.flush().unwrap(); write_4.flush().unwrap();
} }
@@ -215,14 +215,18 @@ mod test {
let r = directory.open_read(path).unwrap(); let r = directory.open_read(path).unwrap();
let composite_file = CompositeFile::open(&r).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 mut file0_buf = file0.as_slice();
let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0; let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0;
assert_eq!(file0_buf.len(), 0); assert_eq!(file0_buf.len(), 0);
assert_eq!(payload_0, 32431123u64); 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 mut file4_buf = file4.as_slice();
let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0; let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
assert_eq!(file4_buf.len(), 0); assert_eq!(file4_buf.len(), 0);

20
src/core/executor.rs
View File

@@ -1,6 +1,6 @@
use crate::Result; use crate::Result;
use crossbeam::channel; use crossbeam::channel;
use scoped_pool::{Pool, ThreadConfig}; use rayon::{ThreadPool, ThreadPoolBuilder};
/// Search executor whether search request are single thread or multithread. /// 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. /// used by the client. Second, we may stop using rayon in the future.
pub enum Executor { pub enum Executor {
SingleThread, SingleThread,
ThreadPool(Pool), ThreadPool(ThreadPool),
} }
impl Executor { impl Executor {
@@ -21,10 +21,12 @@ impl Executor {
} }
// Creates an Executor that dispatches the tasks in a thread pool. // Creates an Executor that dispatches the tasks in a thread pool.
pub fn multi_thread(num_threads: usize, prefix: &'static str) -> Executor { pub fn multi_thread(num_threads: usize, prefix: &'static str) -> Result<Executor> {
let thread_config = ThreadConfig::new().prefix(prefix); let pool = ThreadPoolBuilder::new()
let pool = Pool::with_thread_config(num_threads, thread_config); .num_threads(num_threads)
Executor::ThreadPool(pool) .thread_name(move |num| format!("{}{}", prefix, num))
.build()?;
Ok(Executor::ThreadPool(pool))
} }
// Perform a map in the thread pool. // Perform a map in the thread pool.
@@ -48,9 +50,9 @@ impl Executor {
let num_fruits = args_with_indices.len(); let num_fruits = args_with_indices.len();
let fruit_receiver = { let fruit_receiver = {
let (fruit_sender, fruit_receiver) = channel::unbounded(); let (fruit_sender, fruit_receiver) = channel::unbounded();
pool.scoped(|scope| { pool.scope(|scope| {
for arg_with_idx in args_with_indices { for arg_with_idx in args_with_indices {
scope.execute(|| { scope.spawn(|_| {
let (idx, arg) = arg_with_idx; let (idx, arg) = arg_with_idx;
let fruit = f(arg); let fruit = f(arg);
if let Err(err) = fruit_sender.send((idx, fruit)) { if let Err(err) = fruit_sender.send((idx, fruit)) {
@@ -103,6 +105,7 @@ mod tests {
#[should_panic] //< unfortunately the panic message is not propagated #[should_panic] //< unfortunately the panic message is not propagated
fn test_panic_propagates_multi_thread() { fn test_panic_propagates_multi_thread() {
let _result: Vec<usize> = Executor::multi_thread(1, "search-test") let _result: Vec<usize> = Executor::multi_thread(1, "search-test")
.unwrap()
.map( .map(
|_| { |_| {
panic!("panic should propagate"); panic!("panic should propagate");
@@ -126,6 +129,7 @@ mod tests {
#[test] #[test]
fn test_map_multithread() { fn test_map_multithread() {
let result: Vec<usize> = Executor::multi_thread(3, "search-test") let result: Vec<usize> = Executor::multi_thread(3, "search-test")
.unwrap()
.map(|i| Ok(i * 2), 0..10) .map(|i| Ok(i * 2), 0..10)
.unwrap(); .unwrap();
assert_eq!(result.len(), 10); assert_eq!(result.len(), 10);

9
src/core/index.rs
View File

@@ -73,15 +73,16 @@ impl Index {
/// Replace the default single thread search executor pool /// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads. /// by a thread pool with a given number of threads.
pub fn set_multithread_executor(&mut self, num_threads: usize) { pub fn set_multithread_executor(&mut self, num_threads: usize) -> Result<()> {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")); self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")?);
Ok(())
} }
/// Replace the default single thread search executor pool /// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads. /// 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(); 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`. /// Creates a new index using the `RAMDirectory`.

15
src/core/index_meta.rs
View File

@@ -150,6 +150,21 @@ impl SegmentMeta {
self.num_deleted_docs() > 0 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)] #[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta { pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta {
let delete_meta = DeleteMeta { let delete_meta = DeleteMeta {

11
src/core/segment.rs
View File

@@ -50,6 +50,17 @@ impl Segment {
&self.meta &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)] #[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment { pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment {
Segment { Segment {

2
src/core/segment_id.rs
View File

@@ -76,7 +76,7 @@ impl SegmentId {
} }
/// Error type used when parsing a `SegmentId` from a string fails. /// Error type used when parsing a `SegmentId` from a string fails.
pub struct SegmentIdParseError(uuid::parser::ParseError); pub struct SegmentIdParseError(uuid::Error);
impl Error for SegmentIdParseError {} impl Error for SegmentIdParseError {}

3
src/directory/managed_directory.rs
View File

@@ -327,8 +327,7 @@ mod tests_mmap_specific {
.unwrap(); .unwrap();
assert!(managed_directory.exists(test_path1)); assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path2)); assert!(managed_directory.exists(test_path2));
let living_files: HashSet<PathBuf> = let living_files: HashSet<PathBuf> = [test_path1.to_owned()].iter().cloned().collect();
[test_path1.to_owned()].into_iter().cloned().collect();
managed_directory.garbage_collect(|| living_files); managed_directory.garbage_collect(|| living_files);
assert!(managed_directory.exists(test_path1)); assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2)); assert!(!managed_directory.exists(test_path2));

6
src/error.rs
View File

@@ -170,3 +170,9 @@ impl From<serde_json::Error> for TantivyError {
TantivyError::IOError(io_err.into()) 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` /// Write a delete `BitSet`
/// ///
/// where `delete_bitset` is the set of deleted `DocId`. /// where `delete_bitset` is the set of deleted `DocId`.
pub fn write_delete_bitset(delete_bitset: &BitSet, writer: &mut WritePtr) -> io::Result<()> { pub fn write_delete_bitset(
let max_doc = delete_bitset.capacity(); delete_bitset: &BitSet,
max_doc: u32,
writer: &mut WritePtr,
) -> io::Result<()> {
let mut byte = 0u8; let mut byte = 0u8;
let mut shift = 0u8; let mut shift = 0u8;
for doc in 0..max_doc { for doc in 0..(max_doc as usize) {
if delete_bitset.contains(doc) { if delete_bitset.contains(doc) {
byte |= 1 << shift; byte |= 1 << shift;
} }
@@ -86,18 +89,17 @@ mod tests {
use bit_set::BitSet; use bit_set::BitSet;
use std::path::PathBuf; 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 test_path = PathBuf::from("test");
let mut directory = RAMDirectory::create(); let mut directory = RAMDirectory::create();
{ {
let mut writer = directory.open_write(&*test_path).unwrap(); 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 source = directory.open_read(&test_path).unwrap();
let delete_bitset = DeleteBitSet::open(source); let delete_bitset = DeleteBitSet::open(source);
let n = bitset.capacity(); for doc in 0..max_doc as usize {
for doc in 0..n {
assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId)); assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId));
} }
assert_eq!(delete_bitset.len(), bitset.len()); assert_eq!(delete_bitset.len(), bitset.len());
@@ -110,7 +112,7 @@ mod tests {
let mut bitset = BitSet::with_capacity(10); let mut bitset = BitSet::with_capacity(10);
bitset.insert(1); bitset.insert(1);
bitset.insert(9); bitset.insert(9);
test_delete_bitset_helper(&bitset); test_delete_bitset_helper(&bitset, 10);
} }
{ {
let mut bitset = BitSet::with_capacity(8); let mut bitset = BitSet::with_capacity(8);
@@ -119,7 +121,7 @@ mod tests {
bitset.insert(3); bitset.insert(3);
bitset.insert(5); bitset.insert(5);
bitset.insert(7); bitset.insert(7);
test_delete_bitset_helper(&bitset); test_delete_bitset_helper(&bitset, 8);
} }
} }
} }

3
src/fastfield/readers.rs
View File

@@ -59,8 +59,7 @@ impl FastFieldReaders {
fast_bytes: Default::default(), fast_bytes: Default::default(),
fast_fields_composite: fast_fields_composite.clone(), fast_fields_composite: fast_fields_composite.clone(),
}; };
for (field_id, field_entry) in schema.fields().iter().enumerate() { for (field, field_entry) in schema.fields() {
let field = Field(field_id as u32);
let field_type = field_entry.field_type(); let field_type = field_entry.field_type();
if field_type == &FieldType::Bytes { if field_type == &FieldType::Bytes {
let idx_reader = fast_fields_composite let idx_reader = fast_fields_composite

3
src/fastfield/writer.rs
View File

@@ -24,8 +24,7 @@ impl FastFieldsWriter {
let mut multi_values_writers = Vec::new(); let mut multi_values_writers = Vec::new();
let mut bytes_value_writers = Vec::new(); let mut bytes_value_writers = Vec::new();
for (field_id, field_entry) in schema.fields().iter().enumerate() { for (field, field_entry) in schema.fields() {
let field = Field(field_id as u32);
let default_value = match *field_entry.field_type() { let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64), FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64), FieldType::F64(_) => common::f64_to_u64(0.0f64),

23
src/fieldnorm/writer.rs
View File

@@ -22,11 +22,14 @@ impl FieldNormsWriter {
pub(crate) fn fields_with_fieldnorm(schema: &Schema) -> Vec<Field> { pub(crate) fn fields_with_fieldnorm(schema: &Schema) -> Vec<Field> {
schema schema
.fields() .fields()
.iter() .filter_map(|(field, field_entry)| {
.enumerate() if field_entry.is_indexed() {
.filter(|&(_, field_entry)| field_entry.is_indexed()) Some(field)
.map(|(field, _)| Field(field as u32)) } else {
.collect::<Vec<Field>>() None
}
})
.collect::<Vec<_>>()
} }
/// Initialize with state for tracking the field norm fields /// Initialize with state for tracking the field norm fields
@@ -35,7 +38,7 @@ impl FieldNormsWriter {
let fields = FieldNormsWriter::fields_with_fieldnorm(schema); let fields = FieldNormsWriter::fields_with_fieldnorm(schema);
let max_field = fields let max_field = fields
.iter() .iter()
.map(|field| field.0) .map(Field::field_id)
.max() .max()
.map(|max_field_id| max_field_id as usize + 1) .map(|max_field_id| max_field_id as usize + 1)
.unwrap_or(0); .unwrap_or(0);
@@ -50,8 +53,8 @@ impl FieldNormsWriter {
/// ///
/// Will extend with 0-bytes for documents that have not been seen. /// Will extend with 0-bytes for documents that have not been seen.
pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) { pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) {
for &field in self.fields.iter() { for field in self.fields.iter() {
self.fieldnorms_buffer[field.0 as usize].resize(max_doc as usize, 0u8); 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 /// * field - the field being set
/// * fieldnorm - the number of terms present in document `doc` in field `field` /// * fieldnorm - the number of terms present in document `doc` in field `field`
pub fn record(&mut self, doc: DocId, field: Field, fieldnorm: u32) { 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!( assert!(
fieldnorm_buffer.len() <= doc as usize, fieldnorm_buffer.len() <= doc as usize,
"Cannot register a given fieldnorm twice" "Cannot register a given fieldnorm twice"
@@ -77,7 +80,7 @@ impl FieldNormsWriter {
/// Serialize the seen fieldnorm values to the serializer for all fields. /// Serialize the seen fieldnorm values to the serializer for all fields.
pub fn serialize(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> io::Result<()> { pub fn serialize(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> io::Result<()> {
for &field in self.fields.iter() { for &field in self.fields.iter() {
let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.0 as usize][..]; let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.field_id() as usize][..];
fieldnorms_serializer.serialize_field(field, fieldnorm_values)?; fieldnorms_serializer.serialize_field(field, fieldnorm_values)?;
} }
Ok(()) Ok(())

2
src/indexer/delete_queue.rs
View File

@@ -258,7 +258,7 @@ mod tests {
let delete_queue = DeleteQueue::new(); let delete_queue = DeleteQueue::new();
let make_op = |i: usize| { let make_op = |i: usize| {
let field = Field(1u32); let field = Field::from_field_id(1u32);
DeleteOperation { DeleteOperation {
opstamp: i as u64, opstamp: i as u64,
term: Term::from_field_u64(field, i as u64), term: Term::from_field_u64(field, i as u64),

37
src/indexer/index_writer.rs
View File

@@ -148,7 +148,6 @@ pub(crate) fn advance_deletes(
}; };
let delete_cursor = segment_entry.delete_cursor(); let delete_cursor = segment_entry.delete_cursor();
compute_deleted_bitset( compute_deleted_bitset(
&mut delete_bitset, &mut delete_bitset,
&segment_reader, &segment_reader,
@@ -168,7 +167,7 @@ pub(crate) fn advance_deletes(
if num_deleted_docs > 0 { if num_deleted_docs > 0 {
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp); segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?; 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()?; delete_file.terminate()?;
} }
} }
@@ -178,13 +177,13 @@ pub(crate) fn advance_deletes(
fn index_documents( fn index_documents(
memory_budget: usize, memory_budget: usize,
segment: &Segment, segment: Segment,
grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>, grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>,
segment_updater: &mut SegmentUpdater, segment_updater: &mut SegmentUpdater,
mut delete_cursor: DeleteCursor, mut delete_cursor: DeleteCursor,
) -> Result<bool> { ) -> Result<bool> {
let schema = segment.schema(); let schema = segment.schema();
let segment_id = segment.id();
let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?; let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?;
for document_group in grouped_document_iterator { for document_group in grouped_document_iterator {
for doc in document_group { for doc in document_group {
@@ -204,22 +203,32 @@ fn index_documents(
return Ok(false); 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 // this is ensured by the call to peek before starting
// the worker thread. // the worker thread.
assert!(num_docs > 0); assert!(max_doc > 0);
let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?; let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?;
let segment_meta = segment.index().new_segment_meta(segment_id, num_docs);
let segment_with_max_doc = segment.with_max_doc(max_doc);
let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap()); let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
let delete_bitset_opt = let delete_bitset_opt = apply_deletes(
apply_deletes(&segment, &mut delete_cursor, &doc_opstamps, last_docstamp)?; &segment_with_max_doc,
&mut delete_cursor,
&doc_opstamps,
last_docstamp,
)?;
let segment_entry = SegmentEntry::new(segment_meta, delete_cursor, delete_bitset_opt); let segment_entry = SegmentEntry::new(
Ok(segment_updater.add_segment(segment_entry)) segment_with_max_doc.meta().clone(),
delete_cursor,
delete_bitset_opt,
);
segment_updater.add_segment(segment_entry);
Ok(true)
} }
fn apply_deletes( fn apply_deletes(
@@ -235,7 +244,9 @@ fn apply_deletes(
} }
let segment_reader = SegmentReader::open(segment)?; let segment_reader = SegmentReader::open(segment)?;
let doc_to_opstamps = DocToOpstampMapping::from(doc_opstamps); 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( let may_have_deletes = compute_deleted_bitset(
&mut deleted_bitset, &mut deleted_bitset,
&segment_reader, &segment_reader,
@@ -407,7 +418,7 @@ impl IndexWriter {
let segment = index.new_segment(); let segment = index.new_segment();
index_documents( index_documents(
mem_budget, mem_budget,
&segment, segment,
&mut document_iterator, &mut document_iterator,
&mut segment_updater, &mut segment_updater,
delete_cursor.clone(), delete_cursor.clone(),

16
src/indexer/merger.rs
View File

@@ -190,8 +190,7 @@ impl IndexMerger {
fast_field_serializer: &mut FastFieldSerializer, fast_field_serializer: &mut FastFieldSerializer,
mut term_ord_mappings: HashMap<Field, TermOrdinalMapping>, mut term_ord_mappings: HashMap<Field, TermOrdinalMapping>,
) -> Result<()> { ) -> Result<()> {
for (field_id, field_entry) in self.schema.fields().iter().enumerate() { for (field, field_entry) in self.schema.fields() {
let field = Field(field_id as u32);
let field_type = field_entry.field_type(); let field_type = field_entry.field_type();
match *field_type { match *field_type {
FieldType::HierarchicalFacet => { FieldType::HierarchicalFacet => {
@@ -649,15 +648,12 @@ impl IndexMerger {
serializer: &mut InvertedIndexSerializer, serializer: &mut InvertedIndexSerializer,
) -> Result<HashMap<Field, TermOrdinalMapping>> { ) -> Result<HashMap<Field, TermOrdinalMapping>> {
let mut term_ordinal_mappings = HashMap::new(); 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() { if field_entry.is_indexed() {
let indexed_field = Field(field_ord as u32); if let Some(term_ordinal_mapping) =
if let Some(term_ordinal_mapping) = self.write_postings_for_field( self.write_postings_for_field(field, field_entry.field_type(), serializer)?
indexed_field, {
field_entry.field_type(), term_ordinal_mappings.insert(field, term_ordinal_mapping);
serializer,
)? {
term_ordinal_mappings.insert(indexed_field, term_ordinal_mapping);
} }
} }
} }

22
src/indexer/mod.rs
View File

@@ -28,3 +28,25 @@ pub use self::segment_writer::SegmentWriter;
/// Alias for the default merge policy, which is the `LogMergePolicy`. /// Alias for the default merge policy, which is the `LogMergePolicy`.
pub type DefaultMergePolicy = 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();
}
}

4
src/indexer/segment_updater.rs
View File

@@ -199,14 +199,12 @@ impl SegmentUpdater {
self.0.pool.spawn_fn(move || Ok(f(me_clone))) self.0.pool.spawn_fn(move || Ok(f(me_clone)))
} }
pub fn add_segment(&self, segment_entry: SegmentEntry) -> bool { pub fn add_segment(&self, segment_entry: SegmentEntry) {
self.run_async(|segment_updater| { self.run_async(|segment_updater| {
segment_updater.0.segment_manager.add_segment(segment_entry); segment_updater.0.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options(); segment_updater.consider_merge_options();
true
}) })
.forget(); .forget();
true
} }
/// Orders `SegmentManager` to remove all segments /// Orders `SegmentManager` to remove all segments

72
src/indexer/segment_writer.rs
View File

@@ -6,14 +6,15 @@ use crate::fieldnorm::FieldNormsWriter;
use crate::indexer::segment_serializer::SegmentSerializer; use crate::indexer::segment_serializer::SegmentSerializer;
use crate::postings::compute_table_size; use crate::postings::compute_table_size;
use crate::postings::MultiFieldPostingsWriter; use crate::postings::MultiFieldPostingsWriter;
use crate::schema::FieldEntry;
use crate::schema::FieldType; use crate::schema::FieldType;
use crate::schema::Schema; use crate::schema::Schema;
use crate::schema::Term; use crate::schema::Term;
use crate::schema::Value; use crate::schema::Value;
use crate::schema::{Field, FieldEntry};
use crate::tokenizer::BoxedTokenizer; use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::FacetTokenizer; use crate::tokenizer::FacetTokenizer;
use crate::tokenizer::{TokenStream, Tokenizer}; use crate::tokenizer::PreTokenizedStream;
use crate::tokenizer::{TokenStream, TokenStreamChain, Tokenizer};
use crate::DocId; use crate::DocId;
use crate::Opstamp; use crate::Opstamp;
use crate::Result; use crate::Result;
@@ -70,12 +71,10 @@ impl SegmentWriter {
let table_num_bits = initial_table_size(memory_budget)?; let table_num_bits = initial_table_size(memory_budget)?;
let segment_serializer = SegmentSerializer::for_segment(&mut segment)?; let segment_serializer = SegmentSerializer::for_segment(&mut segment)?;
let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits); let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits);
let tokenizers = let tokenizers = schema
schema .fields()
.fields() .map(
.iter() |(_, field_entry): (Field, &FieldEntry)| match field_entry.field_type() {
.map(FieldEntry::field_type)
.map(|field_type| match *field_type {
FieldType::Str(ref text_options) => text_options FieldType::Str(ref text_options) => text_options
.get_indexing_options() .get_indexing_options()
.and_then(|text_index_option| { .and_then(|text_index_option| {
@@ -83,8 +82,9 @@ impl SegmentWriter {
segment.index().tokenizers().get(tokenizer_name) segment.index().tokenizers().get(tokenizer_name)
}), }),
_ => None, _ => None,
}) },
.collect(); )
.collect();
Ok(SegmentWriter { Ok(SegmentWriter {
max_doc: 0, max_doc: 0,
multifield_postings, multifield_postings,
@@ -159,26 +159,44 @@ impl SegmentWriter {
} }
} }
FieldType::Str(_) => { FieldType::Str(_) => {
let num_tokens = if let Some(ref mut tokenizer) = let mut token_streams: Vec<Box<dyn TokenStream>> = vec![];
self.tokenizers[field.0 as usize] let mut offsets = vec![];
{ let mut total_offset = 0;
let texts: Vec<&str> = field_values
.iter() for field_value in field_values {
.flat_map(|field_value| match *field_value.value() { match field_value.value() {
Value::Str(ref text) => Some(text.as_str()), Value::PreTokStr(tok_str) => {
_ => None, offsets.push(total_offset);
}) if let Some(last_token) = tok_str.tokens.last() {
.collect(); total_offset += last_token.offset_to;
if texts.is_empty() { }
0
} else { token_streams
let mut token_stream = tokenizer.token_stream_texts(&texts[..]); .push(Box::new(PreTokenizedStream::from(tok_str.clone())));
self.multifield_postings }
.index_text(doc_id, field, &mut token_stream) 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 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); self.fieldnorms_writer.record(doc_id, field, num_tokens);
} }
FieldType::U64(ref int_option) => { FieldType::U64(ref int_option) => {

14
src/lib.rs
View File

@@ -212,15 +212,13 @@ pub type Score = f32;
pub type SegmentLocalId = u32; pub type SegmentLocalId = u32;
impl DocAddress { impl DocAddress {
/// Return the segment ordinal. /// Return the segment ordinal id that identifies the segment
/// The segment ordinal is an id identifying the segment /// hosting the document in the `Searcher` it is called from.
/// hosting the document. It is only meaningful, in the context
/// of a searcher.
pub fn segment_ord(self) -> SegmentLocalId { pub fn segment_ord(self) -> SegmentLocalId {
self.0 self.0
} }
/// Return the segment local `DocId` /// Return the segment-local `DocId`
pub fn doc(self) -> DocId { pub fn doc(self) -> DocId {
self.1 self.1
} }
@@ -229,11 +227,11 @@ impl DocAddress {
/// `DocAddress` contains all the necessary information /// `DocAddress` contains all the necessary information
/// to identify a document given a `Searcher` object. /// to identify a document given a `Searcher` object.
/// ///
/// It consists in an id identifying its segment, and /// It consists of an id identifying its segment, and
/// its segment-local `DocId`. /// a segment-local `DocId`.
/// ///
/// The id used for the segment is actually an ordinal /// 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)] #[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
pub struct DocAddress(pub SegmentLocalId, pub DocId); pub struct DocAddress(pub SegmentLocalId, pub DocId);

14
src/postings/mod.rs
View File

@@ -356,9 +356,9 @@ pub mod tests {
#[test] #[test]
fn test_skip_next() { fn test_skip_next() {
let term_0 = Term::from_field_u64(Field(0), 0); let term_0 = Term::from_field_u64(Field::from_field_id(0), 0);
let term_1 = Term::from_field_u64(Field(0), 1); let term_1 = Term::from_field_u64(Field::from_field_id(0), 1);
let term_2 = Term::from_field_u64(Field(0), 2); let term_2 = Term::from_field_u64(Field::from_field_id(0), 2);
let num_docs = 300u32; let num_docs = 300u32;
@@ -511,19 +511,19 @@ pub mod tests {
} }
pub static TERM_A: Lazy<Term> = Lazy::new(|| { 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") Term::from_field_text(field, "a")
}); });
pub static TERM_B: Lazy<Term> = Lazy::new(|| { 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") Term::from_field_text(field, "b")
}); });
pub static TERM_C: Lazy<Term> = Lazy::new(|| { 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") Term::from_field_text(field, "c")
}); });
pub static TERM_D: Lazy<Term> = Lazy::new(|| { 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") Term::from_field_text(field, "d")
}); });

17
src/postings/postings_writer.rs
View File

@@ -61,12 +61,12 @@ fn make_field_partition(
.iter() .iter()
.map(|(key, _, _)| Term::wrap(key).field()) .map(|(key, _, _)| Term::wrap(key).field())
.enumerate(); .enumerate();
let mut prev_field = Field(u32::max_value()); let mut prev_field_opt = None;
let mut fields = vec![]; let mut fields = vec![];
let mut offsets = vec![]; let mut offsets = vec![];
for (offset, field) in term_offsets_it { for (offset, field) in term_offsets_it {
if field != prev_field { if Some(field) != prev_field_opt {
prev_field = field; prev_field_opt = Some(field);
fields.push(field); fields.push(field);
offsets.push(offset); offsets.push(offset);
} }
@@ -86,8 +86,7 @@ impl MultiFieldPostingsWriter {
let term_index = TermHashMap::new(table_bits); let term_index = TermHashMap::new(table_bits);
let per_field_postings_writers: Vec<_> = schema let per_field_postings_writers: Vec<_> = schema
.fields() .fields()
.iter() .map(|(_, field_entry)| posting_from_field_entry(field_entry))
.map(|field_entry| posting_from_field_entry(field_entry))
.collect(); .collect();
MultiFieldPostingsWriter { MultiFieldPostingsWriter {
heap: MemoryArena::new(), heap: MemoryArena::new(),
@@ -107,7 +106,8 @@ impl MultiFieldPostingsWriter {
field: Field, field: Field,
token_stream: &mut dyn TokenStream, token_stream: &mut dyn TokenStream,
) -> u32 { ) -> 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( postings_writer.index_text(
&mut self.term_index, &mut self.term_index,
doc, doc,
@@ -118,7 +118,8 @@ impl MultiFieldPostingsWriter {
} }
pub fn subscribe(&mut self, doc: DocId, term: &Term) -> UnorderedTermId { 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) postings_writer.subscribe(&mut self.term_index, doc, 0u32, term, &mut self.heap)
} }
@@ -160,7 +161,7 @@ impl MultiFieldPostingsWriter {
FieldType::Bytes => {} 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 = let mut field_serializer =
serializer.new_field(field, postings_writer.total_num_tokens())?; serializer.new_field(field, postings_writer.total_num_tokens())?;
postings_writer.serialize( postings_writer.serialize(

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

@@ -9,7 +9,8 @@ use crate::Result;
use crate::Searcher; use crate::Searcher;
use std::collections::BTreeSet; 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 /// The documents matched by the boolean query are
/// those which /// those which
@@ -19,6 +20,113 @@ use std::collections::BTreeSet;
/// `MustNot` occurence. /// `MustNot` occurence.
/// * match at least one of the subqueries that is not /// * match at least one of the subqueries that is not
/// a `MustNot` occurence. /// 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)] #[derive(Debug)]
pub struct BooleanQuery { pub struct BooleanQuery {
subqueries: Vec<(Occur, Box<dyn Query>)>, subqueries: Vec<(Occur, Box<dyn Query>)>,

2
src/query/phrase_query/phrase_query.rs
View File

@@ -40,7 +40,7 @@ impl PhraseQuery {
PhraseQuery::new_with_offset(terms_with_offset) 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. /// Can be used to provide custom offset for each term.
pub fn new_with_offset(mut terms: Vec<(usize, Term)>) -> PhraseQuery { pub fn new_with_offset(mut terms: Vec<(usize, Term)>) -> PhraseQuery {

10
src/query/query_parser/query_parser.rs
View File

@@ -674,13 +674,19 @@ mod test {
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"signed:-2324", "signed:-2324",
&format!("{:?}", Term::from_field_i64(Field(2u32), -2324)), &format!(
"{:?}",
Term::from_field_i64(Field::from_field_id(2u32), -2324)
),
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"float:2.5", "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, false,
); );
} }

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

@@ -118,7 +118,7 @@ mod tests {
#[test] #[test]
fn test_term_query_debug() { fn test_term_query_debug() {
let term_query = TermQuery::new( let term_query = TermQuery::new(
Term::from_field_text(Field(1), "hello"), Term::from_field_text(Field::from_field_id(1), "hello"),
IndexRecordOption::WithFreqs, IndexRecordOption::WithFreqs,
); );
assert_eq!( assert_eq!(

15
src/schema/document.rs
View File

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

23
src/schema/field.rs
View File

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

95
src/schema/field_type.rs
View File

@@ -1,11 +1,11 @@
use base64::decode; use base64::decode;
use crate::schema::{IntOptions, TextOptions};
use crate::schema::Facet; use crate::schema::Facet;
use crate::schema::IndexRecordOption; use crate::schema::IndexRecordOption;
use crate::schema::TextFieldIndexing; use crate::schema::TextFieldIndexing;
use crate::schema::Value; use crate::schema::Value;
use crate::schema::{IntOptions, TextOptions};
use crate::tokenizer::PreTokenizedString;
use serde_json::Value as JsonValue; use serde_json::Value as JsonValue;
/// Possible error that may occur while parsing a field value /// Possible error that may occur while parsing a field value
@@ -169,6 +169,28 @@ impl FieldType {
Err(ValueParsingError::TypeError(msg)) 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!( let msg = format!(
"Json value not supported error {:?}. Expected {:?}", "Json value not supported error {:?}. Expected {:?}",
@@ -184,7 +206,9 @@ impl FieldType {
mod tests { mod tests {
use super::FieldType; use super::FieldType;
use crate::schema::field_type::ValueParsingError; use crate::schema::field_type::ValueParsingError;
use crate::schema::TextOptions;
use crate::schema::Value; use crate::schema::Value;
use crate::tokenizer::{PreTokenizedString, Token};
#[test] #[test]
fn test_bytes_value_from_json() { fn test_bytes_value_from_json() {
@@ -205,4 +229,71 @@ mod tests {
_ => panic!("Expected parse failure for invalid base64"), _ => 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);
}
} }

45
src/schema/schema.rs
View File

@@ -167,7 +167,7 @@ impl SchemaBuilder {
/// Adds a field entry to the schema in build. /// Adds a field entry to the schema in build.
fn add_field(&mut self, field_entry: FieldEntry) -> Field { 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(); let field_name = field_entry.name().to_string();
self.fields.push(field_entry); self.fields.push(field_entry);
self.fields_map.insert(field_name, field); self.fields_map.insert(field_name, field);
@@ -223,7 +223,7 @@ pub struct Schema(Arc<InnerSchema>);
impl Schema { impl Schema {
/// Return the `FieldEntry` associated to a `Field`. /// Return the `FieldEntry` associated to a `Field`.
pub fn get_field_entry(&self, field: Field) -> &FieldEntry { 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`. /// Return the field name for a given `Field`.
@@ -232,8 +232,12 @@ impl Schema {
} }
/// Return the list of all the `Field`s. /// Return the list of all the `Field`s.
pub fn fields(&self) -> &[FieldEntry] { pub fn fields(&self) -> impl Iterator<Item = (Field, &FieldEntry)> {
&self.0.fields self.0
.fields
.iter()
.enumerate()
.map(|(field_id, field_entry)| (Field::from_field_id(field_id as u32), field_entry))
} }
/// Creates a new builder. /// Creates a new builder.
@@ -485,13 +489,32 @@ mod tests {
let schema: Schema = serde_json::from_str(expected).unwrap(); let schema: Schema = serde_json::from_str(expected).unwrap();
let mut fields = schema.fields().iter(); let mut fields = schema.fields();
{
assert_eq!("title", fields.next().unwrap().name()); let (field, field_entry) = fields.next().unwrap();
assert_eq!("author", fields.next().unwrap().name()); assert_eq!("title", field_entry.name());
assert_eq!("count", fields.next().unwrap().name()); assert_eq!(0, field.field_id());
assert_eq!("popularity", fields.next().unwrap().name()); }
assert_eq!("score", fields.next().unwrap().name()); {
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()); assert!(fields.next().is_none());
} }

6
src/schema/term.rs
View File

@@ -105,7 +105,7 @@ impl Term {
if self.0.len() < 4 { if self.0.len() < 4 {
self.0.resize(4, 0u8); 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. /// Sets a u64 value in the term.
@@ -157,7 +157,7 @@ where
/// Returns the field. /// Returns the field.
pub fn field(&self) -> 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. /// Returns the `u64` value stored in a term.
@@ -227,7 +227,7 @@ impl fmt::Debug for Term {
write!( write!(
f, f,
"Term(field={},bytes={:?})", "Term(field={},bytes={:?})",
self.field().0, self.field().field_id(),
self.value_bytes() self.value_bytes()
) )
} }

58
src/schema/value.rs
View File

@@ -1,4 +1,5 @@
use crate::schema::Facet; use crate::schema::Facet;
use crate::tokenizer::PreTokenizedString;
use crate::DateTime; use crate::DateTime;
use serde::de::Visitor; use serde::de::Visitor;
use serde::{Deserialize, Deserializer, Serialize, Serializer}; use serde::{Deserialize, Deserializer, Serialize, Serializer};
@@ -10,6 +11,8 @@ use std::{cmp::Ordering, fmt};
pub enum Value { pub enum Value {
/// The str type is used for any text information. /// The str type is used for any text information.
Str(String), Str(String),
/// Pre-tokenized str type,
PreTokStr(PreTokenizedString),
/// Unsigned 64-bits Integer `u64` /// Unsigned 64-bits Integer `u64`
U64(u64), U64(u64),
/// Signed 64-bits Integer `i64` /// Signed 64-bits Integer `i64`
@@ -29,6 +32,7 @@ impl Ord for Value {
fn cmp(&self, other: &Self) -> Ordering { fn cmp(&self, other: &Self) -> Ordering {
match (self, other) { match (self, other) {
(Value::Str(l), Value::Str(r)) => l.cmp(r), (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::U64(l), Value::U64(r)) => l.cmp(r),
(Value::I64(l), Value::I64(r)) => l.cmp(r), (Value::I64(l), Value::I64(r)) => l.cmp(r),
(Value::Date(l), Value::Date(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::Less,
(_, Value::Str(_)) => Ordering::Greater, (_, Value::Str(_)) => Ordering::Greater,
(Value::PreTokStr(_), _) => Ordering::Less,
(_, Value::PreTokStr(_)) => Ordering::Greater,
(Value::U64(_), _) => Ordering::Less, (Value::U64(_), _) => Ordering::Less,
(_, Value::U64(_)) => Ordering::Greater, (_, Value::U64(_)) => Ordering::Greater,
(Value::I64(_), _) => Ordering::Less, (Value::I64(_), _) => Ordering::Less,
@@ -65,6 +71,7 @@ impl Serialize for Value {
{ {
match *self { match *self {
Value::Str(ref v) => serializer.serialize_str(v), Value::Str(ref v) => serializer.serialize_str(v),
Value::PreTokStr(ref v) => v.serialize(serializer),
Value::U64(u) => serializer.serialize_u64(u), Value::U64(u) => serializer.serialize_u64(u),
Value::I64(u) => serializer.serialize_i64(u), Value::I64(u) => serializer.serialize_i64(u),
Value::F64(u) => serializer.serialize_f64(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. /// Returns the u64-value, provided the value is of the `U64` type.
/// ///
/// # Panics /// # Panics
@@ -221,6 +237,7 @@ mod binary_serialize {
use super::Value; use super::Value;
use crate::common::{f64_to_u64, u64_to_f64, BinarySerializable}; use crate::common::{f64_to_u64, u64_to_f64, BinarySerializable};
use crate::schema::Facet; use crate::schema::Facet;
use crate::tokenizer::PreTokenizedString;
use chrono::{TimeZone, Utc}; use chrono::{TimeZone, Utc};
use std::io::{self, Read, Write}; use std::io::{self, Read, Write};
@@ -231,6 +248,11 @@ mod binary_serialize {
const BYTES_CODE: u8 = 4; const BYTES_CODE: u8 = 4;
const DATE_CODE: u8 = 5; const DATE_CODE: u8 = 5;
const F64_CODE: u8 = 6; const F64_CODE: u8 = 6;
const EXT_CODE: u8 = 7;
// extended types
const TOK_STR_CODE: u8 = 0;
impl BinarySerializable for Value { impl BinarySerializable for Value {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> { fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
@@ -239,6 +261,18 @@ mod binary_serialize {
TEXT_CODE.serialize(writer)?; TEXT_CODE.serialize(writer)?;
text.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) => { Value::U64(ref val) => {
U64_CODE.serialize(writer)?; U64_CODE.serialize(writer)?;
val.serialize(writer) val.serialize(writer)
@@ -290,6 +324,30 @@ mod binary_serialize {
} }
HIERARCHICAL_FACET_CODE => Ok(Value::Facet(Facet::deserialize(reader)?)), HIERARCHICAL_FACET_CODE => Ok(Value::Facet(Facet::deserialize(reader)?)),
BYTES_CODE => Ok(Value::Bytes(Vec::<u8>::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( _ => Err(io::Error::new(
io::ErrorKind::InvalidData, io::ErrorKind::InvalidData,
format!("No field type is associated with code {:?}", type_code), format!("No field type is associated with code {:?}", type_code),

3
src/tokenizer/mod.rs
View File

@@ -136,6 +136,7 @@ mod simple_tokenizer;
mod stemmer; mod stemmer;
mod stop_word_filter; mod stop_word_filter;
mod token_stream_chain; mod token_stream_chain;
mod tokenized_string;
mod tokenizer; mod tokenizer;
mod tokenizer_manager; mod tokenizer_manager;
@@ -152,7 +153,9 @@ pub use self::stop_word_filter::StopWordFilter;
pub(crate) use self::token_stream_chain::TokenStreamChain; pub(crate) use self::token_stream_chain::TokenStreamChain;
pub use self::tokenizer::BoxedTokenizer; pub use self::tokenizer::BoxedTokenizer;
pub use self::tokenized_string::{PreTokenizedStream, PreTokenizedString};
pub use self::tokenizer::{Token, TokenFilter, TokenStream, Tokenizer}; pub use self::tokenizer::{Token, TokenFilter, TokenStream, Tokenizer};
pub use self::tokenizer_manager::TokenizerManager; pub use self::tokenizer_manager::TokenizerManager;
/// Maximum authorized len (in bytes) for a token. /// Maximum authorized len (in bytes) for a token.

189
src/tokenizer/tokenized_string.rs Normal file
View File

@@ -0,0 +1,189 @@
use crate::tokenizer::{Token, TokenStream, TokenStreamChain};
use std::cmp::Ordering;
/// Struct representing pre-tokenized text
#[derive(Debug, Clone, Serialize, Deserialize, Eq, PartialEq)]
pub struct PreTokenizedString {
/// Original text
pub text: String,
/// Tokens derived from the text
pub tokens: Vec<Token>,
}
impl Ord for PreTokenizedString {
fn cmp(&self, other: &Self) -> Ordering {
self.text.cmp(&other.text)
}
}
impl PartialOrd for PreTokenizedString {
fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other))
}
}
/// TokenStream implementation which wraps PreTokenizedString
pub struct PreTokenizedStream {
tokenized_string: PreTokenizedString,
current_token: i64,
}
impl From<PreTokenizedString> for PreTokenizedStream {
fn from(s: PreTokenizedString) -> PreTokenizedStream {
PreTokenizedStream {
tokenized_string: s,
current_token: -1,
}
}
}
impl PreTokenizedStream {
/// Creates a TokenStream from PreTokenizedString array
pub fn chain_tokenized_strings<'a>(
tok_strings: &'a [&'a PreTokenizedString],
) -> Box<dyn TokenStream + 'a> {
if tok_strings.len() == 1 {
Box::new(PreTokenizedStream::from((*tok_strings[0]).clone()))
} else {
let mut offsets = vec![];
let mut total_offset = 0;
for &tok_string in tok_strings {
offsets.push(total_offset);
if let Some(last_token) = tok_string.tokens.last() {
total_offset += last_token.offset_to;
}
}
let token_streams: Vec<_> = tok_strings
.iter()
.map(|tok_string| PreTokenizedStream::from((*tok_string).clone()))
.collect();
Box::new(TokenStreamChain::new(offsets, token_streams))
}
}
}
impl TokenStream for PreTokenizedStream {
fn advance(&mut self) -> bool {
self.current_token += 1;
self.current_token < self.tokenized_string.tokens.len() as i64
}
fn token(&self) -> &Token {
assert!(
self.current_token >= 0,
"TokenStream not initialized. You should call advance() at least once."
);
&self.tokenized_string.tokens[self.current_token as usize]
}
fn token_mut(&mut self) -> &mut Token {
assert!(
self.current_token >= 0,
"TokenStream not initialized. You should call advance() at least once."
);
&mut self.tokenized_string.tokens[self.current_token as usize]
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::tokenizer::Token;
#[test]
fn test_tokenized_stream() {
let tok_text = PreTokenizedString {
text: String::from("A a"),
tokens: vec![
Token {
offset_from: 0,
offset_to: 1,
position: 0,
text: String::from("A"),
position_length: 1,
},
Token {
offset_from: 2,
offset_to: 3,
position: 1,
text: String::from("a"),
position_length: 1,
},
],
};
let mut token_stream = PreTokenizedStream::from(tok_text.clone());
for expected_token in tok_text.tokens {
assert!(token_stream.advance());
assert_eq!(token_stream.token(), &expected_token);
}
assert!(!token_stream.advance());
}
#[test]
fn test_chain_tokenized_strings() {
let tok_text = PreTokenizedString {
text: String::from("A a"),
tokens: vec![
Token {
offset_from: 0,
offset_to: 1,
position: 0,
text: String::from("A"),
position_length: 1,
},
Token {
offset_from: 2,
offset_to: 3,
position: 1,
text: String::from("a"),
position_length: 1,
},
],
};
let chain_parts = vec![&tok_text, &tok_text];
let mut token_stream = PreTokenizedStream::chain_tokenized_strings(&chain_parts[..]);
let expected_tokens = vec![
Token {
offset_from: 0,
offset_to: 1,
position: 0,
text: String::from("A"),
position_length: 1,
},
Token {
offset_from: 2,
offset_to: 3,
position: 1,
text: String::from("a"),
position_length: 1,
},
Token {
offset_from: 3,
offset_to: 4,
position: 3,
text: String::from("A"),
position_length: 1,
},
Token {
offset_from: 5,
offset_to: 6,
position: 4,
text: String::from("a"),
position_length: 1,
},
];
for expected_token in expected_tokens {
assert!(token_stream.advance());
assert_eq!(token_stream.token(), &expected_token);
}
assert!(!token_stream.advance());
}
}

2
src/tokenizer/tokenizer.rs
View File

@@ -4,7 +4,7 @@ use crate::tokenizer::TokenStreamChain;
use std::borrow::{Borrow, BorrowMut}; use std::borrow::{Borrow, BorrowMut};
/// Token /// Token
#[derive(Debug, Clone)] #[derive(Debug, Clone, Serialize, Deserialize, Eq, PartialEq)]
pub struct Token { pub struct Token {
/// Offset (byte index) of the first character of the token. /// Offset (byte index) of the first character of the token.
/// Offsets shall not be modified by token filters. /// Offsets shall not be modified by token filters.

1
tests/failpoints/mod.rs
View File

@@ -1,5 +1,4 @@
use fail; use fail;
use std::io::Write;
use std::path::Path; use std::path::Path;
use tantivy::directory::{Directory, ManagedDirectory, RAMDirectory, TerminatingWrite}; use tantivy::directory::{Directory, ManagedDirectory, RAMDirectory, TerminatingWrite};
use tantivy::doc; use tantivy::doc;