rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2025-12-28 21:12:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

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

3 Commits
removedali ... wasm

Author SHA1 Message Date
Paul Masurel
232ca5c06c Added convert to static [u8] 2018-04-10 21:18:32 +09:00
Paul Masurel
e78af20375 remove comment 2018-04-09 21:51:17 +09:00
Paul Masurel
30637f7a7f Ok on wasm 2018-03-31 17:42:26 +09:00
275 changed files with 12985 additions and 31406 deletions
Expand all files Collapse all files

12
.github/FUNDING.yml vendored
View File

@@ -1,12 +0,0 @@
# 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']

19
.github/ISSUE_TEMPLATE/bug_report.md vendored
View File

@@ -1,19 +0,0 @@
---
name: Bug report
about: Create a report to help us improve
---
**Describe the bug**
- What did you do?
- What happened?
- What was expected?
**Which version of tantivy are you using?**
If "master", ideally give the specific sha1 revision.
**To Reproduce**
If your bug is deterministic, can you give a minimal reproducing code?
Some bugs are not deterministic. Can you describe with precision in which context it happened?
If this is possible, can you share your code?

14
.github/ISSUE_TEMPLATE/feature_request.md vendored
View File

@@ -1,14 +0,0 @@
---
name: Feature request
about: Suggest an idea for this project
---
**Is your feature request related to a problem? Please describe.**
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
**Describe the solution you'd like**
A clear and concise description of what you want to happen.
**[Optional] describe alternatives you've considered**
A clear and concise description of any alternative solutions or features you've considered.

7
.github/ISSUE_TEMPLATE/question.md vendored
View File

@@ -1,7 +0,0 @@
---
name: Question
about: Ask any question about tantivy's usage...
---
Try to be specific about your use case...

1
.gitignore vendored
View File

@@ -1,4 +1,3 @@
tantivy.iml
*.swp
target
target/debug

81
.travis.yml
View File

@@ -1,17 +1,14 @@
# Based on the "trust" template v0.1.2
# https://github.com/japaric/trust/tree/v0.1.2
dist: trusty
language: rust
services: docker
sudo: required
cache: cargo
rust:
- nightly
env:
global:
- CRATE_NAME=tantivy
- CC=gcc-4.8
- CXX=g++-4.8
- TRAVIS_CARGO_NIGHTLY_FEATURE=""
# - secure: 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
- secure: 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
addons:
apt:
sources:
@@ -25,68 +22,16 @@ addons:
- libdw-dev
- binutils-dev
- cmake
matrix:
include:
# Android
- env: TARGET=aarch64-linux-android DISABLE_TESTS=1
#- env: TARGET=arm-linux-androideabi DISABLE_TESTS=1
#- env: TARGET=armv7-linux-androideabi DISABLE_TESTS=1
#- env: TARGET=i686-linux-android DISABLE_TESTS=1
#- env: TARGET=x86_64-linux-android DISABLE_TESTS=1
# Linux
#- env: TARGET=aarch64-unknown-linux-gnu
#- env: TARGET=i686-unknown-linux-gnu
- env: TARGET=x86_64-unknown-linux-gnu CODECOV=1 #UPLOAD_DOCS=1
# - env: TARGET=x86_64-unknown-linux-musl CODECOV=1
# OSX
#- env: TARGET=x86_64-apple-darwin
# os: osx
before_install:
- set -e
- rustup self update
- rustup component add rustfmt
install:
- sh ci/install.sh
- source ~/.cargo/env || true
- env | grep "TRAVIS"
before_script:
- export PATH=$HOME/.cargo/bin:$PATH
- cargo install cargo-update || echo "cargo-update already installed"
- cargo install cargo-travis || echo "cargo-travis already installed"
script:
- bash ci/script.sh
- cargo fmt --all -- --check
before_deploy:
- sh ci/before_deploy.sh
- cargo build
- cargo test
- cargo test -- --ignored
- cargo run --example simple_search
- cargo doc
after_success:
# Needs GH_TOKEN env var to be set in travis settings
- if [[ -v GH_TOKEN ]]; then echo "GH TOKEN IS SET"; else echo "GH TOKEN NOT SET"; fi
- if [[ -v UPLOAD_DOCS ]]; then cargo doc; cargo doc-upload; else echo "doc upload disabled."; fi
#cache: cargo
#before_cache:
# # Travis can't cache files that are not readable by "others"
# - chmod -R a+r $HOME/.cargo
# - find ./target/debug -type f -maxdepth 1 -delete
# - rm -f ./target/.rustc_info.json
# - rm -fr ./target/debug/{deps,.fingerprint}/tantivy*
# - rm -r target/debug/examples/
# - ls -1 examples/ | sed -e 's/\.rs$//' | xargs -I "{}" find target/* -name "*{}*" -type f -delete
#branches:
# only:
# # release tags
# - /^v\d+\.\d+\.\d+.*$/
# - master
notifications:
email:
on_success: never
- cargo coveralls --exclude-pattern src/functional_test.rs
- cargo doc-upload

11
AUTHORS
View File

@@ -1,11 +0,0 @@
# This is the list of authors of tantivy for copyright purposes.
Paul Masurel
Laurentiu Nicola
Dru Sellers
Ashley Mannix
Michael J. Curry
Jason Wolfe
# As an employee of Google I am required to add Google LLC
# in the list of authors, but this project is not affiliated to Google
# in any other way.
Google LLC

265
CHANGELOG.md
View File

@@ -1,258 +1,9 @@
Tantivy 0.13.0
======================
- Bugfix in `FuzzyTermQuery` not matching terms by prefix when it should (@Peachball)
- Relaxed constraints on the custom/tweak score functions. At the segment level, they can be mut, and they are not required to be Sync + Send.
- `MMapDirectory::open` does not return a `Result` anymore.
- Change in the DocSet and Scorer API. (@fulmicoton).
A freshly created DocSet point directly to their first doc. A sentinel value called TERMINATED marks the end of a DocSet.
`.advance()` returns the new DocId. `Scorer::skip(target)` has been replaced by `Scorer::seek(target)` and returns the resulting DocId.
As a result, iterating through DocSet now looks as follows
```rust
let mut doc = docset.doc();
while doc != TERMINATED {
// ...
doc = docset.advance();
}
```
The change made it possible to greatly simplify a lot of the docset's code.
- Misc internal optimization and introduction of the `Scorer::for_each_pruning` function. (@fulmicoton)
- Added an offset option to the Top(.*)Collectors. (@robyoung)
Tantivy 0.12.0
======================
- Removing static dispatch in tokenizers for simplicity. (#762)
- Added backward iteration for `TermDictionary` stream. (@halvorboe)
- Fixed a performance issue when searching for the posting lists of a missing term (@audunhalland)
- Added a configurable maximum number of docs (10M by default) for a segment to be considered for merge (@hntd187, landed by @halvorboe #713)
- Important Bugfix #777, causing tantivy to retain memory mapping. (diagnosed by @poljar)
- Added support for field boosting. (#547, @fulmicoton)
## How to update?
Crates relying on custom tokenizer, or registering tokenizer in the manager will require some
minor changes. Check https://github.com/tantivy-search/tantivy/blob/master/examples/custom_tokenizer.rs
to check for some code sample.
Tantivy 0.11.3
=======================
- Fixed DateTime as a fast field (#735)
Tantivy 0.11.2
=======================
- The future returned by `IndexWriter::merge` does not borrow `self` mutably anymore (#732)
- Exposing a constructor for `WatchHandle` (#731)
Tantivy 0.11.1
=====================
- Bug fix #729
Tantivy 0.11.0
=====================
- Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima)
- Various bugfixes in the query parser.
- Better handling of hyphens in query parser. (#609)
- Better handling of whitespaces.
- Closes #498 - add support for Elastic-style unbounded range queries for alphanumeric types eg. "title:>hello", "weight:>=70.5", "height:<200" (@petr-tik)
- API change around `Box<BoxableTokenizer>`. See detail in #629
- Avoid rebuilding Regex automaton whenever a regex query is reused. #639 (@brainlock)
- Add footer with some metadata to index files. #605 (@fdb-hiroshima)
- Add a method to check the compatibility of the footer in the index with the running version of tantivy (@petr-tik)
- TopDocs collector: ensure stable sorting on equal score. #671 (@brainlock)
- Added handling of pre-tokenized text fields (#642), which will enable users to
load tokens created outside tantivy. See usage in examples/pre_tokenized_text. (@kkoziara)
- Fix crash when committing multiple times with deleted documents. #681 (@brainlock)
## How to update?
- The index format is changed. You are required to reindex your data to use tantivy 0.11.
- `Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
- Regex are now compiled when the `RegexQuery` instance is built. As a result, it can now return
an error and handling the `Result` is required.
- `tantivy::version()` now returns a `Version` object. This object implements `ToString()`
Tantivy 0.10.2
=====================
- Closes #656. Solving memory leak.
Tantivy 0.10.1
=====================
- Closes #544. A few users experienced problems with the directory watching system.
Avoid watching the mmap directory until someone effectively creates a reader that uses
this functionality.
Tantivy 0.10.0
=====================
*Tantivy 0.10.0 index format is compatible with the index format in 0.9.0.*
- Added an API to easily tweak or entirely replace the
default score. See `TopDocs::tweak_score`and `TopScore::custom_score` (@pmasurel)
- Added an ASCII folding filter (@drusellers)
- Bugfix in `query.count` in presence of deletes (@pmasurel)
- Added `.explain(...)` in `Query` and `Weight` to (@pmasurel)
- Added an efficient way to `delete_all_documents` in `IndexWriter` (@petr-tik).
All segments are simply removed.
Minor
---------
- Switched to Rust 2018 (@uvd)
- Small simplification of the code.
Calling .freq() or .doc() when .advance() has never been called
on segment postings should panic from now on.
- Tokens exceeding `u16::max_value() - 4` chars are discarded silently instead of panicking.
- Fast fields are now preloaded when the `SegmentReader` is created.
- `IndexMeta` is now public. (@hntd187)
- `IndexWriter` `add_document`, `delete_term`. `IndexWriter` is `Sync`, making it possible to use it with a `
Arc<RwLock<IndexWriter>>`. `add_document` and `delete_term` can
only require a read lock. (@pmasurel)
- Introducing `Opstamp` as an expressive type alias for `u64`. (@petr-tik)
- Stamper now relies on `AtomicU64` on all platforms (@petr-tik)
- Bugfix - Files get deleted slightly earlier
- Compilation resources improved (@fdb-hiroshima)
## How to update?
Your program should be usable as is.
### Fast fields
Fast fields used to be accessed directly from the `SegmentReader`.
The API changed, you are now required to acquire your fast field reader via the
`segment_reader.fast_fields()`, and use one of the typed method:
- `.u64()`, `.i64()` if your field is single-valued ;
- `.u64s()`, `.i64s()` if your field is multi-valued ;
- `.bytes()` if your field is bytes fast field.
Tantivy 0.9.0
=====================
*0.9.0 index format is not compatible with the
previous index format.*
- MAJOR BUGFIX :
Some `Mmap` objects were being leaked, and would never get released. (@fulmicoton)
- Removed most unsafe (@fulmicoton)
- Indexer memory footprint improved. (VInt comp, inlining the first block. (@fulmicoton)
- Stemming in other language possible (@pentlander)
- Segments with no docs are deleted earlier (@barrotsteindev)
- Added grouped add and delete operations.
They are guaranteed to happen together (i.e. they cannot be split by a commit).
In addition, adds are guaranteed to happen on the same segment. (@elbow-jason)
- Removed `INT_STORED` and `INT_INDEXED`. It is now possible to use `STORED` and `INDEXED`
for int fields. (@fulmicoton)
- Added DateTime field (@barrotsteindev)
- Added IndexReader. By default, index is reloaded automatically upon new commits (@fulmicoton)
- SIMD linear search within blocks (@fulmicoton)
## How to update ?
tantivy 0.9 brought some API breaking change.
To update from tantivy 0.8, you will need to go through the following steps.
- `schema::INT_INDEXED` and `schema::INT_STORED` should be replaced by `schema::INDEXED` and `schema::INT_STORED`.
- The index now does not hold the pool of searcher anymore. You are required to create an intermediary object called
`IndexReader` for this.
```rust
// create the reader. You typically need to create 1 reader for the entire
// lifetime of you program.
let reader = index.reader()?;
// Acquire a searcher (previously `index.searcher()`) is now written:
let searcher = reader.searcher();
// With the default setting of the reader, you are not required to
// call `index.load_searchers()` anymore.
//
// The IndexReader will pick up that change automatically, regardless
// of whether the update was done in a different process or not.
// If this behavior is not wanted, you can create your reader with
// the `ReloadPolicy::Manual`, and manually decide when to reload the index
// by calling `reader.reload()?`.
```
Tantivy 0.8.2
=====================
Fixing build for x86_64 platforms. (#496)
No need to update from 0.8.1 if tantivy
is building on your platform.
Tantivy 0.8.1
=====================
Hotfix of #476.
Merge was reflecting deletes before commit was passed.
Thanks @barrotsteindev for reporting the bug.
Tantivy 0.8.0
=====================
*No change in the index format*
- API Breaking change in the collector API. (@jwolfe, @fulmicoton)
- Multithreaded search (@jwolfe, @fulmicoton)
Tantivy 0.7.1
=====================
*No change in the index format*
- Bugfix: NGramTokenizer panics on non ascii chars
- Added a space usage API
Tantivy 0.7
=====================
- Skip data for doc ids and positions (@fulmicoton),
greatly improving performance
- Tantivy error now rely on the failure crate (@drusellers)
- Added support for `AND`, `OR`, `NOT` syntax in addition to the `+`,`-` syntax
- Added a snippet generator with highlight (@vigneshsarma, @fulmicoton)
- Added a `TopFieldCollector` (@pentlander)
Tantivy 0.6.1
=========================
- Bugfix #324. GC removing was removing file that were still in useful
- Added support for parsing AllQuery and RangeQuery via QueryParser
- AllQuery: `*`
- RangeQuery:
- Inclusive `field:[startIncl to endIncl]`
- Exclusive `field:{startExcl to endExcl}`
- Mixed `field:[startIncl to endExcl}` and vice versa
- Unbounded `field:[start to *]`, `field:[* to end]`
Tantivy 0.6
Tantivy 0.5.2
==========================
Special thanks to @drusellers and @jason-wolfe for their contributions
to this release!
- Removed C code. Tantivy is now pure Rust. (@pmasurel)
- BM25 (@pmasurel)
- Approximate field norms encoded over 1 byte. (@pmasurel)
- Compiles on stable rust (@pmasurel)
- Add &[u8] fastfield for associating arbitrary bytes to each document (@jason-wolfe) (#270)
- Completely uncompressed
- Internally: One u64 fast field for indexes, one fast field for the bytes themselves.
- Add NGram token support (@drusellers)
- Add Stopword Filter support (@drusellers)
- Add a FuzzyTermQuery (@drusellers)
- Add a RegexQuery (@drusellers)
- Various performance improvements (@pmasurel)_
Tantivy 0.5.2
===========================
- bugfix #274
- bugfix #280
- bugfix #289
- Removed C code. Tantivy is now pure Rust.
- BM25
- Approximate field norms encoded over 1 byte.
Tantivy 0.5.1
==========================
@@ -330,7 +81,7 @@ Tantivy 0.3
Special thanks to @Kodraus @lnicola @Ameobea @manuel-woelker @celaus
for their contribution to this release.
Thanks also to everyone in tantivy gitter chat
Thanks also to everyone in tantivy gitter chat
for their advise and company :)
https://gitter.im/tantivy-search/tantivy
@@ -338,9 +89,9 @@ https://gitter.im/tantivy-search/tantivy
Warning:
Tantivy 0.3 is NOT backward compatible with tantivy 0.2
Tantivy 0.3 is NOT backward compatible with tantivy 0.2
code and index format.
You should not expect backward compatibility before
You should not expect backward compatibility before
tantivy 1.0.
@@ -366,7 +117,7 @@ Thanks to @KodrAus ! (#108)
the natural ordering.
- Building binary targets for tantivy-cli (Thanks to @KodrAus)
- Misc invisible bug fixes, and code cleanup.
- Use
- Use

112
Cargo.toml
View File

@@ -1,99 +1,79 @@
[package]
name = "tantivy"
version = "0.12.0"
version = "0.5.1"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://docs.rs/tantivy/"
description = """Tantivy is a search engine library."""
documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
homepage = "https://github.com/tantivy-search/tantivy"
repository = "https://github.com/tantivy-search/tantivy"
readme = "README.md"
keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
base64 = "0.12.0"
byteorder = "1.0"
crc32fast = "1.2.0"
once_cell = "1.0"
regex ={version = "1.3.0", default-features = false, features = ["std"]}
tantivy-fst = "0.3"
memmap = {version = "0.7", optional=true}
lz4 = {version="1.20", optional=true}
snap = "1"
atomicwrites = {version="0.2.2", optional=true}
tempfile = "3.0"
log = "0.4"
serde = {version="1.0", features=["derive"]}
lazy_static = "0.2.1"
tinysegmenter = "0.1.0"
regex = "0.2"
fst = {version="0.2", default-features=false}
atomicwrites = {version="0.1", optional=true}
log = "0.3.6"
combine = "2.2"
tempdir = "0.3"
serde = "1.0"
serde_derive = "1.0"
serde_json = "1.0"
num_cpus = "1.2"
fs2={version="0.4", optional=true}
levenshtein_automata = "0.2"
notify = {version="4", optional=true}
uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.7"
futures = {version = "0.3", features=["thread-pool"] }
owning_ref = "0.4"
itertools = "0.5.9"
bit-set = "0.4.0"
uuid = { version = "0.6", features = ["v4", "serde"] }
chan = "0.1"
crossbeam = "0.3"
futures = "0.1"
futures-cpupool = "0.1"
error-chain = "0.8"
owning_ref = "0.3"
stable_deref_trait = "1.0.0"
rust-stemmers = "1.2"
downcast-rs = { version="1.0" }
tantivy-query-grammar = { version="0.13", path="./query-grammar" }
bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
census = "0.4"
fnv = "1.0.6"
owned-read = "0.4"
failure = "0.1"
htmlescape = "0.3.1"
fail = "0.4"
murmurhash32 = "0.2"
chrono = "0.4"
smallvec = "1.0"
rayon = "1"
rust-stemmers = "0.1.0"
downcast = { version="0.9", features = ["nightly"]}
matches = "0.1"
snap = "0.2"
bitpacking = {path = "../bitpacking"}
[target.'cfg(windows)'.dependencies]
winapi = "0.3"
winapi = "0.2"
[dev-dependencies]
rand = "0.7"
maplit = "1"
matches = "0.1.8"
[dev-dependencies.fail]
version = "0.4"
features = ["failpoints"]
rand = "0.3"
tempfile = "2.1"
env_logger = "0.4"
[profile.release]
opt-level = 3
debug = false
lto = true
debug-assertions = false
[profile.test]
debug-assertions = true
overflow-checks = true
[features]
default = ["mmap"]
mmap = ["atomicwrites", "fs2", "memmap", "notify"]
lz4-compression = ["lz4"]
failpoints = ["fail/failpoints"]
unstable = [] # useful for benches.
wasm-bindgen = ["uuid/wasm-bindgen"]
streamdict = []
mmap = ["fst/mmap", "atomicwrites"]
[workspace]
members = ["query-grammar"]
[badges]
travis-ci = { repository = "tantivy-search/tantivy" }
# Following the "fail" crate best practises, we isolate
# tests that define specific behavior in fail check points
# in a different binary.
#
# We do that because, fail rely on a global definition of
# failpoints behavior and hence, it is incompatible with
# multithreading.
[[test]]
name = "failpoints"
path = "tests/failpoints/mod.rs"
required-features = ["fail/failpoints"]
[[example]]
name = "simple_search"
required-features = ["mmap"]
[[bin]]
name = "convert_to_static"
path = "./bin/convert_to_static.rs"
[[bin]]
name = "test_static_dir"
path = "./bin/test_static_dir.rs"

2
LICENSE
View File

@@ -1,4 +1,4 @@
Copyright (c) 2018 by the project authors, as listed in the AUTHORS file.
Copyright (c) 2016 Paul Masurel
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:

3
Makefile
View File

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

149
README.md
View File

@@ -1,140 +1,85 @@
[![Build Status](https://travis-ci.org/tantivy-search/tantivy.svg?branch=master)](https://travis-ci.org/tantivy-search/tantivy)
[![codecov](https://codecov.io/gh/tantivy-search/tantivy/branch/master/graph/badge.svg)](https://codecov.io/gh/tantivy-search/tantivy)
[![Join the chat at https://gitter.im/tantivy-search/tantivy](https://badges.gitter.im/tantivy-search/tantivy.svg)](https://gitter.im/tantivy-search/tantivy?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj/branch/master?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy/branch/master)
[![Crates.io](https://img.shields.io/crates/v/tantivy.svg)](https://crates.io/crates/tantivy)
[![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton)
![Tantivy](https://tantivy-search.github.io/logo/tantivy-logo.png)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/0)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/0)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/1)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/1)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/2)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/2)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/3)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/3)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/4)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/4)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/5)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/5)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/6)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/6)
[![](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/images/7)](https://sourcerer.io/fame/fulmicoton/tantivy-search/tantivy/links/7)
[![Build Status](https://travis-ci.org/tantivy-search/tantivy.svg?branch=master)](https://travis-ci.org/tantivy-search/tantivy)
[![Coverage Status](https://coveralls.io/repos/github/tantivy-search/tantivy/badge.svg?branch=master&refresh1)](https://coveralls.io/github/tantivy-search/tantivy?branch=master)
[![Join the chat at https://gitter.im/tantivy-search/tantivy](https://badges.gitter.im/tantivy-search/tantivy.svg)](https://gitter.im/tantivy-search/tantivy?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Build status](https://ci.appveyor.com/api/projects/status/r7nb13kj23u8m9pj?svg=true)](https://ci.appveyor.com/project/fulmicoton/tantivy)
[![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) or [Apache Solr](https://lucene.apache.org/solr/) in the sense it is not
an off-the-shelf search engine server, but rather a crate that can be used
to build such a search engine.
Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark
The following [benchmark](https://tantivy-search.github.io/bench/) break downs
performance for different type of queries / collection.
In general, Tantivy tends to be
- slower than Lucene on union with a Top-K due to Block-WAND optimization.
- faster than Lucene on intersection and phrase queries.
Your mileage WILL vary depending on the nature of queries and their load.
It is strongly inspired by Lucene's design.
# Features
- Full-text search
- Configurable tokenizer (stemming available for 17 Latin languages with third party support for Chinese ([tantivy-jieba](https://crates.io/crates/tantivy-jieba) and [cang-jie](https://crates.io/crates/cang-jie)), Japanese ([lindera](https://github.com/lindera-morphology/lindera-tantivy) and [tantivy-tokenizer-tiny-segmente](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter)) and Korean ([lindera](https://github.com/lindera-morphology/lindera-tantivy) + [lindera-ko-dic-builder](https://github.com/lindera-morphology/lindera-ko-dic-builder))
- Fast (check out the :racehorse: :sparkles: [benchmark](https://tantivy-search.github.io/bench/) :sparkles: :racehorse:)
- Tiny startup time (<10ms), perfect for command line tools
- BM25 scoring (the same as Lucene)
- Natural query language (e.g. `(michael AND jackson) OR "king of pop"`)
- Phrase queries search (e.g. `"michael jackson"`)
- tf-idf scoring
- Basic query language
- Phrase queries
- Incremental indexing
- Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop)
- Mmap directory
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set
- Single valued and multivalued u64, i64, and f64 fast fields (equivalent of doc values in Lucene)
- `&[u8]` fast fields
- Text, i64, u64, f64, dates, and hierarchical facet fields
- optional SIMD integer compression
- Single valued and multivalued u64 and i64 fast fields (equivalent of doc values in Lucene)
- LZ4 compressed document store
- Range queries
- Faceted search
- Configurable indexing (optional term frequency and position indexing)
- Faceting
- configurable indexing (optional term frequency and position indexing
- Cheesy logo with a horse
## Non-features
- Distributed search is out of the scope of Tantivy. That being said, Tantivy is a
library upon which one could build a distributed search. Serializable/mergeable collector state for instance,
are within the scope of Tantivy.
Tantivy supports Linux, MacOS and Windows.
# Getting started
Tantivy works on stable Rust (>= 1.27) and supports Linux, MacOS, and Windows.
- [tantivy's usage example](http://fulmicoton.com/tantivy-examples/simple_search.html)
- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli).
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/)
- [For the last master branch](https://tantivy-search.github.io/tantivy/tantivy/index.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` is an actual command line interface that makes it easy for you to create a search engine,
index documents, and search via the CLI or a small server with a REST API.
It walks you through getting a wikipedia search engine up and running in a few minutes.
- [Reference doc for the last released version](https://docs.rs/tantivy/)
# Compiling
# How can I support this project?
## Development
There are many ways to support this project.
Tantivy requires Rust Nightly because it uses requires the features [`box_syntax`](https://doc.rust-lang.org/stable/unstable-book/language-features/box-syntax.html), [`optin_builtin_traits`](https://github.com/rust-lang/rfcs/blob/master/text/0019-opt-in-builtin-traits.md), [`conservative_impl_trait`](https://github.com/rust-lang/rfcs/blob/master/text/1522-conservative-impl-trait.md),
and [simd](https://github.com/rust-lang/rust/issues/27731).
- Use Tantivy and tell us about your experience on [Gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
- Report bugs
- Write a blog post
- Help with documentation by asking questions or submitting PRs
- Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy))
- Talk about Tantivy around you
- 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
To check out and run test, you can simply run :
We use the GitHub Pull Request workflow: reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
## Clone and build locally
Tantivy compiles on stable Rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run:
```bash
git clone https://github.com/tantivy-search/tantivy.git
git clone git@github.com:tantivy-search/tantivy.git
cd tantivy
cargo build
```
cargo +nightly build
## Run tests
Some tests will not run with just `cargo test` because of `fail-rs`.
To run the tests exhaustively, run `./run-tests.sh`.
## Note on release build and performance
## Debug
If your project depends on `tantivy`, for better performance, make sure to enable
`sse3` instructions using a RUSTFLAGS. (This instruction set is likely to
be available on most `x86_64` CPUs you will encounter).
You might find it useful to step through the programme with a debugger.
For instance,
### A failing test
RUSTFLAGS='-C target-feature=+sse3'
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`:
Or, if you are targetting a specific cpu
```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
```
RUSTFLAGS='-C target-cpu=native' build --release
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:
Regardless of the flags you pass, by default `tantivy` will contain `SSE3` instructions.
If you want to disable those, you can run the following command :
```bash
$gdb run --test-threads 1 --test $NAME_OF_TEST
```
cargo build --no-default-features
### An example
Alternatively, if you are trying to compile `tantivy` without simd compression,
you can disable this functionality. In this case, this submodule is not required
and you can compile tantivy by using the `--no-default-features` flag.
By default, `rustc` compiles everything in the `examples/` directory in debug mode. This makes it easy for you to make examples to reproduce bugs:
cargo build --no-default-features
```bash
rust-gdb target/debug/examples/$EXAMPLE_NAME
$ gdb run
```
# Contribute
Send me an email (paul.masurel at gmail.com) if you want to contribute to tantivy.

9
appveyor.yml
View File

@@ -4,8 +4,11 @@
os: Visual Studio 2015
environment:
matrix:
- channel: stable
- channel: nightly
target: x86_64-pc-windows-msvc
- channel: nightly
target: x86_64-pc-windows-gnu
msys_bits: 64
install:
- appveyor DownloadFile https://win.rustup.rs/ -FileName rustup-init.exe
@@ -18,5 +21,5 @@ install:
build: false
test_script:
- REM SET RUST_LOG=tantivy,test & cargo test --all --verbose --no-default-features --features mmap
- REM SET RUST_BACKTRACE=1 & cargo build --examples
- REM SET RUST_LOG=tantivy,test & cargo test --verbose
- REM SET RUST_BACKTRACE=1 & cargo run --example simple_search

20
bin/convert_to_static.rs Normal file
View File

@@ -0,0 +1,20 @@
use std::env;
use std::path::PathBuf;
use std::fs::File;
use std::io::Write;
extern crate tantivy;
use tantivy::directory::write_static_from_directory;
fn main() {
// Prints each argument on a separate line
let mut args = env::args();
args.next().unwrap();
let directory_path= args.next().expect("Expect 2 args.<directory_path> <outputfile>");
let output_path = args.next().expect("Expect 2 args.<directory_path> <outputfile>");
println!("{} => {}", directory_path, output_path);
let buffer = write_static_from_directory(&PathBuf::from(directory_path)).unwrap();
println!("Read all");
let mut output = File::create(output_path).unwrap();
output.write_all(&buffer[..]).unwrap();
output.flush().unwrap();
}

51
bin/test_static_dir.rs Normal file
View File

@@ -0,0 +1,51 @@
use std::env;
use std::path::PathBuf;
use std::fs::File;
use std::io::Write;
extern crate tantivy;
use tantivy::directory::{StaticDirectory, write_static_from_directory};
use tantivy::Index;
use tantivy::query::QueryParser;
use tantivy::collector::TopCollector;
static DATA: &'static [u8] = include_bytes!("output.bin");
fn run() -> tantivy::Result<()> {
// Prints each argument on a separate line
let directory = StaticDirectory::open(DATA).unwrap();
let index = Index::open_directory(directory).unwrap();
index.load_searchers().unwrap();
let searcher = index.searcher();
let schema = index.schema();
let title = schema.get_field("title").unwrap();
let body = schema.get_field("body").unwrap();
let query_parser = QueryParser::for_index(&index, vec![title, body]);
let query = query_parser.parse_query("sea whale")?;
let mut top_collector = TopCollector::with_limit(10);
searcher.search(&*query, &mut top_collector)?;
let doc_addresses = top_collector.docs();
// The actual documents still need to be
// retrieved from Tantivy's store.
//
// Since the body field was not configured as stored,
// the document returned will only contain
// a title.
for doc_address in doc_addresses {
let retrieved_doc = searcher.doc(&doc_address)?;
println!("{}", schema.to_json(&retrieved_doc));
}
Ok(())
}
fn main() {
run().unwrap();
}

23
ci/before_deploy.ps1
View File

@@ -1,23 +0,0 @@
# This script takes care of packaging the build artifacts that will go in the
# release zipfile
$SRC_DIR = $PWD.Path
$STAGE = [System.Guid]::NewGuid().ToString()
Set-Location $ENV:Temp
New-Item -Type Directory -Name $STAGE
Set-Location $STAGE
$ZIP = "$SRC_DIR\$($Env:CRATE_NAME)-$($Env:APPVEYOR_REPO_TAG_NAME)-$($Env:TARGET).zip"
# TODO Update this to package the right artifacts
Copy-Item "$SRC_DIR\target\$($Env:TARGET)\release\hello.exe" '.\'
7z a "$ZIP" *
Push-AppveyorArtifact "$ZIP"
Remove-Item *.* -Force
Set-Location ..
Remove-Item $STAGE
Set-Location $SRC_DIR

33
ci/before_deploy.sh
View File

@@ -1,33 +0,0 @@
# This script takes care of building your crate and packaging it for release
set -ex
main() {
local src=$(pwd) \
stage=
case $TRAVIS_OS_NAME in
linux)
stage=$(mktemp -d)
;;
osx)
stage=$(mktemp -d -t tmp)
;;
esac
test -f Cargo.lock || cargo generate-lockfile
# TODO Update this to build the artifacts that matter to you
cross rustc --bin hello --target $TARGET --release -- -C lto
# TODO Update this to package the right artifacts
cp target/$TARGET/release/hello $stage/
cd $stage
tar czf $src/$CRATE_NAME-$TRAVIS_TAG-$TARGET.tar.gz *
cd $src
rm -rf $stage
}
main

47
ci/install.sh
View File

@@ -1,47 +0,0 @@
set -ex
main() {
local target=
if [ $TRAVIS_OS_NAME = linux ]; then
target=x86_64-unknown-linux-musl
sort=sort
else
target=x86_64-apple-darwin
sort=gsort # for `sort --sort-version`, from brew's coreutils.
fi
# Builds for iOS are done on OSX, but require the specific target to be
# installed.
case $TARGET in
aarch64-apple-ios)
rustup target install aarch64-apple-ios
;;
armv7-apple-ios)
rustup target install armv7-apple-ios
;;
armv7s-apple-ios)
rustup target install armv7s-apple-ios
;;
i386-apple-ios)
rustup target install i386-apple-ios
;;
x86_64-apple-ios)
rustup target install x86_64-apple-ios
;;
esac
# This fetches latest stable release
local tag=$(git ls-remote --tags --refs --exit-code https://github.com/japaric/cross \
| cut -d/ -f3 \
| grep -E '^v[0.1.0-9.]+$' \
| $sort --version-sort \
| tail -n1)
curl -LSfs https://japaric.github.io/trust/install.sh | \
sh -s -- \
--force \
--git japaric/cross \
--tag $tag \
--target $target
}
main

30
ci/script.sh
View File

@@ -1,30 +0,0 @@
#!/usr/bin/env bash
# This script takes care of testing your crate
set -ex
main() {
if [ ! -z $CODECOV ]; then
echo "Codecov"
cargo build --verbose && cargo coverage --verbose --all && bash <(curl -s https://codecov.io/bash) -s target/kcov
else
echo "Build"
cross build --target $TARGET
if [ ! -z $DISABLE_TESTS ]; then
return
fi
echo "Test"
cross test --target $TARGET --no-default-features --features mmap
cross test --target $TARGET --no-default-features --features mmap query-grammar
fi
for example in $(ls examples/*.rs)
do
cargo run --example $(basename $example .rs)
done
}
# we don't run the "test phase" when doing deploys
if [ -z $TRAVIS_TAG ]; then
main
fi

1
doc/.gitignore vendored
View File

@@ -1 +0,0 @@
book

5
doc/book.toml
View File

@@ -1,5 +0,0 @@
[book]
authors = ["Paul Masurel"]
multilingual = false
src = "src"
title = "Tantivy, the user guide"

15
doc/src/SUMMARY.md
View File

@@ -1,15 +0,0 @@
# Summary
[Avant Propos](./avant-propos.md)
- [Segments](./basis.md)
- [Defining your schema](./schema.md)
- [Facetting](./facetting.md)
- [Innerworkings](./innerworkings.md)
- [Inverted index](./inverted_index.md)
- [Best practise](./inverted_index.md)
[Frequently Asked Questions](./faq.md)
[Examples](./examples.md)

34
doc/src/avant-propos.md
View File

@@ -1,34 +0,0 @@
# Foreword, what is the scope of tantivy?
> Tantivy is a **search** engine **library** for Rust.
If you are familiar with Lucene, it's an excellent approximation to consider tantivy as Lucene for rust. tantivy is heavily inspired by Lucene's design and
they both have the same scope and targetted use cases.
If you are not familiar with Lucene, let's break down our little tagline.
- **Search** here means full-text search : fundamentally, tantivy is here to help you
identify efficiently what are the documents matching a given query in your corpus.
But modern search UI are so much more : text processing, facetting, autocomplete, fuzzy search, good
relevancy, collapsing, highlighting, spatial search.
While some of these features are not available in tantivy yet, all of these are relevant
feature requests. Tantivy's objective is to offer a solid toolbox to create the best search
experience. But keep in mind this is just a toolbox.
Which bring us to the second keyword...
- **Library** means that you will have to write code. tantivy is not an *all-in-one* server solution like elastic search for instance.
Sometimes a functionality will not be available in tantivy because it is too
specific to your use case. By design, tantivy should make it possible to extend
the available set of features using the existing rock-solid datastructures.
Most frequently this will mean writing your own `Collector`, your own `Scorer` or your own
`TokenFilter`... Some of your requirements may also be related to
something closer to architecture or operations. For instance, you may
want to build a large corpus on Hadoop, fine-tune the merge policy to keep your
index sharded in a time-wise fashion, or you may want to convert and existing
index from a different format.
Tantivy exposes a lot of low level API to do all of these things.

77
doc/src/basis.md
View File

@@ -1,77 +0,0 @@
# Anatomy of an index
## Straight from disk
Tantivy accesses its data using an abstracting trait called `Directory`.
In theory, one can come and override the data access logic. In practise, the
trait somewhat assumes that your data can be mapped to memory, and tantivy
seems deeply married to using `mmap` for its io [^1], and the only persisting
directory shipped with tantivy is the `MmapDirectory`.
While this design has some downsides, this greatly simplifies the source code of
tantivy. Caching is also entirely delegated to the OS.
`tantivy` works entirely (or almost) by directly reading the datastructures as they are layed on disk. As a result, the act of opening an indexing does not involve loading different datastructures from the disk into random access memory : starting a process, opening an index, and performing your first query can typically be done in a matter of milliseconds.
This is an interesting property for a command line search engine, or for some multi-tenant log search engine : spawning a new process for each new query can be a perfectly sensible solution in some use case.
In later chapters, we will discuss tantivy's inverted index data layout.
One key take away is that to achieve great performance, search indexes are extremely compact.
Of course this is crucial to reduce IO, and ensure that as much of our index can sit in RAM.
Also, whenever possible its data is accessed sequentially. Of course, this is an amazing property when tantivy needs to access the data from your spinning hard disk, but this is also
critical for performance, if your data is read from and an `SSD` or even already in your pagecache.
## Segments, and the log method
That kind of compact layout comes at one cost: it prevents our datastructures from being dynamic.
In fact, the `Directory` trait does not even allow you to modify part of a file.
To allow the addition / deletion of documents, and create the illusion that
your index is dynamic (i.e.: adding and deleting documents), tantivy uses a common database trick sometimes referred to as the *log method*.
Let's forget about deletes for a moment.
As you add documents, these documents are processed and stored in a dedicated datastructure, in a `RAM` buffer. This datastructure is not ready for search, but it is useful to receive your data and rearrange it very rapidly.
As you add documents, this buffer will reach its capacity and tantivy will transparently stop adding document to it and start converting this datastructure to its final read-only format on disk. Once written, an brand empty buffer is available to resume adding documents.
The resulting chunk of index obtained after this serialization is called a `Segment`.
> A segment is a self-contained atomic piece of index. It is identified with a UUID, and all of its files are identified using the naming scheme : `<UUID>.*`.
Which brings us to the nature of a tantivy `Index`.
> A tantivy `Index` is a collection of `Segments`.
Physically, this really just means and index is a bunch of segment files in a given `Directory`,
linked together by a `meta.json` file. This transparency can become extremely handy
to get tantivy to fit your use case:
*Example 1* You could for instance use hadoop to build a very large search index in a timely manner, copy all of the resulting segment files in the same directory and edit the `meta.json` to get a functional index.[^2]
*Example 2* You could also disable your merge policy and enforce daily segments. Removing data after one week can then be done very efficiently by just editing the `meta.json` and deleting the files associated to segment `D-7`.
# Merging
As you index more and more data, your index will accumulate more and more segments.
Having a lot of small segments is not really optimal. There is a bit of redundancy in having
all these term dictionary. Also when searching, we will need to do term lookups as many times as we have segments. It can hurt search performance a bit.
That's where merging or compacting comes into place. Tantivy will continuously consider merge
opportunities and start merging segments in the background.
# Indexing throughput, number of indexing threads
[^1]: This may eventually change.
[^2]: Be careful however. By default these files will not be considered as *managed* by tantivy. This means they will never be garbage collected by tantivy, regardless of whether they become obsolete or not.

0
doc/src/best_practise.md.rs
View File

3
doc/src/examples.md
View File

@@ -1,3 +0,0 @@
# Examples
- [Basic search](/examples/basic_search.html)

5
doc/src/facetting.md
View File

@@ -1,5 +0,0 @@
# Facetting
wewew
## weeewe

0
doc/src/faq.md
View File

1
doc/src/innerworkings.md
View File

@@ -1 +0,0 @@
# Innerworkings

1
doc/src/inverted_index.md
View File

@@ -1 +0,0 @@
# Inverted index

1
doc/src/schema.md
View File

@@ -1 +0,0 @@
# Defining your schema

237
examples/basic_search.rs
View File

@@ -1,237 +0,0 @@
// # Basic Example
//
// This example covers the basic functionalities of
// tantivy.
//
// We will :
// - define our schema
// - create an index in a directory
// - index a few documents into our index
// - search for the best document matching a basic query
// - retrieve the best document's original content.
// ---
// Importing tantivy...
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::{doc, Index, ReloadPolicy};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new()?;
// # Defining the schema
//
// The Tantivy index requires a very strict schema.
// The schema declares which fields are in the index,
// and for each field, its type and "the way it should
// be indexed".
// First we need to define a schema ...
let mut schema_builder = Schema::builder();
// Our first field is title.
// We want full-text search for it, and we also want
// to be able to retrieve the document after the search.
//
// `TEXT | STORED` is some syntactic sugar to describe
// that.
//
// `TEXT` means the field should be tokenized and indexed,
// along with its term frequency and term positions.
//
// `STORED` means that the field will also be saved
// in a compressed, row-oriented key-value store.
// This store is useful for reconstructing the
// documents that were selected during the search phase.
schema_builder.add_text_field("title", TEXT | STORED);
// Our second field is body.
// We want full-text search for it, but we do not
// need to be able to be able to retrieve it
// for our application.
//
// We can make our index lighter by omitting the `STORED` flag.
schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
// # Indexing documents
//
// Let's create a brand new index.
//
// This will actually just save a meta.json
// with our schema in the directory.
let index = Index::create_in_dir(&index_path, schema.clone())?;
// To insert a document we will need an index writer.
// There must be only one writer at a time.
// This single `IndexWriter` is already
// multithreaded.
//
// Here we give tantivy a budget of `50MB`.
// Using a bigger heap for the indexer may increase
// throughput, but 50 MB is already plenty.
let mut index_writer = index.writer(50_000_000)?;
// Let's index our documents!
// We first need a handle on the title and the body field.
// ### Adding documents
//
// 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 mut old_man_doc = Document::default();
old_man_doc.add_text(title, "The Old Man and the Sea");
old_man_doc.add_text(
body,
"He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish.",
);
// ... and add it to the `IndexWriter`.
index_writer.add_document(old_man_doc);
// For convenience, tantivy also comes with a macro to
// reduce the boilerplate above.
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
// Multivalued field just need to be repeated.
index_writer.add_document(doc!(
title => "Frankenstein",
title => "The Modern Prometheus",
body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
));
// This is an example, so we will only index 3 documents
// here. You can check out tantivy's tutorial to index
// the English wikipedia. Tantivy's indexing is rather fast.
// Indexing 5 million articles of the English wikipedia takes
// around 3 minutes on my computer!
// ### Committing
//
// At this point our documents are not searchable.
//
//
// We need to call `.commit()` explicitly to force the
// `index_writer` to finish processing the documents in the queue,
// flush the current index to the disk, and advertise
// the existence of new documents.
//
// This call is blocking.
index_writer.commit()?;
// If `.commit()` returns correctly, then all of the
// documents that have been added are guaranteed to be
// persistently indexed.
//
// In the scenario of a crash or a power failure,
// tantivy behaves as if it has rolled back to its last
// commit.
// # Searching
//
// ### Searcher
//
// A reader is required first in order to search an index.
// It acts as a `Searcher` pool that reloads itself,
// depending on a `ReloadPolicy`.
//
// For a search server you will typically create one reader for the entire lifetime of your
// program, and acquire a new searcher for every single request.
//
// In the code below, we rely on the 'ON_COMMIT' policy: the reader
// will reload the index automatically after each commit.
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()?;
// We now need to acquire a searcher.
//
// A searcher points to a snapshotted, immutable version of the index.
//
// Some search experience might require more than
// one query. Using the same searcher ensures that all of these queries will run on the
// same version of the index.
//
// Acquiring a `searcher` is very cheap.
//
// You should acquire a searcher every time you start processing a request and
// and release it right after your query is finished.
let searcher = reader.searcher();
// ### Query
// The query parser can interpret human queries.
// Here, if the user does not specify which
// field they want to search, tantivy will search
// in both title and body.
let query_parser = QueryParser::for_index(&index, vec![title, body]);
// `QueryParser` may fail if the query is not in the right
// format. For user facing applications, this can be a problem.
// A ticket has been opened regarding this problem.
let query = query_parser.parse_query("sea whale")?;
// A query defines a set of documents, as
// well as the way they should be scored.
//
// A query created by the query parser is scored according
// to a metric called Tf-Idf, and will consider
// any document matching at least one of our terms.
// ### Collectors
//
// We are not interested in all of the documents but
// only in the top 10. Keeping track of our top 10 best documents
// is the role of the `TopDocs` collector.
// We can now perform our query.
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
// The actual documents still need to be
// retrieved from Tantivy's store.
//
// Since the body field was not configured as stored,
// the document returned will only contain
// a title.
for (_score, doc_address) in top_docs {
let retrieved_doc = searcher.doc(doc_address)?;
println!("{}", schema.to_json(&retrieved_doc));
}
Ok(())
}

191
examples/custom_collector.rs
View File

@@ -1,191 +0,0 @@
// # Custom collector example
//
// This example shows how you can implement your own
// collector. As an example, we will compute a collector
// that computes the standard deviation of a given fast field.
//
// Of course, you can have a look at the tantivy's built-in collectors
// such as the `CountCollector` for more examples.
// ---
// Importing tantivy...
use tantivy::collector::{Collector, SegmentCollector};
use tantivy::fastfield::FastFieldReader;
use tantivy::query::QueryParser;
use tantivy::schema::Field;
use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
use tantivy::{doc, Index, SegmentReader, TantivyError};
#[derive(Default)]
struct Stats {
count: usize,
sum: f64,
squared_sum: f64,
}
impl Stats {
pub fn count(&self) -> usize {
self.count
}
pub fn mean(&self) -> f64 {
self.sum / (self.count as f64)
}
fn square_mean(&self) -> f64 {
self.squared_sum / (self.count as f64)
}
pub fn standard_deviation(&self) -> f64 {
let mean = self.mean();
(self.square_mean() - mean * mean).sqrt()
}
fn non_zero_count(self) -> Option<Stats> {
if self.count == 0 {
None
} else {
Some(self)
}
}
}
struct StatsCollector {
field: Field,
}
impl StatsCollector {
fn with_field(field: Field) -> StatsCollector {
StatsCollector { field }
}
}
impl Collector for StatsCollector {
// That's the type of our result.
// Our standard deviation will be a float.
type Fruit = Option<Stats>;
type Child = StatsSegmentCollector;
fn for_segment(
&self,
_segment_local_id: u32,
segment_reader: &SegmentReader,
) -> tantivy::Result<StatsSegmentCollector> {
let fast_field_reader = segment_reader
.fast_fields()
.u64(self.field)
.ok_or_else(|| {
let field_name = segment_reader.schema().get_field_name(self.field);
TantivyError::SchemaError(format!(
"Field {:?} is not a u64 fast field.",
field_name
))
})?;
Ok(StatsSegmentCollector {
fast_field_reader,
stats: Stats::default(),
})
}
fn requires_scoring(&self) -> bool {
// this collector does not care about score.
false
}
fn merge_fruits(&self, segment_stats: Vec<Option<Stats>>) -> tantivy::Result<Option<Stats>> {
let mut stats = Stats::default();
for segment_stats_opt in segment_stats {
if let Some(segment_stats) = segment_stats_opt {
stats.count += segment_stats.count;
stats.sum += segment_stats.sum;
stats.squared_sum += segment_stats.squared_sum;
}
}
Ok(stats.non_zero_count())
}
}
struct StatsSegmentCollector {
fast_field_reader: FastFieldReader<u64>,
stats: Stats,
}
impl SegmentCollector for StatsSegmentCollector {
type Fruit = Option<Stats>;
fn collect(&mut self, doc: u32, _score: f32) {
let value = self.fast_field_reader.get(doc) as f64;
self.stats.count += 1;
self.stats.sum += value;
self.stats.squared_sum += value * value;
}
fn harvest(self) -> <Self as SegmentCollector>::Fruit {
self.stats.non_zero_count()
}
}
fn main() -> tantivy::Result<()> {
// # Defining the schema
//
// The Tantivy index requires a very strict schema.
// The schema declares which fields are in the index,
// and for each field, its type and "the way it should
// be indexed".
// first we need to define a schema ...
let mut schema_builder = Schema::builder();
// We'll assume a fictional index containing
// products, and with a name, a description, and a price.
let product_name = schema_builder.add_text_field("name", TEXT);
let product_description = schema_builder.add_text_field("description", TEXT);
let price = schema_builder.add_u64_field("price", INDEXED | FAST);
let schema = schema_builder.build();
// # Indexing documents
//
// Lets index a bunch of fake documents for the sake of
// this example.
let index = Index::create_in_ram(schema.clone());
let mut index_writer = index.writer(50_000_000)?;
index_writer.add_document(doc!(
product_name => "Super Broom 2000",
product_description => "While it is ok for short distance travel, this broom \
was designed quiditch. It will up your game.",
price => 30_200u64
));
index_writer.add_document(doc!(
product_name => "Turbulobroom",
product_description => "You might have heard of this broom before : it is the sponsor of the Wales team.\
You'll enjoy its sharp turns, and rapid acceleration",
price => 29_240u64
));
index_writer.add_document(doc!(
product_name => "Broomio",
product_description => "Great value for the price. This broom is a market favorite",
price => 21_240u64
));
index_writer.add_document(doc!(
product_name => "Whack a Mole",
product_description => "Prime quality bat.",
price => 5_200u64
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let query_parser = QueryParser::for_index(&index, vec![product_name, product_description]);
// here we want to get a hit on the 'ken' in Frankenstein
let query = query_parser.parse_query("broom")?;
if let Some(stats) = searcher.search(&query, &StatsCollector::with_field(price))? {
println!("count: {}", stats.count());
println!("mean: {}", stats.mean());
println!("standard deviation: {}", stats.standard_deviation());
}
Ok(())
}

112
examples/custom_tokenizer.rs
View File

@@ -1,112 +0,0 @@
// # Defining a tokenizer pipeline
//
// In this example, we'll see how to define a tokenizer pipeline
// by aligning a bunch of `TokenFilter`.
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::tokenizer::NgramTokenizer;
use tantivy::{doc, Index};
fn main() -> tantivy::Result<()> {
// # Defining the schema
//
// The Tantivy index requires a very strict schema.
// The schema declares which fields are in the index,
// and for each field, its type and "the way it should
// be indexed".
// first we need to define a schema ...
let mut schema_builder = Schema::builder();
// Our first field is title.
// In this example we want to use NGram searching
// we will set that to 3 characters, so any three
// char in the title should be findable.
let text_field_indexing = TextFieldIndexing::default()
.set_tokenizer("ngram3")
.set_index_option(IndexRecordOption::WithFreqsAndPositions);
let text_options = TextOptions::default()
.set_indexing_options(text_field_indexing)
.set_stored();
let title = schema_builder.add_text_field("title", text_options);
// Our second field is body.
// We want full-text search for it, but we do not
// need to be able to be able to retrieve it
// for our application.
//
// We can make our index lighter and
// by omitting `STORED` flag.
let body = schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
// # Indexing documents
//
// Let's create a brand new index.
// To simplify we will work entirely in RAM.
// This is not what you want in reality, but it is very useful
// for your unit tests... Or this example.
let index = Index::create_in_ram(schema.clone());
// here we are registering our custome tokenizer
// this will store tokens of 3 characters each
index
.tokenizers()
.register("ngram3", NgramTokenizer::new(3, 3, false));
// To insert document we need an index writer.
// There must be only one writer at a time.
// This single `IndexWriter` is already
// multithreaded.
//
// Here we use a buffer of 50MB per thread. Using a bigger
// heap for the indexer can increase its throughput.
let mut index_writer = index.writer(50_000_000)?;
index_writer.add_document(doc!(
title => "The Old Man and the Sea",
body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish."
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => r#"A few miles south of Soledad, the Salinas River drops in close to the hillside
bank and runs deep and green. The water is warm too, for it has slipped twinkling
over the yellow sands in the sunlight before reaching the narrow pool. On one
side of the river the golden foothill slopes curve up to the strong and rocky
Gabilan Mountains, but on the valley side the water is lined with trees—willows
fresh and green with every spring, carrying in their lower leaf junctures the
debris of the winter’s flooding; and sycamores with mottled, white, recumbent
limbs and branches that arch over the pool"#
));
index_writer.add_document(doc!(
title => "Frankenstein",
body => r#"You will rejoice to hear that no disaster has accompanied the commencement of an
enterprise which you have regarded with such evil forebodings. I arrived here
yesterday, and my first task is to assure my dear sister of my welfare and
increasing confidence in the success of my undertaking."#
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
// The query parser can interpret human queries.
// Here, if the user does not specify which
// field they want to search, tantivy will search
// in both title and body.
let query_parser = QueryParser::for_index(&index, vec![title, body]);
// here we want to get a hit on the 'ken' in Frankenstein
let query = query_parser.parse_query("ken")?;
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
for (_, doc_address) in top_docs {
let retrieved_doc = searcher.doc(doc_address)?;
println!("{}", schema.to_json(&retrieved_doc));
}
Ok(())
}

143
examples/deleting_updating_documents.rs
View File

@@ -1,143 +0,0 @@
// # Deleting and Updating (?) documents
//
// This example explains how to delete and update documents.
// In fact there is actually no such thing as an update in tantivy.
//
// To update a document, you need to delete a document and then reinsert
// its new version.
//
// ---
// Importing tantivy...
use tantivy::collector::TopDocs;
use tantivy::query::TermQuery;
use tantivy::schema::*;
use tantivy::{doc, Index, IndexReader};
// A simple helper function to fetch a single document
// given its id from our index.
// It will be helpful to check our work.
fn extract_doc_given_isbn(
reader: &IndexReader,
isbn_term: &Term,
) -> tantivy::Result<Option<Document>> {
let searcher = reader.searcher();
// This is the simplest query you can think of.
// It matches all of the documents containing a specific term.
//
// The second argument is here to tell we don't care about decoding positions,
// or term frequencies.
let term_query = TermQuery::new(isbn_term.clone(), IndexRecordOption::Basic);
let top_docs = searcher.search(&term_query, &TopDocs::with_limit(1))?;
if let Some((_score, doc_address)) = top_docs.first() {
let doc = searcher.doc(*doc_address)?;
Ok(Some(doc))
} else {
// no doc matching this ID.
Ok(None)
}
}
fn main() -> tantivy::Result<()> {
// # Defining the schema
//
// Check out the *basic_search* example if this makes
// small sense to you.
let mut schema_builder = Schema::builder();
// Tantivy does not really have a notion of primary id.
// This may change in the future.
//
// Still, we can create a `isbn` field and use it as an id. This
// field can be `u64` or a `text`, depending on your use case.
// It just needs to be indexed.
//
// If it is `text`, let's make sure to keep it `raw` and let's avoid
// running any text processing on it.
// This is done by associating this field to the tokenizer named `raw`.
// Rather than building our [`TextOptions`](//docs.rs/tantivy/~0/tantivy/schema/struct.TextOptions.html) manually,
// We use the `STRING` shortcut. `STRING` stands for indexed (without term frequency or positions)
// and untokenized.
//
// Because we also want to be able to see this `id` in our returned documents,
// we also mark the field as stored.
let isbn = schema_builder.add_text_field("isbn", STRING | STORED);
let title = schema_builder.add_text_field("title", TEXT | STORED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let mut index_writer = index.writer(50_000_000)?;
// Let's add a couple of documents, for the sake of the example.
let mut old_man_doc = Document::default();
old_man_doc.add_text(title, "The Old Man and the Sea");
index_writer.add_document(doc!(
isbn => "978-0099908401",
title => "The old Man and the see"
));
index_writer.add_document(doc!(
isbn => "978-0140177398",
title => "Of Mice and Men",
));
index_writer.add_document(doc!(
title => "Frankentein", //< Oops there is a typo here.
isbn => "978-9176370711",
));
index_writer.commit()?;
let reader = index.reader()?;
let frankenstein_isbn = Term::from_field_text(isbn, "978-9176370711");
// Oops our frankenstein doc seems mispelled
let frankenstein_doc_misspelled = extract_doc_given_isbn(&reader, &frankenstein_isbn)?.unwrap();
assert_eq!(
schema.to_json(&frankenstein_doc_misspelled),
r#"{"isbn":["978-9176370711"],"title":["Frankentein"]}"#,
);
// # Update = Delete + Insert
//
// Here we will want to update the typo in the `Frankenstein` book.
//
// Tantivy does not handle updates directly, we need to delete
// and reinsert the document.
//
// This can be complicated as it means you need to have access
// to the entire document. It is good practise to integrate tantivy
// with a key value store for this reason.
//
// To remove one of the document, we just call `delete_term`
// on its id.
//
// Note that `tantivy` does nothing to enforce the idea that
// there is only one document associated to this id.
//
// Also you might have noticed that we apply the delete before
// having committed. This does not matter really...
index_writer.delete_term(frankenstein_isbn.clone());
// We now need to reinsert our document without the typo.
index_writer.add_document(doc!(
title => "Frankenstein",
isbn => "978-9176370711",
));
// You are guaranteed that your clients will only observe your index in
// the state it was in after a commit.
// In this example, your search engine will at no point be missing the *Frankenstein* document.
// Everything happened as if the document was updated.
index_writer.commit()?;
// We reload our searcher to make our change available to clients.
reader.reload()?;
// No more typo!
let frankenstein_new_doc = extract_doc_given_isbn(&reader, &frankenstein_isbn)?.unwrap();
assert_eq!(
schema.to_json(&frankenstein_new_doc),
r#"{"isbn":["978-9176370711"],"title":["Frankenstein"]}"#,
);
Ok(())
}

112
examples/faceted_search.rs
View File

@@ -1,112 +0,0 @@
// # Basic Example
//
// This example covers the basic functionalities of
// tantivy.
//
// We will :
// - define our schema
// = create an index in a directory
// - index few documents in our index
// - search for the best document matchings "sea whale"
// - retrieve the best document original content.
// ---
// Importing tantivy...
use tantivy::collector::FacetCollector;
use tantivy::query::{AllQuery, TermQuery};
use tantivy::schema::*;
use tantivy::{doc, Index};
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the sake of this example
let mut schema_builder = Schema::builder();
let name = schema_builder.add_text_field("felin_name", TEXT | STORED);
// this is our faceted field: its scientific classification
let classification = schema_builder.add_facet_field("classification");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer(30_000_000)?;
// For convenience, tantivy also comes with a macro to
// reduce the boilerplate above.
index_writer.add_document(doc!(
name => "Cat",
classification => Facet::from("/Felidae/Felinae/Felis")
));
index_writer.add_document(doc!(
name => "Canada lynx",
classification => Facet::from("/Felidae/Felinae/Lynx")
));
index_writer.add_document(doc!(
name => "Cheetah",
classification => Facet::from("/Felidae/Felinae/Acinonyx")
));
index_writer.add_document(doc!(
name => "Tiger",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Lion",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Jaguar",
classification => Facet::from("/Felidae/Pantherinae/Panthera")
));
index_writer.add_document(doc!(
name => "Sunda clouded leopard",
classification => Facet::from("/Felidae/Pantherinae/Neofelis")
));
index_writer.add_document(doc!(
name => "Fossa",
classification => Facet::from("/Eupleridae/Cryptoprocta")
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
{
let mut facet_collector = FacetCollector::for_field(classification);
facet_collector.add_facet("/Felidae");
let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
// This lists all of the facet counts, right below "/Felidae".
let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/Felidae/Felinae"), 3),
(&Facet::from("/Felidae/Pantherinae"), 4),
]
);
}
// Facets are also searchable.
//
// For instance a common UI pattern is to allow the user someone to click on a facet link
// (e.g: `Pantherinae`) to drill down and filter the current result set with this subfacet.
//
// The search would then look as follows.
// Check the reference doc for different ways to create a `Facet` object.
{
let facet = Facet::from_text("/Felidae/Pantherinae");
let facet_term = Term::from_facet(classification, &facet);
let facet_term_query = TermQuery::new(facet_term, IndexRecordOption::Basic);
let mut facet_collector = FacetCollector::for_field(classification);
facet_collector.add_facet("/Felidae/Pantherinae");
let facet_counts = searcher.search(&facet_term_query, &facet_collector)?;
let facets: Vec<(&Facet, u64)> = facet_counts.get("/Felidae/Pantherinae").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/Felidae/Pantherinae/Neofelis"), 1),
(&Facet::from("/Felidae/Pantherinae/Panthera"), 3),
]
);
}
Ok(())
}

98
examples/faceted_search_with_tweaked_score.rs
View File

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

2
examples/generate_html.sh Executable file
View File

@@ -0,0 +1,2 @@
#!/bin/bash
docco simple_search.rs -o html

518
examples/html/docco.css Normal file
View File

@@ -0,0 +1,518 @@
/*--------------------- Typography ----------------------------*/
@font-face {
font-family: 'aller-light';
src: url('public/fonts/aller-light.eot');
src: url('public/fonts/aller-light.eot?#iefix') format('embedded-opentype'),
url('public/fonts/aller-light.woff') format('woff'),
url('public/fonts/aller-light.ttf') format('truetype');
font-weight: normal;
font-style: normal;
}
@font-face {
font-family: 'aller-bold';
src: url('public/fonts/aller-bold.eot');
src: url('public/fonts/aller-bold.eot?#iefix') format('embedded-opentype'),
url('public/fonts/aller-bold.woff') format('woff'),
url('public/fonts/aller-bold.ttf') format('truetype');
font-weight: normal;
font-style: normal;
}
@font-face {
font-family: 'roboto-black';
src: url('public/fonts/roboto-black.eot');
src: url('public/fonts/roboto-black.eot?#iefix') format('embedded-opentype'),
url('public/fonts/roboto-black.woff') format('woff'),
url('public/fonts/roboto-black.ttf') format('truetype');
font-weight: normal;
font-style: normal;
}
/*--------------------- Layout ----------------------------*/
html { height: 100%; }
body {
font-family: "aller-light";
font-size: 14px;
line-height: 18px;
color: #30404f;
margin: 0; padding: 0;
height:100%;
}
#container { min-height: 100%; }
a {
color: #000;
}
b, strong {
font-weight: normal;
font-family: "aller-bold";
}
p {
margin: 15px 0 0px;
}
.annotation ul, .annotation ol {
margin: 25px 0;
}
.annotation ul li, .annotation ol li {
font-size: 14px;
line-height: 18px;
margin: 10px 0;
}
h1, h2, h3, h4, h5, h6 {
color: #112233;
line-height: 1em;
font-weight: normal;
font-family: "roboto-black";
text-transform: uppercase;
margin: 30px 0 15px 0;
}
h1 {
margin-top: 40px;
}
h2 {
font-size: 1.26em;
}
hr {
border: 0;
background: 1px #ddd;
height: 1px;
margin: 20px 0;
}
pre, tt, code {
font-size: 12px; line-height: 16px;
font-family: Menlo, Monaco, Consolas, "Lucida Console", monospace;
margin: 0; padding: 0;
}
.annotation pre {
display: block;
margin: 0;
padding: 7px 10px;
background: #fcfcfc;
-moz-box-shadow: inset 0 0 10px rgba(0,0,0,0.1);
-webkit-box-shadow: inset 0 0 10px rgba(0,0,0,0.1);
box-shadow: inset 0 0 10px rgba(0,0,0,0.1);
overflow-x: auto;
}
.annotation pre code {
border: 0;
padding: 0;
background: transparent;
}
blockquote {
border-left: 5px solid #ccc;
margin: 0;
padding: 1px 0 1px 1em;
}
.sections blockquote p {
font-family: Menlo, Consolas, Monaco, monospace;
font-size: 12px; line-height: 16px;
color: #999;
margin: 10px 0 0;
white-space: pre-wrap;
}
ul.sections {
list-style: none;
padding:0 0 5px 0;;
margin:0;
}
/*
Force border-box so that % widths fit the parent
container without overlap because of margin/padding.
More Info : http://www.quirksmode.org/css/box.html
*/
ul.sections > li > div {
-moz-box-sizing: border-box; /* firefox */
-ms-box-sizing: border-box; /* ie */
-webkit-box-sizing: border-box; /* webkit */
-khtml-box-sizing: border-box; /* konqueror */
box-sizing: border-box; /* css3 */
}
/*---------------------- Jump Page -----------------------------*/
#jump_to, #jump_page {
margin: 0;
background: white;
-webkit-box-shadow: 0 0 25px #777; -moz-box-shadow: 0 0 25px #777;
-webkit-border-bottom-left-radius: 5px; -moz-border-radius-bottomleft: 5px;
font: 16px Arial;
cursor: pointer;
text-align: right;
list-style: none;
}
#jump_to a {
text-decoration: none;
}
#jump_to a.large {
display: none;
}
#jump_to a.small {
font-size: 22px;
font-weight: bold;
color: #676767;
}
#jump_to, #jump_wrapper {
position: fixed;
right: 0; top: 0;
padding: 10px 15px;
margin:0;
}
#jump_wrapper {
display: none;
padding:0;
}
#jump_to:hover #jump_wrapper {
display: block;
}
#jump_page_wrapper{
position: fixed;
right: 0;
top: 0;
bottom: 0;
}
#jump_page {
padding: 5px 0 3px;
margin: 0 0 25px 25px;
max-height: 100%;
overflow: auto;
}
#jump_page .source {
display: block;
padding: 15px;
text-decoration: none;
border-top: 1px solid #eee;
}
#jump_page .source:hover {
background: #f5f5ff;
}
#jump_page .source:first-child {
}
/*---------------------- Low resolutions (> 320px) ---------------------*/
@media only screen and (min-width: 320px) {
.pilwrap { display: none; }
ul.sections > li > div {
display: block;
padding:5px 10px 0 10px;
}
ul.sections > li > div.annotation ul, ul.sections > li > div.annotation ol {
padding-left: 30px;
}
ul.sections > li > div.content {
overflow-x:auto;
-webkit-box-shadow: inset 0 0 5px #e5e5ee;
box-shadow: inset 0 0 5px #e5e5ee;
border: 1px solid #dedede;
margin:5px 10px 5px 10px;
padding-bottom: 5px;
}
ul.sections > li > div.annotation pre {
margin: 7px 0 7px;
padding-left: 15px;
}
ul.sections > li > div.annotation p tt, .annotation code {
background: #f8f8ff;
border: 1px solid #dedede;
font-size: 12px;
padding: 0 0.2em;
}
}
/*---------------------- (> 481px) ---------------------*/
@media only screen and (min-width: 481px) {
#container {
position: relative;
}
body {
background-color: #F5F5FF;
font-size: 15px;
line-height: 21px;
}
pre, tt, code {
line-height: 18px;
}
p, ul, ol {
margin: 0 0 15px;
}
#jump_to {
padding: 5px 10px;
}
#jump_wrapper {
padding: 0;
}
#jump_to, #jump_page {
font: 10px Arial;
text-transform: uppercase;
}
#jump_page .source {
padding: 5px 10px;
}
#jump_to a.large {
display: inline-block;
}
#jump_to a.small {
display: none;
}
#background {
position: absolute;
top: 0; bottom: 0;
width: 350px;
background: #fff;
border-right: 1px solid #e5e5ee;
z-index: -1;
}
ul.sections > li > div.annotation ul, ul.sections > li > div.annotation ol {
padding-left: 40px;
}
ul.sections > li {
white-space: nowrap;
}
ul.sections > li > div {
display: inline-block;
}
ul.sections > li > div.annotation {
max-width: 350px;
min-width: 350px;
min-height: 5px;
padding: 13px;
overflow-x: hidden;
white-space: normal;
vertical-align: top;
text-align: left;
}
ul.sections > li > div.annotation pre {
margin: 15px 0 15px;
padding-left: 15px;
}
ul.sections > li > div.content {
padding: 13px;
vertical-align: top;
border: none;
-webkit-box-shadow: none;
box-shadow: none;
}
.pilwrap {
position: relative;
display: inline;
}
.pilcrow {
font: 12px Arial;
text-decoration: none;
color: #454545;
position: absolute;
top: 3px; left: -20px;
padding: 1px 2px;
opacity: 0;
-webkit-transition: opacity 0.2s linear;
}
.for-h1 .pilcrow {
top: 47px;
}
.for-h2 .pilcrow, .for-h3 .pilcrow, .for-h4 .pilcrow {
top: 35px;
}
ul.sections > li > div.annotation:hover .pilcrow {
opacity: 1;
}
}
/*---------------------- (> 1025px) ---------------------*/
@media only screen and (min-width: 1025px) {
body {
font-size: 16px;
line-height: 24px;
}
#background {
width: 525px;
}
ul.sections > li > div.annotation {
max-width: 525px;
min-width: 525px;
padding: 10px 25px 1px 50px;
}
ul.sections > li > div.content {
padding: 9px 15px 16px 25px;
}
}
/*---------------------- Syntax Highlighting -----------------------------*/
td.linenos { background-color: #f0f0f0; padding-right: 10px; }
span.lineno { background-color: #f0f0f0; padding: 0 5px 0 5px; }
/*
github.com style (c) Vasily Polovnyov <vast@whiteants.net>
*/
pre code {
display: block; padding: 0.5em;
color: #000;
background: #f8f8ff
}
pre .hljs-comment,
pre .hljs-template_comment,
pre .hljs-diff .hljs-header,
pre .hljs-javadoc {
color: #408080;
font-style: italic
}
pre .hljs-keyword,
pre .hljs-assignment,
pre .hljs-literal,
pre .hljs-css .hljs-rule .hljs-keyword,
pre .hljs-winutils,
pre .hljs-javascript .hljs-title,
pre .hljs-lisp .hljs-title,
pre .hljs-subst {
color: #954121;
/*font-weight: bold*/
}
pre .hljs-number,
pre .hljs-hexcolor {
color: #40a070
}
pre .hljs-string,
pre .hljs-tag .hljs-value,
pre .hljs-phpdoc,
pre .hljs-tex .hljs-formula {
color: #219161;
}
pre .hljs-title,
pre .hljs-id {
color: #19469D;
}
pre .hljs-params {
color: #00F;
}
pre .hljs-javascript .hljs-title,
pre .hljs-lisp .hljs-title,
pre .hljs-subst {
font-weight: normal
}
pre .hljs-class .hljs-title,
pre .hljs-haskell .hljs-label,
pre .hljs-tex .hljs-command {
color: #458;
font-weight: bold
}
pre .hljs-tag,
pre .hljs-tag .hljs-title,
pre .hljs-rules .hljs-property,
pre .hljs-django .hljs-tag .hljs-keyword {
color: #000080;
font-weight: normal
}
pre .hljs-attribute,
pre .hljs-variable,
pre .hljs-instancevar,
pre .hljs-lisp .hljs-body {
color: #008080
}
pre .hljs-regexp {
color: #B68
}
pre .hljs-class {
color: #458;
font-weight: bold
}
pre .hljs-symbol,
pre .hljs-ruby .hljs-symbol .hljs-string,
pre .hljs-ruby .hljs-symbol .hljs-keyword,
pre .hljs-ruby .hljs-symbol .hljs-keymethods,
pre .hljs-lisp .hljs-keyword,
pre .hljs-tex .hljs-special,
pre .hljs-input_number {
color: #990073
}
pre .hljs-builtin,
pre .hljs-constructor,
pre .hljs-built_in,
pre .hljs-lisp .hljs-title {
color: #0086b3
}
pre .hljs-preprocessor,
pre .hljs-pi,
pre .hljs-doctype,
pre .hljs-shebang,
pre .hljs-cdata {
color: #999;
font-weight: bold
}
pre .hljs-deletion {
background: #fdd
}
pre .hljs-addition {
background: #dfd
}
pre .hljs-diff .hljs-change {
background: #0086b3
}
pre .hljs-chunk {
color: #aaa
}
pre .hljs-tex .hljs-formula {
opacity: 0.5;
}

BIN
examples/html/public/fonts/aller-bold.eot Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/aller-bold.ttf Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/aller-bold.woff Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/aller-light.eot Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/aller-light.ttf Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/aller-light.woff Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/fleurons.eot Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/fleurons.ttf Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/fleurons.woff Normal file
View File

Binary file not shown.

BIN
examples/html/public/fonts/roboto-black.eot Executable file
View File

Binary file not shown.

BIN
examples/html/public/fonts/roboto-black.ttf Executable file
View File

Binary file not shown.

BIN
examples/html/public/fonts/roboto-black.woff Executable file
View File

Binary file not shown.

BIN
examples/html/public/images/gray.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 56 KiB

375
examples/html/public/stylesheets/normalize.css vendored Normal file
View File

@@ -0,0 +1,375 @@
/*! normalize.css v2.0.1 | MIT License | git.io/normalize */
/* ==========================================================================
HTML5 display definitions
========================================================================== */
/*
* Corrects `block` display not defined in IE 8/9.
*/
article,
aside,
details,
figcaption,
figure,
footer,
header,
hgroup,
nav,
section,
summary {
display: block;
}
/*
* Corrects `inline-block` display not defined in IE 8/9.
*/
audio,
canvas,
video {
display: inline-block;
}
/*
* Prevents modern browsers from displaying `audio` without controls.
* Remove excess height in iOS 5 devices.
*/
audio:not([controls]) {
display: none;
height: 0;
}
/*
* Addresses styling for `hidden` attribute not present in IE 8/9.
*/
[hidden] {
display: none;
}
/* ==========================================================================
Base
========================================================================== */
/*
* 1. Sets default font family to sans-serif.
* 2. Prevents iOS text size adjust after orientation change, without disabling
* user zoom.
*/
html {
font-family: sans-serif; /* 1 */
-webkit-text-size-adjust: 100%; /* 2 */
-ms-text-size-adjust: 100%; /* 2 */
}
/*
* Removes default margin.
*/
body {
margin: 0;
}
/* ==========================================================================
Links
========================================================================== */
/*
* Addresses `outline` inconsistency between Chrome and other browsers.
*/
a:focus {
outline: thin dotted;
}
/*
* Improves readability when focused and also mouse hovered in all browsers.
*/
a:active,
a:hover {
outline: 0;
}
/* ==========================================================================
Typography
========================================================================== */
/*
* Addresses `h1` font sizes within `section` and `article` in Firefox 4+,
* Safari 5, and Chrome.
*/
h1 {
font-size: 2em;
}
/*
* Addresses styling not present in IE 8/9, Safari 5, and Chrome.
*/
abbr[title] {
border-bottom: 1px dotted;
}
/*
* Addresses style set to `bolder` in Firefox 4+, Safari 5, and Chrome.
*/
b,
strong {
font-weight: bold;
}
/*
* Addresses styling not present in Safari 5 and Chrome.
*/
dfn {
font-style: italic;
}
/*
* Addresses styling not present in IE 8/9.
*/
mark {
background: #ff0;
color: #000;
}
/*
* Corrects font family set oddly in Safari 5 and Chrome.
*/
code,
kbd,
pre,
samp {
font-family: monospace, serif;
font-size: 1em;
}
/*
* Improves readability of pre-formatted text in all browsers.
*/
pre {
white-space: pre;
white-space: pre-wrap;
word-wrap: break-word;
}
/*
* Sets consistent quote types.
*/
q {
quotes: "\201C" "\201D" "\2018" "\2019";
}
/*
* Addresses inconsistent and variable font size in all browsers.
*/
small {
font-size: 80%;
}
/*
* Prevents `sub` and `sup` affecting `line-height` in all browsers.
*/
sub,
sup {
font-size: 75%;
line-height: 0;
position: relative;
vertical-align: baseline;
}
sup {
top: -0.5em;
}
sub {
bottom: -0.25em;
}
/* ==========================================================================
Embedded content
========================================================================== */
/*
* Removes border when inside `a` element in IE 8/9.
*/
img {
border: 0;
}
/*
* Corrects overflow displayed oddly in IE 9.
*/
svg:not(:root) {
overflow: hidden;
}
/* ==========================================================================
Figures
========================================================================== */
/*
* Addresses margin not present in IE 8/9 and Safari 5.
*/
figure {
margin: 0;
}
/* ==========================================================================
Forms
========================================================================== */
/*
* Define consistent border, margin, and padding.
*/
fieldset {
border: 1px solid #c0c0c0;
margin: 0 2px;
padding: 0.35em 0.625em 0.75em;
}
/*
* 1. Corrects color not being inherited in IE 8/9.
* 2. Remove padding so people aren't caught out if they zero out fieldsets.
*/
legend {
border: 0; /* 1 */
padding: 0; /* 2 */
}
/*
* 1. Corrects font family not being inherited in all browsers.
* 2. Corrects font size not being inherited in all browsers.
* 3. Addresses margins set differently in Firefox 4+, Safari 5, and Chrome
*/
button,
input,
select,
textarea {
font-family: inherit; /* 1 */
font-size: 100%; /* 2 */
margin: 0; /* 3 */
}
/*
* Addresses Firefox 4+ setting `line-height` on `input` using `!important` in
* the UA stylesheet.
*/
button,
input {
line-height: normal;
}
/*
* 1. Avoid the WebKit bug in Android 4.0.* where (2) destroys native `audio`
* and `video` controls.
* 2. Corrects inability to style clickable `input` types in iOS.
* 3. Improves usability and consistency of cursor style between image-type
* `input` and others.
*/
button,
html input[type="button"], /* 1 */
input[type="reset"],
input[type="submit"] {
-webkit-appearance: button; /* 2 */
cursor: pointer; /* 3 */
}
/*
* Re-set default cursor for disabled elements.
*/
button[disabled],
input[disabled] {
cursor: default;
}
/*
* 1. Addresses box sizing set to `content-box` in IE 8/9.
* 2. Removes excess padding in IE 8/9.
*/
input[type="checkbox"],
input[type="radio"] {
box-sizing: border-box; /* 1 */
padding: 0; /* 2 */
}
/*
* 1. Addresses `appearance` set to `searchfield` in Safari 5 and Chrome.
* 2. Addresses `box-sizing` set to `border-box` in Safari 5 and Chrome
* (include `-moz` to future-proof).
*/
input[type="search"] {
-webkit-appearance: textfield; /* 1 */
-moz-box-sizing: content-box;
-webkit-box-sizing: content-box; /* 2 */
box-sizing: content-box;
}
/*
* Removes inner padding and search cancel button in Safari 5 and Chrome
* on OS X.
*/
input[type="search"]::-webkit-search-cancel-button,
input[type="search"]::-webkit-search-decoration {
-webkit-appearance: none;
}
/*
* Removes inner padding and border in Firefox 4+.
*/
button::-moz-focus-inner,
input::-moz-focus-inner {
border: 0;
padding: 0;
}
/*
* 1. Removes default vertical scrollbar in IE 8/9.
* 2. Improves readability and alignment in all browsers.
*/
textarea {
overflow: auto; /* 1 */
vertical-align: top; /* 2 */
}
/* ==========================================================================
Tables
========================================================================== */
/*
* Remove most spacing between table cells.
*/
table {
border-collapse: collapse;
border-spacing: 0;
}

542
examples/html/simple_search.html Normal file
View File

@@ -0,0 +1,542 @@
<!DOCTYPE html>
<html>
<head>
<title>simple_search.rs</title>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
<meta name="viewport" content="width=device-width, target-densitydpi=160dpi, initial-scale=1.0; maximum-scale=1.0; user-scalable=0;">
<link rel="stylesheet" media="all" href="docco.css" />
</head>
<body>
<div id="container">
<div id="background"></div>
<ul class="sections">
<li id="title">
<div class="annotation">
<h1>simple_search.rs</h1>
</div>
</li>
<li id="section-1">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-1">&#182;</a>
</div>
</div>
<div class="content"><div class='highlight'><pre><span class="hljs-keyword">extern</span> <span class="hljs-keyword">crate</span> tantivy;
<span class="hljs-keyword">extern</span> <span class="hljs-keyword">crate</span> tempdir;
<span class="hljs-meta">#[macro_use]</span>
<span class="hljs-keyword">extern</span> <span class="hljs-keyword">crate</span> serde_json;
<span class="hljs-keyword">use</span> std::path::Path;
<span class="hljs-keyword">use</span> tempdir::TempDir;
<span class="hljs-keyword">use</span> tantivy::Index;
<span class="hljs-keyword">use</span> tantivy::schema::*;
<span class="hljs-keyword">use</span> tantivy::collector::TopCollector;
<span class="hljs-keyword">use</span> tantivy::query::QueryParser;
<span class="hljs-function"><span class="hljs-keyword">fn</span> <span class="hljs-title">main</span></span>() {</pre></div></div>
</li>
<li id="section-2">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-2">&#182;</a>
</div>
<p>Let’s create a temporary directory for the
sake of this example</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">if</span> <span class="hljs-keyword">let</span> <span class="hljs-literal">Ok</span>(dir) = TempDir::new(<span class="hljs-string">"tantivy_example_dir"</span>) {
run_example(dir.path()).unwrap();
dir.close().unwrap();
}
}
<span class="hljs-function"><span class="hljs-keyword">fn</span> <span class="hljs-title">run_example</span></span>(index_path: &amp;Path) -&gt; tantivy::<span class="hljs-built_in">Result</span>&lt;()&gt; {</pre></div></div>
</li>
<li id="section-3">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-3">&#182;</a>
</div>
<h1 id="defining-the-schema">Defining the schema</h1>
<p>The Tantivy index requires a very strict schema.
The schema declares which fields are in the index,
and for each field, its type and “the way it should
be indexed”.</p>
</div>
</li>
<li id="section-4">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-4">&#182;</a>
</div>
<p>first we need to define a schema …</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> schema_builder = SchemaBuilder::<span class="hljs-keyword">default</span>();</pre></div></div>
</li>
<li id="section-5">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-5">&#182;</a>
</div>
<p>Our first field is title.
We want full-text search for it, and we also want
to be able to retrieve the document after the search.</p>
<p>TEXT | STORED is some syntactic sugar to describe
that.</p>
<p><code>TEXT</code> means the field should be tokenized and indexed,
along with its term frequency and term positions.</p>
<p><code>STORED</code> means that the field will also be saved
in a compressed, row-oriented key-value store.
This store is useful to reconstruct the
documents that were selected during the search phase.</p>
</div>
<div class="content"><div class='highlight'><pre> schema_builder.add_text_field(<span class="hljs-string">"title"</span>, TEXT | STORED);</pre></div></div>
</li>
<li id="section-6">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-6">&#182;</a>
</div>
<p>Our second field is body.
We want full-text search for it, but we do not
need to be able to be able to retrieve it
for our application. </p>
<p>We can make our index lighter and
by omitting <code>STORED</code> flag.</p>
</div>
<div class="content"><div class='highlight'><pre> schema_builder.add_text_field(<span class="hljs-string">"body"</span>, TEXT);
<span class="hljs-keyword">let</span> schema = schema_builder.build();</pre></div></div>
</li>
<li id="section-7">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-7">&#182;</a>
</div>
<h1 id="indexing-documents">Indexing documents</h1>
<p>Let’s create a brand new index.</p>
<p>This will actually just save a meta.json
with our schema in the directory.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> index = Index::create(index_path, schema.clone())?;</pre></div></div>
</li>
<li id="section-8">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-8">&#182;</a>
</div>
<p>To insert document we need an index writer.
There must be only one writer at a time.
This single <code>IndexWriter</code> is already
multithreaded.</p>
<p>Here we use a buffer of 50MB per thread. Using a bigger
heap for the indexer can increase its throughput.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> index_writer = index.writer(<span class="hljs-number">50_000_000</span>)?;</pre></div></div>
</li>
<li id="section-9">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-9">&#182;</a>
</div>
<p>Let’s index our documents!
We first need a handle on the title and the body field.</p>
</div>
</li>
<li id="section-10">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-10">&#182;</a>
</div>
<h3 id="create-a-document-manually-">Create a document “manually”.</h3>
<p>We can create a document manually, by setting the fields
one by one in a Document object.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> title = schema.get_field(<span class="hljs-string">"title"</span>).unwrap();
<span class="hljs-keyword">let</span> body = schema.get_field(<span class="hljs-string">"body"</span>).unwrap();
<span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> old_man_doc = Document::<span class="hljs-keyword">default</span>();
old_man_doc.add_text(title, <span class="hljs-string">"The Old Man and the Sea"</span>);
old_man_doc.add_text(
body,
<span class="hljs-string">"He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish."</span>,
);</pre></div></div>
</li>
<li id="section-11">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-11">&#182;</a>
</div>
<p>… and add it to the <code>IndexWriter</code>.</p>
</div>
<div class="content"><div class='highlight'><pre> index_writer.add_document(old_man_doc);</pre></div></div>
</li>
<li id="section-12">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-12">&#182;</a>
</div>
<h3 id="create-a-document-directly-from-json-">Create a document directly from json.</h3>
<p>Alternatively, we can use our schema to parse a
document object directly from json.
The document is a string, but we use the <code>json</code> macro
from <code>serde_json</code> for the convenience of multi-line support.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> json = json!({
<span class="hljs-string">"title"</span>: <span class="hljs-string">"Of Mice and Men"</span>,
<span class="hljs-string">"body"</span>: <span class="hljs-string">"A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"</span>
});
<span class="hljs-keyword">let</span> mice_and_men_doc = schema.parse_document(&amp;json.to_string())?;
index_writer.add_document(mice_and_men_doc);</pre></div></div>
</li>
<li id="section-13">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-13">&#182;</a>
</div>
<p>Multi-valued field are allowed, they are
expressed in JSON by an array.
The following document has two titles.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> json = json!({
<span class="hljs-string">"title"</span>: [<span class="hljs-string">"Frankenstein"</span>, <span class="hljs-string">"The Modern Prometheus"</span>],
<span class="hljs-string">"body"</span>: <span class="hljs-string">"You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."</span>
});
<span class="hljs-keyword">let</span> frankenstein_doc = schema.parse_document(&amp;json.to_string())?;
index_writer.add_document(frankenstein_doc);</pre></div></div>
</li>
<li id="section-14">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-14">&#182;</a>
</div>
<p>This is an example, so we will only index 3 documents
here. You can check out tantivy’s tutorial to index
the English wikipedia. Tantivy’s indexing is rather fast.
Indexing 5 million articles of the English wikipedia takes
around 4 minutes on my computer!</p>
</div>
</li>
<li id="section-15">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-15">&#182;</a>
</div>
<h3 id="committing">Committing</h3>
<p>At this point our documents are not searchable.</p>
<p>We need to call .commit() explicitly to force the
index_writer to finish processing the documents in the queue,
flush the current index to the disk, and advertise
the existence of new documents.</p>
<p>This call is blocking.</p>
</div>
<div class="content"><div class='highlight'><pre> index_writer.commit()?;</pre></div></div>
</li>
<li id="section-16">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-16">&#182;</a>
</div>
<p>If <code>.commit()</code> returns correctly, then all of the
documents that have been added are guaranteed to be
persistently indexed.</p>
<p>In the scenario of a crash or a power failure,
tantivy behaves as if has rolled back to its last
commit.</p>
</div>
</li>
<li id="section-17">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-17">&#182;</a>
</div>
<h1 id="searching">Searching</h1>
<p>Let’s search our index. Start by reloading
searchers in the index. This should be done
after every commit().</p>
</div>
<div class="content"><div class='highlight'><pre> index.load_searchers()?;</pre></div></div>
</li>
<li id="section-18">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-18">&#182;</a>
</div>
<p>Afterwards create one (or more) searchers.</p>
<p>You should create a searcher
every time you start a “search query”.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> searcher = index.searcher();</pre></div></div>
</li>
<li id="section-19">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-19">&#182;</a>
</div>
<p>The query parser can interpret human queries.
Here, if the user does not specify which
field they want to search, tantivy will search
in both title and body.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> query_parser = QueryParser::for_index(index, <span class="hljs-built_in">vec!</span>[title, body]);</pre></div></div>
</li>
<li id="section-20">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-20">&#182;</a>
</div>
<p>QueryParser may fail if the query is not in the right
format. For user facing applications, this can be a problem.
A ticket has been opened regarding this problem.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> query = query_parser.parse_query(<span class="hljs-string">"sea whale"</span>)?;</pre></div></div>
</li>
<li id="section-21">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-21">&#182;</a>
</div>
<p>A query defines a set of documents, as
well as the way they should be scored.</p>
<p>A query created by the query parser is scored according
to a metric called Tf-Idf, and will consider
any document matching at least one of our terms.</p>
</div>
</li>
<li id="section-22">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-22">&#182;</a>
</div>
<h3 id="collectors">Collectors</h3>
<p>We are not interested in all of the documents but
only in the top 10. Keeping track of our top 10 best documents
is the role of the TopCollector.</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> <span class="hljs-keyword">mut</span> top_collector = TopCollector::with_limit(<span class="hljs-number">10</span>);</pre></div></div>
</li>
<li id="section-23">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-23">&#182;</a>
</div>
<p>We can now perform our query.</p>
</div>
<div class="content"><div class='highlight'><pre> searcher.search(&amp;*query, &amp;<span class="hljs-keyword">mut</span> top_collector)?;</pre></div></div>
</li>
<li id="section-24">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-24">&#182;</a>
</div>
<p>Our top collector now contains the 10
most relevant doc ids…</p>
</div>
<div class="content"><div class='highlight'><pre> <span class="hljs-keyword">let</span> doc_addresses = top_collector.docs();</pre></div></div>
</li>
<li id="section-25">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-25">&#182;</a>
</div>
<p>The actual documents still need to be
retrieved from Tantivy’s store.</p>
<p>Since the body field was not configured as stored,
the document returned will only contain
a title.</p>
</div>
<div class="content"><div class='highlight'><pre>
<span class="hljs-keyword">for</span> doc_address <span class="hljs-keyword">in</span> doc_addresses {
<span class="hljs-keyword">let</span> retrieved_doc = searcher.doc(&amp;doc_address)?;
<span class="hljs-built_in">println!</span>(<span class="hljs-string">"{}"</span>, schema.to_json(&amp;retrieved_doc));
}</pre></div></div>
</li>
<li id="section-26">
<div class="annotation">
<div class="pilwrap ">
<a class="pilcrow" href="#section-26">&#182;</a>
</div>
<p>Wait for indexing and merging threads to shut down.
Usually this isn’t needed, but in <code>main</code> we try to
delete the temporary directory and that fails on
Windows if the files are still open.</p>
</div>
<div class="content"><div class='highlight'><pre> index_writer.wait_merging_threads()?;
<span class="hljs-literal">Ok</span>(())
}</pre></div></div>
</li>
</ul>
</div>
</body>
</html>

39
examples/integer_range_search.rs
View File

@@ -1,39 +0,0 @@
// # Searching a range on an indexed int field.
//
// Below is an example of creating an indexed integer field in your schema
// You can use RangeQuery to get a Count of all occurrences in a given range.
use tantivy::collector::Count;
use tantivy::query::RangeQuery;
use tantivy::schema::{Schema, INDEXED};
use tantivy::{doc, Index, Result};
fn run() -> Result<()> {
// For the sake of simplicity, this schema will only have 1 field
let mut schema_builder = Schema::builder();
// `INDEXED` is a short-hand to indicate that our field should be "searchable".
let year_field = schema_builder.add_u64_field("year", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let reader = index.reader()?;
{
let mut index_writer = index.writer_with_num_threads(1, 6_000_000)?;
for year in 1950u64..2019u64 {
index_writer.add_document(doc!(year_field => year));
}
index_writer.commit()?;
// The index will be a range of years
}
reader.reload()?;
let searcher = reader.searcher();
// The end is excluded i.e. here we are searching up to 1969
let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960..1970);
// Uses a Count collector to sum the total number of docs in the range
let num_60s_books = searcher.search(&docs_in_the_sixties, &Count)?;
assert_eq!(num_60s_books, 10);
Ok(())
}
fn main() {
run().unwrap()
}

130
examples/iterating_docs_and_positions.rs
View File

@@ -1,130 +0,0 @@
// # Iterating docs and positioms.
//
// At its core of tantivy, relies on a data structure
// called an inverted index.
//
// This example shows how to manually iterate through
// the list of documents containing a term, getting
// its term frequency, and accessing its positions.
// ---
// Importing tantivy...
use tantivy::schema::*;
use tantivy::{doc, DocSet, Index, Postings, TERMINATED};
fn main() -> tantivy::Result<()> {
// We first create a schema for the sake of the
// example. Check the `basic_search` example for more information.
let mut schema_builder = Schema::builder();
// For this example, we need to make sure to index positions for our title
// field. `TEXT` precisely does this.
let title = schema_builder.add_text_field("title", TEXT | STORED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
let mut index_writer = index.writer_with_num_threads(1, 50_000_000)?;
index_writer.add_document(doc!(title => "The Old Man and the Sea"));
index_writer.add_document(doc!(title => "Of Mice and Men"));
index_writer.add_document(doc!(title => "The modern Promotheus"));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
// A tantivy index is actually a collection of segments.
// Similarly, a searcher just wraps a list `segment_reader`.
//
// (Because we indexed a very small number of documents over one thread
// there is actually only one segment here, but let's iterate through the list
// anyway)
for segment_reader in searcher.segment_readers() {
// A segment contains different data structure.
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title);
// A `Term` is a text token associated with a field.
// Let's go through all docs containing the term `title:the` and access their position
let term_the = Term::from_field_text(title, "the");
// This segment posting object is like a cursor over the documents matching the term.
// The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
// and positions.
//
// If you don't need all this information, you may get better performance by decompressing less
// information.
if let Some(mut segment_postings) =
inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)
{
// this buffer will be used to request for positions
let mut positions: Vec<u32> = Vec::with_capacity(100);
let mut doc_id = segment_postings.doc();
while doc_id != TERMINATED {
// This MAY contains deleted documents as well.
if segment_reader.is_deleted(doc_id) {
doc_id = segment_postings.advance();
continue;
}
// the number of time the term appears in the document.
let term_freq: u32 = segment_postings.term_freq();
// accessing positions is slightly expensive and lazy, do not request
// for them if you don't need them for some documents.
segment_postings.positions(&mut positions);
// By definition we should have `term_freq` positions.
assert_eq!(positions.len(), term_freq as usize);
// This prints:
// ```
// Doc 0: TermFreq 2: [0, 4]
// Doc 2: TermFreq 1: [0]
// ```
println!("Doc {}: TermFreq {}: {:?}", doc_id, term_freq, positions);
doc_id = segment_postings.advance();
}
}
}
// A `Term` is a text token associated with a field.
// Let's go through all docs containing the term `title:the` and access their position
let term_the = Term::from_field_text(title, "the");
// Some other powerful operations (especially `.skip_to`) may be useful to consume these
// posting lists rapidly.
// You can check for them in the [`DocSet`](https://docs.rs/tantivy/~0/tantivy/trait.DocSet.html) trait
// and the [`Postings`](https://docs.rs/tantivy/~0/tantivy/trait.Postings.html) trait
// Also, for some VERY specific high performance use case like an OLAP analysis of logs,
// you can get better performance by accessing directly the blocks of doc ids.
for segment_reader in searcher.segment_readers() {
// A segment contains different data structure.
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title);
// This segment posting object is like a cursor over the documents matching the term.
// The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
// and positions.
//
// If you don't need all this information, you may get better performance by decompressing less
// information.
if let Some(mut block_segment_postings) =
inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)
{
while block_segment_postings.advance() {
// Once again these docs MAY contains deleted documents as well.
let docs = block_segment_postings.docs();
// Prints `Docs [0, 2].`
println!("Docs {:?}", docs);
}
}
}
Ok(())
}

100
examples/multiple_producer.rs
View File

@@ -1,100 +0,0 @@
// # Indexing from different threads.
//
// It is fairly common to have to index from different threads.
// Tantivy forbids to create more than one `IndexWriter` at a time.
//
// This `IndexWriter` itself has its own multithreaded layer, so managing your own
// indexing threads will not help. However, it can still be useful for some applications.
//
// For instance, if preparing documents to send to tantivy before indexing is the bottleneck of
// your application, it is reasonable to have multiple threads.
//
// Another very common reason to want to index from multiple threads, is implementing a webserver
// with CRUD capabilities. The server framework will most likely handle request from
// different threads.
//
// The recommended way to address both of these use case is to wrap your `IndexWriter` into a
// `Arc<RwLock<IndexWriter>>`.
//
// While this is counterintuitive, adding and deleting documents do not require mutability
// over the `IndexWriter`, so several threads will be able to do this operation concurrently.
//
// The example below does not represent an actual real-life use case (who would spawn thread to
// index a single document?), but aims at demonstrating the mechanism that makes indexing
// from several threads possible.
// ---
// Importing tantivy...
use std::sync::{Arc, RwLock};
use std::thread;
use std::time::Duration;
use tantivy::schema::{Schema, STORED, TEXT};
use tantivy::{doc, Index, IndexWriter, Opstamp};
fn main() -> tantivy::Result<()> {
// # Defining the schema
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field("title", TEXT | STORED);
let body = schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let index_writer: Arc<RwLock<IndexWriter>> = Arc::new(RwLock::new(index.writer(50_000_000)?));
// # First indexing thread.
let index_writer_clone_1 = index_writer.clone();
thread::spawn(move || {
// we index 100 times the document... for the sake of the example.
for i in 0..100 {
let opstamp = index_writer_clone_1
.read().unwrap() //< A read lock is sufficient here.
.add_document(
doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
println!("add doc {} from thread 1 - opstamp {}", i, opstamp);
thread::sleep(Duration::from_millis(20));
}
});
// # Second indexing thread.
let index_writer_clone_2 = index_writer.clone();
// For convenience, tantivy also comes with a macro to
// reduce the boilerplate above.
thread::spawn(move || {
// we index 100 times the document... for the sake of the example.
for i in 0..100 {
// A read lock is sufficient here.
let opstamp = {
let index_writer_rlock = index_writer_clone_2.read().unwrap();
index_writer_rlock.add_document(doc!(
title => "Manufacturing consent",
body => "Some great book description..."
))
};
println!("add doc {} from thread 2 - opstamp {}", i, opstamp);
thread::sleep(Duration::from_millis(10));
}
});
// # In the main thread, we commit 10 times, once every 500ms.
for _ in 0..10 {
let opstamp: Opstamp = {
// Committing or rollbacking on the other hand requires write lock. This will block other threads.
let mut index_writer_wlock = index_writer.write().unwrap();
index_writer_wlock.commit().unwrap()
};
println!("committed with opstamp {}", opstamp);
thread::sleep(Duration::from_millis(500));
}
Ok(())
}

139
examples/pre_tokenized_text.rs
View File

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

225
examples/simple_search.rs Normal file
View File

@@ -0,0 +1,225 @@
extern crate tantivy;
extern crate tempdir;
#[macro_use]
extern crate serde_json;
use std::path::Path;
use tempdir::TempDir;
use tantivy::Index;
use tantivy::schema::*;
use tantivy::collector::TopCollector;
use tantivy::query::QueryParser;
fn main() {
// Let's create a temporary directory for the
// sake of this example
if let Ok(dir) = TempDir::new("tantivy_example_dir") {
run_example(dir.path()).unwrap();
dir.close().unwrap();
}
}
fn run_example(index_path: &Path) -> tantivy::Result<()> {
// # Defining the schema
//
// The Tantivy index requires a very strict schema.
// The schema declares which fields are in the index,
// and for each field, its type and "the way it should
// be indexed".
// first we need to define a schema ...
let mut schema_builder = SchemaBuilder::default();
// Our first field is title.
// We want full-text search for it, and we also want
// to be able to retrieve the document after the search.
//
// TEXT | STORED is some syntactic sugar to describe
// that.
//
// `TEXT` means the field should be tokenized and indexed,
// along with its term frequency and term positions.
//
// `STORED` means that the field will also be saved
// in a compressed, row-oriented key-value store.
// This store is useful to reconstruct the
// documents that were selected during the search phase.
schema_builder.add_text_field("title", TEXT | STORED);
// Our second field is body.
// We want full-text search for it, but we do not
// need to be able to be able to retrieve it
// for our application.
//
// We can make our index lighter and
// by omitting `STORED` flag.
schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
// # Indexing documents
//
// Let's create a brand new index.
//
// This will actually just save a meta.json
// with our schema in the directory.
let index = Index::create(index_path, schema.clone())?;
// To insert document we need an index writer.
// There must be only one writer at a time.
// This single `IndexWriter` is already
// multithreaded.
//
// Here we use a buffer of 50MB per thread. Using a bigger
// heap for the indexer can increase its throughput.
let mut index_writer = index.writer(50_000_000)?;
// Let's index our documents!
// We first need a handle on the title and the body field.
// ### Create a document "manually".
//
// 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 mut old_man_doc = Document::default();
old_man_doc.add_text(title, "The Old Man and the Sea");
old_man_doc.add_text(
body,
"He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish.",
);
// ... and add it to the `IndexWriter`.
index_writer.add_document(old_man_doc);
// ### Create a document directly from json.
//
// Alternatively, we can use our schema to parse a
// document object directly from json.
// The document is a string, but we use the `json` macro
// from `serde_json` for the convenience of multi-line support.
let json = json!({
"title": "Of Mice and Men",
"body": "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
});
let mice_and_men_doc = schema.parse_document(&json.to_string())?;
index_writer.add_document(mice_and_men_doc);
// Multi-valued field are allowed, they are
// expressed in JSON by an array.
// The following document has two titles.
let json = json!({
"title": ["Frankenstein", "The Modern Prometheus"],
"body": "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
});
let frankenstein_doc = schema.parse_document(&json.to_string())?;
index_writer.add_document(frankenstein_doc);
// This is an example, so we will only index 3 documents
// here. You can check out tantivy's tutorial to index
// the English wikipedia. Tantivy's indexing is rather fast.
// Indexing 5 million articles of the English wikipedia takes
// around 4 minutes on my computer!
// ### Committing
//
// At this point our documents are not searchable.
//
//
// We need to call .commit() explicitly to force the
// index_writer to finish processing the documents in the queue,
// flush the current index to the disk, and advertise
// the existence of new documents.
//
// This call is blocking.
index_writer.commit()?;
// If `.commit()` returns correctly, then all of the
// documents that have been added are guaranteed to be
// persistently indexed.
//
// In the scenario of a crash or a power failure,
// tantivy behaves as if has rolled back to its last
// commit.
// # Searching
//
// Let's search our index. Start by reloading
// searchers in the index. This should be done
// after every commit().
index.load_searchers()?;
// Afterwards create one (or more) searchers.
//
// You should create a searcher
// every time you start a "search query".
let searcher = index.searcher();
// The query parser can interpret human queries.
// Here, if the user does not specify which
// field they want to search, tantivy will search
// in both title and body.
let query_parser = QueryParser::for_index(&index, vec![title, body]);
// QueryParser may fail if the query is not in the right
// format. For user facing applications, this can be a problem.
// A ticket has been opened regarding this problem.
let query = query_parser.parse_query("sea whale")?;
// A query defines a set of documents, as
// well as the way they should be scored.
//
// A query created by the query parser is scored according
// to a metric called Tf-Idf, and will consider
// any document matching at least one of our terms.
// ### Collectors
//
// We are not interested in all of the documents but
// only in the top 10. Keeping track of our top 10 best documents
// is the role of the TopCollector.
let mut top_collector = TopCollector::with_limit(10);
// We can now perform our query.
searcher.search(&*query, &mut top_collector)?;
// Our top collector now contains the 10
// most relevant doc ids...
let doc_addresses = top_collector.docs();
// The actual documents still need to be
// retrieved from Tantivy's store.
//
// Since the body field was not configured as stored,
// the document returned will only contain
// a title.
for doc_address in doc_addresses {
let retrieved_doc = searcher.doc(&doc_address)?;
println!("{}", schema.to_json(&retrieved_doc));
}
// Wait for indexing and merging threads to shut down.
// Usually this isn't needed, but in `main` we try to
// delete the temporary directory and that fails on
// Windows if the files are still open.
index_writer.wait_merging_threads()?;
Ok(())
}

82
examples/snippet.rs
View File

@@ -1,82 +0,0 @@
// # Snippet example
//
// This example shows how to return a representative snippet of
// your hit result.
// Snippet are an extracted of a target document, and returned in HTML format.
// The keyword searched by the user are highlighted with a `<b>` tag.
// ---
// Importing tantivy...
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::{doc, Index, Snippet, SnippetGenerator};
use tempfile::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new()?;
// # Defining the schema
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field("title", TEXT | STORED);
let body = schema_builder.add_text_field("body", TEXT | STORED);
let schema = schema_builder.build();
// # Indexing documents
let index = Index::create_in_dir(&index_path, schema.clone())?;
let mut index_writer = index.writer(50_000_000)?;
// we'll only need one doc for this example.
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
// ...
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let query_parser = QueryParser::for_index(&index, vec![title, body]);
let query = query_parser.parse_query("sycamore spring")?;
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
let snippet_generator = SnippetGenerator::create(&searcher, &*query, body)?;
for (score, doc_address) in top_docs {
let doc = searcher.doc(doc_address)?;
let snippet = snippet_generator.snippet_from_doc(&doc);
println!("Document score {}:", score);
println!("title: {}", doc.get_first(title).unwrap().text().unwrap());
println!("snippet: {}", snippet.to_html());
println!("custom highlighting: {}", highlight(snippet));
}
Ok(())
}
fn highlight(snippet: Snippet) -> String {
let mut result = String::new();
let mut start_from = 0;
for (start, end) in snippet.highlighted().iter().map(|h| h.bounds()) {
result.push_str(&snippet.fragments()[start_from..start]);
result.push_str(" --> ");
result.push_str(&snippet.fragments()[start..end]);
result.push_str(" <-- ");
start_from = end;
}
result.push_str(&snippet.fragments()[start_from..]);
result
}

113
examples/stop_words.rs
View File

@@ -1,113 +0,0 @@
// # Stop Words Example
//
// This example covers the basic usage of stop words
// with tantivy
//
// We will :
// - define our schema
// - create an index in a directory
// - add a few stop words
// - index few documents in our index
// ---
// Importing tantivy...
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::tokenizer::*;
use tantivy::{doc, Index};
fn main() -> tantivy::Result<()> {
// this example assumes you understand the content in `basic_search`
let mut schema_builder = Schema::builder();
// This configures your custom options for how tantivy will
// store and process your content in the index; The key
// to note is that we are setting the tokenizer to `stoppy`
// which will be defined and registered below.
let text_field_indexing = TextFieldIndexing::default()
.set_tokenizer("stoppy")
.set_index_option(IndexRecordOption::WithFreqsAndPositions);
let text_options = TextOptions::default()
.set_indexing_options(text_field_indexing)
.set_stored();
// Our first field is title.
schema_builder.add_text_field("title", text_options);
// Our second field is body.
let text_field_indexing = TextFieldIndexing::default()
.set_tokenizer("stoppy")
.set_index_option(IndexRecordOption::WithFreqsAndPositions);
let text_options = TextOptions::default()
.set_indexing_options(text_field_indexing)
.set_stored();
schema_builder.add_text_field("body", text_options);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
// This tokenizer lowers all of the text (to help with stop word matching)
// then removes all instances of `the` and `and` from the corpus
let tokenizer = TextAnalyzer::from(SimpleTokenizer)
.filter(LowerCaser)
.filter(StopWordFilter::remove(vec![
"the".to_string(),
"and".to_string(),
]));
index.tokenizers().register("stoppy", tokenizer);
let mut index_writer = index.writer(50_000_000)?;
let title = schema.get_field("title").unwrap();
let body = schema.get_field("body").unwrap();
index_writer.add_document(doc!(
title => "The Old Man and the Sea",
body => "He was an old man who fished alone in a skiff in the Gulf Stream and \
he had gone eighty-four days now without taking a fish."
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
index_writer.add_document(doc!(
title => "Frankenstein",
body => "You will rejoice to hear that no disaster has accompanied the commencement of an \
enterprise which you have regarded with such evil forebodings. I arrived here \
yesterday, and my first task is to assure my dear sister of my welfare and \
increasing confidence in the success of my undertaking."
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
let query_parser = QueryParser::for_index(&index, vec![title, body]);
// stop words are applied on the query as well.
// The following will be equivalent to `title:frankenstein`
let query = query_parser.parse_query("title:\"the Frankenstein\"")?;
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;
for (score, doc_address) in top_docs {
let retrieved_doc = searcher.doc(doc_address)?;
println!("\n==\nDocument score {}:", score);
println!("{}", schema.to_json(&retrieved_doc));
}
Ok(())
}

41
examples/working_with_json.rs
View File

@@ -1,41 +0,0 @@
use tantivy;
use tantivy::schema::*;
// # Document from json
//
// For convenience, `Document` can be parsed directly from json.
fn main() -> tantivy::Result<()> {
// Let's first define a schema and an index.
// Check out the basic example if this is confusing to you.
//
// first we need to define a schema ...
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("title", TEXT | STORED);
schema_builder.add_text_field("body", TEXT);
schema_builder.add_u64_field("year", INDEXED);
let schema = schema_builder.build();
// Let's assume we have a json-serialized document.
let mice_and_men_doc_json = r#"{
"title": "Of Mice and Men",
"year": 1937
}"#;
// We can parse our document
let _mice_and_men_doc = schema.parse_document(&mice_and_men_doc_json)?;
// Multi-valued field are allowed, they are
// expressed in JSON by an array.
// The following document has two titles.
let frankenstein_json = r#"{
"title": ["Frankenstein", "The Modern Prometheus"],
"year": 1818
}"#;
let _frankenstein_doc = schema.parse_document(&frankenstein_json)?;
// Note that the schema is saved in your index directory.
//
// As a result, Indexes are aware of their schema, and you can use this feature
// just by opening an existing `Index`, and calling `index.schema()..parse_document(json)`.
Ok(())
}

16
query-grammar/Cargo.toml
View File

@@ -1,16 +0,0 @@
[package]
name = "tantivy-query-grammar"
version = "0.13.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
homepage = "https://github.com/tantivy-search/tantivy"
repository = "https://github.com/tantivy-search/tantivy"
readme = "README.md"
keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
combine = {version="4", default-features=false, features=[] }

3
query-grammar/README.md
View File

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

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

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

58
query-grammar/src/occur.rs
View File

@@ -1,58 +0,0 @@
use std::fmt;
use std::fmt::Write;
/// Defines whether a term in a query must be present,
/// should be present or must be not present.
#[derive(Debug, Clone, Hash, Copy, Eq, PartialEq)]
pub enum Occur {
/// For a given document to be considered for scoring,
/// at least one of the document with the Should or the Must
/// Occur constraint must be within the document.
Should,
/// Document without the term are excluded from the search.
Must,
/// Document that contain the term are excluded from the
/// search.
MustNot,
}
impl Occur {
/// Returns the one-char prefix symbol for this `Occur`.
/// - `Should` => '?',
/// - `Must` => '+'
/// - `Not` => '-'
fn to_char(self) -> char {
match self {
Occur::Should => '?',
Occur::Must => '+',
Occur::MustNot => '-',
}
}
/// Compose two occur values.
pub fn compose(left: Occur, right: Occur) -> Occur {
match left {
Occur::Should => right,
Occur::Must => {
if right == Occur::MustNot {
Occur::MustNot
} else {
Occur::Must
}
}
Occur::MustNot => {
if right == Occur::MustNot {
Occur::Must
} else {
Occur::MustNot
}
}
}
}
}
impl fmt::Display for Occur {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
f.write_char(self.to_char())
}
}

510
query-grammar/src/query_grammar.rs
View File

@@ -1,510 +0,0 @@
use super::user_input_ast::{UserInputAST, UserInputBound, UserInputLeaf, UserInputLiteral};
use crate::Occur;
use combine::error::StringStreamError;
use combine::parser::char::{char, digit, letter, space, spaces, string};
use combine::parser::Parser;
use combine::{
attempt, choice, eof, many, many1, one_of, optional, parser, satisfy, skip_many1, value,
};
fn field<'a>() -> impl Parser<&'a str, Output = String> {
(
letter(),
many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
)
.skip(char(':'))
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
fn word<'a>() -> impl Parser<&'a str, Output = String> {
(
satisfy(|c: char| {
!c.is_whitespace()
&& !['-', '^', '`', ':', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
}),
many(satisfy(|c: char| {
!c.is_whitespace() && ![':', '^', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
})),
)
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
.and_then(|s: String| match s.as_str() {
"OR" | "AND " | "NOT" => Err(StringStreamError::UnexpectedParse),
_ => Ok(s),
})
}
fn term_val<'a>() -> impl Parser<&'a str, Output = String> {
let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
phrase.or(word())
}
fn term_query<'a>() -> impl Parser<&'a str, Output = UserInputLiteral> {
let term_val_with_field = negative_number().or(term_val());
(field(), term_val_with_field).map(|(field_name, phrase)| UserInputLiteral {
field_name: Some(field_name),
phrase,
})
}
fn literal<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let term_default_field = term_val().map(|phrase| UserInputLiteral {
field_name: None,
phrase,
});
attempt(term_query())
.or(term_default_field)
.map(UserInputLeaf::from)
}
fn negative_number<'a>() -> impl Parser<&'a str, Output = String> {
(
char('-'),
many1(digit()),
optional((char('.'), many1(digit()))),
)
.map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
if let Some(('.', s3)) = s3 {
format!("{}{}.{}", s1, s2, s3)
} else {
format!("{}{}", s1, s2)
}
})
}
fn spaces1<'a>() -> impl Parser<&'a str, Output = ()> {
skip_many1(space())
}
/// Function that parses a range out of a Stream
/// Supports ranges like:
/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
/// [a TO *], [a TO c], [abc TO bcd}
fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let range_term_val = || {
word()
.or(negative_number())
.or(char('*').with(value("*".to_string())))
};
// check for unbounded range in the form of <5, <=10, >5, >=5
let elastic_unbounded_range = (
choice([
attempt(string(">=")),
attempt(string("<=")),
attempt(string("<")),
attempt(string(">")),
])
.skip(spaces()),
range_term_val(),
)
.map(
|(comparison_sign, bound): (&str, String)| match comparison_sign {
">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
"<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
"<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
// default case
_ => (UserInputBound::Unbounded, UserInputBound::Unbounded),
},
);
let lower_bound = (one_of("{[".chars()), range_term_val()).map(
|(boundary_char, lower_bound): (char, String)| {
if lower_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '{' {
UserInputBound::Exclusive(lower_bound)
} else {
UserInputBound::Inclusive(lower_bound)
}
},
);
let upper_bound = (range_term_val(), one_of("}]".chars())).map(
|(higher_bound, boundary_char): (String, char)| {
if higher_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '}' {
UserInputBound::Exclusive(higher_bound)
} else {
UserInputBound::Inclusive(higher_bound)
}
},
);
// return only lower and upper
let lower_to_upper = (
lower_bound.skip((spaces(), string("TO"), spaces())),
upper_bound,
);
(
optional(field()).skip(spaces()),
// try elastic first, if it matches, the range is unbounded
attempt(elastic_unbounded_range).or(lower_to_upper),
)
.map(|(field, (lower, upper))|
// Construct the leaf from extracted field (optional)
// and bounds
UserInputLeaf::Range {
field,
lower,
upper
})
}
fn negate(expr: UserInputAST) -> UserInputAST {
expr.unary(Occur::MustNot)
}
fn leaf<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
parser(|input| {
char('(')
.with(ast())
.skip(char(')'))
.or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
.or(attempt(
string("NOT").skip(spaces1()).with(leaf()).map(negate),
))
.or(attempt(range().map(UserInputAST::from)))
.or(literal().map(UserInputAST::from))
.parse_stream(input)
.into_result()
})
}
fn occur_symbol<'a>() -> impl Parser<&'a str, Output = Occur> {
char('-')
.map(|_| Occur::MustNot)
.or(char('+').map(|_| Occur::Must))
}
fn occur_leaf<'a>() -> impl Parser<&'a str, Output = (Option<Occur>, UserInputAST)> {
(optional(occur_symbol()), boosted_leaf())
}
fn positive_float_number<'a>() -> impl Parser<&'a str, Output = f32> {
(many1(digit()), optional((char('.'), many1(digit())))).map(
|(int_part, decimal_part_opt): (String, Option<(char, String)>)| {
let mut float_str = int_part;
if let Some((chr, decimal_str)) = decimal_part_opt {
float_str.push(chr);
float_str.push_str(&decimal_str);
}
float_str.parse::<f32>().unwrap()
},
)
}
fn boost<'a>() -> impl Parser<&'a str, Output = f32> {
(char('^'), positive_float_number()).map(|(_, boost)| boost)
}
fn boosted_leaf<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
(leaf(), optional(boost())).map(|(leaf, boost_opt)| match boost_opt {
Some(boost) if (boost - 1.0).abs() > std::f32::EPSILON => {
UserInputAST::Boost(Box::new(leaf), boost)
}
_ => leaf,
})
}
#[derive(Clone, Copy)]
enum BinaryOperand {
Or,
And,
}
fn binary_operand<'a>() -> impl Parser<&'a str, Output = BinaryOperand> {
string("AND")
.with(value(BinaryOperand::And))
.or(string("OR").with(value(BinaryOperand::Or)))
}
fn aggregate_binary_expressions(
left: UserInputAST,
others: Vec<(BinaryOperand, UserInputAST)>,
) -> UserInputAST {
let mut dnf: Vec<Vec<UserInputAST>> = vec![vec![left]];
for (operator, operand_ast) in others {
match operator {
BinaryOperand::And => {
if let Some(last) = dnf.last_mut() {
last.push(operand_ast);
}
}
BinaryOperand::Or => {
dnf.push(vec![operand_ast]);
}
}
}
if dnf.len() == 1 {
UserInputAST::and(dnf.into_iter().next().unwrap()) //< safe
} else {
let conjunctions = dnf.into_iter().map(UserInputAST::and).collect();
UserInputAST::or(conjunctions)
}
}
fn operand_leaf<'a>() -> impl Parser<&'a str, Output = (BinaryOperand, UserInputAST)> {
(
binary_operand().skip(spaces()),
boosted_leaf().skip(spaces()),
)
}
pub fn ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
let boolean_expr = (boosted_leaf().skip(spaces()), many1(operand_leaf()))
.map(|(left, right)| aggregate_binary_expressions(left, right));
let whitespace_separated_leaves = many1(occur_leaf().skip(spaces().silent())).map(
|subqueries: Vec<(Option<Occur>, UserInputAST)>| {
if subqueries.len() == 1 {
let (occur_opt, ast) = subqueries.into_iter().next().unwrap();
match occur_opt.unwrap_or(Occur::Should) {
Occur::Must | Occur::Should => ast,
Occur::MustNot => UserInputAST::Clause(vec![(Some(Occur::MustNot), ast)]),
}
} else {
UserInputAST::Clause(subqueries.into_iter().collect())
}
},
);
let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
spaces().with(expr).skip(spaces())
}
pub fn parse_to_ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
spaces()
.with(optional(ast()).skip(eof()))
.map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
}
#[cfg(test)]
mod test {
use super::*;
use combine::parser::Parser;
pub fn nearly_equals(a: f32, b: f32) -> bool {
(a - b).abs() < 0.0005 * (a + b).abs()
}
fn assert_nearly_equals(expected: f32, val: f32) {
assert!(
nearly_equals(val, expected),
"Got {}, expected {}.",
val,
expected
);
}
#[test]
fn test_occur_symbol() {
assert_eq!(super::occur_symbol().parse("-"), Ok((Occur::MustNot, "")));
assert_eq!(super::occur_symbol().parse("+"), Ok((Occur::Must, "")));
}
#[test]
fn test_positive_float_number() {
fn valid_parse(float_str: &str, expected_val: f32, expected_remaining: &str) {
let (val, remaining) = positive_float_number().parse(float_str).unwrap();
assert_eq!(remaining, expected_remaining);
assert_nearly_equals(val, expected_val);
}
fn error_parse(float_str: &str) {
assert!(positive_float_number().parse(float_str).is_err());
}
valid_parse("1.0", 1.0f32, "");
valid_parse("1", 1.0f32, "");
valid_parse("0.234234 aaa", 0.234234f32, " aaa");
error_parse(".3332");
error_parse("1.");
error_parse("-1.");
}
fn test_parse_query_to_ast_helper(query: &str, expected: &str) {
let query = parse_to_ast().parse(query).unwrap().0;
let query_str = format!("{:?}", query);
assert_eq!(query_str, expected);
}
fn test_is_parse_err(query: &str) {
assert!(parse_to_ast().parse(query).is_err());
}
#[test]
fn test_parse_empty_to_ast() {
test_parse_query_to_ast_helper("", "<emptyclause>");
}
#[test]
fn test_parse_query_to_ast_hyphen() {
test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
}
#[test]
fn test_parse_query_to_ast_not_op() {
assert_eq!(
format!("{:?}", parse_to_ast().parse("NOT")),
"Err(UnexpectedParse)"
);
test_parse_query_to_ast_helper("NOTa", "\"NOTa\"");
test_parse_query_to_ast_helper("NOT a", "(-\"a\")");
}
#[test]
fn test_boosting() {
assert!(parse_to_ast().parse("a^2^3").is_err());
assert!(parse_to_ast().parse("a^2^").is_err());
test_parse_query_to_ast_helper("a^3", "(\"a\")^3");
test_parse_query_to_ast_helper("a^3 b^2", "(*(\"a\")^3 *(\"b\")^2)");
test_parse_query_to_ast_helper("a^1", "\"a\"");
}
#[test]
fn test_parse_query_to_ast_binary_op() {
test_parse_query_to_ast_helper("a AND b", "(+\"a\" +\"b\")");
test_parse_query_to_ast_helper("a OR b", "(?\"a\" ?\"b\")");
test_parse_query_to_ast_helper("a OR b AND c", "(?\"a\" ?(+\"b\" +\"c\"))");
test_parse_query_to_ast_helper("a AND b AND c", "(+\"a\" +\"b\" +\"c\")");
assert_eq!(
format!("{:?}", parse_to_ast().parse("a OR b aaa")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("a AND b aaa")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("aaa a OR b ")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("aaa ccc a OR b ")),
"Err(UnexpectedParse)"
);
}
#[test]
fn test_parse_elastic_query_ranges() {
test_parse_query_to_ast_helper("title: >a", "title:{\"a\" TO \"*\"}");
test_parse_query_to_ast_helper("title:>=a", "title:[\"a\" TO \"*\"}");
test_parse_query_to_ast_helper("title: <a", "title:{\"*\" TO \"a\"}");
test_parse_query_to_ast_helper("title:<=a", "title:{\"*\" TO \"a\"]");
test_parse_query_to_ast_helper("title:<=bsd", "title:{\"*\" TO \"bsd\"]");
test_parse_query_to_ast_helper("weight: >70", "weight:{\"70\" TO \"*\"}");
test_parse_query_to_ast_helper("weight:>=70", "weight:[\"70\" TO \"*\"}");
test_parse_query_to_ast_helper("weight: <70", "weight:{\"*\" TO \"70\"}");
test_parse_query_to_ast_helper("weight:<=70", "weight:{\"*\" TO \"70\"]");
test_parse_query_to_ast_helper("weight: >60.7", "weight:{\"60.7\" TO \"*\"}");
test_parse_query_to_ast_helper("weight: <= 70", "weight:{\"*\" TO \"70\"]");
test_parse_query_to_ast_helper("weight: <= 70.5", "weight:{\"*\" TO \"70.5\"]");
}
#[test]
fn test_occur_leaf() {
let ((occur, ast), _) = super::occur_leaf().parse("+abc").unwrap();
assert_eq!(occur, Some(Occur::Must));
assert_eq!(format!("{:?}", ast), "\"abc\"");
}
#[test]
fn test_range_parser() {
// testing the range() parser separately
let res = range().parse("title: <hello").unwrap().0;
let expected = UserInputLeaf::Range {
field: Some("title".to_string()),
lower: UserInputBound::Unbounded,
upper: UserInputBound::Exclusive("hello".to_string()),
};
let res2 = range().parse("title:{* TO hello}").unwrap().0;
assert_eq!(res, expected);
assert_eq!(res2, expected);
let expected_weight = UserInputLeaf::Range {
field: Some("weight".to_string()),
lower: UserInputBound::Inclusive("71.2".to_string()),
upper: UserInputBound::Unbounded,
};
let res3 = range().parse("weight: >=71.2").unwrap().0;
let res4 = range().parse("weight:[71.2 TO *}").unwrap().0;
assert_eq!(res3, expected_weight);
assert_eq!(res4, expected_weight);
}
#[test]
fn test_parse_query_to_triming_spaces() {
test_parse_query_to_ast_helper(" abc", "\"abc\"");
test_parse_query_to_ast_helper("abc ", "\"abc\"");
test_parse_query_to_ast_helper("( a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("a OR abc ", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc )", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc) ", "(?\"a\" ?\"abc\")");
}
#[test]
fn test_parse_query_single_term() {
test_parse_query_to_ast_helper("abc", "\"abc\"");
}
#[test]
fn test_parse_query_default_clause() {
test_parse_query_to_ast_helper("a b", "(*\"a\" *\"b\")");
}
#[test]
fn test_parse_query_must_default_clause() {
test_parse_query_to_ast_helper("+(a b)", "(*\"a\" *\"b\")");
}
#[test]
fn test_parse_query_must_single_term() {
test_parse_query_to_ast_helper("+d", "\"d\"");
}
#[test]
fn test_single_term_with_field() {
test_parse_query_to_ast_helper("abc:toto", "abc:\"toto\"");
}
#[test]
fn test_single_term_with_float() {
test_parse_query_to_ast_helper("abc:1.1", "abc:\"1.1\"");
}
#[test]
fn test_must_clause() {
test_parse_query_to_ast_helper("(+a +b)", "(+\"a\" +\"b\")");
}
#[test]
fn test_parse_test_query_plus_a_b_plus_d() {
test_parse_query_to_ast_helper("+(a b) +d", "(+(*\"a\" *\"b\") +\"d\")");
}
#[test]
fn test_parse_test_query_other() {
test_parse_query_to_ast_helper("(+a +b) d", "(*(+\"a\" +\"b\") *\"d\")");
test_parse_query_to_ast_helper("+abc:toto", "abc:\"toto\"");
test_parse_query_to_ast_helper("(+abc:toto -titi)", "(+abc:\"toto\" -\"titi\")");
test_parse_query_to_ast_helper("-abc:toto", "(-abc:\"toto\")");
test_parse_query_to_ast_helper("abc:a b", "(*abc:\"a\" *\"b\")");
test_parse_query_to_ast_helper("abc:\"a b\"", "abc:\"a b\"");
test_parse_query_to_ast_helper("foo:[1 TO 5]", "foo:[\"1\" TO \"5\"]");
}
#[test]
fn test_parse_query_with_range() {
test_parse_query_to_ast_helper("[1 TO 5]", "[\"1\" TO \"5\"]");
test_parse_query_to_ast_helper("foo:{a TO z}", "foo:{\"a\" TO \"z\"}");
test_parse_query_to_ast_helper("foo:[1 TO toto}", "foo:[\"1\" TO \"toto\"}");
test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:{\"*\" TO \"toto\"}");
test_parse_query_to_ast_helper("foo:[1 TO *}", "foo:[\"1\" TO \"*\"}");
test_parse_query_to_ast_helper("foo:[1.1 TO *}", "foo:[\"1.1\" TO \"*\"}");
test_is_parse_err("abc + ");
}
}

171
query-grammar/src/user_input_ast.rs
View File

@@ -1,171 +0,0 @@
use std::fmt;
use std::fmt::{Debug, Formatter};
use crate::Occur;
#[derive(PartialEq)]
pub enum UserInputLeaf {
Literal(UserInputLiteral),
All,
Range {
field: Option<String>,
lower: UserInputBound,
upper: UserInputBound,
},
}
impl Debug for UserInputLeaf {
fn fmt(&self, formatter: &mut Formatter<'_>) -> Result<(), fmt::Error> {
match self {
UserInputLeaf::Literal(literal) => literal.fmt(formatter),
UserInputLeaf::Range {
ref field,
ref lower,
ref upper,
} => {
if let Some(ref field) = field {
write!(formatter, "{}:", field)?;
}
lower.display_lower(formatter)?;
write!(formatter, " TO ")?;
upper.display_upper(formatter)?;
Ok(())
}
UserInputLeaf::All => write!(formatter, "*"),
}
}
}
#[derive(PartialEq)]
pub struct UserInputLiteral {
pub field_name: Option<String>,
pub phrase: String,
}
impl fmt::Debug for UserInputLiteral {
fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
match self.field_name {
Some(ref field_name) => write!(formatter, "{}:\"{}\"", field_name, self.phrase),
None => write!(formatter, "\"{}\"", self.phrase),
}
}
}
#[derive(PartialEq)]
pub enum UserInputBound {
Inclusive(String),
Exclusive(String),
Unbounded,
}
impl UserInputBound {
fn display_lower(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
match *self {
UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word),
UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word),
UserInputBound::Unbounded => write!(formatter, "{{\"*\""),
}
}
fn display_upper(&self, formatter: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
match *self {
UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word),
UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word),
UserInputBound::Unbounded => write!(formatter, "\"*\"}}"),
}
}
pub fn term_str(&self) -> &str {
match *self {
UserInputBound::Inclusive(ref contents) => contents,
UserInputBound::Exclusive(ref contents) => contents,
UserInputBound::Unbounded => &"*",
}
}
}
pub enum UserInputAST {
Clause(Vec<(Option<Occur>, UserInputAST)>),
Leaf(Box<UserInputLeaf>),
Boost(Box<UserInputAST>, f32),
}
impl UserInputAST {
pub fn unary(self, occur: Occur) -> UserInputAST {
UserInputAST::Clause(vec![(Some(occur), self)])
}
fn compose(occur: Occur, asts: Vec<UserInputAST>) -> UserInputAST {
assert_ne!(occur, Occur::MustNot);
assert!(!asts.is_empty());
if asts.len() == 1 {
asts.into_iter().next().unwrap() //< safe
} else {
UserInputAST::Clause(
asts.into_iter()
.map(|ast: UserInputAST| (Some(occur), ast))
.collect::<Vec<_>>(),
)
}
}
pub fn empty_query() -> UserInputAST {
UserInputAST::Clause(Vec::default())
}
pub fn and(asts: Vec<UserInputAST>) -> UserInputAST {
UserInputAST::compose(Occur::Must, asts)
}
pub fn or(asts: Vec<UserInputAST>) -> UserInputAST {
UserInputAST::compose(Occur::Should, asts)
}
}
impl From<UserInputLiteral> for UserInputLeaf {
fn from(literal: UserInputLiteral) -> UserInputLeaf {
UserInputLeaf::Literal(literal)
}
}
impl From<UserInputLeaf> for UserInputAST {
fn from(leaf: UserInputLeaf) -> UserInputAST {
UserInputAST::Leaf(Box::new(leaf))
}
}
fn print_occur_ast(
occur_opt: Option<Occur>,
ast: &UserInputAST,
formatter: &mut fmt::Formatter,
) -> fmt::Result {
if let Some(occur) = occur_opt {
write!(formatter, "{}{:?}", occur, ast)?;
} else {
write!(formatter, "*{:?}", ast)?;
}
Ok(())
}
impl fmt::Debug for UserInputAST {
fn fmt(&self, formatter: &mut fmt::Formatter) -> fmt::Result {
match *self {
UserInputAST::Clause(ref subqueries) => {
if subqueries.is_empty() {
write!(formatter, "<emptyclause>")?;
} else {
write!(formatter, "(")?;
print_occur_ast(subqueries[0].0, &subqueries[0].1, formatter)?;
for subquery in &subqueries[1..] {
write!(formatter, " ")?;
print_occur_ast(subquery.0, &subquery.1, formatter)?;
}
write!(formatter, ")")?;
}
Ok(())
}
UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
UserInputAST::Boost(ref leaf, boost) => write!(formatter, "({:?})^{}", leaf, boost),
}
}
}

2
run-tests.sh
View File

@@ -1,2 +0,0 @@
#!/bin/bash
cargo test

91
src/collector/chained_collector.rs Normal file
View File

@@ -0,0 +1,91 @@
use Result;
use collector::Collector;
use SegmentLocalId;
use SegmentReader;
use DocId;
use Score;
/// Collector that does nothing.
/// This is used in the chain Collector and will hopefully
/// be optimized away by the compiler.
pub struct DoNothingCollector;
impl Collector for DoNothingCollector {
#[inline]
fn set_segment(&mut self, _: SegmentLocalId, _: &SegmentReader) -> Result<()> {
Ok(())
}
#[inline]
fn collect(&mut self, _doc: DocId, _score: Score) {}
#[inline]
fn requires_scoring(&self) -> bool {
false
}
}
/// Zero-cost abstraction used to collect on multiple collectors.
/// This contraption is only usable if the type of your collectors
/// are known at compile time.
pub struct ChainedCollector<Left: Collector, Right: Collector> {
left: Left,
right: Right,
}
impl<Left: Collector, Right: Collector> ChainedCollector<Left, Right> {
/// Adds a collector
pub fn push<C: Collector>(self, new_collector: &mut C) -> ChainedCollector<Self, &mut C> {
ChainedCollector {
left: self,
right: new_collector,
}
}
}
impl<Left: Collector, Right: Collector> Collector for ChainedCollector<Left, Right> {
fn set_segment(
&mut self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> Result<()> {
self.left.set_segment(segment_local_id, segment)?;
self.right.set_segment(segment_local_id, segment)?;
Ok(())
}
fn collect(&mut self, doc: DocId, score: Score) {
self.left.collect(doc, score);
self.right.collect(doc, score);
}
fn requires_scoring(&self) -> bool {
self.left.requires_scoring() || self.right.requires_scoring()
}
}
/// Creates a `ChainedCollector`
pub fn chain() -> ChainedCollector<DoNothingCollector, DoNothingCollector> {
ChainedCollector {
left: DoNothingCollector,
right: DoNothingCollector,
}
}
#[cfg(test)]
mod tests {
use super::*;
use collector::{Collector, CountCollector, TopCollector};
#[test]
fn test_chained_collector() {
let mut top_collector = TopCollector::with_limit(2);
let mut count_collector = CountCollector::default();
{
let mut collectors = chain().push(&mut top_collector).push(&mut count_collector);
collectors.collect(1, 0.2);
collectors.collect(2, 0.1);
collectors.collect(3, 0.5);
}
assert_eq!(count_collector.count(), 3);
assert!(top_collector.at_capacity());
}
}

122
src/collector/count_collector.rs
View File

@@ -1,114 +1,54 @@
use super::Collector;
use crate::collector::SegmentCollector;
use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use DocId;
use Score;
use Result;
use SegmentReader;
use SegmentLocalId;
/// `CountCollector` collector only counts how many
/// documents match the query.
///
/// ```rust
/// use tantivy::collector::Count;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer(3_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// // Here comes the important part
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let count = searcher.search(&query, &Count).unwrap();
///
/// assert_eq!(count, 2);
/// ```
pub struct Count;
impl Collector for Count {
type Fruit = usize;
type Child = SegmentCountCollector;
fn for_segment(
&self,
_: SegmentLocalId,
_: &SegmentReader,
) -> crate::Result<SegmentCountCollector> {
Ok(SegmentCountCollector::default())
}
fn requires_scoring(&self) -> bool {
false
}
fn merge_fruits(&self, segment_counts: Vec<usize>) -> crate::Result<usize> {
Ok(segment_counts.into_iter().sum())
}
}
#[derive(Default)]
pub struct SegmentCountCollector {
pub struct CountCollector {
count: usize,
}
impl SegmentCollector for SegmentCountCollector {
type Fruit = usize;
impl CountCollector {
/// Returns the count of documents that were
/// collected.
pub fn count(&self) -> usize {
self.count
}
}
impl Collector for CountCollector {
fn set_segment(&mut self, _: SegmentLocalId, _: &SegmentReader) -> Result<()> {
Ok(())
}
fn collect(&mut self, _: DocId, _: Score) {
self.count += 1;
}
fn harvest(self) -> usize {
self.count
fn requires_scoring(&self) -> bool {
false
}
}
#[cfg(test)]
mod tests {
use super::{Count, SegmentCountCollector};
use crate::collector::Collector;
use crate::collector::SegmentCollector;
use collector::{Collector, CountCollector};
#[test]
fn test_count_collect_does_not_requires_scoring() {
assert!(!Count.requires_scoring());
fn test_count_collector() {
let mut count_collector = CountCollector::default();
assert_eq!(count_collector.count(), 0);
count_collector.collect(0u32, 1f32);
assert_eq!(count_collector.count(), 1);
assert_eq!(count_collector.count(), 1);
count_collector.collect(1u32, 1f32);
assert_eq!(count_collector.count(), 2);
assert!(!count_collector.requires_scoring());
}
#[test]
fn test_segment_count_collector() {
{
let count_collector = SegmentCountCollector::default();
assert_eq!(count_collector.harvest(), 0);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1f32);
assert_eq!(count_collector.harvest(), 1);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1f32);
assert_eq!(count_collector.harvest(), 1);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1f32);
count_collector.collect(1u32, 1f32);
assert_eq!(count_collector.harvest(), 2);
}
}
}

125
src/collector/custom_score_top_collector.rs
View File

@@ -1,125 +0,0 @@
use crate::collector::top_collector::{TopCollector, TopSegmentCollector};
use crate::collector::{Collector, SegmentCollector};
use crate::{DocAddress, DocId, Score, SegmentReader};
pub(crate) struct CustomScoreTopCollector<TCustomScorer, TScore = Score> {
custom_scorer: TCustomScorer,
collector: TopCollector<TScore>,
}
impl<TCustomScorer, TScore> CustomScoreTopCollector<TCustomScorer, TScore>
where
TScore: Clone + PartialOrd,
{
pub(crate) fn new(
custom_scorer: TCustomScorer,
collector: TopCollector<TScore>,
) -> CustomScoreTopCollector<TCustomScorer, TScore> {
CustomScoreTopCollector {
custom_scorer,
collector,
}
}
}
/// A custom segment scorer makes it possible to define any kind of score
/// for a given document belonging to a specific segment.
///
/// It is the segment local version of the [`CustomScorer`](./trait.CustomScorer.html).
pub trait CustomSegmentScorer<TScore>: 'static {
/// Computes the score of a specific `doc`.
fn score(&mut self, doc: DocId) -> TScore;
}
/// `CustomScorer` makes it possible to define any kind of score.
///
/// The `CustomerScorer` itself does not make much of the computation itself.
/// Instead, it helps constructing `Self::Child` instances that will compute
/// the score at a segment scale.
pub trait CustomScorer<TScore>: Sync {
/// Type of the associated [`CustomSegmentScorer`](./trait.CustomSegmentScorer.html).
type Child: CustomSegmentScorer<TScore>;
/// Builds a child scorer for a specific segment. The child scorer is associated to
/// a specific segment.
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child>;
}
impl<TCustomScorer, TScore> Collector for CustomScoreTopCollector<TCustomScorer, TScore>
where
TCustomScorer: CustomScorer<TScore>,
TScore: 'static + PartialOrd + Clone + Send + Sync,
{
type Fruit = Vec<(TScore, DocAddress)>;
type Child = CustomScoreTopSegmentCollector<TCustomScorer::Child, TScore>;
fn for_segment(
&self,
segment_local_id: u32,
segment_reader: &SegmentReader,
) -> crate::Result<Self::Child> {
let segment_scorer = self.custom_scorer.segment_scorer(segment_reader)?;
let segment_collector = self
.collector
.for_segment(segment_local_id, segment_reader)?;
Ok(CustomScoreTopSegmentCollector {
segment_collector,
segment_scorer,
})
}
fn requires_scoring(&self) -> bool {
false
}
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
self.collector.merge_fruits(segment_fruits)
}
}
pub struct CustomScoreTopSegmentCollector<T, TScore>
where
TScore: 'static + PartialOrd + Clone + Send + Sync + Sized,
T: CustomSegmentScorer<TScore>,
{
segment_collector: TopSegmentCollector<TScore>,
segment_scorer: T,
}
impl<T, TScore> SegmentCollector for CustomScoreTopSegmentCollector<T, TScore>
where
TScore: 'static + PartialOrd + Clone + Send + Sync,
T: 'static + CustomSegmentScorer<TScore>,
{
type Fruit = Vec<(TScore, DocAddress)>;
fn collect(&mut self, doc: DocId, _score: Score) {
let score = self.segment_scorer.score(doc);
self.segment_collector.collect(doc, score);
}
fn harvest(self) -> Vec<(TScore, DocAddress)> {
self.segment_collector.harvest()
}
}
impl<F, TScore, T> CustomScorer<TScore> for F
where
F: 'static + Send + Sync + Fn(&SegmentReader) -> T,
T: CustomSegmentScorer<TScore>,
{
type Child = T;
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
Ok((self)(segment_reader))
}
}
impl<F, TScore> CustomSegmentScorer<TScore> for F
where
F: 'static + FnMut(DocId) -> TScore,
{
fn score(&mut self, doc: DocId) -> TScore {
(self)(doc)
}
}

548
src/collector/facet_collector.rs
View File

@@ -1,21 +1,27 @@
use crate::collector::Collector;
use crate::collector::SegmentCollector;
use crate::fastfield::FacetReader;
use crate::schema::Facet;
use crate::schema::Field;
use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use crate::TantivyError;
use std::cmp::Ordering;
use std::collections::btree_map;
use std::mem;
use collector::Collector;
use fastfield::FacetReader;
use schema::Field;
use std::cell::UnsafeCell;
use schema::Facet;
use std::collections::BTreeMap;
use std::collections::BTreeSet;
use std::collections::BinaryHeap;
use std::collections::Bound;
use termdict::TermDictionary;
use termdict::TermStreamer;
use termdict::TermStreamerBuilder;
use std::collections::BTreeSet;
use termdict::TermMerger;
use docset::SkipResult;
use std::{usize, u64};
use std::iter::Peekable;
use std::{u64, usize};
use DocId;
use Result;
use Score;
use SegmentReader;
use SegmentLocalId;
use std::cmp::Ordering;
struct Hit<'a> {
count: u64,
@@ -25,13 +31,13 @@ struct Hit<'a> {
impl<'a> Eq for Hit<'a> {}
impl<'a> PartialEq<Hit<'a>> for Hit<'a> {
fn eq(&self, other: &Hit<'_>) -> bool {
fn eq(&self, other: &Hit) -> bool {
self.count == other.count
}
}
impl<'a> PartialOrd<Hit<'a>> for Hit<'a> {
fn partial_cmp(&self, other: &Hit<'_>) -> Option<Ordering> {
fn partial_cmp(&self, other: &Hit) -> Option<Ordering> {
Some(self.cmp(other))
}
}
@@ -42,6 +48,12 @@ impl<'a> Ord for Hit<'a> {
}
}
struct SegmentFacetCounter {
pub facet_reader: FacetReader,
pub facet_ords: Vec<u64>,
pub facet_counts: Vec<u64>,
}
fn facet_depth(facet_bytes: &[u8]) -> usize {
if facet_bytes.is_empty() {
0
@@ -79,13 +91,16 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Facet, SchemaBuilder, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::FacetCollector;
/// use tantivy::query::AllQuery;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{doc, Index};
///
/// fn example() -> tantivy::Result<()> {
/// let mut schema_builder = Schema::builder();
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = SchemaBuilder::new();
///
/// // Facet have their own specific type.
/// // It is not a bad practise to put all of your
@@ -118,19 +133,23 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// facet => Facet::from("/lang/en"),
/// facet => Facet::from("/category/biography")
/// ));
/// index_writer.commit()?;
/// index_writer.commit().unwrap();
/// }
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
///
/// index.load_searchers()?;
/// let searcher = index.searcher();
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/lang");
/// facet_collector.add_facet("/category");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
/// searcher.search(&AllQuery, &mut facet_collector).unwrap();
///
/// // this object contains count aggregate for all of the facets.
/// let counts = facet_collector.harvest();
///
/// // This lists all of the facet counts
/// let facets: Vec<(&Facet, u64)> = facet_counts
/// let facets: Vec<(&Facet, u64)> = counts
/// .get("/category")
/// .collect();
/// assert_eq!(facets, vec![
@@ -140,12 +159,15 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// }
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/category/fiction");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
/// searcher.search(&AllQuery, &mut facet_collector).unwrap();
///
/// // this object contains count aggregate for all of the facets.
/// let counts = facet_collector.harvest();
///
/// // This lists all of the facet counts
/// let facets: Vec<(&Facet, u64)> = facet_counts
/// let facets: Vec<(&Facet, u64)> = counts
/// .get("/category/fiction")
/// .collect();
/// assert_eq!(facets, vec![
@@ -155,13 +177,16 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// ]);
/// }
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/category/fiction");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
/// searcher.search(&AllQuery, &mut facet_collector).unwrap();
///
/// // this object contains count aggregate for all of the facets.
/// let counts = facet_collector.harvest();
///
/// // This lists all of the facet counts
/// let facets: Vec<(&Facet, u64)> = facet_counts.top_k("/category/fiction", 1);
/// let facets: Vec<(&Facet, u64)> = counts.top_k("/category/fiction", 1);
/// assert_eq!(facets, vec![
/// (&Facet::from("/category/fiction/fantasy"), 2)
/// ]);
@@ -169,27 +194,21 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
/// Ok(())
/// }
/// # assert!(example().is_ok());
/// ```
pub struct FacetCollector {
facet_ords: Vec<u64>,
field: Field,
facets: BTreeSet<Facet>,
}
ff_reader: Option<UnsafeCell<FacetReader>>,
segment_counters: Vec<SegmentFacetCounter>,
pub struct FacetSegmentCollector {
reader: FacetReader,
facet_ords_buf: Vec<u64>,
// facet_ord -> collapse facet_id
collapse_mapping: Vec<usize>,
current_segment_collapse_mapping: Vec<usize>,
// collapse facet_id -> count
counts: Vec<u64>,
current_segment_counts: Vec<u64>,
// collapse facet_id -> facet_ord
collapse_facet_ords: Vec<u64>,
}
current_collapse_facet_ords: Vec<u64>,
enum SkipResult {
Found,
NotFound,
facets: BTreeSet<Facet>,
}
fn skip<'a, I: Iterator<Item = &'a Facet>>(
@@ -198,17 +217,17 @@ fn skip<'a, I: Iterator<Item = &'a Facet>>(
) -> SkipResult {
loop {
match collapse_it.peek() {
Some(facet_bytes) => match facet_bytes.encoded_str().as_bytes().cmp(target) {
Some(facet_bytes) => match facet_bytes.encoded_bytes().cmp(target) {
Ordering::Less => {}
Ordering::Greater => {
return SkipResult::NotFound;
return SkipResult::OverStep;
}
Ordering::Equal => {
return SkipResult::Found;
return SkipResult::Reached;
}
},
None => {
return SkipResult::NotFound;
return SkipResult::End;
}
}
collapse_it.next();
@@ -223,8 +242,15 @@ impl FacetCollector {
/// is of the proper type.
pub fn for_field(field: Field) -> FacetCollector {
FacetCollector {
facet_ords: Vec::with_capacity(255),
segment_counters: Vec::new(),
field,
facets: BTreeSet::default(),
ff_reader: None,
facets: BTreeSet::new(),
current_segment_collapse_mapping: Vec::new(),
current_collapse_facet_ords: Vec::new(),
current_segment_counts: Vec::new(),
}
}
@@ -254,103 +280,139 @@ impl FacetCollector {
}
self.facets.insert(facet);
}
}
impl Collector for FacetCollector {
type Fruit = FacetCounts;
type Child = FacetSegmentCollector;
fn for_segment(
&self,
_: SegmentLocalId,
reader: &SegmentReader,
) -> crate::Result<FacetSegmentCollector> {
let field_name = reader.schema().get_field_name(self.field);
let facet_reader = reader.facet_reader(self.field).ok_or_else(|| {
TantivyError::SchemaError(format!("Field {:?} is not a facet field.", field_name))
})?;
let mut collapse_mapping = Vec::new();
let mut counts = Vec::new();
let mut collapse_facet_ords = Vec::new();
fn set_collapse_mapping(&mut self, facet_reader: &FacetReader) {
self.current_segment_collapse_mapping.clear();
self.current_collapse_facet_ords.clear();
self.current_segment_counts.clear();
let mut collapse_facet_it = self.facets.iter().peekable();
collapse_facet_ords.push(0);
{
let mut facet_streamer = facet_reader.facet_dict().range().into_stream();
if facet_streamer.advance() {
'outer: loop {
// at the begining of this loop, facet_streamer
// is positionned on a term that has not been processed yet.
let skip_result = skip(facet_streamer.key(), &mut collapse_facet_it);
match skip_result {
SkipResult::Found => {
// we reach a facet we decided to collapse.
let collapse_depth = facet_depth(facet_streamer.key());
let mut collapsed_id = 0;
collapse_mapping.push(0);
while facet_streamer.advance() {
let depth = facet_depth(facet_streamer.key());
if depth <= collapse_depth {
continue 'outer;
}
if depth == collapse_depth + 1 {
collapsed_id = collapse_facet_ords.len();
collapse_facet_ords.push(facet_streamer.term_ord());
collapse_mapping.push(collapsed_id);
} else {
collapse_mapping.push(collapsed_id);
}
}
break;
self.current_collapse_facet_ords.push(0);
let mut facet_streamer = facet_reader.facet_dict().range().into_stream();
if !facet_streamer.advance() {
return;
}
'outer: loop {
// at the begining of this loop, facet_streamer
// is positionned on a term that has not been processed yet.
let skip_result = skip(facet_streamer.key(), &mut collapse_facet_it);
match skip_result {
SkipResult::Reached => {
// we reach a facet we decided to collapse.
let collapse_depth = facet_depth(facet_streamer.key());
let mut collapsed_id = 0;
self.current_segment_collapse_mapping.push(0);
while facet_streamer.advance() {
let depth = facet_depth(facet_streamer.key());
if depth <= collapse_depth {
continue 'outer;
}
SkipResult::NotFound => {
collapse_mapping.push(0);
if !facet_streamer.advance() {
break;
}
if depth == collapse_depth + 1 {
collapsed_id = self.current_collapse_facet_ords.len();
self.current_collapse_facet_ords
.push(facet_streamer.term_ord());
self.current_segment_collapse_mapping.push(collapsed_id);
} else {
self.current_segment_collapse_mapping.push(collapsed_id);
}
}
break;
}
SkipResult::End | SkipResult::OverStep => {
self.current_segment_collapse_mapping.push(0);
if !facet_streamer.advance() {
break;
}
}
}
}
counts.resize(collapse_facet_ords.len(), 0);
Ok(FacetSegmentCollector {
reader: facet_reader,
facet_ords_buf: Vec::with_capacity(255),
collapse_mapping,
counts,
collapse_facet_ords,
})
}
fn requires_scoring(&self) -> bool {
false
fn finalize_segment(&mut self) {
if self.ff_reader.is_some() {
self.segment_counters.push(SegmentFacetCounter {
facet_reader: self.ff_reader.take().unwrap().into_inner(),
facet_ords: mem::replace(&mut self.current_collapse_facet_ords, Vec::new()),
facet_counts: mem::replace(&mut self.current_segment_counts, Vec::new()),
});
}
}
fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> crate::Result<FacetCounts> {
let mut facet_counts: BTreeMap<Facet, u64> = BTreeMap::new();
for segment_facet_counts in segments_facet_counts {
for (facet, count) in segment_facet_counts.facet_counts {
*(facet_counts.entry(facet).or_insert(0)) += count;
/// Returns the results of the collection.
///
/// This method does not just return the counters,
/// it also translates the facet ordinals of the last segment.
pub fn harvest(mut self) -> FacetCounts {
self.finalize_segment();
let collapsed_facet_ords: Vec<&[u64]> = self.segment_counters
.iter()
.map(|segment_counter| &segment_counter.facet_ords[..])
.collect();
let collapsed_facet_counts: Vec<&[u64]> = self.segment_counters
.iter()
.map(|segment_counter| &segment_counter.facet_counts[..])
.collect();
let facet_streams = self.segment_counters
.iter()
.map(|seg_counts| seg_counts.facet_reader.facet_dict().range().into_stream())
.collect::<Vec<_>>();
let mut facet_merger = TermMerger::new(facet_streams);
let mut facet_counts = BTreeMap::new();
while facet_merger.advance() {
let count = facet_merger
.current_kvs()
.iter()
.map(|it| {
let seg_ord = it.segment_ord;
let term_ord = it.streamer.term_ord();
collapsed_facet_ords[seg_ord]
.binary_search(&term_ord)
.map(|collapsed_term_id| {
if collapsed_term_id == 0 {
0
} else {
collapsed_facet_counts[seg_ord][collapsed_term_id]
}
})
.unwrap_or(0)
})
.sum();
if count > 0u64 {
let bytes = facet_merger.key().to_owned();
facet_counts.insert(Facet::from_encoded(bytes), count);
}
}
Ok(FacetCounts { facet_counts })
FacetCounts { facet_counts }
}
}
impl SegmentCollector for FacetSegmentCollector {
type Fruit = FacetCounts;
impl Collector for FacetCollector {
fn set_segment(&mut self, _: SegmentLocalId, reader: &SegmentReader) -> Result<()> {
self.finalize_segment();
let facet_reader = reader.facet_reader(self.field)?;
self.set_collapse_mapping(&facet_reader);
self.current_segment_counts
.resize(self.current_collapse_facet_ords.len(), 0);
self.ff_reader = Some(UnsafeCell::new(facet_reader));
Ok(())
}
fn collect(&mut self, doc: DocId, _: Score) {
self.reader.facet_ords(doc, &mut self.facet_ords_buf);
let facet_reader: &mut FacetReader = unsafe {
&mut *self.ff_reader
.as_ref()
.expect("collect() was called before set_segment. This should never happen.")
.get()
};
facet_reader.facet_ords(doc, &mut self.facet_ords);
let mut previous_collapsed_ord: usize = usize::MAX;
for &facet_ord in &self.facet_ords_buf {
let collapsed_ord = self.collapse_mapping[facet_ord as usize];
self.counts[collapsed_ord] += if collapsed_ord == previous_collapsed_ord {
for &facet_ord in &self.facet_ords {
let collapsed_ord = self.current_segment_collapse_mapping[facet_ord as usize];
self.current_segment_counts[collapsed_ord] += if collapsed_ord == previous_collapsed_ord
{
0
} else {
1
@@ -359,24 +421,8 @@ impl SegmentCollector for FacetSegmentCollector {
}
}
/// Returns the results of the collection.
///
/// This method does not just return the counters,
/// it also translates the facet ordinals of the last segment.
fn harvest(self) -> FacetCounts {
let mut facet_counts = BTreeMap::new();
let facet_dict = self.reader.facet_dict();
for (collapsed_facet_ord, count) in self.counts.iter().cloned().enumerate() {
if count == 0 {
continue;
}
let mut facet = vec![];
let facet_ord = self.collapse_facet_ords[collapsed_facet_ord];
facet_dict.ord_to_term(facet_ord as u64, &mut facet);
// TODO
facet_counts.insert(Facet::from_encoded(facet).unwrap(), count);
}
FacetCounts { facet_counts }
fn requires_scoring(&self) -> bool {
false
}
}
@@ -386,20 +432,9 @@ pub struct FacetCounts {
facet_counts: BTreeMap<Facet, u64>,
}
pub struct FacetChildIterator<'a> {
underlying: btree_map::Range<'a, Facet, u64>,
}
impl<'a> Iterator for FacetChildIterator<'a> {
type Item = (&'a Facet, u64);
fn next(&mut self) -> Option<Self::Item> {
self.underlying.next().map(|(facet, count)| (facet, *count))
}
}
impl FacetCounts {
pub fn get<T>(&self, facet_from: T) -> FacetChildIterator<'_>
#[allow(needless_lifetimes)] //< compiler fails if we remove the lifetime
pub fn get<'a, T>(&'a self, facet_from: T) -> impl Iterator<Item = (&'a Facet, u64)>
where
Facet: From<T>,
{
@@ -408,14 +443,15 @@ impl FacetCounts {
let right_bound = if facet.is_root() {
Bound::Unbounded
} else {
let mut facet_after_bytes: String = facet.encoded_str().to_owned();
facet_after_bytes.push('\u{1}');
let facet_after = Facet::from_encoded_string(facet_after_bytes);
let mut facet_after_bytes = facet.encoded_bytes().to_owned();
facet_after_bytes.push(1u8);
let facet_after = Facet::from_encoded(facet_after_bytes);
Bound::Excluded(facet_after)
};
let underlying: btree_map::Range<'_, _, _> =
self.facet_counts.range((left_bound, right_bound));
FacetChildIterator { underlying }
self.facet_counts
.range((left_bound, right_bound))
.map(|(facet, count)| (facet, *count))
}
pub fn top_k<T>(&self, facet: T, k: usize) -> Vec<(&Facet, u64)>
@@ -425,24 +461,17 @@ impl FacetCounts {
let mut heap = BinaryHeap::with_capacity(k);
let mut it = self.get(facet);
// push the first k elements to first bring the heap
// to capacity
for (facet, count) in (&mut it).take(k) {
heap.push(Hit { count, facet });
}
let mut lowest_count: u64 = heap.peek().map(|hit| hit.count).unwrap_or(u64::MIN); //< the `unwrap_or` case may be triggered but the value
// is never used in that case.
let mut lowest_count: u64 = heap.peek().map(|hit| hit.count).unwrap_or(u64::MIN);
for (facet, count) in it {
if count > lowest_count {
lowest_count = count;
if let Some(mut head) = heap.peek_mut() {
*head = Hit { count, facet };
}
// the heap gets reconstructed at this point
if let Some(head) = heap.peek() {
lowest_count = head.count;
}
}
}
heap.into_sorted_vec()
@@ -454,25 +483,23 @@ impl FacetCounts {
#[cfg(test)]
mod tests {
use test::Bencher;
use core::Index;
use schema::{Document, Facet, SchemaBuilder};
use query::AllQuery;
use super::{FacetCollector, FacetCounts};
use crate::collector::Count;
use crate::core::Index;
use crate::query::{AllQuery, QueryParser, TermQuery};
use crate::schema::{Document, Facet, Field, IndexRecordOption, Schema};
use crate::Term;
use rand::distributions::Uniform;
use rand::prelude::SliceRandom;
use rand::{thread_rng, Rng};
use std::iter;
use schema::Field;
use rand::{thread_rng, Rng};
#[test]
fn test_facet_collector_drilldown() {
let mut schema_builder = Schema::builder();
let mut schema_builder = SchemaBuilder::new();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer(3_000_000).unwrap();
let num_facets: usize = 3 * 4 * 5;
let facets: Vec<Facet> = (0..num_facets)
.map(|mut n| {
@@ -490,12 +517,14 @@ mod tests {
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
index.load_searchers().unwrap();
let searcher = index.searcher();
let mut facet_collector = FacetCollector::for_field(facet_field);
facet_collector.add_facet(Facet::from("/top1"));
let counts = searcher.search(&AllQuery, &facet_collector).unwrap();
searcher.search(&AllQuery, &mut facet_collector).unwrap();
let counts: FacetCounts = facet_collector.harvest();
{
let facets: Vec<(String, u64)> = counts
.get("/top1")
@@ -508,10 +537,9 @@ mod tests {
("/top1/mid1", 50),
("/top1/mid2", 50),
("/top1/mid3", 50),
]
.iter()
.map(|&(facet_str, count)| (String::from(facet_str), count))
.collect::<Vec<_>>()
].iter()
.map(|&(facet_str, count)| (String::from(facet_str), count))
.collect::<Vec<_>>()
);
}
}
@@ -520,156 +548,65 @@ mod tests {
#[should_panic(expected = "Tried to add a facet which is a descendant of \
an already added facet.")]
fn test_misused_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
let mut facet_collector = FacetCollector::for_field(Field(0));
facet_collector.add_facet(Facet::from("/country"));
facet_collector.add_facet(Facet::from("/country/europe"));
}
#[test]
fn test_doc_unsorted_multifacet() {
let mut schema_builder = Schema::builder();
let facet_field = schema_builder.add_facet_field("facets");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/subjects/A/a"),
facet_field => Facet::from_text(&"/subjects/B/a"),
facet_field => Facet::from_text(&"/subjects/A/b"),
facet_field => Facet::from_text(&"/subjects/B/b"),
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 1);
let mut facet_collector = FacetCollector::for_field(facet_field);
facet_collector.add_facet("/subjects");
let counts = searcher.search(&AllQuery, &facet_collector).unwrap();
let facets: Vec<(&Facet, u64)> = counts.get("/subjects").collect();
assert_eq!(facets[0].1, 1);
}
#[test]
fn test_doc_search_by_facet() {
let mut schema_builder = Schema::builder();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/B"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/C/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/D/C/A"),
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 4);
let count_facet = |facet_str: &str| {
let term = Term::from_facet(facet_field, &Facet::from_text(facet_str));
searcher
.search(&TermQuery::new(term, IndexRecordOption::Basic), &Count)
.unwrap()
};
assert_eq!(count_facet("/"), 4);
assert_eq!(count_facet("/A"), 3);
assert_eq!(count_facet("/A/B"), 1);
assert_eq!(count_facet("/A/C"), 1);
assert_eq!(count_facet("/A/C/A"), 1);
assert_eq!(count_facet("/C/A"), 0);
{
let query_parser = QueryParser::for_index(&index, vec![]);
{
let query = query_parser.parse_query("facet:/A/B").unwrap();
assert_eq!(1, searcher.search(&query, &Count).unwrap());
}
{
let query = query_parser.parse_query("facet:/A").unwrap();
assert_eq!(3, searcher.search(&query, &Count).unwrap());
}
}
}
#[test]
fn test_non_used_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
let mut facet_collector = FacetCollector::for_field(Field(0));
facet_collector.add_facet(Facet::from("/country"));
facet_collector.add_facet(Facet::from("/countryeurope"));
}
#[test]
fn test_facet_collector_topk() {
let mut schema_builder = Schema::builder();
let mut schema_builder = SchemaBuilder::new();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let uniform = Uniform::new_inclusive(1, 100_000);
let mut docs: Vec<Document> = vec![("a", 10), ("b", 100), ("c", 7), ("d", 12), ("e", 21)]
.into_iter()
.flat_map(|(c, count)| {
let facet = Facet::from(&format!("/facet/{}", c));
let facet = Facet::from(&format!("/facet_{}", c));
let doc = doc!(facet_field => facet);
iter::repeat(doc).take(count)
})
.map(|mut doc| {
doc.add_facet(
facet_field,
&format!("/facet/{}", thread_rng().sample(&uniform)),
);
doc
})
.collect();
docs[..].shuffle(&mut thread_rng());
thread_rng().shuffle(&mut docs[..]);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer(3_000_000).unwrap();
for doc in docs {
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let searcher = index.reader().unwrap().searcher();
index.load_searchers().unwrap();
let searcher = index.searcher();
let mut facet_collector = FacetCollector::for_field(facet_field);
facet_collector.add_facet("/facet");
let counts: FacetCounts = searcher.search(&AllQuery, &facet_collector).unwrap();
facet_collector.add_facet("/");
searcher.search(&AllQuery, &mut facet_collector).unwrap();
let counts: FacetCounts = facet_collector.harvest();
{
let facets: Vec<(&Facet, u64)> = counts.top_k("/facet", 3);
let facets: Vec<(&Facet, u64)> = counts.top_k("/", 3);
assert_eq!(
facets,
vec![
(&Facet::from("/facet/b"), 100),
(&Facet::from("/facet/e"), 21),
(&Facet::from("/facet/d"), 12),
(&Facet::from("/facet_b"), 100),
(&Facet::from("/facet_e"), 21),
(&Facet::from("/facet_d"), 12),
]
);
}
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use crate::collector::FacetCollector;
use crate::query::AllQuery;
use crate::schema::{Facet, Schema};
use crate::Index;
use rand::seq::SliceRandom;
use rand::thread_rng;
use test::Bencher;
#[bench]
fn bench_facet_collector(b: &mut Bencher) {
let mut schema_builder = Schema::builder();
let mut schema_builder = SchemaBuilder::new();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
@@ -682,18 +619,19 @@ mod bench {
}
}
// 40425 docs
docs[..].shuffle(&mut thread_rng());
thread_rng().shuffle(&mut docs[..]);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer(3_000_000).unwrap();
for doc in docs {
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
index.load_searchers().unwrap();
b.iter(|| {
let searcher = reader.searcher();
let facet_collector = FacetCollector::for_field(facet_field);
searcher.search(&AllQuery, &facet_collector).unwrap();
let searcher = index.searcher();
let mut facet_collector = FacetCollector::for_field(facet_field);
searcher.search(&AllQuery, &mut facet_collector).unwrap();
});
}
}

14
src/collector/int_facet_collector.rs
View File

@@ -79,23 +79,21 @@ mod tests {
// make sure we have facet counters correctly filled
fn test_facet_collector_results() {
let mut schema_builder = schema::Schema::builder();
let mut schema_builder = schema::SchemaBuilder::new();
let num_field_i64 = schema_builder.add_i64_field("num_i64", FAST);
let num_field_u64 = schema_builder.add_u64_field("num_u64", FAST);
let num_field_f64 = schema_builder.add_f64_field("num_f64", FAST);
let text_field = schema_builder.add_text_field("text", STRING);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema.clone());
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 40_000_000).unwrap();
{
for i in 0u64..10u64 {
index_writer.add_document(doc!(
num_field_i64 => ((i as i64) % 3i64) as i64,
num_field_u64 => (i % 2u64) as u64,
num_field_f64 => (i % 4u64) as f64,
text_field => "text"
));
}
@@ -103,14 +101,14 @@ mod tests {
assert_eq!(index_writer.commit().unwrap(), 10u64);
}
let searcher = index.reader().searcher();
index.load_searchers().unwrap();
let searcher = index.searcher();
let mut ffvf_i64: IntFacetCollector<I64FastFieldReader> = IntFacetCollector::new(num_field_i64);
let mut ffvf_u64: IntFacetCollector<U64FastFieldReader> = IntFacetCollector::new(num_field_u64);
let mut ffvf_f64: IntFacetCollector<F64FastFieldReader> = IntFacetCollector::new(num_field_f64);
{
// perform the query
let mut facet_collectors = chain().push(&mut ffvf_i64).push(&mut ffvf_u64).push(&mut ffvf_f64);
let mut facet_collectors = chain().push(&mut ffvf_i64).push(&mut ffvf_u64);
let mut query_parser = QueryParser::for_index(index, vec![text_field]);
let query = query_parser.parse_query("text:text").unwrap();
query.search(&searcher, &mut facet_collectors).unwrap();
@@ -120,8 +118,6 @@ mod tests {
assert_eq!(ffvf_u64.counters[&1], 5);
assert_eq!(ffvf_i64.counters[&0], 4);
assert_eq!(ffvf_i64.counters[&1], 3);
assert_eq!(ffvf_f64.counters[&0.0], 3);
assert_eq!(ffvf_f64.counters[&2.0], 2);
}
}

513
src/collector/mod.rs
View File

@@ -1,401 +1,200 @@
/*!
# Collectors
Collectors define the information you want to extract from the documents matching the queries.
In tantivy jargon, we call this information your search "fruit".
Your fruit could for instance be :
- [the count of matching documents](./struct.Count.html)
- [the top 10 documents, by relevancy or by a fast field](./struct.TopDocs.html)
- [facet counts](./struct.FacetCollector.html)
At one point in your code, you will trigger the actual search operation by calling
[the `search(...)` method of your `Searcher` object](../struct.Searcher.html#method.search).
This call will look like this.
```verbatim
let fruit = searcher.search(&query, &collector)?;
```
Here the type of fruit is actually determined as an associated type of the collector (`Collector::Fruit`).
# Combining several collectors
A rich search experience often requires to run several collectors on your search query.
For instance,
- selecting the top-K products matching your query
- counting the matching documents
- computing several facets
- computing statistics about the matching product prices
A simple and efficient way to do that is to pass your collectors as one tuple.
The resulting `Fruit` will then be a typed tuple with each collector's original fruits
in their respective position.
```rust
# use tantivy::schema::*;
# use tantivy::*;
# use tantivy::query::*;
use tantivy::collector::{Count, TopDocs};
#
# fn main() -> tantivy::Result<()> {
# let mut schema_builder = Schema::builder();
# let title = schema_builder.add_text_field("title", TEXT);
# let schema = schema_builder.build();
# let index = Index::create_in_ram(schema);
# let mut index_writer = index.writer(3_000_000)?;
# index_writer.add_document(doc!(
# title => "The Name of the Wind",
# ));
# index_writer.add_document(doc!(
# title => "The Diary of Muadib",
# ));
# index_writer.commit()?;
# let reader = index.reader()?;
# let searcher = reader.searcher();
# let query_parser = QueryParser::for_index(&index, vec![title]);
# let query = query_parser.parse_query("diary")?;
let (doc_count, top_docs): (usize, Vec<(Score, DocAddress)>) =
searcher.search(&query, &(Count, TopDocs::with_limit(2)))?;
# Ok(())
# }
```
The `Collector` trait is implemented for up to 4 collectors.
If you have more than 4 collectors, you can either group them into
tuples of tuples `(a,(b,(c,d)))`, or rely on [`MultiCollector`](./struct.MultiCollector.html).
# Combining several collectors dynamically
Combining collectors into a tuple is a zero-cost abstraction: everything
happens as if you had manually implemented a single collector
combining all of our features.
Unfortunately it requires you to know at compile time your collector types.
If on the other hand, the collectors depend on some query parameter,
you can rely on `MultiCollector`'s.
# Implementing your own collectors.
See the `custom_collector` example.
Defines how the documents matching a search query should be processed.
*/
use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use downcast_rs::impl_downcast;
use SegmentReader;
use SegmentLocalId;
use DocId;
use Score;
use Result;
mod count_collector;
pub use self::count_collector::Count;
pub use self::count_collector::CountCollector;
mod multi_collector;
pub use self::multi_collector::MultiCollector;
mod top_collector;
mod top_score_collector;
pub use self::top_score_collector::TopDocs;
mod custom_score_top_collector;
pub use self::custom_score_top_collector::{CustomScorer, CustomSegmentScorer};
mod tweak_score_top_collector;
pub use self::tweak_score_top_collector::{ScoreSegmentTweaker, ScoreTweaker};
pub use self::top_collector::TopCollector;
mod facet_collector;
pub use self::facet_collector::FacetCollector;
use crate::query::Weight;
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
pub trait Fruit: Send + downcast_rs::Downcast {}
impl<T> Fruit for T where T: Send + downcast_rs::Downcast {}
mod chained_collector;
pub use self::chained_collector::chain;
/// Collectors are in charge of collecting and retaining relevant
/// information from the document found and scored by the query.
///
///
/// For instance,
///
/// - keeping track of the top 10 best documents
/// - computing a breakdown over a fast field
/// - computing the number of documents matching the query
///
/// Our search index is in fact a collection of segments, so
/// a `Collector` trait is actually more of a factory to instance
/// `SegmentCollector`s for each segments.
/// Queries are in charge of pushing the `DocSet` to the collector.
///
/// The collection logic itself is in the `SegmentCollector`.
/// As they work on multiple segments, they first inform
/// the collector of a change in a segment and then
/// call the `collect` method to push the document to the collector.
///
/// Temporally, our collector will receive calls
/// - `.set_segment(0, segment_reader_0)`
/// - `.collect(doc0_of_segment_0)`
/// - `.collect(...)`
/// - `.collect(last_doc_of_segment_0)`
/// - `.set_segment(1, segment_reader_1)`
/// - `.collect(doc0_of_segment_1)`
/// - `.collect(...)`
/// - `.collect(last_doc_of_segment_1)`
/// - `...`
/// - `.collect(last_doc_of_last_segment)`
///
/// Segments are not guaranteed to be visited in any specific order.
pub trait Collector: Sync {
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
type Fruit: Fruit;
/// Type of the `SegmentCollector` associated to this collector.
type Child: SegmentCollector<Fruit = Self::Fruit>;
pub trait Collector {
/// `set_segment` is called before beginning to enumerate
/// on this segment.
fn for_segment(
&self,
fn set_segment(
&mut self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> crate::Result<Self::Child>;
/// Returns true iff the collector requires to compute scores for documents.
fn requires_scoring(&self) -> bool;
/// Combines the fruit associated to the collection of each segments
/// into one fruit.
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> crate::Result<Self::Fruit>;
/// Created a segment collector and
fn collect_segment(
&self,
weight: &dyn Weight,
segment_ord: u32,
reader: &SegmentReader,
) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
let mut segment_collector = self.for_segment(segment_ord as u32, reader)?;
if let Some(delete_bitset) = reader.delete_bitset() {
weight.for_each(reader, &mut |doc, score| {
if delete_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
}
})?;
} else {
weight.for_each(reader, &mut |doc, score| {
segment_collector.collect(doc, score);
})?;
}
Ok(segment_collector.harvest())
}
}
/// The `SegmentCollector` is the trait in charge of defining the
/// collect operation at the scale of the segment.
///
/// `.collect(doc, score)` will be called for every documents
/// matching the query.
pub trait SegmentCollector: 'static {
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
type Fruit: Fruit;
) -> Result<()>;
/// The query pushes the scored document to the collector via this method.
fn collect(&mut self, doc: DocId, score: Score);
/// Extract the fruit of the collection from the `SegmentCollector`.
fn harvest(self) -> Self::Fruit;
/// Returns true iff the collector requires to compute scores for documents.
fn requires_scoring(&self) -> bool;
}
// -----------------------------------------------
// Tuple implementations.
impl<Left, Right> Collector for (Left, Right)
where
Left: Collector,
Right: Collector,
{
type Fruit = (Left::Fruit, Right::Fruit);
type Child = (Left::Child, Right::Child);
fn for_segment(
&self,
segment_local_id: u32,
impl<'a, C: Collector> Collector for &'a mut C {
fn set_segment(
&mut self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let left = self.0.for_segment(segment_local_id, segment)?;
let right = self.1.for_segment(segment_local_id, segment)?;
Ok((left, right))
) -> Result<()> {
(*self).set_segment(segment_local_id, segment)
}
/// The query pushes the scored document to the collector via this method.
fn collect(&mut self, doc: DocId, score: Score) {
C::collect(self, doc, score)
}
fn requires_scoring(&self) -> bool {
self.0.requires_scoring() || self.1.requires_scoring()
}
fn merge_fruits(
&self,
children: Vec<(Left::Fruit, Right::Fruit)>,
) -> crate::Result<(Left::Fruit, Right::Fruit)> {
let mut left_fruits = vec![];
let mut right_fruits = vec![];
for (left_fruit, right_fruit) in children {
left_fruits.push(left_fruit);
right_fruits.push(right_fruit);
}
Ok((
self.0.merge_fruits(left_fruits)?,
self.1.merge_fruits(right_fruits)?,
))
C::requires_scoring(self)
}
}
impl<Left, Right> SegmentCollector for (Left, Right)
where
Left: SegmentCollector,
Right: SegmentCollector,
{
type Fruit = (Left::Fruit, Right::Fruit);
fn collect(&mut self, doc: DocId, score: Score) {
self.0.collect(doc, score);
self.1.collect(doc, score);
}
fn harvest(self) -> <Self as SegmentCollector>::Fruit {
(self.0.harvest(), self.1.harvest())
}
}
// 3-Tuple
impl<One, Two, Three> Collector for (One, Two, Three)
where
One: Collector,
Two: Collector,
Three: Collector,
{
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit);
type Child = (One::Child, Two::Child, Three::Child);
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let one = self.0.for_segment(segment_local_id, segment)?;
let two = self.1.for_segment(segment_local_id, segment)?;
let three = self.2.for_segment(segment_local_id, segment)?;
Ok((one, two, three))
}
fn requires_scoring(&self) -> bool {
self.0.requires_scoring() || self.1.requires_scoring() || self.2.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];
for (one_fruit, two_fruit, three_fruit) in children {
one_fruits.push(one_fruit);
two_fruits.push(two_fruit);
three_fruits.push(three_fruit);
}
Ok((
self.0.merge_fruits(one_fruits)?,
self.1.merge_fruits(two_fruits)?,
self.2.merge_fruits(three_fruits)?,
))
}
}
impl<One, Two, Three> SegmentCollector for (One, Two, Three)
where
One: SegmentCollector,
Two: SegmentCollector,
Three: SegmentCollector,
{
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit);
fn collect(&mut self, doc: DocId, score: Score) {
self.0.collect(doc, score);
self.1.collect(doc, score);
self.2.collect(doc, score);
}
fn harvest(self) -> <Self as SegmentCollector>::Fruit {
(self.0.harvest(), self.1.harvest(), self.2.harvest())
}
}
// 4-Tuple
impl<One, Two, Three, Four> Collector for (One, Two, Three, Four)
where
One: Collector,
Two: Collector,
Three: Collector,
Four: Collector,
{
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit, Four::Fruit);
type Child = (One::Child, Two::Child, Three::Child, Four::Child);
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
let one = self.0.for_segment(segment_local_id, segment)?;
let two = self.1.for_segment(segment_local_id, segment)?;
let three = self.2.for_segment(segment_local_id, segment)?;
let four = self.3.for_segment(segment_local_id, segment)?;
Ok((one, two, three, four))
}
fn requires_scoring(&self) -> bool {
self.0.requires_scoring()
|| self.1.requires_scoring()
|| self.2.requires_scoring()
|| self.3.requires_scoring()
}
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> crate::Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];
let mut four_fruits = vec![];
for (one_fruit, two_fruit, three_fruit, four_fruit) in children {
one_fruits.push(one_fruit);
two_fruits.push(two_fruit);
three_fruits.push(three_fruit);
four_fruits.push(four_fruit);
}
Ok((
self.0.merge_fruits(one_fruits)?,
self.1.merge_fruits(two_fruits)?,
self.2.merge_fruits(three_fruits)?,
self.3.merge_fruits(four_fruits)?,
))
}
}
impl<One, Two, Three, Four> SegmentCollector for (One, Two, Three, Four)
where
One: SegmentCollector,
Two: SegmentCollector,
Three: SegmentCollector,
Four: SegmentCollector,
{
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit, Four::Fruit);
fn collect(&mut self, doc: DocId, score: Score) {
self.0.collect(doc, score);
self.1.collect(doc, score);
self.2.collect(doc, score);
self.3.collect(doc, score);
}
fn harvest(self) -> <Self as SegmentCollector>::Fruit {
(
self.0.harvest(),
self.1.harvest(),
self.2.harvest(),
self.3.harvest(),
)
}
}
impl_downcast!(Fruit);
#[cfg(test)]
pub mod tests;
pub mod tests {
use super::*;
use test::Bencher;
use DocId;
use Score;
use core::SegmentReader;
use SegmentLocalId;
use fastfield::FastFieldReader;
use schema::Field;
/// Stores all of the doc ids.
/// This collector is only used for tests.
/// It is unusable in practise, as it does not store
/// the segment ordinals
pub struct TestCollector {
offset: DocId,
segment_max_doc: DocId,
docs: Vec<DocId>,
scores: Vec<Score>,
}
impl TestCollector {
/// Return the exhalist of documents.
pub fn docs(self) -> Vec<DocId> {
self.docs
}
pub fn scores(self) -> Vec<Score> {
self.scores
}
}
impl Default for TestCollector {
fn default() -> TestCollector {
TestCollector {
offset: 0,
segment_max_doc: 0,
docs: Vec::new(),
scores: Vec::new(),
}
}
}
impl Collector for TestCollector {
fn set_segment(&mut self, _: SegmentLocalId, reader: &SegmentReader) -> Result<()> {
self.offset += self.segment_max_doc;
self.segment_max_doc = reader.max_doc();
Ok(())
}
fn collect(&mut self, doc: DocId, score: Score) {
self.docs.push(doc + self.offset);
self.scores.push(score);
}
fn requires_scoring(&self) -> bool {
true
}
}
/// Collects in order all of the fast fields for all of the
/// doc in the `DocSet`
///
/// This collector is mainly useful for tests.
pub struct FastFieldTestCollector {
vals: Vec<u64>,
field: Field,
ff_reader: Option<FastFieldReader<u64>>,
}
impl FastFieldTestCollector {
pub fn for_field(field: Field) -> FastFieldTestCollector {
FastFieldTestCollector {
vals: Vec::new(),
field,
ff_reader: None,
}
}
pub fn vals(self) -> Vec<u64> {
self.vals
}
}
impl Collector for FastFieldTestCollector {
fn set_segment(&mut self, _: SegmentLocalId, reader: &SegmentReader) -> Result<()> {
self.ff_reader = Some(reader.fast_field_reader(self.field)?);
Ok(())
}
fn collect(&mut self, doc: DocId, _score: Score) {
let val = self.ff_reader.as_ref().unwrap().get(doc);
self.vals.push(val);
}
fn requires_scoring(&self) -> bool {
false
}
}
#[bench]
fn build_collector(b: &mut Bencher) {
b.iter(|| {
let mut count_collector = CountCollector::default();
let docs: Vec<u32> = (0..1_000_000).collect();
for doc in docs {
count_collector.collect(doc, 1f32);
}
count_collector.count()
});
}
}

281
src/collector/multi_collector.rs
View File

@@ -1,242 +1,46 @@
use super::Collector;
use super::SegmentCollector;
use crate::collector::Fruit;
use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use crate::TantivyError;
use std::marker::PhantomData;
use std::ops::Deref;
pub struct MultiFruit {
sub_fruits: Vec<Option<Box<dyn Fruit>>>,
}
pub struct CollectorWrapper<TCollector: Collector>(TCollector);
impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
type Fruit = Box<dyn Fruit>;
type Child = Box<dyn BoxableSegmentCollector>;
fn for_segment(
&self,
segment_local_id: u32,
reader: &SegmentReader,
) -> crate::Result<Box<dyn BoxableSegmentCollector>> {
let child = self.0.for_segment(segment_local_id, reader)?;
Ok(Box::new(SegmentCollectorWrapper(child)))
}
fn requires_scoring(&self) -> bool {
self.0.requires_scoring()
}
fn merge_fruits(
&self,
children: Vec<<Self as Collector>::Fruit>,
) -> crate::Result<Box<dyn Fruit>> {
let typed_fruit: Vec<TCollector::Fruit> = children
.into_iter()
.map(|untyped_fruit| {
untyped_fruit
.downcast::<TCollector::Fruit>()
.map(|boxed_but_typed| *boxed_but_typed)
.map_err(|_| {
TantivyError::InvalidArgument("Failed to cast child fruit.".to_string())
})
})
.collect::<crate::Result<_>>()?;
let merged_fruit = self.0.merge_fruits(typed_fruit)?;
Ok(Box::new(merged_fruit))
}
}
impl SegmentCollector for Box<dyn BoxableSegmentCollector> {
type Fruit = Box<dyn Fruit>;
fn collect(&mut self, doc: u32, score: f32) {
self.as_mut().collect(doc, score);
}
fn harvest(self) -> Box<dyn Fruit> {
BoxableSegmentCollector::harvest_from_box(self)
}
}
pub trait BoxableSegmentCollector {
fn collect(&mut self, doc: u32, score: f32);
fn harvest_from_box(self: Box<Self>) -> Box<dyn Fruit>;
}
pub struct SegmentCollectorWrapper<TSegmentCollector: SegmentCollector>(TSegmentCollector);
impl<TSegmentCollector: SegmentCollector> BoxableSegmentCollector
for SegmentCollectorWrapper<TSegmentCollector>
{
fn collect(&mut self, doc: u32, score: f32) {
self.0.collect(doc, score);
}
fn harvest_from_box(self: Box<Self>) -> Box<dyn Fruit> {
Box::new(self.0.harvest())
}
}
pub struct FruitHandle<TFruit: Fruit> {
pos: usize,
_phantom: PhantomData<TFruit>,
}
impl<TFruit: Fruit> FruitHandle<TFruit> {
pub fn extract(self, fruits: &mut MultiFruit) -> TFruit {
let boxed_fruit = fruits.sub_fruits[self.pos].take().expect("");
*boxed_fruit
.downcast::<TFruit>()
.map_err(|_| ())
.expect("Failed to downcast collector fruit.")
}
}
use DocId;
use Score;
use Result;
use SegmentReader;
use SegmentLocalId;
/// Multicollector makes it possible to collect on more than one collector.
/// It should only be used for use cases where the Collector types is unknown
/// at compile time.
///
/// If the type of the collectors is known, you can just group yours collectors
/// in a tuple. See the
/// [Combining several collectors section of the collector documentation](./index.html#combining-several-collectors).
///
/// ```rust
/// use tantivy::collector::{Count, TopDocs, MultiCollector};
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer(3_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let mut collectors = MultiCollector::new();
/// let top_docs_handle = collectors.add_collector(TopDocs::with_limit(2));
/// let count_handle = collectors.add_collector(Count);
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let mut multi_fruit = searcher.search(&query, &collectors).unwrap();
///
/// let count = count_handle.extract(&mut multi_fruit);
/// let top_docs = top_docs_handle.extract(&mut multi_fruit);
///
/// assert_eq!(count, 2);
/// assert_eq!(top_docs.len(), 2);
/// ```
#[allow(clippy::type_complexity)]
#[derive(Default)]
/// If the type of the collectors is known, you should prefer to use `ChainedCollector`.
pub struct MultiCollector<'a> {
collector_wrappers: Vec<
Box<dyn Collector<Child = Box<dyn BoxableSegmentCollector>, Fruit = Box<dyn Fruit>> + 'a>,
>,
collectors: Vec<&'a mut Collector>,
}
impl<'a> MultiCollector<'a> {
/// Create a new `MultiCollector`
pub fn new() -> Self {
Default::default()
}
/// Add a new collector to our `MultiCollector`.
pub fn add_collector<'b: 'a, TCollector: Collector + 'b>(
&mut self,
collector: TCollector,
) -> FruitHandle<TCollector::Fruit> {
let pos = self.collector_wrappers.len();
self.collector_wrappers
.push(Box::new(CollectorWrapper(collector)));
FruitHandle {
pos,
_phantom: PhantomData,
}
/// Constructor
pub fn from(collectors: Vec<&'a mut Collector>) -> MultiCollector {
MultiCollector { collectors }
}
}
impl<'a> Collector for MultiCollector<'a> {
type Fruit = MultiFruit;
type Child = MultiCollectorChild;
fn for_segment(
&self,
fn set_segment(
&mut self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> crate::Result<MultiCollectorChild> {
let children = self
.collector_wrappers
.iter()
.map(|collector_wrapper| collector_wrapper.for_segment(segment_local_id, segment))
.collect::<crate::Result<Vec<_>>>()?;
Ok(MultiCollectorChild { children })
}
fn requires_scoring(&self) -> bool {
self.collector_wrappers
.iter()
.map(Deref::deref)
.any(Collector::requires_scoring)
}
fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> crate::Result<MultiFruit> {
let mut segment_fruits_list: Vec<Vec<Box<dyn Fruit>>> = (0..self.collector_wrappers.len())
.map(|_| Vec::with_capacity(segments_multifruits.len()))
.collect::<Vec<_>>();
for segment_multifruit in segments_multifruits {
for (idx, segment_fruit_opt) in segment_multifruit.sub_fruits.into_iter().enumerate() {
if let Some(segment_fruit) = segment_fruit_opt {
segment_fruits_list[idx].push(segment_fruit);
}
}
) -> Result<()> {
for collector in &mut self.collectors {
collector.set_segment(segment_local_id, segment)?;
}
let sub_fruits = self
.collector_wrappers
.iter()
.zip(segment_fruits_list)
.map(|(child_collector, segment_fruits)| {
Ok(Some(child_collector.merge_fruits(segment_fruits)?))
})
.collect::<crate::Result<_>>()?;
Ok(MultiFruit { sub_fruits })
Ok(())
}
}
pub struct MultiCollectorChild {
children: Vec<Box<dyn BoxableSegmentCollector>>,
}
impl SegmentCollector for MultiCollectorChild {
type Fruit = MultiFruit;
fn collect(&mut self, doc: DocId, score: Score) {
for child in &mut self.children {
child.collect(doc, score);
for collector in &mut self.collectors {
collector.collect(doc, score);
}
}
fn harvest(self) -> MultiFruit {
MultiFruit {
sub_fruits: self
.children
.into_iter()
.map(|child| Some(child.harvest()))
.collect(),
}
fn requires_scoring(&self) -> bool {
self.collectors
.iter()
.any(|collector| collector.requires_scoring())
}
}
@@ -244,41 +48,20 @@ impl SegmentCollector for MultiCollectorChild {
mod tests {
use super::*;
use crate::collector::{Count, TopDocs};
use crate::query::TermQuery;
use crate::schema::IndexRecordOption;
use crate::schema::{Schema, TEXT};
use crate::Index;
use crate::Term;
use collector::{Collector, CountCollector, TopCollector};
#[test]
fn test_multi_collector() {
let mut schema_builder = Schema::builder();
let text = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut top_collector = TopCollector::with_limit(2);
let mut count_collector = CountCollector::default();
{
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(text=>"abc"));
index_writer.add_document(doc!(text=>"abc abc abc"));
index_writer.add_document(doc!(text=>"abc abc"));
index_writer.commit().unwrap();
index_writer.add_document(doc!(text=>""));
index_writer.add_document(doc!(text=>"abc abc abc abc"));
index_writer.add_document(doc!(text=>"abc"));
index_writer.commit().unwrap();
let mut collectors =
MultiCollector::from(vec![&mut top_collector, &mut count_collector]);
collectors.collect(1, 0.2);
collectors.collect(2, 0.1);
collectors.collect(3, 0.5);
}
let searcher = index.reader().unwrap().searcher();
let term = Term::from_field_text(text, "abc");
let query = TermQuery::new(term, IndexRecordOption::Basic);
let mut collectors = MultiCollector::new();
let topdocs_handler = collectors.add_collector(TopDocs::with_limit(2));
let count_handler = collectors.add_collector(Count);
let mut multifruits = searcher.search(&query, &mut collectors).unwrap();
assert_eq!(count_handler.extract(&mut multifruits), 5);
assert_eq!(topdocs_handler.extract(&mut multifruits).len(), 2);
assert_eq!(count_collector.count(), 3);
assert!(top_collector.at_capacity());
}
}

217
src/collector/tests.rs
View File

@@ -1,217 +0,0 @@
use super::*;
use crate::core::SegmentReader;
use crate::fastfield::BytesFastFieldReader;
use crate::fastfield::FastFieldReader;
use crate::schema::Field;
use crate::DocAddress;
use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
pub const TEST_COLLECTOR_WITH_SCORE: TestCollector = TestCollector {
compute_score: true,
};
pub const TEST_COLLECTOR_WITHOUT_SCORE: TestCollector = TestCollector {
compute_score: true,
};
/// Stores all of the doc ids.
/// This collector is only used for tests.
/// It is unusable in pr
///
/// actise, as it does not store
/// the segment ordinals
pub struct TestCollector {
pub compute_score: bool,
}
pub struct TestSegmentCollector {
segment_id: SegmentLocalId,
fruit: TestFruit,
}
#[derive(Default)]
pub struct TestFruit {
docs: Vec<DocAddress>,
scores: Vec<Score>,
}
impl TestFruit {
/// Return the list of matching documents exhaustively.
pub fn docs(&self) -> &[DocAddress] {
&self.docs[..]
}
pub fn scores(&self) -> &[Score] {
&self.scores[..]
}
}
impl Collector for TestCollector {
type Fruit = TestFruit;
type Child = TestSegmentCollector;
fn for_segment(
&self,
segment_id: SegmentLocalId,
_reader: &SegmentReader,
) -> crate::Result<TestSegmentCollector> {
Ok(TestSegmentCollector {
segment_id,
fruit: TestFruit::default(),
})
}
fn requires_scoring(&self) -> bool {
self.compute_score
}
fn merge_fruits(&self, mut children: Vec<TestFruit>) -> crate::Result<TestFruit> {
children.sort_by_key(|fruit| {
if fruit.docs().is_empty() {
0
} else {
fruit.docs()[0].segment_ord()
}
});
let mut docs = vec![];
let mut scores = vec![];
for child in children {
docs.extend(child.docs());
scores.extend(child.scores);
}
Ok(TestFruit { docs, scores })
}
}
impl SegmentCollector for TestSegmentCollector {
type Fruit = TestFruit;
fn collect(&mut self, doc: DocId, score: Score) {
self.fruit.docs.push(DocAddress(self.segment_id, doc));
self.fruit.scores.push(score);
}
fn harvest(self) -> <Self as SegmentCollector>::Fruit {
self.fruit
}
}
/// Collects in order all of the fast fields for all of the
/// doc in the `DocSet`
///
/// This collector is mainly useful for tests.
pub struct FastFieldTestCollector {
field: Field,
}
pub struct FastFieldSegmentCollector {
vals: Vec<u64>,
reader: FastFieldReader<u64>,
}
impl FastFieldTestCollector {
pub fn for_field(field: Field) -> FastFieldTestCollector {
FastFieldTestCollector { field }
}
}
impl Collector for FastFieldTestCollector {
type Fruit = Vec<u64>;
type Child = FastFieldSegmentCollector;
fn for_segment(
&self,
_: SegmentLocalId,
segment_reader: &SegmentReader,
) -> crate::Result<FastFieldSegmentCollector> {
let reader = segment_reader
.fast_fields()
.u64(self.field)
.expect("Requested field is not a fast field.");
Ok(FastFieldSegmentCollector {
vals: Vec::new(),
reader,
})
}
fn requires_scoring(&self) -> bool {
false
}
fn merge_fruits(&self, children: Vec<Vec<u64>>) -> crate::Result<Vec<u64>> {
Ok(children.into_iter().flat_map(|v| v.into_iter()).collect())
}
}
impl SegmentCollector for FastFieldSegmentCollector {
type Fruit = Vec<u64>;
fn collect(&mut self, doc: DocId, _score: Score) {
let val = self.reader.get(doc);
self.vals.push(val);
}
fn harvest(self) -> Vec<u64> {
self.vals
}
}
/// Collects in order all of the fast field bytes for all of the
/// docs in the `DocSet`
///
/// This collector is mainly useful for tests.
pub struct BytesFastFieldTestCollector {
field: Field,
}
pub struct BytesFastFieldSegmentCollector {
vals: Vec<u8>,
reader: BytesFastFieldReader,
}
impl BytesFastFieldTestCollector {
pub fn for_field(field: Field) -> BytesFastFieldTestCollector {
BytesFastFieldTestCollector { field }
}
}
impl Collector for BytesFastFieldTestCollector {
type Fruit = Vec<u8>;
type Child = BytesFastFieldSegmentCollector;
fn for_segment(
&self,
_segment_local_id: u32,
segment_reader: &SegmentReader,
) -> crate::Result<BytesFastFieldSegmentCollector> {
Ok(BytesFastFieldSegmentCollector {
vals: Vec::new(),
reader: segment_reader
.fast_fields()
.bytes(self.field)
.expect("Field is not a bytes fast field."),
})
}
fn requires_scoring(&self) -> bool {
false
}
fn merge_fruits(&self, children: Vec<Vec<u8>>) -> crate::Result<Vec<u8>> {
Ok(children.into_iter().flat_map(|c| c.into_iter()).collect())
}
}
impl SegmentCollector for BytesFastFieldSegmentCollector {
type Fruit = Vec<u8>;
fn collect(&mut self, doc: u32, _score: f32) {
let data = self.reader.get_bytes(doc);
self.vals.extend(data);
}
fn harvest(self) -> <Self as SegmentCollector>::Fruit {
self.vals
}
}

426
src/collector/top_collector.rs
View File

@@ -1,383 +1,189 @@
use crate::DocAddress;
use crate::DocId;
use crate::SegmentLocalId;
use crate::SegmentReader;
use serde::export::PhantomData;
use std::cmp::Ordering;
use super::Collector;
use SegmentReader;
use SegmentLocalId;
use DocAddress;
use Result;
use std::collections::BinaryHeap;
use std::cmp::Ordering;
use DocId;
use Score;
/// Contains a feature (field, score, etc.) of a document along with the document address.
///
/// It has a custom implementation of `PartialOrd` that reverses the order. This is because the
/// default Rust heap is a max heap, whereas a min heap is needed.
///
/// Additionally, it guarantees stable sorting: in case of a tie on the feature, the document
/// address is used.
///
/// WARNING: equality is not what you would expect here.
/// Two elements are equal if their feature is equal, and regardless of whether `doc`
/// is equal. This should be perfectly fine for this usage, but let's make sure this
/// struct is never public.
pub(crate) struct ComparableDoc<T, D> {
pub feature: T,
pub doc: D,
// Rust heap is a max-heap and we need a min heap.
#[derive(Clone, Copy)]
struct GlobalScoredDoc {
score: Score,
doc_address: DocAddress,
}
impl<T: PartialOrd, D: PartialOrd> PartialOrd for ComparableDoc<T, D> {
fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
impl PartialOrd for GlobalScoredDoc {
fn partial_cmp(&self, other: &GlobalScoredDoc) -> Option<Ordering> {
Some(self.cmp(other))
}
}
impl<T: PartialOrd, D: PartialOrd> Ord for ComparableDoc<T, D> {
impl Ord for GlobalScoredDoc {
#[inline]
fn cmp(&self, other: &Self) -> Ordering {
// Reversed to make BinaryHeap work as a min-heap
let by_feature = other
.feature
.partial_cmp(&self.feature)
.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)
fn cmp(&self, other: &GlobalScoredDoc) -> Ordering {
other
.score
.partial_cmp(&self.score)
.unwrap_or_else(|| other.doc_address.cmp(&self.doc_address))
}
}
impl<T: PartialOrd, D: PartialOrd> PartialEq for ComparableDoc<T, D> {
fn eq(&self, other: &Self) -> bool {
impl PartialEq for GlobalScoredDoc {
fn eq(&self, other: &GlobalScoredDoc) -> bool {
self.cmp(other) == Ordering::Equal
}
}
impl<T: PartialOrd, D: PartialOrd> Eq for ComparableDoc<T, D> {}
impl Eq for GlobalScoredDoc {}
pub(crate) struct TopCollector<T> {
pub limit: usize,
pub offset: usize,
_marker: PhantomData<T>,
/// The Top Collector keeps track of the K documents
/// with the best scores.
///
/// The implementation is based on a `BinaryHeap`.
/// The theorical complexity is `O(n log K)`.
pub struct TopCollector {
limit: usize,
heap: BinaryHeap<GlobalScoredDoc>,
segment_id: u32,
}
impl<T> TopCollector<T>
where
T: PartialOrd + Clone,
{
impl TopCollector {
/// Creates a top collector, with a number of documents equal to "limit".
///
/// # Panics
/// The method panics if limit is 0
pub fn with_limit(limit: usize) -> TopCollector<T> {
pub fn with_limit(limit: usize) -> TopCollector {
if limit < 1 {
panic!("Limit must be strictly greater than 0.");
}
Self {
limit,
offset: 0,
_marker: PhantomData,
}
}
/// Skip the first "offset" documents when collecting.
///
/// This is equivalent to `OFFSET` in MySQL or PostgreSQL and `start` in
/// Lucene's TopDocsCollector.
pub fn and_offset(mut self, offset: usize) -> TopCollector<T> {
self.offset = offset;
self
}
pub fn merge_fruits(
&self,
children: Vec<Vec<(T, DocAddress)>>,
) -> crate::Result<Vec<(T, DocAddress)>> {
if self.limit == 0 {
return Ok(Vec::new());
}
let mut top_collector = BinaryHeap::new();
for child_fruit in children {
for (feature, doc) in child_fruit {
if top_collector.len() < (self.limit + self.offset) {
top_collector.push(ComparableDoc { feature, doc });
} else if let Some(mut head) = top_collector.peek_mut() {
if head.feature < feature {
*head = ComparableDoc { feature, doc };
}
}
}
}
Ok(top_collector
.into_sorted_vec()
.into_iter()
.skip(self.offset)
.map(|cdoc| (cdoc.feature, cdoc.doc))
.collect())
}
pub(crate) fn for_segment<F: PartialOrd>(
&self,
segment_id: SegmentLocalId,
_: &SegmentReader,
) -> crate::Result<TopSegmentCollector<F>> {
Ok(TopSegmentCollector::new(
segment_id,
self.limit + self.offset,
))
}
/// Create a new TopCollector with the same limit and offset.
///
/// Ideally we would use Into but the blanket implementation seems to cause the Scorer traits
/// to fail.
#[doc(hidden)]
pub(crate) fn into_tscore<TScore: PartialOrd + Clone>(self) -> TopCollector<TScore> {
TopCollector {
limit: self.limit,
offset: self.offset,
_marker: PhantomData,
}
}
}
/// The Top Collector keeps track of the K documents
/// sorted by type `T`.
///
/// The implementation is based on a `BinaryHeap`.
/// The theorical complexity for collecting the top `K` out of `n` documents
/// is `O(n log K)`.
pub(crate) struct TopSegmentCollector<T> {
limit: usize,
heap: BinaryHeap<ComparableDoc<T, DocId>>,
segment_id: u32,
}
impl<T: PartialOrd> TopSegmentCollector<T> {
fn new(segment_id: SegmentLocalId, limit: usize) -> TopSegmentCollector<T> {
TopSegmentCollector {
limit,
heap: BinaryHeap::with_capacity(limit),
segment_id,
segment_id: 0,
}
}
}
impl<T: PartialOrd + Clone> TopSegmentCollector<T> {
pub fn harvest(self) -> Vec<(T, DocAddress)> {
let segment_id = self.segment_id;
self.heap
.into_sorted_vec()
/// Returns K best documents sorted in decreasing order.
///
/// Calling this method triggers the sort.
/// The result of the sort is not cached.
pub fn docs(&self) -> Vec<DocAddress> {
self.score_docs()
.into_iter()
.map(|comparable_doc| {
(
comparable_doc.feature,
DocAddress(segment_id, comparable_doc.doc),
)
})
.map(|score_doc| score_doc.1)
.collect()
}
/// Returns K best ScoredDocument sorted in decreasing order.
///
/// Calling this method triggers the sort.
/// The result of the sort is not cached.
pub fn score_docs(&self) -> Vec<(Score, DocAddress)> {
let mut scored_docs: Vec<GlobalScoredDoc> = self.heap.iter().cloned().collect();
scored_docs.sort();
scored_docs
.into_iter()
.map(|GlobalScoredDoc { score, doc_address }| (score, doc_address))
.collect()
}
/// Return true iff at least K documents have gone through
/// the collector.
#[inline(always)]
pub(crate) fn at_capacity(&self) -> bool {
#[inline]
pub fn at_capacity(&self) -> bool {
self.heap.len() >= self.limit
}
}
/// Collects a document scored by the given feature
///
/// It collects documents until it has reached the max capacity. Once it reaches capacity, it
/// will compare the lowest scoring item with the given one and keep whichever is greater.
#[inline(always)]
pub fn collect(&mut self, doc: DocId, feature: T) {
impl Collector for TopCollector {
fn set_segment(&mut self, segment_id: SegmentLocalId, _: &SegmentReader) -> Result<()> {
self.segment_id = segment_id;
Ok(())
}
fn collect(&mut self, doc: DocId, score: Score) {
if self.at_capacity() {
// It's ok to unwrap as long as a limit of 0 is forbidden.
if let Some(limit_feature) = self.heap.peek().map(|head| head.feature.clone()) {
if limit_feature < feature {
if let Some(mut head) = self.heap.peek_mut() {
head.feature = feature;
head.doc = doc;
}
}
let limit_doc: GlobalScoredDoc = *self.heap
.peek()
.expect("Top collector with size 0 is forbidden");
if limit_doc.score < score {
let mut mut_head = self.heap
.peek_mut()
.expect("Top collector with size 0 is forbidden");
mut_head.score = score;
mut_head.doc_address = DocAddress(self.segment_id, doc);
}
} else {
// we have not reached capacity yet, so we can just push the
// element.
self.heap.push(ComparableDoc { feature, doc });
let wrapped_doc = GlobalScoredDoc {
score,
doc_address: DocAddress(self.segment_id, doc),
};
self.heap.push(wrapped_doc);
}
}
fn requires_scoring(&self) -> bool {
true
}
}
#[cfg(test)]
mod tests {
use super::{TopCollector, TopSegmentCollector};
use crate::DocAddress;
use super::*;
use DocId;
use Score;
use collector::Collector;
#[test]
fn test_top_collector_not_at_capacity() {
let mut top_collector = TopSegmentCollector::new(0, 4);
let mut top_collector = TopCollector::with_limit(4);
top_collector.collect(1, 0.8);
top_collector.collect(3, 0.2);
top_collector.collect(5, 0.3);
assert_eq!(
top_collector.harvest(),
vec![
(0.8, DocAddress(0, 1)),
(0.3, DocAddress(0, 5)),
(0.2, DocAddress(0, 3))
]
);
assert!(!top_collector.at_capacity());
let score_docs: Vec<(Score, DocId)> = top_collector
.score_docs()
.into_iter()
.map(|(score, doc_address)| (score, doc_address.doc()))
.collect();
assert_eq!(score_docs, vec![(0.8, 1), (0.3, 5), (0.2, 3)]);
}
#[test]
fn test_top_collector_at_capacity() {
let mut top_collector = TopSegmentCollector::new(0, 4);
let mut top_collector = TopCollector::with_limit(4);
top_collector.collect(1, 0.8);
top_collector.collect(3, 0.2);
top_collector.collect(5, 0.3);
top_collector.collect(7, 0.9);
top_collector.collect(9, -0.2);
assert_eq!(
top_collector.harvest(),
vec![
(0.9, DocAddress(0, 7)),
(0.8, DocAddress(0, 1)),
(0.3, DocAddress(0, 5)),
(0.2, DocAddress(0, 3))
]
);
}
#[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);
assert!(top_collector.at_capacity());
{
let score_docs: Vec<(Score, DocId)> = top_collector
.score_docs()
.into_iter()
.map(|(score, doc_address)| (score, doc_address.doc()))
.collect();
assert_eq!(score_docs, vec![(0.9, 7), (0.8, 1), (0.3, 5), (0.2, 3)]);
}
let mut top_collector_limit_3 = TopSegmentCollector::new(0, 3);
for id in &doc_ids_collection {
top_collector_limit_3.collect(*id, score);
{
let docs: Vec<DocId> = top_collector
.docs()
.into_iter()
.map(|doc_address| doc_address.doc())
.collect();
assert_eq!(docs, vec![7, 1, 5, 3]);
}
assert_eq!(
top_collector_limit_2.harvest(),
top_collector_limit_3.harvest()[..2].to_vec(),
);
}
#[test]
fn test_top_collector_with_limit_and_offset() {
let collector = TopCollector::with_limit(2).and_offset(1);
let results = collector
.merge_fruits(vec![vec![
(0.9, DocAddress(0, 1)),
(0.8, DocAddress(0, 2)),
(0.7, DocAddress(0, 3)),
(0.6, DocAddress(0, 4)),
(0.5, DocAddress(0, 5)),
]])
.unwrap();
assert_eq!(
results,
vec![(0.8, DocAddress(0, 2)), (0.7, DocAddress(0, 3)),]
);
}
#[test]
fn test_top_collector_with_limit_larger_than_set_and_offset() {
let collector = TopCollector::with_limit(2).and_offset(1);
let results = collector
.merge_fruits(vec![vec![(0.9, DocAddress(0, 1)), (0.8, DocAddress(0, 2))]])
.unwrap();
assert_eq!(results, vec![(0.8, DocAddress(0, 2)),]);
}
#[test]
fn test_top_collector_with_limit_and_offset_larger_than_set() {
let collector = TopCollector::with_limit(2).and_offset(20);
let results = collector
.merge_fruits(vec![vec![(0.9, DocAddress(0, 1)), (0.8, DocAddress(0, 2))]])
.unwrap();
assert_eq!(results, vec![]);
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use super::TopSegmentCollector;
use test::Bencher;
#[bench]
fn bench_top_segment_collector_collect_not_at_capacity(b: &mut Bencher) {
let mut top_collector = TopSegmentCollector::new(0, 400);
b.iter(|| {
for i in 0..100 {
top_collector.collect(i, 0.8);
}
});
}
#[bench]
fn bench_top_segment_collector_collect_at_capacity(b: &mut Bencher) {
let mut top_collector = TopSegmentCollector::new(0, 100);
for i in 0..100 {
top_collector.collect(i, 0.8);
}
b.iter(|| {
for i in 0..100 {
top_collector.collect(i, 0.8);
}
});
}
#[bench]
fn bench_top_segment_collector_collect_and_harvest_many_ties(b: &mut Bencher) {
b.iter(|| {
let mut top_collector = TopSegmentCollector::new(0, 100);
for i in 0..100 {
top_collector.collect(i, 0.8);
}
// it would be nice to be able to do the setup N times but still
// measure only harvest(). We can't since harvest() consumes
// the top_collector.
top_collector.harvest()
});
}
#[bench]
fn bench_top_segment_collector_collect_and_harvest_no_tie(b: &mut Bencher) {
b.iter(|| {
let mut top_collector = TopSegmentCollector::new(0, 100);
let mut score = 1.0;
for i in 0..100 {
score += 1.0;
top_collector.collect(i, score);
}
// it would be nice to be able to do the setup N times but still
// measure only harvest(). We can't since harvest() consumes
// the top_collector.
top_collector.harvest()
});
#[should_panic]
fn test_top_0() {
TopCollector::with_limit(0);
}
}

824
src/collector/top_score_collector.rs
View File

@@ -1,824 +0,0 @@
use super::Collector;
use crate::collector::custom_score_top_collector::CustomScoreTopCollector;
use crate::collector::top_collector::TopSegmentCollector;
use crate::collector::top_collector::{ComparableDoc, TopCollector};
use crate::collector::tweak_score_top_collector::TweakedScoreTopCollector;
use crate::collector::{
CustomScorer, CustomSegmentScorer, ScoreSegmentTweaker, ScoreTweaker, SegmentCollector,
};
use crate::fastfield::FastFieldReader;
use crate::query::Weight;
use crate::schema::Field;
use crate::DocAddress;
use crate::DocId;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use std::collections::BinaryHeap;
use std::fmt;
/// The `TopDocs` collector keeps track of the top `K` documents
/// sorted by their score.
///
/// The implementation is based on a `BinaryHeap`.
/// The theorical complexity for collecting the top `K` out of `n` documents
/// is `O(n log K)`.
///
/// This collector guarantees a stable sorting in case of a tie on the
/// document score. As such, it is suitable to implement pagination.
///
/// ```rust
/// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, DocAddress, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let top_docs = searcher.search(&query, &TopDocs::with_limit(2)).unwrap();
///
/// assert_eq!(&top_docs[0], &(0.7261542, DocAddress(0, 1)));
/// assert_eq!(&top_docs[1], &(0.6099695, DocAddress(0, 3)));
/// ```
pub struct TopDocs(TopCollector<Score>);
impl fmt::Debug for TopDocs {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"TopDocs(limit={}, offset={})",
self.0.limit, self.0.offset
)
}
}
struct ScorerByFastFieldReader {
ff_reader: FastFieldReader<u64>,
}
impl CustomSegmentScorer<u64> for ScorerByFastFieldReader {
fn score(&mut self, doc: DocId) -> u64 {
self.ff_reader.get_u64(u64::from(doc))
}
}
struct ScorerByField {
field: Field,
}
impl CustomScorer<u64> for ScorerByField {
type Child = ScorerByFastFieldReader;
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child> {
let ff_reader = segment_reader
.fast_fields()
.u64(self.field)
.ok_or_else(|| {
crate::TantivyError::SchemaError(format!(
"Field requested ({:?}) is not a i64/u64 fast field.",
self.field
))
})?;
Ok(ScorerByFastFieldReader { ff_reader })
}
}
impl TopDocs {
/// Creates a top score collector, with a number of documents equal to "limit".
///
/// # Panics
/// The method panics if limit is 0
pub fn with_limit(limit: usize) -> TopDocs {
TopDocs(TopCollector::with_limit(limit))
}
/// Skip the first "offset" documents when collecting.
///
/// This is equivalent to `OFFSET` in MySQL or PostgreSQL and `start` in
/// Lucene's TopDocsCollector.
///
/// ```rust
/// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, DocAddress, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind"));
/// index_writer.add_document(doc!(title => "The Diary of Muadib"));
/// index_writer.add_document(doc!(title => "A Dairy Cow"));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl"));
/// index_writer.add_document(doc!(title => "The Diary of Lena Mukhina"));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let top_docs = searcher.search(&query, &TopDocs::with_limit(2).and_offset(1)).unwrap();
///
/// assert_eq!(top_docs.len(), 2);
/// assert_eq!(&top_docs[0], &(0.5204813, DocAddress(0, 4)));
/// assert_eq!(&top_docs[1], &(0.4793185, DocAddress(0, 3)));
/// ```
pub fn and_offset(self, offset: usize) -> TopDocs {
TopDocs(self.0.and_offset(offset))
}
/// Set top-K to rank documents by a given fast field.
///
/// ```rust
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, DocAddress};
/// # use tantivy::query::{Query, QueryParser};
/// use tantivy::Searcher;
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::Field;
///
/// # fn main() -> tantivy::Result<()> {
/// # let mut schema_builder = Schema::builder();
/// # let title = schema_builder.add_text_field("title", TEXT);
/// # let rating = schema_builder.add_u64_field("rating", FAST);
/// # let schema = schema_builder.build();
/// #
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # index_writer.add_document(doc!(title => "The Name of the Wind", rating => 92u64));
/// # index_writer.add_document(doc!(title => "The Diary of Muadib", rating => 97u64));
/// # index_writer.add_document(doc!(title => "A Dairy Cow", rating => 63u64));
/// # index_writer.add_document(doc!(title => "The Diary of a Young Girl", rating => 80u64));
/// # assert!(index_writer.commit().is_ok());
/// # let reader = index.reader().unwrap();
/// # let query = QueryParser::for_index(&index, vec![title]).parse_query("diary")?;
/// # let top_docs = docs_sorted_by_rating(&reader.searcher(), &query, rating)?;
/// # assert_eq!(top_docs,
/// # vec![(97u64, DocAddress(0u32, 1)),
/// # (80u64, DocAddress(0u32, 3))]);
/// # Ok(())
/// # }
///
///
/// /// Searches the document matching the given query, and
/// /// collects the top 10 documents, order by the u64-`field`
/// /// given in argument.
/// ///
/// /// `field` is required to be a FAST field.
/// fn docs_sorted_by_rating(searcher: &Searcher,
/// query: &dyn Query,
/// sort_by_field: Field)
/// -> tantivy::Result<Vec<(u64, DocAddress)>> {
///
/// // This is where we build our topdocs collector
/// //
/// // Note the generics parameter that needs to match the
/// // type `sort_by_field`.
/// let top_docs_by_rating = TopDocs
/// ::with_limit(10)
/// .order_by_u64_field(sort_by_field);
///
/// // ... and here are our documents. Note this is a simple vec.
/// // The `u64` in the pair is the value of our fast field for
/// // each documents.
/// //
/// // The vec is sorted decreasingly by `sort_by_field`, and has a
/// // length of 10, or less if not enough documents matched the
/// // query.
/// let resulting_docs: Vec<(u64, DocAddress)> =
/// searcher.search(query, &top_docs_by_rating)?;
///
/// Ok(resulting_docs)
/// }
/// ```
///
/// # Panics
///
/// May panic if the field requested is not a fast field.
///
pub fn order_by_u64_field(
self,
field: Field,
) -> impl Collector<Fruit = Vec<(u64, DocAddress)>> {
self.custom_score(ScorerByField { field })
}
/// Ranks the documents using a custom score.
///
/// This method offers a convenient way to tweak or replace
/// the documents score. As suggested by the prototype you can
/// manually define your own [`ScoreTweaker`](./trait.ScoreTweaker.html)
/// and pass it as an argument, but there is a much simpler way to
/// tweak your score: you can use a closure as in the following
/// example.
///
/// # Example
///
/// Typically, you will want to rely on one or more fast fields,
/// to alter the original relevance `Score`.
///
/// For instance, in the following, we assume that we are implementing
/// an e-commerce website that has a fast field called `popularity`
/// that rates whether a product is typically often bought by users.
///
/// In the following example will will tweak our ranking a bit by
/// boosting popular products a notch.
///
/// In more serious application, this tweaking could involved running a
/// learning-to-rank model over various features
///
/// ```rust
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, DocAddress, DocId, Score};
/// # use tantivy::query::QueryParser;
/// use tantivy::SegmentReader;
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::Field;
///
/// fn create_schema() -> Schema {
/// let mut schema_builder = Schema::builder();
/// schema_builder.add_text_field("product_name", TEXT);
/// schema_builder.add_u64_field("popularity", FAST);
/// schema_builder.build()
/// }
///
/// fn create_index() -> tantivy::Result<Index> {
/// let schema = create_schema();
/// let index = Index::create_in_ram(schema);
/// let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// let product_name = index.schema().get_field("product_name").unwrap();
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
/// index_writer.add_document(doc!(product_name => "The Diary of Muadib", popularity => 1u64));
/// index_writer.add_document(doc!(product_name => "A Dairy Cow", popularity => 10u64));
/// index_writer.add_document(doc!(product_name => "The Diary of a Young Girl", popularity => 15u64));
/// index_writer.commit()?;
/// Ok(index)
/// }
///
/// let index = create_index().unwrap();
/// let product_name = index.schema().get_field("product_name").unwrap();
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
///
/// let user_query_str = "diary";
/// let query_parser = QueryParser::for_index(&index, vec![product_name]);
/// let query = query_parser.parse_query(user_query_str).unwrap();
///
/// // This is where we build our collector with our custom score.
/// let top_docs_by_custom_score = TopDocs
/// ::with_limit(10)
/// .tweak_score(move |segment_reader: &SegmentReader| {
/// // The argument is a function that returns our scoring
/// // function.
/// //
/// // The point of this "mother" function is to gather all
/// // of the segment level information we need for scoring.
/// // Typically, fast_fields.
/// //
/// // In our case, we will get a reader for the popularity
/// // fast field.
/// let popularity_reader =
/// segment_reader.fast_fields().u64(popularity).unwrap();
///
/// // We can now define our actual scoring function
/// move |doc: DocId, original_score: Score| {
/// let popularity: u64 = popularity_reader.get(doc);
/// // Well.. For the sake of the example we use a simple logarithm
/// // function.
/// let popularity_boost_score = ((2u64 + popularity) as f32).log2();
/// popularity_boost_score * original_score
/// }
/// });
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
/// // ... and here are our documents. Note this is a simple vec.
/// // The `Score` in the pair is our tweaked score.
/// let resulting_docs: Vec<(Score, DocAddress)> =
/// searcher.search(&query, &top_docs_by_custom_score).unwrap();
/// ```
///
/// # See also
/// [custom_score(...)](#method.custom_score).
pub fn tweak_score<TScore, TScoreSegmentTweaker, TScoreTweaker>(
self,
score_tweaker: TScoreTweaker,
) -> impl Collector<Fruit = Vec<(TScore, DocAddress)>>
where
TScore: 'static + Send + Sync + Clone + PartialOrd,
TScoreSegmentTweaker: ScoreSegmentTweaker<TScore> + 'static,
TScoreTweaker: ScoreTweaker<TScore, Child = TScoreSegmentTweaker>,
{
TweakedScoreTopCollector::new(score_tweaker, self.0.into_tscore())
}
/// Ranks the documents using a custom score.
///
/// This method offers a convenient way to use a different score.
///
/// As suggested by the prototype you can manually define your
/// own [`CustomScorer`](./trait.CustomScorer.html)
/// and pass it as an argument, but there is a much simpler way to
/// tweak your score: you can use a closure as in the following
/// example.
///
/// # Limitation
///
/// This method only makes it possible to compute the score from a given
/// `DocId`, fastfield values for the doc and any information you could
/// have precomputed beforehands. It does not make it possible for instance
/// to compute something like TfIdf as it does not have access to the list of query
/// terms present in the document, nor the term frequencies for the different terms.
///
/// It can be used if your search engine relies on a learning-to-rank model for instance,
/// which does not rely on the term frequencies or positions as features.
///
/// # Example
///
/// ```rust
/// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, DocAddress, DocId};
/// # use tantivy::query::QueryParser;
/// use tantivy::SegmentReader;
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::Field;
///
/// # fn create_schema() -> Schema {
/// # let mut schema_builder = Schema::builder();
/// # schema_builder.add_text_field("product_name", TEXT);
/// # schema_builder.add_u64_field("popularity", FAST);
/// # schema_builder.add_u64_field("boosted", FAST);
/// # schema_builder.build()
/// # }
/// #
/// # fn main() -> tantivy::Result<()> {
/// # let schema = create_schema();
/// # let index = Index::create_in_ram(schema);
/// # let mut index_writer = index.writer_with_num_threads(1, 3_000_000)?;
/// # let product_name = index.schema().get_field("product_name").unwrap();
/// #
/// let popularity: Field = index.schema().get_field("popularity").unwrap();
/// let boosted: Field = index.schema().get_field("boosted").unwrap();
/// # index_writer.add_document(doc!(boosted=>1u64, product_name => "The Diary of Muadib", popularity => 1u64));
/// # index_writer.add_document(doc!(boosted=>0u64, product_name => "A Dairy Cow", popularity => 10u64));
/// # index_writer.add_document(doc!(boosted=>0u64, product_name => "The Diary of a Young Girl", popularity => 15u64));
/// # index_writer.commit()?;
/// // ...
/// # let user_query = "diary";
/// # let query = QueryParser::for_index(&index, vec![product_name]).parse_query(user_query)?;
///
/// // This is where we build our collector with our custom score.
/// let top_docs_by_custom_score = TopDocs
/// ::with_limit(10)
/// .custom_score(move |segment_reader: &SegmentReader| {
/// // The argument is a function that returns our scoring
/// // function.
/// //
/// // The point of this "mother" function is to gather all
/// // of the segment level information we need for scoring.
/// // Typically, fast_fields.
/// //
/// // In our case, we will get a reader for the popularity
/// // fast field and a boosted field.
/// //
/// // We want to get boosted items score, and when we get
/// // a tie, return the item with the highest popularity.
/// //
/// // Note that this is implemented by using a `(u64, u64)`
/// // as a score.
/// let popularity_reader =
/// segment_reader.fast_fields().u64(popularity).unwrap();
/// let boosted_reader =
/// segment_reader.fast_fields().u64(boosted).unwrap();
///
/// // We can now define our actual scoring function
/// move |doc: DocId| {
/// let popularity: u64 = popularity_reader.get(doc);
/// let boosted: u64 = boosted_reader.get(doc);
/// // Score do not have to be `f64` in tantivy.
/// // Here we return a couple to get lexicographical order
/// // for free.
/// (boosted, popularity)
/// }
/// });
/// # let reader = index.reader()?;
/// # let searcher = reader.searcher();
/// // ... and here are our documents. Note this is a simple vec.
/// // The `Score` in the pair is our tweaked score.
/// let resulting_docs: Vec<((u64, u64), DocAddress)> =
/// searcher.search(&*query, &top_docs_by_custom_score)?;
///
/// # Ok(())
/// # }
/// ```
///
/// # See also
/// [tweak_score(...)](#method.tweak_score).
pub fn custom_score<TScore, TCustomSegmentScorer, TCustomScorer>(
self,
custom_score: TCustomScorer,
) -> impl Collector<Fruit = Vec<(TScore, DocAddress)>>
where
TScore: 'static + Send + Sync + Clone + PartialOrd,
TCustomSegmentScorer: CustomSegmentScorer<TScore> + 'static,
TCustomScorer: CustomScorer<TScore, Child = TCustomSegmentScorer>,
{
CustomScoreTopCollector::new(custom_score, self.0.into_tscore())
}
}
impl Collector for TopDocs {
type Fruit = Vec<(Score, DocAddress)>;
type Child = TopScoreSegmentCollector;
fn for_segment(
&self,
segment_local_id: SegmentLocalId,
reader: &SegmentReader,
) -> crate::Result<Self::Child> {
let collector = self.0.for_segment(segment_local_id, reader)?;
Ok(TopScoreSegmentCollector(collector))
}
fn requires_scoring(&self) -> bool {
true
}
fn merge_fruits(
&self,
child_fruits: Vec<Vec<(Score, DocAddress)>>,
) -> crate::Result<Self::Fruit> {
self.0.merge_fruits(child_fruits)
}
fn collect_segment(
&self,
weight: &dyn Weight,
segment_ord: u32,
reader: &SegmentReader,
) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
let heap_len = self.0.limit + self.0.offset;
let mut heap: BinaryHeap<ComparableDoc<Score, DocId>> = BinaryHeap::with_capacity(heap_len);
if let Some(delete_bitset) = reader.delete_bitset() {
let mut threshold = f32::MIN;
weight.for_each_pruning(threshold, reader, &mut |doc, score| {
if delete_bitset.is_deleted(doc) {
return threshold;
}
let heap_item = ComparableDoc {
feature: score,
doc,
};
if heap.len() < heap_len {
heap.push(heap_item);
if heap.len() == heap_len {
threshold = heap.peek().map(|el| el.feature).unwrap_or(f32::MIN);
}
return threshold;
}
*heap.peek_mut().unwrap() = heap_item;
threshold = heap.peek().map(|el| el.feature).unwrap_or(std::f32::MIN);
threshold
})?;
} else {
weight.for_each_pruning(f32::MIN, reader, &mut |doc, score| {
let heap_item = ComparableDoc {
feature: score,
doc,
};
if heap.len() < heap_len {
heap.push(heap_item);
// TODO the threshold is suboptimal for heap.len == heap_len
if heap.len() == heap_len {
return heap.peek().map(|el| el.feature).unwrap_or(f32::MIN);
} else {
return f32::MIN;
}
}
*heap.peek_mut().unwrap() = heap_item;
heap.peek().map(|el| el.feature).unwrap_or(std::f32::MIN)
})?;
}
let fruit = heap
.into_sorted_vec()
.into_iter()
.map(|cid| (cid.feature, DocAddress(segment_ord, cid.doc)))
.collect();
Ok(fruit)
}
}
/// Segment Collector associated to `TopDocs`.
pub struct TopScoreSegmentCollector(TopSegmentCollector<Score>);
impl SegmentCollector for TopScoreSegmentCollector {
type Fruit = Vec<(Score, DocAddress)>;
fn collect(&mut self, doc: DocId, score: Score) {
self.0.collect(doc, score);
}
fn harvest(self) -> Vec<(Score, DocAddress)> {
self.0.harvest()
}
}
#[cfg(test)]
mod tests {
use super::TopDocs;
use crate::collector::Collector;
use crate::query::{AllQuery, Query, QueryParser};
use crate::schema::{Field, Schema, FAST, STORED, TEXT};
use crate::Index;
use crate::IndexWriter;
use crate::Score;
use crate::{DocAddress, DocId, SegmentReader};
fn make_index() -> Index {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
// writing the segment
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(text_field=>"Hello happy tax payer."));
index_writer.add_document(doc!(text_field=>"Droopy says hello happy tax payer"));
index_writer.add_document(doc!(text_field=>"I like Droopy"));
assert!(index_writer.commit().is_ok());
}
index
}
#[test]
fn test_top_collector_not_at_capacity() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let score_docs: Vec<(Score, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &TopDocs::with_limit(4))
.unwrap();
assert_eq!(
score_docs,
vec![
(0.81221175, DocAddress(0u32, 1)),
(0.5376842, DocAddress(0u32, 2)),
(0.48527452, DocAddress(0, 0))
]
);
}
#[test]
fn test_top_collector_not_at_capacity_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let score_docs: Vec<(Score, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &TopDocs::with_limit(4).and_offset(2))
.unwrap();
assert_eq!(score_docs, vec![(0.48527452, DocAddress(0, 0))]);
}
#[test]
fn test_top_collector_at_capacity() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let score_docs: Vec<(Score, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &TopDocs::with_limit(2))
.unwrap();
assert_eq!(
score_docs,
vec![
(0.81221175, DocAddress(0u32, 1)),
(0.5376842, DocAddress(0u32, 2)),
]
);
}
#[test]
fn test_top_collector_at_capacity_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let score_docs: Vec<(Score, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &TopDocs::with_limit(2).and_offset(1))
.unwrap();
assert_eq!(
score_docs,
vec![
(0.5376842, DocAddress(0u32, 2)),
(0.48527452, DocAddress(0, 0))
]
);
}
#[test]
fn test_top_collector_stable_sorting() {
let index = make_index();
// using AllQuery to get a constant score
let searcher = index.reader().unwrap().searcher();
let page_1 = searcher.search(&AllQuery, &TopDocs::with_limit(2)).unwrap();
let page_2 = searcher.search(&AllQuery, &TopDocs::with_limit(3)).unwrap();
// precondition for the test to be meaningful: we did get documents
// with the same score
assert!(page_1.iter().all(|result| result.0 == page_1[0].0));
assert!(page_2.iter().all(|result| result.0 == page_2[0].0));
// sanity check since we're relying on make_index()
assert_eq!(page_1.len(), 2);
assert_eq!(page_2.len(), 3);
assert_eq!(page_1, &page_2[..page_1.len()]);
}
#[test]
#[should_panic]
fn test_top_0() {
TopDocs::with_limit(0);
}
const TITLE: &str = "title";
const SIZE: &str = "size";
#[test]
fn test_top_field_collector_not_at_capacity() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field(TITLE, TEXT);
let size = schema_builder.add_u64_field(SIZE, FAST);
let schema = schema_builder.build();
let (index, query) = index("beer", title, schema, |index_writer| {
index_writer.add_document(doc!(
title => "bottle of beer",
size => 12u64,
));
index_writer.add_document(doc!(
title => "growler of beer",
size => 64u64,
));
index_writer.add_document(doc!(
title => "pint of beer",
size => 16u64,
));
});
let searcher = index.reader().unwrap().searcher();
let top_collector = TopDocs::with_limit(4).order_by_u64_field(size);
let top_docs: Vec<(u64, DocAddress)> = searcher.search(&query, &top_collector).unwrap();
assert_eq!(
top_docs,
vec![
(64, DocAddress(0, 1)),
(16, DocAddress(0, 2)),
(12, DocAddress(0, 0))
]
);
}
#[test]
#[should_panic]
fn test_field_does_not_exist() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field(TITLE, TEXT);
let size = schema_builder.add_u64_field(SIZE, FAST);
let schema = schema_builder.build();
let (index, _) = index("beer", title, schema, |index_writer| {
index_writer.add_document(doc!(
title => "bottle of beer",
size => 12u64,
));
});
let searcher = index.reader().unwrap().searcher();
let top_collector = TopDocs::with_limit(4).order_by_u64_field(Field::from_field_id(2));
let segment_reader = searcher.segment_reader(0u32);
top_collector
.for_segment(0, segment_reader)
.expect("should panic");
}
#[test]
fn test_field_not_fast_field() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field(TITLE, TEXT);
let size = schema_builder.add_u64_field(SIZE, STORED);
let schema = schema_builder.build();
let (index, _) = index("beer", title, schema, |index_writer| {
index_writer.add_document(doc!(
title => "bottle of beer",
size => 12u64,
));
});
let searcher = index.reader().unwrap().searcher();
let segment = searcher.segment_reader(0);
let top_collector = TopDocs::with_limit(4).order_by_u64_field(size);
let err = top_collector.for_segment(0, segment);
if let Err(crate::TantivyError::SchemaError(msg)) = err {
assert_eq!(
msg,
"Field requested (Field(1)) is not a i64/u64 fast field."
);
} else {
assert!(false);
}
}
#[test]
fn test_tweak_score_top_collector_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let collector = TopDocs::with_limit(2).and_offset(1).tweak_score(
move |_segment_reader: &SegmentReader| move |doc: DocId, _original_score: Score| doc,
);
let score_docs: Vec<(u32, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &collector)
.unwrap();
assert_eq!(
score_docs,
vec![(1, DocAddress(0, 1)), (0, DocAddress(0, 0)),]
);
}
#[test]
fn test_custom_score_top_collector_with_offset() {
let index = make_index();
let field = index.schema().get_field("text").unwrap();
let query_parser = QueryParser::for_index(&index, vec![field]);
let text_query = query_parser.parse_query("droopy tax").unwrap();
let collector = TopDocs::with_limit(2)
.and_offset(1)
.custom_score(move |_segment_reader: &SegmentReader| move |doc: DocId| doc);
let score_docs: Vec<(u32, DocAddress)> = index
.reader()
.unwrap()
.searcher()
.search(&text_query, &collector)
.unwrap();
assert_eq!(
score_docs,
vec![(1, DocAddress(0, 1)), (0, DocAddress(0, 0)),]
);
}
fn index(
query: &str,
query_field: Field,
schema: Schema,
mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
) -> (Index, Box<dyn Query>) {
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
doc_adder(&mut index_writer);
index_writer.commit().unwrap();
let query_parser = QueryParser::for_index(&index, vec![query_field]);
let query = query_parser.parse_query(query).unwrap();
(index, query)
}
}

129
src/collector/tweak_score_top_collector.rs
View File

@@ -1,129 +0,0 @@
use crate::collector::top_collector::{TopCollector, TopSegmentCollector};
use crate::collector::{Collector, SegmentCollector};
use crate::DocAddress;
use crate::{DocId, Result, Score, SegmentReader};
pub(crate) struct TweakedScoreTopCollector<TScoreTweaker, TScore = Score> {
score_tweaker: TScoreTweaker,
collector: TopCollector<TScore>,
}
impl<TScoreTweaker, TScore> TweakedScoreTopCollector<TScoreTweaker, TScore>
where
TScore: Clone + PartialOrd,
{
pub fn new(
score_tweaker: TScoreTweaker,
collector: TopCollector<TScore>,
) -> TweakedScoreTopCollector<TScoreTweaker, TScore> {
TweakedScoreTopCollector {
score_tweaker,
collector,
}
}
}
/// A `ScoreSegmentTweaker` makes it possible to modify the default score
/// for a given document belonging to a specific segment.
///
/// It is the segment local version of the [`ScoreTweaker`](./trait.ScoreTweaker.html).
pub trait ScoreSegmentTweaker<TScore>: 'static {
/// Tweak the given `score` for the document `doc`.
fn score(&mut self, doc: DocId, score: Score) -> TScore;
}
/// `ScoreTweaker` makes it possible to tweak the score
/// emitted by the scorer into another one.
///
/// The `ScoreTweaker` itself does not make much of the computation itself.
/// Instead, it helps constructing `Self::Child` instances that will compute
/// the score at a segment scale.
pub trait ScoreTweaker<TScore>: Sync {
/// Type of the associated [`ScoreSegmentTweaker`](./trait.ScoreSegmentTweaker.html).
type Child: ScoreSegmentTweaker<TScore>;
/// Builds a child tweaker for a specific segment. The child scorer is associated to
/// a specific segment.
fn segment_tweaker(&self, segment_reader: &SegmentReader) -> Result<Self::Child>;
}
impl<TScoreTweaker, TScore> Collector for TweakedScoreTopCollector<TScoreTweaker, TScore>
where
TScoreTweaker: ScoreTweaker<TScore>,
TScore: 'static + PartialOrd + Clone + Send + Sync,
{
type Fruit = Vec<(TScore, DocAddress)>;
type Child = TopTweakedScoreSegmentCollector<TScoreTweaker::Child, TScore>;
fn for_segment(
&self,
segment_local_id: u32,
segment_reader: &SegmentReader,
) -> Result<Self::Child> {
let segment_scorer = self.score_tweaker.segment_tweaker(segment_reader)?;
let segment_collector = self
.collector
.for_segment(segment_local_id, segment_reader)?;
Ok(TopTweakedScoreSegmentCollector {
segment_collector,
segment_scorer,
})
}
fn requires_scoring(&self) -> bool {
true
}
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit> {
self.collector.merge_fruits(segment_fruits)
}
}
pub struct TopTweakedScoreSegmentCollector<TSegmentScoreTweaker, TScore>
where
TScore: 'static + PartialOrd + Clone + Send + Sync + Sized,
TSegmentScoreTweaker: ScoreSegmentTweaker<TScore>,
{
segment_collector: TopSegmentCollector<TScore>,
segment_scorer: TSegmentScoreTweaker,
}
impl<TSegmentScoreTweaker, TScore> SegmentCollector
for TopTweakedScoreSegmentCollector<TSegmentScoreTweaker, TScore>
where
TScore: 'static + PartialOrd + Clone + Send + Sync,
TSegmentScoreTweaker: 'static + ScoreSegmentTweaker<TScore>,
{
type Fruit = Vec<(TScore, DocAddress)>;
fn collect(&mut self, doc: DocId, score: Score) {
let score = self.segment_scorer.score(doc, score);
self.segment_collector.collect(doc, score);
}
fn harvest(self) -> Vec<(TScore, DocAddress)> {
self.segment_collector.harvest()
}
}
impl<F, TScore, TSegmentScoreTweaker> ScoreTweaker<TScore> for F
where
F: 'static + Send + Sync + Fn(&SegmentReader) -> TSegmentScoreTweaker,
TSegmentScoreTweaker: ScoreSegmentTweaker<TScore>,
{
type Child = TSegmentScoreTweaker;
fn segment_tweaker(&self, segment_reader: &SegmentReader) -> Result<Self::Child> {
Ok((self)(segment_reader))
}
}
impl<F, TScore> ScoreSegmentTweaker<TScore> for F
where
F: 'static + FnMut(DocId, Score) -> TScore,
{
fn score(&mut self, doc: DocId, score: Score) -> TScore {
(self)(doc, score)
}
}

95
src/common/bitpacker.rs
View File

@@ -1,6 +1,9 @@
use byteorder::{ByteOrder, LittleEndian, WriteBytesExt};
use std::io::Write;
use std::io;
use common::serialize::BinarySerializable;
use std::mem;
use std::ops::Deref;
use std::ptr;
pub(crate) struct BitPacker {
mini_buffer: u64,
@@ -15,7 +18,7 @@ impl BitPacker {
}
}
pub fn write<TWrite: io::Write>(
pub fn write<TWrite: Write>(
&mut self,
val: u64,
num_bits: u8,
@@ -25,14 +28,14 @@ impl BitPacker {
let num_bits = num_bits as usize;
if self.mini_buffer_written + num_bits > 64 {
self.mini_buffer |= val_u64.wrapping_shl(self.mini_buffer_written as u32);
output.write_u64::<LittleEndian>(self.mini_buffer)?;
self.mini_buffer.serialize(output)?;
self.mini_buffer = val_u64.wrapping_shr((64 - self.mini_buffer_written) as u32);
self.mini_buffer_written = self.mini_buffer_written + num_bits - 64;
} else {
self.mini_buffer |= val_u64 << self.mini_buffer_written;
self.mini_buffer_written += num_bits;
if self.mini_buffer_written == 64 {
output.write_u64::<LittleEndian>(self.mini_buffer)?;
self.mini_buffer.serialize(output)?;
self.mini_buffer_written = 0;
self.mini_buffer = 0u64;
}
@@ -40,18 +43,17 @@ impl BitPacker {
Ok(())
}
pub fn flush<TWrite: io::Write>(&mut self, output: &mut TWrite) -> io::Result<()> {
pub fn flush<TWrite: Write>(&mut self, output: &mut TWrite) -> io::Result<()> {
if self.mini_buffer_written > 0 {
let num_bytes = (self.mini_buffer_written + 7) / 8;
let mut arr: [u8; 8] = [0u8; 8];
LittleEndian::write_u64(&mut arr, self.mini_buffer);
let arr: [u8; 8] = unsafe { mem::transmute::<u64, [u8; 8]>(self.mini_buffer) };
output.write_all(&arr[..num_bytes])?;
self.mini_buffer_written = 0;
}
Ok(())
}
pub fn close<TWrite: io::Write>(&mut self, output: &mut TWrite) -> io::Result<()> {
pub fn close<TWrite: Write>(&mut self, output: &mut TWrite) -> io::Result<()> {
self.flush(output)?;
// Padding the write file to simplify reads.
output.write_all(&[0u8; 7])?;
@@ -64,7 +66,7 @@ pub struct BitUnpacker<Data>
where
Data: Deref<Target = [u8]>,
{
num_bits: u64,
num_bits: usize,
mask: u64,
data: Data,
}
@@ -80,13 +82,13 @@ where
(1u64 << num_bits) - 1u64
};
BitUnpacker {
num_bits: u64::from(num_bits),
num_bits: num_bits as usize,
mask,
data,
}
}
pub fn get(&self, idx: u64) -> u64 {
pub fn get(&self, idx: usize) -> u64 {
if self.num_bits == 0 {
return 0u64;
}
@@ -96,13 +98,55 @@ where
let addr_in_bits = idx * num_bits;
let addr = addr_in_bits >> 3;
let bit_shift = addr_in_bits & 7;
debug_assert!(
addr + 8 <= data.len() as u64,
"The fast field field should have been padded with 7 bytes."
);
let val_unshifted_unmasked: u64 = LittleEndian::read_u64(&data[(addr as usize)..]);
let val_shifted = (val_unshifted_unmasked >> bit_shift) as u64;
val_shifted & mask
if cfg!(feature = "simdcompression") {
// for simdcompression,
// the bitpacker is only used for fastfields,
// and we expect them to be always padded.
debug_assert!(
addr + 8 <= data.len(),
"The fast field field should have been padded with 7 bytes."
);
let val_unshifted_unmasked: u64 = unsafe { ptr::read_unaligned(data[addr..].as_ptr() as *const u64) };
let val_shifted = (val_unshifted_unmasked >> bit_shift) as u64;
val_shifted & mask
} else {
let val_unshifted_unmasked: u64 = if addr + 8 <= data.len() {
unsafe { ptr::read_unaligned(data[addr..].as_ptr() as *const u64) }
} else {
let mut buffer = [0u8; 8];
for i in addr..data.len() {
buffer[i - addr] += data[i];
}
unsafe { ptr::read_unaligned(buffer[..].as_ptr() as *const u64) }
};
let val_shifted = val_unshifted_unmasked >> (bit_shift as u64);
val_shifted & mask
}
}
/// Reads a range of values from the fast field.
///
/// The range of values read is from
/// `[start..start + output.len()[`
pub fn get_range(&self, start: u32, output: &mut [u64]) {
if self.num_bits == 0 {
for val in output.iter_mut() {
*val = 0u64;
}
} else {
let data: &[u8] = &*self.data;
let num_bits = self.num_bits;
let mask = self.mask;
let mut addr_in_bits = (start as usize) * num_bits;
for output_val in output.iter_mut() {
let addr = addr_in_bits >> 3;
let bit_shift = addr_in_bits & 7;
let val_unshifted_unmasked: u64 = unsafe { ptr::read_unaligned(data[addr..].as_ptr() as *const u64) };
let val_shifted = (val_unshifted_unmasked >> bit_shift) as u64;
*output_val = val_shifted & mask;
addr_in_bits += num_bits;
}
}
}
}
@@ -129,7 +173,7 @@ mod test {
fn test_bitpacker_util(len: usize, num_bits: u8) {
let (bitunpacker, vals) = create_fastfield_bitpacker(len, num_bits);
for (i, val) in vals.iter().enumerate() {
assert_eq!(bitunpacker.get(i as u64), *val);
assert_eq!(bitunpacker.get(i), *val);
}
}
@@ -141,4 +185,17 @@ mod test {
test_bitpacker_util(6, 14);
test_bitpacker_util(1000, 14);
}
#[test]
fn test_bitpacker_range() {
let (bitunpacker, vals) = create_fastfield_bitpacker(100_000, 12);
let buffer_len = 100;
let mut buffer = vec![0u64; buffer_len];
for start in vec![0, 10, 20, 100, 1_000] {
bitunpacker.get_range(start as u32, &mut buffer[..]);
for i in 0..buffer_len {
assert_eq!(buffer[i], vals[start + i]);
}
}
}
}

65
src/common/bitset.rs
View File

@@ -5,7 +5,7 @@ use std::u64;
pub(crate) struct TinySet(u64);
impl fmt::Debug for TinySet {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.into_iter().collect::<Vec<u32>>().fmt(f)
}
}
@@ -33,27 +33,18 @@ impl TinySet {
TinySet(0u64)
}
pub fn clear(&mut self) {
self.0 = 0u64;
}
/// Returns the complement of the set in `[0, 64[`.
fn complement(self) -> TinySet {
fn complement(&self) -> TinySet {
TinySet(!self.0)
}
/// Returns true iff the `TinySet` contains the element `el`.
pub fn contains(self, el: u32) -> bool {
pub fn contains(&self, el: u32) -> bool {
!self.intersect(TinySet::singleton(el)).is_empty()
}
/// Returns the number of elements in the TinySet.
pub fn len(self) -> u32 {
self.0.count_ones()
}
/// Returns the intersection of `self` and `other`
pub fn intersect(self, other: TinySet) -> TinySet {
pub fn intersect(&self, other: TinySet) -> TinySet {
TinySet(self.0 & other.0)
}
@@ -86,7 +77,7 @@ impl TinySet {
/// Returns true iff the `TinySet` is empty.
#[inline(always)]
pub fn is_empty(self) -> bool {
pub fn is_empty(&self) -> bool {
self.0 == 0u64
}
@@ -118,12 +109,22 @@ impl TinySet {
pub fn range_greater_or_equal(from_included: u32) -> TinySet {
TinySet::range_lower(from_included).complement()
}
pub fn clear(&mut self) {
self.0 = 0u64;
}
pub fn len(&self) -> u32 {
self.0.count_ones()
}
}
#[derive(Clone)]
pub struct BitSet {
tinysets: Box<[TinySet]>,
len: usize,
len: usize, //< Technically it should be u32, but we
// count multiple inserts.
// `usize` guards us from overflow.
max_value: u32,
}
@@ -201,14 +202,15 @@ impl BitSet {
#[cfg(test)]
mod tests {
extern crate test;
use tests;
use std::collections::HashSet;
use super::BitSet;
use super::TinySet;
use crate::docset::{DocSet, TERMINATED};
use crate::query::BitSetDocSet;
use crate::tests;
use crate::tests::generate_nonunique_unsorted;
use tests::generate_nonunique_unsorted;
use std::collections::BTreeSet;
use std::collections::HashSet;
use query::BitSetDocSet;
use docset::DocSet;
#[test]
fn test_tiny_set() {
@@ -265,25 +267,23 @@ mod tests {
#[test]
fn test_bitset_large() {
let arr = generate_nonunique_unsorted(100_000, 5_000);
let arr = generate_nonunique_unsorted(1_000_000, 50_000);
let mut btreeset: BTreeSet<u32> = BTreeSet::new();
let mut bitset = BitSet::with_max_value(100_000);
let mut bitset = BitSet::with_max_value(1_000_000);
for el in arr {
btreeset.insert(el);
bitset.insert(el);
}
for i in 0..100_000 {
for i in 0..1_000_000 {
assert_eq!(btreeset.contains(&i), bitset.contains(i));
}
assert_eq!(btreeset.len(), bitset.len());
let mut bitset_docset = BitSetDocSet::from(bitset);
let mut remaining = true;
for el in btreeset.into_iter() {
assert!(remaining);
bitset_docset.advance();
assert_eq!(bitset_docset.doc(), el);
remaining = bitset_docset.advance() != TERMINATED;
}
assert!(!remaining);
assert!(!bitset_docset.advance());
}
#[test]
@@ -343,7 +343,7 @@ mod tests {
#[test]
fn test_bitset_clear() {
let mut bitset = BitSet::with_max_value(1_000);
let els = tests::sample(1_000, 0.01f64);
let els = tests::sample(1_000, 0.01f32);
for &el in &els {
bitset.insert(el);
}
@@ -353,14 +353,6 @@ mod tests {
assert!(!bitset.contains(el));
}
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use super::BitSet;
use super::TinySet;
use test;
#[bench]
fn bench_tinyset_pop(b: &mut test::Bencher) {
@@ -393,4 +385,5 @@ mod bench {
fn bench_bitset_initialize(b: &mut test::Bencher) {
b.iter(|| BitSet::with_max_value(1_000_000));
}
}

70
src/common/composite_file.rs
View File

@@ -1,14 +1,12 @@
use crate::common::BinarySerializable;
use crate::common::CountingWriter;
use crate::common::VInt;
use crate::directory::ReadOnlySource;
use crate::directory::{TerminatingWrite, WritePtr};
use crate::schema::Field;
use crate::space_usage::FieldUsage;
use crate::space_usage::PerFieldSpaceUsage;
use std::collections::HashMap;
use std::io::Write;
use common::CountingWriter;
use std::collections::HashMap;
use schema::Field;
use common::VInt;
use directory::WritePtr;
use std::io::{self, Read};
use directory::ReadOnlySource;
use common::BinarySerializable;
#[derive(Eq, PartialEq, Hash, Copy, Ord, PartialOrd, Clone, Debug)]
pub struct FileAddr {
@@ -32,17 +30,20 @@ impl BinarySerializable for FileAddr {
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
let field = Field::deserialize(reader)?;
let idx = VInt::deserialize(reader)?.0 as usize;
Ok(FileAddr { field, idx })
Ok(FileAddr {
field,
idx,
})
}
}
/// A `CompositeWrite` is used to write a `CompositeFile`.
pub struct CompositeWrite<W = WritePtr> {
write: CountingWriter<W>,
offsets: HashMap<FileAddr, u64>,
offsets: HashMap<FileAddr, usize>,
}
impl<W: TerminatingWrite + Write> CompositeWrite<W> {
impl<W: Write> CompositeWrite<W> {
/// Crate a new API writer that writes a composite file
/// in a given write.
pub fn wrap(w: W) -> CompositeWrite<W> {
@@ -66,7 +67,7 @@ impl<W: TerminatingWrite + Write> CompositeWrite<W> {
&mut self.write
}
/// Close the composite file
/// Close the composite file.
///
/// An index of the different field offsets
/// will be written as a footer.
@@ -74,8 +75,7 @@ impl<W: TerminatingWrite + Write> CompositeWrite<W> {
let footer_offset = self.write.written_bytes();
VInt(self.offsets.len() as u64).serialize(&mut self.write)?;
let mut offset_fields: Vec<_> = self
.offsets
let mut offset_fields: Vec<_> = self.offsets
.iter()
.map(|(file_addr, offset)| (*offset, *file_addr))
.collect();
@@ -91,7 +91,8 @@ impl<W: TerminatingWrite + Write> CompositeWrite<W> {
let footer_len = (self.write.written_bytes() - footer_offset) as u32;
footer_len.serialize(&mut self.write)?;
self.write.terminate()
self.write.flush()?;
Ok(())
}
}
@@ -114,6 +115,7 @@ impl CompositeFile {
let end = data.len();
let footer_len_data = data.slice_from(end - 4);
let footer_len = u32::deserialize(&mut footer_len_data.as_slice())? as usize;
let footer_start = end - 4 - footer_len;
let footer_data = data.slice(footer_start, footer_start + footer_len);
let mut footer_buffer = footer_data.as_slice();
@@ -164,31 +166,20 @@ impl CompositeFile {
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<ReadOnlySource> {
self.offsets_index
.get(&FileAddr { field, idx })
.get(&FileAddr { field, idx, })
.map(|&(from, to)| self.data.slice(from, to))
}
pub fn space_usage(&self) -> PerFieldSpaceUsage {
let mut fields = HashMap::new();
for (&field_addr, &(start, end)) in self.offsets_index.iter() {
fields
.entry(field_addr.field)
.or_insert_with(|| FieldUsage::empty(field_addr.field))
.add_field_idx(field_addr.idx, end - start);
}
PerFieldSpaceUsage::new(fields)
}
}
#[cfg(test)]
mod test {
use super::{CompositeFile, CompositeWrite};
use crate::common::BinarySerializable;
use crate::common::VInt;
use crate::directory::{Directory, RAMDirectory};
use crate::schema::Field;
use std::io::Write;
use super::{CompositeFile, CompositeWrite};
use directory::{Directory, RAMDirectory};
use schema::Field;
use common::VInt;
use common::BinarySerializable;
use std::path::Path;
#[test]
@@ -199,13 +190,13 @@ mod test {
let w = directory.open_write(path).unwrap();
let mut composite_write = CompositeWrite::wrap(w);
{
let mut write_0 = composite_write.for_field(Field::from_field_id(0u32));
let mut write_0 = composite_write.for_field(Field(0u32));
VInt(32431123u64).serialize(&mut write_0).unwrap();
write_0.flush().unwrap();
}
{
let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
let mut write_4 = composite_write.for_field(Field(4u32));
VInt(2).serialize(&mut write_4).unwrap();
write_4.flush().unwrap();
}
@@ -215,18 +206,14 @@ mod test {
let r = directory.open_read(path).unwrap();
let composite_file = CompositeFile::open(&r).unwrap();
{
let file0 = composite_file
.open_read(Field::from_field_id(0u32))
.unwrap();
let file0 = composite_file.open_read(Field(0u32)).unwrap();
let mut file0_buf = file0.as_slice();
let payload_0 = VInt::deserialize(&mut file0_buf).unwrap().0;
assert_eq!(file0_buf.len(), 0);
assert_eq!(payload_0, 32431123u64);
}
{
let file4 = composite_file
.open_read(Field::from_field_id(4u32))
.unwrap();
let file4 = composite_file.open_read(Field(4u32)).unwrap();
let mut file4_buf = file4.as_slice();
let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
assert_eq!(file4_buf.len(), 0);
@@ -234,4 +221,5 @@ mod test {
}
}
}
}

29
src/common/counting_writer.rs
View File

@@ -1,11 +1,9 @@
use crate::directory::AntiCallToken;
use crate::directory::TerminatingWrite;
use std::io;
use std::io::Write;
use std::io;
pub struct CountingWriter<W> {
underlying: W,
written_bytes: u64,
written_bytes: usize,
}
impl<W: Write> CountingWriter<W> {
@@ -16,11 +14,11 @@ impl<W: Write> CountingWriter<W> {
}
}
pub fn written_bytes(&self) -> u64 {
pub fn written_bytes(&self) -> usize {
self.written_bytes
}
pub fn finish(mut self) -> io::Result<(W, u64)> {
pub fn finish(mut self) -> io::Result<(W, usize)> {
self.flush()?;
Ok((self.underlying, self.written_bytes))
}
@@ -29,28 +27,15 @@ impl<W: Write> CountingWriter<W> {
impl<W: Write> Write for CountingWriter<W> {
fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
let written_size = self.underlying.write(buf)?;
self.written_bytes += written_size as u64;
self.written_bytes += written_size;
Ok(written_size)
}
fn write_all(&mut self, buf: &[u8]) -> io::Result<()> {
self.underlying.write_all(buf)?;
self.written_bytes += buf.len() as u64;
Ok(())
}
fn flush(&mut self) -> io::Result<()> {
self.underlying.flush()
}
}
impl<W: TerminatingWrite> TerminatingWrite for CountingWriter<W> {
fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
self.flush()?;
self.underlying.terminate_ref(token)
}
}
#[cfg(test)]
mod test {
@@ -63,8 +48,8 @@ mod test {
let mut counting_writer = CountingWriter::wrap(buffer);
let bytes = (0u8..10u8).collect::<Vec<u8>>();
counting_writer.write_all(&bytes).unwrap();
let (w, len): (Vec<u8>, u64) = counting_writer.finish().unwrap();
assert_eq!(len, 10u64);
let (w, len): (Vec<u8>, usize) = counting_writer.finish().unwrap();
assert_eq!(len, 10);
assert_eq!(w.len(), 10);
}
}

126
src/common/mod.rs
View File

@@ -1,35 +1,19 @@
mod serialize;
mod vint;
mod counting_writer;
mod composite_file;
pub mod bitpacker;
mod bitset;
mod composite_file;
mod counting_writer;
mod serialize;
mod vint;
pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
pub use self::serialize::{BinarySerializable, FixedSize};
pub use self::vint::VInt;
pub use self::counting_writer::CountingWriter;
pub use self::bitset::BitSet;
pub(crate) use self::bitset::TinySet;
pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
pub use self::counting_writer::CountingWriter;
pub use self::serialize::{BinarySerializable, FixedSize};
pub use self::vint::{read_u32_vint, serialize_vint_u32, write_u32_vint, VInt};
pub use byteorder::LittleEndian as Endianness;
/// Segment's max doc must be `< MAX_DOC_LIMIT`.
///
/// We do not allow segments with more than
pub const MAX_DOC_LIMIT: u32 = 1 << 31;
pub fn minmax<I, T>(mut vals: I) -> Option<(T, T)>
where
I: Iterator<Item = T>,
T: Copy + Ord,
{
if let Some(first_el) = vals.next() {
return Some(vals.fold((first_el, first_el), |(min_val, max_val), el| {
(min_val.min(el), max_val.max(el))
}));
}
None
}
use std::io;
/// Computes the number of bits that will be used for bitpacking.
///
@@ -68,6 +52,11 @@ pub(crate) fn is_power_of_2(n: usize) -> bool {
(n > 0) && (n & (n - 1) == 0)
}
/// Create a default io error given a string.
pub(crate) fn make_io_err(msg: String) -> io::Error {
io::Error::new(io::ErrorKind::Other, msg)
}
/// Has length trait
pub trait HasLen {
/// Return length
@@ -112,54 +101,16 @@ pub fn u64_to_i64(val: u64) -> i64 {
(val ^ HIGHEST_BIT) as i64
}
/// Maps a `f64` to `u64`
///
/// For simplicity, tantivy internally handles `f64` as `u64`.
/// The mapping is defined by this function.
///
/// Maps `f64` to `u64` so that lexical order is preserved.
///
/// This is more suited than simply casting (`val as u64`)
/// which would truncate the result
///
/// # See also
/// The [reverse mapping is `u64_to_f64`](./fn.u64_to_f64.html).
#[inline(always)]
pub fn f64_to_u64(val: f64) -> u64 {
let bits = val.to_bits();
if val.is_sign_positive() {
bits ^ HIGHEST_BIT
} else {
!bits
}
}
/// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html).
#[inline(always)]
pub fn u64_to_f64(val: u64) -> f64 {
f64::from_bits(if val & HIGHEST_BIT != 0 {
val ^ HIGHEST_BIT
} else {
!val
})
}
#[cfg(test)]
pub(crate) mod test {
pub use super::minmax;
use super::{compute_num_bits, i64_to_u64, u64_to_i64};
pub use super::serialize::test::fixed_size_test;
use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
use std::f64;
fn test_i64_converter_helper(val: i64) {
assert_eq!(u64_to_i64(i64_to_u64(val)), val);
}
fn test_f64_converter_helper(val: f64) {
assert_eq!(u64_to_f64(f64_to_u64(val)), val);
}
#[test]
fn test_i64_converter() {
assert_eq!(i64_to_u64(i64::min_value()), u64::min_value());
@@ -172,29 +123,6 @@ pub(crate) mod test {
}
}
#[test]
fn test_f64_converter() {
test_f64_converter_helper(f64::INFINITY);
test_f64_converter_helper(f64::NEG_INFINITY);
test_f64_converter_helper(0.0);
test_f64_converter_helper(-0.0);
test_f64_converter_helper(1.0);
test_f64_converter_helper(-1.0);
}
#[test]
fn test_f64_order() {
assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
.contains(&f64_to_u64(f64::NAN))); //nan is not a number
assert!(f64_to_u64(1.5) > f64_to_u64(1.0)); //same exponent, different mantissa
assert!(f64_to_u64(2.0) > f64_to_u64(1.0)); //same mantissa, different exponent
assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa
assert!(f64_to_u64(1.0) > f64_to_u64(-1.0)); // pos > neg
assert!(f64_to_u64(-1.5) < f64_to_u64(-1.0));
assert!(f64_to_u64(-2.0) < f64_to_u64(1.0));
assert!(f64_to_u64(-2.0) < f64_to_u64(-1.5));
}
#[test]
fn test_compute_num_bits() {
assert_eq!(compute_num_bits(1), 1u8);
@@ -206,28 +134,4 @@ pub(crate) mod test {
assert_eq!(compute_num_bits(256), 9u8);
assert_eq!(compute_num_bits(5_000_000_000), 33u8);
}
#[test]
fn test_max_doc() {
// this is the first time I write a unit test for a constant.
assert!(((super::MAX_DOC_LIMIT - 1) as i32) >= 0);
assert!((super::MAX_DOC_LIMIT as i32) < 0);
}
#[test]
fn test_minmax_empty() {
let vals: Vec<u32> = vec![];
assert_eq!(minmax(vals.into_iter()), None);
}
#[test]
fn test_minmax_one() {
assert_eq!(minmax(vec![1].into_iter()), Some((1, 1)));
}
#[test]
fn test_minmax_two() {
assert_eq!(minmax(vec![1, 2].into_iter()), Some((1, 2)));
assert_eq!(minmax(vec![2, 1].into_iter()), Some((1, 2)));
}
}

33
src/common/serialize.rs
View File

@@ -1,10 +1,10 @@
use crate::common::Endianness;
use crate::common::VInt;
use byteorder::{ReadBytesExt, WriteBytesExt};
use common::Endianness;
use std::fmt;
use std::io;
use std::io::Read;
use std::io::Write;
use std::io::Read;
use std::io;
use common::VInt;
/// Trait for a simple binary serialization.
pub trait BinarySerializable: fmt::Debug + Sized {
@@ -102,19 +102,6 @@ impl FixedSize for i64 {
const SIZE_IN_BYTES: usize = 8;
}
impl BinarySerializable for f64 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_f64::<Endianness>(*self)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
reader.read_f64::<Endianness>()
}
}
impl FixedSize for f64 {
const SIZE_IN_BYTES: usize = 8;
}
impl BinarySerializable for u8 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_u8(*self)
@@ -148,8 +135,8 @@ impl BinarySerializable for String {
#[cfg(test)]
pub mod test {
use common::VInt;
use super::*;
use crate::common::VInt;
pub fn fixed_size_test<O: BinarySerializable + FixedSize + Default>() {
let mut buffer = Vec::new();
@@ -185,11 +172,6 @@ pub mod test {
fixed_size_test::<i64>();
}
#[test]
fn test_serialize_f64() {
fixed_size_test::<f64>();
}
#[test]
fn test_serialize_u64() {
fixed_size_test::<u64>();
@@ -199,7 +181,10 @@ pub mod test {
fn test_serialize_string() {
assert_eq!(serialize_test(String::from("")), 1);
assert_eq!(serialize_test(String::from("ぽよぽよ")), 1 + 3 * 4);
assert_eq!(serialize_test(String::from("富士さん見える。")), 1 + 3 * 8);
assert_eq!(
serialize_test(String::from("富士さん見える。")),
1 + 3 * 8
);
}
#[test]

211
src/common/vint.rs
View File

@@ -1,109 +1,12 @@
use super::BinarySerializable;
use byteorder::{ByteOrder, LittleEndian};
use std::io;
use std::io::Read;
use std::io::Write;
use std::io::Read;
/// Wrapper over a `u64` that serializes as a variable int.
#[derive(Debug, Eq, PartialEq)]
pub struct VInt(pub u64);
const STOP_BIT: u8 = 128;
pub fn serialize_vint_u32(val: u32) -> (u64, usize) {
const START_2: u64 = 1 << 7;
const START_3: u64 = 1 << 14;
const START_4: u64 = 1 << 21;
const START_5: u64 = 1 << 28;
const STOP_1: u64 = START_2 - 1;
const STOP_2: u64 = START_3 - 1;
const STOP_3: u64 = START_4 - 1;
const STOP_4: u64 = START_5 - 1;
const MASK_1: u64 = 127;
const MASK_2: u64 = MASK_1 << 7;
const MASK_3: u64 = MASK_2 << 7;
const MASK_4: u64 = MASK_3 << 7;
const MASK_5: u64 = MASK_4 << 7;
let val = u64::from(val);
const STOP_BIT: u64 = 128u64;
match val {
0..=STOP_1 => (val | STOP_BIT, 1),
START_2..=STOP_2 => (
(val & MASK_1) | ((val & MASK_2) << 1) | (STOP_BIT << (8)),
2,
),
START_3..=STOP_3 => (
(val & MASK_1) | ((val & MASK_2) << 1) | ((val & MASK_3) << 2) | (STOP_BIT << (8 * 2)),
3,
),
START_4..=STOP_4 => (
(val & MASK_1)
| ((val & MASK_2) << 1)
| ((val & MASK_3) << 2)
| ((val & MASK_4) << 3)
| (STOP_BIT << (8 * 3)),
4,
),
_ => (
(val & MASK_1)
| ((val & MASK_2) << 1)
| ((val & MASK_3) << 2)
| ((val & MASK_4) << 3)
| ((val & MASK_5) << 4)
| (STOP_BIT << (8 * 4)),
5,
),
}
}
/// Returns the number of bytes covered by a
/// serialized vint `u32`.
///
/// Expects a buffer data that starts
/// by the serialized `vint`, scans at most 5 bytes ahead until
/// it finds the vint final byte.
///
/// # May Panic
/// If the payload does not start by a valid `vint`
fn vint_len(data: &[u8]) -> usize {
for (i, &val) in data.iter().enumerate().take(5) {
if val >= STOP_BIT {
return i + 1;
}
}
panic!("Corrupted data. Invalid VInt 32");
}
/// Reads a vint `u32` from a buffer, and
/// consumes its payload data.
///
/// # Panics
///
/// If the buffer does not start by a valid
/// vint payload
pub fn read_u32_vint(data: &mut &[u8]) -> u32 {
let vlen = vint_len(*data);
let mut result = 0u32;
let mut shift = 0u64;
for &b in &data[..vlen] {
result |= u32::from(b & 127u8) << shift;
shift += 7;
}
*data = &data[vlen..];
result
}
/// Write a `u32` as a vint payload.
pub fn write_u32_vint<W: io::Write>(val: u32, writer: &mut W) -> io::Result<()> {
let (val, num_bytes) = serialize_vint_u32(val);
let mut buffer = [0u8; 8];
LittleEndian::write_u64(&mut buffer, val);
writer.write_all(&buffer[..num_bytes])
}
impl VInt {
pub fn val(&self) -> u64 {
self.0
@@ -112,34 +15,24 @@ impl VInt {
pub fn deserialize_u64<R: Read>(reader: &mut R) -> io::Result<u64> {
VInt::deserialize(reader).map(|vint| vint.0)
}
pub fn serialize_into_vec(&self, output: &mut Vec<u8>) {
let mut buffer = [0u8; 10];
let num_bytes = self.serialize_into(&mut buffer);
output.extend(&buffer[0..num_bytes]);
}
pub fn serialize_into(&self, buffer: &mut [u8; 10]) -> usize {
let mut remaining = self.0;
for (i, b) in buffer.iter_mut().enumerate() {
let next_byte: u8 = (remaining % 128u64) as u8;
remaining /= 128u64;
if remaining == 0u64 {
*b = next_byte | STOP_BIT;
return i + 1;
} else {
*b = next_byte;
}
}
unreachable!();
}
}
impl BinarySerializable for VInt {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
let mut remaining = self.0;
let mut buffer = [0u8; 10];
let num_bytes = self.serialize_into(&mut buffer);
writer.write_all(&buffer[0..num_bytes])
let mut i = 0;
loop {
let next_byte: u8 = (remaining % 128u64) as u8;
remaining /= 128u64;
if remaining == 0u64 {
buffer[i] = next_byte | 128u8;
return writer.write_all(&buffer[0..i + 1]);
} else {
buffer[i] = next_byte;
}
i += 1;
}
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
@@ -149,84 +42,20 @@ impl BinarySerializable for VInt {
loop {
match bytes.next() {
Some(Ok(b)) => {
result |= u64::from(b % 128u8) << shift;
if b >= STOP_BIT {
return Ok(VInt(result));
result += u64::from(b % 128u8) << shift;
if b & 128u8 != 0u8 {
break;
}
shift += 7;
}
_ => {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
"Reach end of buffer while reading VInt",
));
"Reach end of buffer",
))
}
}
}
}
}
#[cfg(test)]
mod tests {
use super::serialize_vint_u32;
use super::VInt;
use crate::common::BinarySerializable;
use byteorder::{ByteOrder, LittleEndian};
fn aux_test_vint(val: u64) {
let mut v = [14u8; 10];
let num_bytes = VInt(val).serialize_into(&mut v);
for i in num_bytes..10 {
assert_eq!(v[i], 14u8);
}
assert!(num_bytes > 0);
if num_bytes < 10 {
assert!(1u64 << (7 * num_bytes) > val);
}
if num_bytes > 1 {
assert!(1u64 << (7 * (num_bytes - 1)) <= val);
}
let serdeser_val = VInt::deserialize(&mut &v[..]).unwrap();
assert_eq!(val, serdeser_val.0);
}
#[test]
fn test_vint() {
aux_test_vint(0);
aux_test_vint(1);
aux_test_vint(5);
aux_test_vint(u64::max_value());
for i in 1..9 {
let power_of_128 = 1u64 << (7 * i);
aux_test_vint(power_of_128 - 1u64);
aux_test_vint(power_of_128);
aux_test_vint(power_of_128 + 1u64);
}
aux_test_vint(10);
}
fn aux_test_serialize_vint_u32(val: u32) {
let mut buffer = [0u8; 10];
let mut buffer2 = [0u8; 10];
let len_vint = VInt(val as u64).serialize_into(&mut buffer);
let (vint, len) = serialize_vint_u32(val);
assert_eq!(len, len_vint, "len wrong for val {}", val);
LittleEndian::write_u64(&mut buffer2, vint);
assert_eq!(&buffer[..len], &buffer2[..len], "array wrong for {}", val);
}
#[test]
fn test_vint_u32() {
aux_test_serialize_vint_u32(0);
aux_test_serialize_vint_u32(1);
aux_test_serialize_vint_u32(5);
for i in 1..3 {
let power_of_128 = 1u32 << (7 * i);
aux_test_serialize_vint_u32(power_of_128 - 1u32);
aux_test_serialize_vint_u32(power_of_128);
aux_test_serialize_vint_u32(power_of_128 + 1u32);
}
aux_test_serialize_vint_u32(u32::max_value());
Ok(VInt(result))
}
}

195
src/postings/compression/mod.rs → src/compression/mod.rs
View File

@@ -1,15 +1,20 @@
use crate::common::FixedSize;
use crate::docset::TERMINATED;
#![allow(dead_code)]
mod stream;
pub const COMPRESSION_BLOCK_SIZE: usize = 128;
const COMPRESSED_BLOCK_MAX_SIZE: usize = COMPRESSION_BLOCK_SIZE * 4 + 1;
pub use self::stream::CompressedIntStream;
use bitpacking::{BitPacker, BitPacker4x};
pub const COMPRESSION_BLOCK_SIZE: usize = BitPacker4x::BLOCK_LEN;
const COMPRESSED_BLOCK_MAX_SIZE: usize = COMPRESSION_BLOCK_SIZE * u32::SIZE_IN_BYTES;
mod vint;
/// Returns the size in bytes of a compressed block, given `num_bits`.
pub fn compressed_block_size(num_bits: u8) -> usize {
(num_bits as usize) * COMPRESSION_BLOCK_SIZE / 8
1 + (num_bits as usize) * COMPRESSION_BLOCK_SIZE / 8
}
pub struct BlockEncoder {
@@ -18,12 +23,6 @@ pub struct BlockEncoder {
pub output_len: usize,
}
impl Default for BlockEncoder {
fn default() -> Self {
BlockEncoder::new()
}
}
impl BlockEncoder {
pub fn new() -> BlockEncoder {
BlockEncoder {
@@ -33,89 +32,71 @@ impl BlockEncoder {
}
}
pub fn compress_block_sorted(&mut self, block: &[u32], offset: u32) -> (u8, &[u8]) {
pub fn compress_block_sorted(&mut self, block: &[u32], offset: u32) -> &[u8] {
let num_bits = self.bitpacker.num_bits_sorted(offset, block);
let written_size =
self.bitpacker
.compress_sorted(offset, block, &mut self.output[..], num_bits);
(num_bits, &self.output[..written_size])
self.output[0] = num_bits;
let written_size = 1 + self.bitpacker.compress_sorted(offset, block, &mut self.output[1..], num_bits);
&self.output[..written_size]
}
pub fn compress_block_unsorted(&mut self, block: &[u32]) -> (u8, &[u8]) {
pub fn compress_block_unsorted(&mut self, block: &[u32]) -> &[u8] {
let num_bits = self.bitpacker.num_bits(block);
let written_size = self
.bitpacker
.compress(block, &mut self.output[..], num_bits);
(num_bits, &self.output[..written_size])
self.output[0] = num_bits;
let written_size = 1 + self.bitpacker.compress(block, &mut self.output[1..], num_bits);
&self.output[..written_size]
}
}
/// We ensure that the OutputBuffer is align on 128 bits
/// in order to run SSE2 linear search on it.
#[repr(align(128))]
pub(crate) struct AlignedBuffer(pub [u32; COMPRESSION_BLOCK_SIZE]);
pub struct BlockDecoder {
bitpacker: BitPacker4x,
output: AlignedBuffer,
pub output: [u32; COMPRESSION_BLOCK_SIZE + 1],
pub output_len: usize,
}
impl Default for BlockDecoder {
fn default() -> Self {
impl BlockDecoder {
pub fn new() -> BlockDecoder {
BlockDecoder::with_val(0u32)
}
}
impl BlockDecoder {
pub fn with_val(val: u32) -> BlockDecoder {
let mut output = [val; COMPRESSION_BLOCK_SIZE + 1];
output[COMPRESSION_BLOCK_SIZE] = 0u32;
BlockDecoder {
bitpacker: BitPacker4x::new(),
output: AlignedBuffer([val; COMPRESSION_BLOCK_SIZE]),
output,
output_len: 0,
}
}
pub fn uncompress_block_sorted(
&mut self,
compressed_data: &[u8],
offset: u32,
num_bits: u8,
) -> usize {
pub fn uncompress_block_sorted(&mut self, compressed_data: &[u8], offset: u32) -> usize {
let num_bits = compressed_data[0];
self.output_len = COMPRESSION_BLOCK_SIZE;
self.bitpacker
.decompress_sorted(offset, &compressed_data, &mut self.output.0, num_bits)
1 + self.bitpacker.decompress_sorted(offset, &compressed_data[1..], &mut self.output, num_bits)
}
pub fn uncompress_block_unsorted(&mut self, compressed_data: &[u8], num_bits: u8) -> usize {
pub fn uncompress_block_unsorted<'a>(&mut self, compressed_data: &'a [u8]) -> usize {
let num_bits = compressed_data[0];
self.output_len = COMPRESSION_BLOCK_SIZE;
self.bitpacker
.decompress(&compressed_data, &mut self.output.0, num_bits)
1 + self.bitpacker.decompress(&compressed_data[1..], &mut self.output, num_bits)
}
#[inline]
pub fn output_array(&self) -> &[u32] {
&self.output.0[..self.output_len]
}
#[inline]
pub(crate) fn output_aligned(&self) -> &AlignedBuffer {
&self.output
&self.output[..self.output_len]
}
#[inline]
pub fn output(&self, idx: usize) -> u32 {
self.output.0[idx]
}
pub fn clear(&mut self) {
self.output.0.iter_mut().for_each(|el| *el = TERMINATED);
self.output[idx]
}
}
mod vint;
pub trait VIntEncoder {
/// Compresses an array of `u32` integers,
/// using [delta-encoding](https://en.wikipedia.org/wiki/Delta_ encoding)
/// using [delta-encoding](https://en.wikipedia.org/wiki/Delta_encoding)
/// and variable bytes encoding.
///
/// The method takes an array of ints to compress, and returns
@@ -147,9 +128,9 @@ pub trait VIntDecoder {
/// For instance, if delta encoded are `1, 3, 9`, and the
/// `offset` is 5, then the output will be:
/// `5 + 1 = 6, 6 + 3= 9, 9 + 9 = 18`
fn uncompress_vint_sorted(
fn uncompress_vint_sorted<'a>(
&mut self,
compressed_data: &[u8],
compressed_data: &'a [u8],
offset: u32,
num_els: usize,
) -> usize;
@@ -159,7 +140,7 @@ pub trait VIntDecoder {
///
/// The method takes a number of int to decompress, and returns
/// the amount of bytes that were read to decompress them.
fn uncompress_vint_unsorted(&mut self, compressed_data: &[u8], num_els: usize) -> usize;
fn uncompress_vint_unsorted<'a>(&mut self, compressed_data: &'a [u8], num_els: usize) -> usize;
}
impl VIntEncoder for BlockEncoder {
@@ -173,19 +154,19 @@ impl VIntEncoder for BlockEncoder {
}
impl VIntDecoder for BlockDecoder {
fn uncompress_vint_sorted(
fn uncompress_vint_sorted<'a>(
&mut self,
compressed_data: &[u8],
compressed_data: &'a [u8],
offset: u32,
num_els: usize,
) -> usize {
self.output_len = num_els;
vint::uncompress_sorted(compressed_data, &mut self.output.0[..num_els], offset)
vint::uncompress_sorted(compressed_data, &mut self.output[..num_els], offset)
}
fn uncompress_vint_unsorted(&mut self, compressed_data: &[u8], num_els: usize) -> usize {
fn uncompress_vint_unsorted<'a>(&mut self, compressed_data: &'a [u8], num_els: usize) -> usize {
self.output_len = num_els;
vint::uncompress_unsorted(compressed_data, &mut self.output.0[..num_els])
vint::uncompress_unsorted(compressed_data, &mut self.output[..num_els])
}
}
@@ -193,15 +174,17 @@ impl VIntDecoder for BlockDecoder {
pub mod tests {
use super::*;
use tests;
use test::Bencher;
#[test]
fn test_encode_sorted_block() {
let vals: Vec<u32> = (0u32..128u32).map(|i| i * 7).collect();
let mut encoder = BlockEncoder::new();
let (num_bits, compressed_data) = encoder.compress_block_sorted(&vals, 0);
let mut decoder = BlockDecoder::default();
let compressed_data = encoder.compress_block_sorted(&vals, 0);
let mut decoder = BlockDecoder::new();
{
let consumed_num_bytes = decoder.uncompress_block_sorted(compressed_data, 0, num_bits);
let consumed_num_bytes = decoder.uncompress_block_sorted(compressed_data, 0);
assert_eq!(consumed_num_bytes, compressed_data.len());
}
for i in 0..128 {
@@ -212,11 +195,11 @@ pub mod tests {
#[test]
fn test_encode_sorted_block_with_offset() {
let vals: Vec<u32> = (0u32..128u32).map(|i| 11 + i * 7).collect();
let mut encoder = BlockEncoder::default();
let (num_bits, compressed_data) = encoder.compress_block_sorted(&vals, 10);
let mut decoder = BlockDecoder::default();
let mut encoder = BlockEncoder::new();
let compressed_data = encoder.compress_block_sorted(&vals, 10);
let mut decoder = BlockDecoder::new();
{
let consumed_num_bytes = decoder.uncompress_block_sorted(compressed_data, 10, num_bits);
let consumed_num_bytes = decoder.uncompress_block_sorted(compressed_data, 10);
assert_eq!(consumed_num_bytes, compressed_data.len());
}
for i in 0..128 {
@@ -229,13 +212,13 @@ pub mod tests {
let mut compressed: Vec<u8> = Vec::new();
let n = 128;
let vals: Vec<u32> = (0..n).map(|i| 11u32 + (i as u32) * 7u32).collect();
let mut encoder = BlockEncoder::default();
let (num_bits, compressed_data) = encoder.compress_block_sorted(&vals, 10);
let mut encoder = BlockEncoder::new();
let compressed_data = encoder.compress_block_sorted(&vals, 10);
compressed.extend_from_slice(compressed_data);
compressed.push(173u8);
let mut decoder = BlockDecoder::default();
let mut decoder = BlockDecoder::new();
{
let consumed_num_bytes = decoder.uncompress_block_sorted(&compressed, 10, num_bits);
let consumed_num_bytes = decoder.uncompress_block_sorted(&compressed, 10);
assert_eq!(consumed_num_bytes, compressed.len() - 1);
assert_eq!(compressed[consumed_num_bytes], 173u8);
}
@@ -249,13 +232,13 @@ pub mod tests {
let mut compressed: Vec<u8> = Vec::new();
let n = 128;
let vals: Vec<u32> = (0..n).map(|i| 11u32 + (i as u32) * 7u32 % 12).collect();
let mut encoder = BlockEncoder::default();
let (num_bits, compressed_data) = encoder.compress_block_unsorted(&vals);
let mut encoder = BlockEncoder::new();
let compressed_data = encoder.compress_block_unsorted(&vals);
compressed.extend_from_slice(compressed_data);
compressed.push(173u8);
let mut decoder = BlockDecoder::default();
let mut decoder = BlockDecoder::new();
{
let consumed_num_bytes = decoder.uncompress_block_unsorted(&compressed, num_bits);
let consumed_num_bytes = decoder.uncompress_block_unsorted(&compressed);
assert_eq!(consumed_num_bytes + 1, compressed.len());
assert_eq!(compressed[consumed_num_bytes], 173u8);
}
@@ -264,11 +247,6 @@ pub mod tests {
}
}
#[test]
fn test_block_decoder_initialization() {
let block = BlockDecoder::with_val(TERMINATED);
assert_eq!(block.output(0), TERMINATED);
}
#[test]
fn test_encode_vint() {
{
@@ -278,7 +256,7 @@ pub mod tests {
for offset in &[0u32, 1u32, 2u32] {
let encoded_data = encoder.compress_vint_sorted(&input, *offset);
assert!(encoded_data.len() <= expected_length);
let mut decoder = BlockDecoder::default();
let mut decoder = BlockDecoder::new();
let consumed_num_bytes =
decoder.uncompress_vint_sorted(&encoded_data, *offset, input.len());
assert_eq!(consumed_num_bytes, encoded_data.len());
@@ -286,32 +264,11 @@ pub mod tests {
}
}
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use super::*;
use rand::rngs::StdRng;
use rand::Rng;
use rand::SeedableRng;
use test::Bencher;
fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> {
let mut seed: [u8; 32] = [0; 32];
seed[31] = seed_val;
let mut rng = StdRng::from_seed(seed);
(0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect()
}
pub fn generate_array(n: usize, ratio: f64) -> Vec<u32> {
generate_array_with_seed(n, ratio, 4)
}
#[bench]
fn bench_compress(b: &mut Bencher) {
let mut encoder = BlockEncoder::new();
let data = generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
let data = tests::generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
b.iter(|| {
encoder.compress_block_sorted(&data, 0u32);
});
@@ -320,24 +277,25 @@ mod bench {
#[bench]
fn bench_uncompress(b: &mut Bencher) {
let mut encoder = BlockEncoder::new();
let data = generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
let (num_bits, compressed) = encoder.compress_block_sorted(&data, 0u32);
let data = tests::generate_array(COMPRESSION_BLOCK_SIZE, 0.1);
let compressed = encoder.compress_block_sorted(&data, 0u32);
let mut decoder = BlockDecoder::new();
b.iter(|| {
decoder.uncompress_block_sorted(compressed, 0u32, num_bits);
decoder.uncompress_block_sorted(compressed, 0u32);
});
}
#[test]
fn test_all_docs_compression_numbits() {
for expected_num_bits in 0u8.. {
for num_bits in 0..33 {
let mut data = [0u32; 128];
if expected_num_bits > 0 {
data[0] = (1u64 << (expected_num_bits as usize) - 1) as u32;
if num_bits > 0 {
data[0] = 1 << (num_bits - 1);
}
let mut encoder = BlockEncoder::new();
let (num_bits, compressed) = encoder.compress_block_unsorted(&data);
assert_eq!(compressed.len(), compressed_block_size(num_bits));
let compressed = encoder.compress_block_unsorted(&data);
assert_eq!(compressed[0] as usize, num_bits);
assert_eq!(compressed.len(), compressed_block_size(compressed[0]));
}
}
@@ -346,7 +304,7 @@ mod bench {
#[bench]
fn bench_compress_vint(b: &mut Bencher) {
let mut encoder = BlockEncoder::new();
let data = generate_array(NUM_INTS_BENCH_VINT, 0.001);
let data = tests::generate_array(NUM_INTS_BENCH_VINT, 0.001);
b.iter(|| {
encoder.compress_vint_sorted(&data, 0u32);
});
@@ -355,11 +313,12 @@ mod bench {
#[bench]
fn bench_uncompress_vint(b: &mut Bencher) {
let mut encoder = BlockEncoder::new();
let data = generate_array(NUM_INTS_BENCH_VINT, 0.001);
let data = tests::generate_array(NUM_INTS_BENCH_VINT, 0.001);
let compressed = encoder.compress_vint_sorted(&data, 0u32);
let mut decoder = BlockDecoder::new();
b.iter(|| {
decoder.uncompress_vint_sorted(compressed, 0u32, NUM_INTS_BENCH_VINT);
});
}
}

158
src/compression/stream.rs Normal file
View File

@@ -0,0 +1,158 @@
use compression::BlockDecoder;
use compression::COMPRESSION_BLOCK_SIZE;
use compression::compressed_block_size;
use directory::{ReadOnlySource, SourceRead};
/// Reads a stream of compressed ints.
///
/// Tantivy uses `CompressedIntStream` to read
/// the position file.
/// The `.skip(...)` makes it possible to avoid
/// decompressing blocks that are not required.
pub struct CompressedIntStream {
buffer: SourceRead,
block_decoder: BlockDecoder,
cached_addr: usize, // address of the currently decoded block
cached_next_addr: usize, // address following the currently decoded block
addr: usize, // address of the block associated to the current position
inner_offset: usize,
}
impl CompressedIntStream {
/// Opens a compressed int stream.
pub(crate) fn wrap(source: ReadOnlySource) -> CompressedIntStream {
CompressedIntStream {
buffer: SourceRead::from(source),
block_decoder: BlockDecoder::new(),
cached_addr: usize::max_value(),
cached_next_addr: usize::max_value(),
addr: 0,
inner_offset: 0,
}
}
/// Loads the block at the given address and return the address of the
/// following block
pub fn read_block(&mut self, addr: usize) -> usize {
if self.cached_addr == addr {
// we are already on this block.
// no need to read.
self.cached_next_addr
} else {
let next_addr = addr + self.block_decoder.uncompress_block_unsorted(self.buffer.slice_from(addr));
self.cached_addr = addr;
self.cached_next_addr = next_addr;
next_addr
}
}
/// Fills a buffer with the next `output.len()` integers.
/// This does not consume / advance the stream.
pub fn read(&mut self, output: &mut [u32]) {
let mut cursor = self.addr;
let mut inner_offset = self.inner_offset;
let mut num_els: usize = output.len();
let mut start = 0;
loop {
cursor = self.read_block(cursor);
let block = &self.block_decoder.output_array()[inner_offset..];
let block_len = block.len();
if num_els >= block_len {
output[start..start + block_len].clone_from_slice(&block);
start += block_len;
num_els -= block_len;
inner_offset = 0;
} else {
output[start..].clone_from_slice(&block[..num_els]);
break;
}
}
}
/// Skip the next `skip_len` integer.
///
/// If a full block is skipped, calling
/// `.skip(...)` will avoid decompressing it.
///
/// May panic if the end of the stream is reached.
pub fn skip(&mut self, mut skip_len: usize) {
loop {
let available = COMPRESSION_BLOCK_SIZE - self.inner_offset;
if available >= skip_len {
self.inner_offset += skip_len;
break;
} else {
skip_len -= available;
// entirely skip decompressing some blocks.
let num_bits: u8 = self.buffer.get(self.addr);
let block_len = compressed_block_size(num_bits);
self.addr += block_len;
self.inner_offset = 0;
}
}
}
}
#[cfg(test)]
pub mod tests {
use super::CompressedIntStream;
use compression::compressed_block_size;
use compression::COMPRESSION_BLOCK_SIZE;
use compression::BlockEncoder;
use directory::ReadOnlySource;
fn create_stream_buffer() -> ReadOnlySource {
let mut buffer: Vec<u8> = vec![];
let mut encoder = BlockEncoder::new();
let vals: Vec<u32> = (0u32..1152u32).collect();
for chunk in vals.chunks(COMPRESSION_BLOCK_SIZE) {
let compressed_block = encoder.compress_block_unsorted(chunk);
let num_bits = compressed_block[0];
assert_eq!(compressed_block_size(num_bits), compressed_block.len());
buffer.extend_from_slice(compressed_block);
}
if cfg!(simd) {
buffer.extend_from_slice(&[0u8; 7]);
}
ReadOnlySource::from(buffer)
}
#[test]
fn test_compressed_int_stream() {
let buffer = create_stream_buffer();
let mut stream = CompressedIntStream::wrap(buffer);
let mut block: [u32; COMPRESSION_BLOCK_SIZE] = [0u32; COMPRESSION_BLOCK_SIZE];
stream.read(&mut block[0..2]);
assert_eq!(block[0], 0);
assert_eq!(block[1], 1);
// reading does not consume the stream
stream.read(&mut block[0..2]);
assert_eq!(block[0], 0);
assert_eq!(block[1], 1);
stream.skip(2);
stream.skip(5);
stream.read(&mut block[0..3]);
stream.skip(3);
assert_eq!(block[0], 7);
assert_eq!(block[1], 8);
assert_eq!(block[2], 9);
stream.skip(500);
stream.read(&mut block[0..3]);
stream.skip(3);
assert_eq!(block[0], 510);
assert_eq!(block[1], 511);
assert_eq!(block[2], 512);
stream.skip(511);
stream.read(&mut block[..1]);
assert_eq!(block[0], 1024);
}
}

28
src/postings/compression/vint.rs → src/compression/vint.rs
View File

@@ -1,5 +1,9 @@
#[inline(always)]
pub fn compress_sorted<'a>(input: &[u32], output: &'a mut [u8], mut offset: u32) -> &'a [u8] {
pub(crate) fn compress_sorted<'a>(
input: &[u32],
output: &'a mut [u8],
mut offset: u32,
) -> &'a [u8] {
let mut byte_written = 0;
for &v in input {
let mut to_encode: u32 = v - offset;
@@ -42,41 +46,47 @@ pub(crate) fn compress_unsorted<'a>(input: &[u32], output: &'a mut [u8]) -> &'a
}
#[inline(always)]
pub fn uncompress_sorted(compressed_data: &[u8], output: &mut [u32], offset: u32) -> usize {
pub(crate) fn uncompress_sorted<'a>(
compressed_data: &'a [u8],
output: &mut [u32],
offset: u32,
) -> usize {
let mut read_byte = 0;
let mut result = offset;
for output_mut in output.iter_mut() {
let num_els = output.len();
for i in 0..num_els {
let mut shift = 0u32;
loop {
let cur_byte = compressed_data[read_byte];
read_byte += 1;
result += u32::from(cur_byte % 128u8) << shift;
result += ((cur_byte % 128u8) as u32) << shift;
if cur_byte & 128u8 != 0u8 {
break;
}
shift += 7;
}
*output_mut = result;
output[i] = result;
}
read_byte
}
#[inline(always)]
pub(crate) fn uncompress_unsorted(compressed_data: &[u8], output_arr: &mut [u32]) -> usize {
pub(crate) fn uncompress_unsorted<'a>(compressed_data: &'a [u8], output: &mut [u32]) -> usize {
let mut read_byte = 0;
for output_mut in output_arr.iter_mut() {
let num_els = output.len();
for i in 0..num_els {
let mut result = 0u32;
let mut shift = 0u32;
loop {
let cur_byte = compressed_data[read_byte];
read_byte += 1;
result += u32::from(cur_byte % 128u8) << shift;
result += ((cur_byte % 128u8) as u32) << shift;
if cur_byte & 128u8 != 0u8 {
break;
}
shift += 7;
}
*output_mut = result;
output[i] = result;
}
read_byte
}

141
src/core/executor.rs
View File

@@ -1,141 +0,0 @@
use crossbeam::channel;
use rayon::{ThreadPool, ThreadPoolBuilder};
/// Search executor whether search request are single thread or multithread.
///
/// We don't expose Rayon thread pool directly here for several reasons.
///
/// First dependency hell. It is not a good idea to expose the
/// API of a dependency, knowing it might conflict with a different version
/// used by the client. Second, we may stop using rayon in the future.
pub enum Executor {
/// Single thread variant of an Executor
SingleThread,
/// Thread pool variant of an Executor
ThreadPool(ThreadPool),
}
impl Executor {
/// Creates an Executor that performs all task in the caller thread.
pub fn single_thread() -> Executor {
Executor::SingleThread
}
/// Creates an Executor that dispatches the tasks in a thread pool.
pub fn multi_thread(num_threads: usize, prefix: &'static str) -> crate::Result<Executor> {
let pool = ThreadPoolBuilder::new()
.num_threads(num_threads)
.thread_name(move |num| format!("{}{}", prefix, num))
.build()?;
Ok(Executor::ThreadPool(pool))
}
/// Perform a map in the thread pool.
///
/// Regardless of the executor (`SingleThread` or `ThreadPool`), panics in the task
/// will propagate to the caller.
pub fn map<
A: Send,
R: Send,
AIterator: Iterator<Item = A>,
F: Sized + Sync + Fn(A) -> crate::Result<R>,
>(
&self,
f: F,
args: AIterator,
) -> crate::Result<Vec<R>> {
match self {
Executor::SingleThread => args.map(f).collect::<crate::Result<_>>(),
Executor::ThreadPool(pool) => {
let args_with_indices: Vec<(usize, A)> = args.enumerate().collect();
let num_fruits = args_with_indices.len();
let fruit_receiver = {
let (fruit_sender, fruit_receiver) = channel::unbounded();
pool.scope(|scope| {
for arg_with_idx in args_with_indices {
scope.spawn(|_| {
let (idx, arg) = arg_with_idx;
let fruit = f(arg);
if let Err(err) = fruit_sender.send((idx, fruit)) {
error!("Failed to send search task. It probably means all search threads have panicked. {:?}", err);
}
});
}
});
fruit_receiver
// This ends the scope of fruit_sender.
// This is important as it makes it possible for the fruit_receiver iteration to
// terminate.
};
// This is lame, but safe.
let mut results_with_position = Vec::with_capacity(num_fruits);
for (pos, fruit_res) in fruit_receiver {
let fruit = fruit_res?;
results_with_position.push((pos, fruit));
}
results_with_position.sort_by_key(|(pos, _)| *pos);
assert_eq!(results_with_position.len(), num_fruits);
Ok(results_with_position
.into_iter()
.map(|(_, fruit)| fruit)
.collect::<Vec<_>>())
}
}
}
}
#[cfg(test)]
mod tests {
use super::Executor;
#[test]
#[should_panic(expected = "panic should propagate")]
fn test_panic_propagates_single_thread() {
let _result: Vec<usize> = Executor::single_thread()
.map(
|_| {
panic!("panic should propagate");
},
vec![0].into_iter(),
)
.unwrap();
}
#[test]
#[should_panic] //< unfortunately the panic message is not propagated
fn test_panic_propagates_multi_thread() {
let _result: Vec<usize> = Executor::multi_thread(1, "search-test")
.unwrap()
.map(
|_| {
panic!("panic should propagate");
},
vec![0].into_iter(),
)
.unwrap();
}
#[test]
fn test_map_singlethread() {
let result: Vec<usize> = Executor::single_thread()
.map(|i| Ok(i * 2), 0..1_000)
.unwrap();
assert_eq!(result.len(), 1_000);
for i in 0..1_000 {
assert_eq!(result[i], i * 2);
}
}
#[test]
fn test_map_multithread() {
let result: Vec<usize> = Executor::multi_thread(3, "search-test")
.unwrap()
.map(|i| Ok(i * 2), 0..10)
.unwrap();
assert_eq!(result.len(), 10);
for i in 0..10 {
assert_eq!(result[i], i * 2);
}
}
}

609
src/core/index.rs
View File

@@ -1,127 +1,80 @@
use super::segment::Segment;
use crate::core::Executor;
use crate::core::IndexMeta;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SegmentMetaInventory;
use crate::core::META_FILEPATH;
use crate::directory::ManagedDirectory;
#[cfg(feature = "mmap")]
use crate::directory::MmapDirectory;
use crate::directory::INDEX_WRITER_LOCK;
use crate::directory::{Directory, RAMDirectory};
use crate::error::DataCorruption;
use crate::error::TantivyError;
use crate::indexer::index_writer::HEAP_SIZE_MIN;
use crate::indexer::segment_updater::save_new_metas;
use crate::reader::IndexReader;
use crate::reader::IndexReaderBuilder;
use crate::schema::Field;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::tokenizer::{TextAnalyzer, TokenizerManager};
use crate::IndexWriter;
use std::borrow::BorrowMut;
use std::collections::HashSet;
use std::fmt;
#[cfg(feature = "mmap")]
use std::path::{Path, PathBuf};
use Result;
use error::{ErrorKind, ResultExt};
use serde_json;
use schema::Schema;
use std::sync::Arc;
use std::borrow::BorrowMut;
use std::fmt;
use core::SegmentId;
fn load_metas(
directory: &dyn Directory,
inventory: &SegmentMetaInventory,
) -> crate::Result<IndexMeta> {
#[cfg(feature="mmap")]
use directory::MmapDirectory;
use directory::{Directory, RAMDirectory};
use indexer::index_writer::open_index_writer;
use core::searcher::Searcher;
use std::convert::From;
use num_cpus;
use super::segment::Segment;
use core::SegmentReader;
use super::pool::Pool;
use core::SegmentMeta;
use super::pool::LeasedItem;
use std::path::Path;
use core::IndexMeta;
use indexer::DirectoryLock;
use IndexWriter;
use directory::ManagedDirectory;
use core::META_FILEPATH;
use super::segment::create_segment;
use indexer::segment_updater::save_new_metas;
use tokenizer::TokenizerManager;
const NUM_SEARCHERS: usize = 12;
fn load_metas(directory: &Directory) -> Result<IndexMeta> {
let meta_data = directory.atomic_read(&META_FILEPATH)?;
let meta_string = String::from_utf8_lossy(&meta_data);
IndexMeta::deserialize(&meta_string, &inventory)
.map_err(|e| {
DataCorruption::new(
META_FILEPATH.to_path_buf(),
format!("Meta file cannot be deserialized. {:?}.", e),
)
})
.map_err(From::from)
serde_json::from_str(&meta_string).chain_err(|| ErrorKind::CorruptedFile(META_FILEPATH.clone()))
}
/// Search Index
#[derive(Clone)]
pub struct Index {
directory: ManagedDirectory,
schema: Schema,
executor: Arc<Executor>,
searcher_pool: Arc<Pool<Searcher>>,
tokenizers: TokenizerManager,
inventory: SegmentMetaInventory,
}
impl Index {
/// Examines the director to see if it contains an index
pub fn exists<Dir: Directory>(dir: &Dir) -> bool {
dir.exists(&META_FILEPATH)
}
/// Accessor to the search executor.
///
/// This pool is used by default when calling `searcher.search(...)`
/// to perform search on the individual segments.
///
/// By default the executor is single thread, and simply runs in the calling thread.
pub fn search_executor(&self) -> &Executor {
self.executor.as_ref()
}
/// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads.
pub fn set_multithread_executor(&mut self, num_threads: usize) -> crate::Result<()> {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")?);
Ok(())
}
/// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads.
pub fn set_default_multithread_executor(&mut self) -> crate::Result<()> {
let default_num_threads = num_cpus::get();
self.set_multithread_executor(default_num_threads)
}
/// Creates a new index using the `RAMDirectory`.
///
/// The index will be allocated in anonymous memory.
/// This should only be used for unit tests.
pub fn create_in_ram(schema: Schema) -> Index {
let ram_directory = RAMDirectory::create();
Index::create(ram_directory, schema).expect("Creating a RAMDirectory should never fail")
// unwrap is ok here
let directory = ManagedDirectory::new(ram_directory).expect(
"Creating a managed directory from a brand new RAM directory \
should never fail.",
);
Index::from_directory(directory, schema).expect("Creating a RAMDirectory should never fail")
}
/// Creates a new index in a given filepath.
/// The index will use the `MMapDirectory`.
///
/// If a previous index was in this directory, then its meta file will be destroyed.
#[cfg(feature = "mmap")]
pub fn create_in_dir<P: AsRef<Path>>(
directory_path: P,
schema: Schema,
) -> crate::Result<Index> {
#[cfg(feature="mmap")]
pub fn create<P: AsRef<Path>>(directory_path: P, schema: Schema) -> Result<Index> {
let mmap_directory = MmapDirectory::open(directory_path)?;
if Index::exists(&mmap_directory) {
return Err(TantivyError::IndexAlreadyExists);
}
Index::create(mmap_directory, schema)
let directory = ManagedDirectory::new(mmap_directory)?;
Index::from_directory(directory, schema)
}
/// Opens or creates a new index in the provided directory
pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
if !Index::exists(&dir) {
return Index::create(dir, schema);
}
let index = Index::open(dir)?;
if index.schema() == schema {
Ok(index)
} else {
Err(TantivyError::SchemaError(
"An index exists but the schema does not match.".to_string(),
))
}
/// Accessor for the tokenizer manager.
pub fn tokenizers(&self) -> &TokenizerManager {
&self.tokenizers
}
/// Creates a new index in a temp directory.
@@ -132,121 +85,53 @@ impl Index {
///
/// The temp directory is only used for testing the `MmapDirectory`.
/// For other unit tests, prefer the `RAMDirectory`, see: `create_in_ram`.
#[cfg(feature = "mmap")]
pub fn create_from_tempdir(schema: Schema) -> crate::Result<Index> {
#[cfg(feature="mmap")]
#[cfg(test)]
pub fn create_from_tempdir(schema: Schema) -> Result<Index> {
let mmap_directory = MmapDirectory::create_from_tempdir()?;
Index::create(mmap_directory, schema)
}
/// Creates a new index given an implementation of the trait `Directory`
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
let directory = ManagedDirectory::wrap(dir)?;
let directory = ManagedDirectory::new(mmap_directory)?;
Index::from_directory(directory, schema)
}
/// Create a new index from a directory.
///
/// This will overwrite existing meta.json
fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
save_new_metas(schema.clone(), directory.borrow_mut())?;
let metas = IndexMeta::with_schema(schema);
Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
}
/// Creates a new index given a directory and an `IndexMeta`.
fn create_from_metas(
directory: ManagedDirectory,
metas: &IndexMeta,
inventory: SegmentMetaInventory,
) -> crate::Result<Index> {
fn create_from_metas(directory: ManagedDirectory, metas: &IndexMeta) -> Result<Index> {
let schema = metas.schema.clone();
Ok(Index {
let index = Index {
directory,
schema,
searcher_pool: Arc::new(Pool::new()),
tokenizers: TokenizerManager::default(),
executor: Arc::new(Executor::single_thread()),
inventory,
})
}
/// Accessor for the tokenizer manager.
pub fn tokenizers(&self) -> &TokenizerManager {
&self.tokenizers
}
/// Helper to access the tokenizer associated to a specific field.
pub fn tokenizer_for_field(&self, field: Field) -> crate::Result<TextAnalyzer> {
let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type();
let tokenizer_manager: &TokenizerManager = self.tokenizers();
let tokenizer_name_opt: Option<TextAnalyzer> = match field_type {
FieldType::Str(text_options) => text_options
.get_indexing_options()
.map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
.and_then(|tokenizer_name| tokenizer_manager.get(&tokenizer_name)),
_ => None,
};
match tokenizer_name_opt {
Some(tokenizer) => Ok(tokenizer),
None => Err(TantivyError::SchemaError(format!(
"{:?} is not a text field.",
field_entry.name()
))),
}
index.load_searchers()?;
Ok(index)
}
/// Create a default `IndexReader` for the given index.
///
/// See [`Index.reader_builder()`](#method.reader_builder).
pub fn reader(&self) -> crate::Result<IndexReader> {
self.reader_builder().try_into()
}
/// Create a `IndexReader` for the given index.
///
/// Most project should create at most one reader for a given index.
/// This method is typically called only once per `Index` instance,
/// over the lifetime of most problem.
pub fn reader_builder(&self) -> IndexReaderBuilder {
IndexReaderBuilder::new(self.clone())
/// Create a new index from a directory.
pub fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> Result<Index> {
save_new_metas(schema.clone(), 0, directory.borrow_mut())?;
let metas = IndexMeta::with_schema(schema);
Index::create_from_metas(directory, &metas)
}
/// Opens a new directory from an index path.
#[cfg(feature = "mmap")]
pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> crate::Result<Index> {
#[cfg(feature="mmap")]
pub fn open<P: AsRef<Path>>(directory_path: P) -> Result<Index> {
let mmap_directory = MmapDirectory::open(directory_path)?;
Index::open(mmap_directory)
let directory = ManagedDirectory::new(mmap_directory)?;
let metas = load_metas(&directory)?;
Index::create_from_metas(directory, &metas)
}
/// Returns the list of the segment metas tracked by the index.
///
/// Such segments can of course be part of the index,
/// but also they could be segments being currently built or in the middle of a merge
/// operation.
pub fn list_all_segment_metas(&self) -> Vec<SegmentMeta> {
self.inventory.all()
pub fn open_directory<TDirectory: Directory>(directory: TDirectory) -> Result<Index> {
let directory = ManagedDirectory::new(directory)?;
let metas = load_metas(&directory)?;
Index::create_from_metas(directory, &metas)
}
/// Creates a new segment_meta (Advanced user only).
///
/// As long as the `SegmentMeta` lives, the files associated with the
/// `SegmentMeta` are guaranteed to not be garbage collected, regardless of
/// whether the segment is recorded as part of the index or not.
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
self.inventory.new_segment_meta(segment_id, max_doc)
}
/// Open the index using the provided directory
pub fn open<D: Directory>(directory: D) -> crate::Result<Index> {
let directory = ManagedDirectory::wrap(directory)?;
let inventory = SegmentMetaInventory::default();
let metas = load_metas(&directory, &inventory)?;
Index::create_from_metas(directory, &metas, inventory)
}
/// Reads the index meta file from the directory.
pub fn load_metas(&self) -> crate::Result<IndexMeta> {
load_metas(self.directory(), &self.inventory)
pub fn load_metas(&self) -> Result<IndexMeta> {
load_metas(self.directory())
}
/// Open a new index writer. Attempts to acquire a lockfile.
@@ -257,64 +142,31 @@ impl Index {
/// `IndexWriter` on the system is accessing the index directory,
/// it is safe to manually delete the lockfile.
///
/// - `num_threads` defines the number of indexing workers that
/// num_threads specifies the number of indexing workers that
/// should work at the same time.
///
/// - `overall_heap_size_in_bytes` sets the amount of memory
/// allocated for all indexing thread.
/// Each thread will receive a budget of `overall_heap_size_in_bytes / num_threads`.
///
/// # Errors
/// If the lockfile already exists, returns `Error::DirectoryLockBusy` or an `Error::IOError`.
///
/// # Panics
/// If the heap size per thread is too small, panics.
pub fn writer_with_num_threads(
&self,
num_threads: usize,
overall_heap_size_in_bytes: usize,
) -> crate::Result<IndexWriter> {
let directory_lock = self
.directory
.acquire_lock(&INDEX_WRITER_LOCK)
.map_err(|err| {
TantivyError::LockFailure(
err,
Some(
"Failed to acquire index lock. If you are using\
a regular directory, this means there is already an \
`IndexWriter` working on this `Directory`, in this process \
or in a different process."
.to_string(),
),
)
})?;
let heap_size_in_bytes_per_thread = overall_heap_size_in_bytes / num_threads;
IndexWriter::new(
self,
num_threads,
heap_size_in_bytes_per_thread,
directory_lock,
)
}
/// Creates a multithreaded writer
///
/// Tantivy will automatically define the number of threads to use.
/// `overall_heap_size_in_bytes` is the total target memory usage that will be split
/// between a given number of threads.
///
/// # Errors
/// If the lockfile already exists, returns `Error::FileAlreadyExists`.
/// # Panics
/// If the heap size per thread is too small, panics.
pub fn writer(&self, overall_heap_size_in_bytes: usize) -> crate::Result<IndexWriter> {
let mut num_threads = num_cpus::get();
let heap_size_in_bytes_per_thread = overall_heap_size_in_bytes / num_threads;
if heap_size_in_bytes_per_thread < HEAP_SIZE_MIN {
num_threads = (overall_heap_size_in_bytes / HEAP_SIZE_MIN).max(1);
}
self.writer_with_num_threads(num_threads, overall_heap_size_in_bytes)
pub fn writer_with_num_threads(
&self,
num_threads: usize,
heap_size_in_bytes: usize,
) -> Result<IndexWriter> {
let directory_lock = DirectoryLock::lock(self.directory().box_clone())?;
open_index_writer(self, num_threads, heap_size_in_bytes, directory_lock)
}
/// Creates a multithreaded writer
/// It just calls `writer_with_num_threads` with the number of cores as `num_threads`
///
/// # Errors
/// If the lockfile already exists, returns `Error::FileAlreadyExists`.
/// # Panics
/// If the heap size per thread is too small, panics.
pub fn writer(&self, heap_size_in_bytes: usize) -> Result<IndexWriter> {
self.writer_with_num_threads(num_cpus::get(), heap_size_in_bytes)
}
/// Accessor to the index schema
@@ -325,9 +177,8 @@ impl Index {
}
/// Returns the list of segments that are searchable
pub fn searchable_segments(&self) -> crate::Result<Vec<Segment>> {
Ok(self
.searchable_segment_metas()?
pub fn searchable_segments(&self) -> Result<Vec<Segment>> {
Ok(self.searchable_segment_metas()?
.into_iter()
.map(|segment_meta| self.segment(segment_meta))
.collect())
@@ -335,15 +186,13 @@ impl Index {
#[doc(hidden)]
pub fn segment(&self, segment_meta: SegmentMeta) -> Segment {
Segment::for_index(self.clone(), segment_meta)
create_segment(self.clone(), segment_meta)
}
/// Creates a new segment.
pub fn new_segment(&self) -> Segment {
let segment_meta = self
.inventory
.new_segment_meta(SegmentId::generate_random(), 0);
self.segment(segment_meta)
let segment_meta = SegmentMeta::new(SegmentId::generate_random());
create_segment(self.clone(), segment_meta)
}
/// Return a reference to the index directory.
@@ -358,243 +207,65 @@ impl Index {
/// Reads the meta.json and returns the list of
/// `SegmentMeta` from the last commit.
pub fn searchable_segment_metas(&self) -> crate::Result<Vec<SegmentMeta>> {
pub fn searchable_segment_metas(&self) -> Result<Vec<SegmentMeta>> {
Ok(self.load_metas()?.segments)
}
/// Returns the list of segment ids that are searchable.
pub fn searchable_segment_ids(&self) -> crate::Result<Vec<SegmentId>> {
Ok(self
.searchable_segment_metas()?
pub fn searchable_segment_ids(&self) -> Result<Vec<SegmentId>> {
Ok(self.searchable_segment_metas()?
.iter()
.map(SegmentMeta::id)
.map(|segment_meta| segment_meta.id())
.collect())
}
/// Returns the set of corrupted files
pub fn validate_checksum(&self) -> crate::Result<HashSet<PathBuf>> {
self.directory.list_damaged().map_err(Into::into)
/// Creates a new generation of searchers after
/// a change of the set of searchable indexes.
///
/// This needs to be called when a new segment has been
/// published or after a merge.
pub fn load_searchers(&self) -> Result<()> {
let searchable_segments = self.searchable_segments()?;
let segment_readers: Vec<SegmentReader> = searchable_segments
.iter()
.map(SegmentReader::open)
.collect::<Result<_>>()?;
let searchers = (0..NUM_SEARCHERS)
.map(|_| Searcher::from(segment_readers.clone()))
.collect();
self.searcher_pool.publish_new_generation(searchers);
Ok(())
}
/// Returns a searcher
///
/// This method should be called every single time a search
/// query is performed.
/// The searchers are taken from a pool of `NUM_SEARCHERS` searchers.
/// If no searcher is available
/// this may block.
///
/// The same searcher must be used for a given query, as it ensures
/// the use of a consistent segment set.
pub fn searcher(&self) -> LeasedItem<Searcher> {
self.searcher_pool.acquire()
}
}
impl fmt::Debug for Index {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "Index({:?})", self.directory)
}
}
#[cfg(test)]
mod tests {
use crate::directory::RAMDirectory;
use crate::schema::Field;
use crate::schema::{Schema, INDEXED, TEXT};
use crate::IndexReader;
use crate::ReloadPolicy;
use crate::{Directory, Index};
#[test]
fn test_indexer_for_field() {
let mut schema_builder = Schema::builder();
let num_likes_field = schema_builder.add_u64_field("num_likes", INDEXED);
let body_field = schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
assert!(index.tokenizer_for_field(body_field).is_ok());
assert_eq!(
format!("{:?}", index.tokenizer_for_field(num_likes_field).err()),
"Some(SchemaError(\"\\\"num_likes\\\" is not a text field.\"))"
);
}
#[test]
fn test_index_exists() {
let directory = RAMDirectory::create();
assert!(!Index::exists(&directory));
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
}
#[test]
fn open_or_create_should_create() {
let directory = RAMDirectory::create();
assert!(!Index::exists(&directory));
assert!(Index::open_or_create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
}
#[test]
fn open_or_create_should_open() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::open_or_create(directory, throw_away_schema()).is_ok());
}
#[test]
fn create_should_wipeoff_existing() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::create(directory.clone(), Schema::builder().build()).is_ok());
}
#[test]
fn open_or_create_exists_but_schema_does_not_match() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory));
assert!(Index::open_or_create(directory.clone(), throw_away_schema()).is_ok());
let err = Index::open_or_create(directory, Schema::builder().build());
assert_eq!(
format!("{:?}", err.unwrap_err()),
"SchemaError(\"An index exists but the schema does not match.\")"
);
}
fn throw_away_schema() -> Schema {
let mut schema_builder = Schema::builder();
let _ = schema_builder.add_u64_field("num_likes", INDEXED);
schema_builder.build()
}
#[test]
fn test_index_on_commit_reload_policy() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let index = Index::create_in_ram(schema);
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
}
#[cfg(feature = "mmap")]
mod mmap_specific {
use super::*;
use crate::Directory;
use std::path::PathBuf;
use tempfile::TempDir;
#[test]
fn test_index_on_commit_reload_policy_mmap() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
impl Clone for Index {
fn clone(&self) -> Index {
Index {
directory: self.directory.clone(),
schema: self.schema.clone(),
searcher_pool: Arc::clone(&self.searcher_pool),
tokenizers: self.tokenizers.clone(),
}
#[test]
fn test_index_manual_policy_mmap() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let mut index = Index::create_from_tempdir(schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = index.directory_mut().watch(Box::new(move || {
let _ = sender.send(());
}));
writer.commit().unwrap();
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 0);
reader.reload().unwrap();
assert_eq!(reader.searcher().num_docs(), 1);
}
#[test]
fn test_index_on_commit_reload_policy_different_directories() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let read_index = Index::open_in_dir(&tempdir_path).unwrap();
let reader = read_index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &write_index, &reader);
}
}
fn test_index_on_commit_reload_policy_aux(field: Field, index: &Index, reader: &IndexReader) {
let mut reader_index = reader.index();
let (sender, receiver) = crossbeam::channel::unbounded();
let _watch_handle = reader_index.directory_mut().watch(Box::new(move || {
let _ = sender.send(());
}));
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
writer.commit().unwrap();
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 1);
writer.add_document(doc!(field=>2u64));
writer.commit().unwrap();
assert!(receiver.recv().is_ok());
assert_eq!(reader.searcher().num_docs(), 2);
}
// This test will not pass on windows, because windows
// prevent deleting files that are MMapped.
#[cfg(not(target_os = "windows"))]
#[test]
fn garbage_collect_works_as_intended() {
let directory = RAMDirectory::create();
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let index = Index::create(directory.clone(), schema).unwrap();
let mut writer = index.writer_with_num_threads(8, 24_000_000).unwrap();
for i in 0u64..8_000u64 {
writer.add_document(doc!(field => i));
}
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = directory.watch(Box::new(move || {
let _ = sender.send(());
}));
writer.commit().unwrap();
let mem_right_after_commit = directory.total_mem_usage();
assert!(receiver.recv().is_ok());
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 8_000);
writer.wait_merging_threads().unwrap();
let mem_right_after_merge_finished = directory.total_mem_usage();
reader.reload().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 8_000);
assert!(
mem_right_after_merge_finished < mem_right_after_commit,
"(mem after merge){} is expected < (mem before merge){}",
mem_right_after_merge_finished,
mem_right_after_commit
);
}
}

261
src/core/index_meta.rs
View File

@@ -1,198 +1,7 @@
use super::SegmentComponent;
use crate::core::SegmentId;
use crate::schema::Schema;
use crate::Opstamp;
use census::{Inventory, TrackedObject};
use serde::{Deserialize, Serialize};
use std::collections::HashSet;
use schema::Schema;
use core::SegmentMeta;
use std::fmt;
use std::path::PathBuf;
#[derive(Clone, Debug, Serialize, Deserialize)]
struct DeleteMeta {
num_deleted_docs: u32,
opstamp: Opstamp,
}
#[derive(Clone, Default)]
pub struct SegmentMetaInventory {
inventory: Inventory<InnerSegmentMeta>,
}
impl SegmentMetaInventory {
/// Lists all living `SegmentMeta` object at the time of the call.
pub fn all(&self) -> Vec<SegmentMeta> {
self.inventory
.list()
.into_iter()
.map(SegmentMeta::from)
.collect::<Vec<_>>()
}
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
let inner = InnerSegmentMeta {
segment_id,
max_doc,
deletes: None,
};
SegmentMeta::from(self.inventory.track(inner))
}
}
/// `SegmentMeta` contains simple meta information about a segment.
///
/// For instance the number of docs it contains,
/// how many are deleted, etc.
#[derive(Clone)]
pub struct SegmentMeta {
tracked: TrackedObject<InnerSegmentMeta>,
}
impl fmt::Debug for SegmentMeta {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
self.tracked.fmt(f)
}
}
impl serde::Serialize for SegmentMeta {
fn serialize<S>(
&self,
serializer: S,
) -> Result<<S as serde::Serializer>::Ok, <S as serde::Serializer>::Error>
where
S: serde::Serializer,
{
self.tracked.serialize(serializer)
}
}
impl From<TrackedObject<InnerSegmentMeta>> for SegmentMeta {
fn from(tracked: TrackedObject<InnerSegmentMeta>) -> SegmentMeta {
SegmentMeta { tracked }
}
}
impl SegmentMeta {
// Creates a new `SegmentMeta` object.
/// Returns the segment id.
pub fn id(&self) -> SegmentId {
self.tracked.segment_id
}
/// Returns the number of deleted documents.
pub fn num_deleted_docs(&self) -> u32 {
self.tracked
.deletes
.as_ref()
.map(|delete_meta| delete_meta.num_deleted_docs)
.unwrap_or(0u32)
}
/// Returns the list of files that
/// are required for the segment meta.
///
/// This is useful as the way tantivy removes files
/// is by removing all files that have been created by tantivy
/// and are not used by any segment anymore.
pub fn list_files(&self) -> HashSet<PathBuf> {
SegmentComponent::iterator()
.map(|component| self.relative_path(*component))
.collect::<HashSet<PathBuf>>()
}
/// Returns the relative path of a component of our segment.
///
/// It just joins the segment id with the extension
/// associated to a segment component.
pub fn relative_path(&self, component: SegmentComponent) -> PathBuf {
let mut path = self.id().uuid_string();
path.push_str(&*match component {
SegmentComponent::POSTINGS => ".idx".to_string(),
SegmentComponent::POSITIONS => ".pos".to_string(),
SegmentComponent::POSITIONSSKIP => ".posidx".to_string(),
SegmentComponent::TERMS => ".term".to_string(),
SegmentComponent::STORE => ".store".to_string(),
SegmentComponent::FASTFIELDS => ".fast".to_string(),
SegmentComponent::FIELDNORMS => ".fieldnorm".to_string(),
SegmentComponent::DELETE => format!(".{}.del", self.delete_opstamp().unwrap_or(0)),
});
PathBuf::from(path)
}
/// Return the highest doc id + 1
///
/// If there are no deletes, then num_docs = max_docs
/// and all the doc ids contains in this segment
/// are exactly (0..max_doc).
pub fn max_doc(&self) -> u32 {
self.tracked.max_doc
}
/// Return the number of documents in the segment.
pub fn num_docs(&self) -> u32 {
self.max_doc() - self.num_deleted_docs()
}
/// Returns the `Opstamp` of the last delete operation
/// taken in account in this segment.
pub fn delete_opstamp(&self) -> Option<Opstamp> {
self.tracked
.deletes
.as_ref()
.map(|delete_meta| delete_meta.opstamp)
}
/// Returns true iff the segment meta contains
/// delete information.
pub fn has_deletes(&self) -> bool {
self.num_deleted_docs() > 0
}
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> SegmentMeta {
assert_eq!(self.tracked.max_doc, 0);
assert!(self.tracked.deletes.is_none());
let tracked = self.tracked.map(move |inner_meta| InnerSegmentMeta {
segment_id: inner_meta.segment_id,
max_doc,
deletes: None,
});
SegmentMeta { tracked }
}
#[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta {
let delete_meta = DeleteMeta {
num_deleted_docs,
opstamp,
};
let tracked = self.tracked.map(move |inner_meta| InnerSegmentMeta {
segment_id: inner_meta.segment_id,
max_doc: inner_meta.max_doc,
deletes: Some(delete_meta),
});
SegmentMeta { tracked }
}
}
#[derive(Debug, Clone, Serialize, Deserialize)]
struct InnerSegmentMeta {
segment_id: SegmentId,
max_doc: u32,
deletes: Option<DeleteMeta>,
}
impl InnerSegmentMeta {
pub fn track(self, inventory: &SegmentMetaInventory) -> SegmentMeta {
SegmentMeta {
tracked: inventory.inventory.track(self),
}
}
}
use serde_json;
/// Meta information about the `Index`.
///
@@ -202,53 +11,16 @@ impl InnerSegmentMeta {
/// * the index `docstamp`
/// * the schema
///
#[derive(Clone, Serialize)]
#[derive(Clone, Serialize, Deserialize)]
pub struct IndexMeta {
/// List of `SegmentMeta` informations associated to each finalized segment of the index.
pub segments: Vec<SegmentMeta>,
/// Index `Schema`
pub schema: Schema,
/// Opstamp associated to the last `commit` operation.
pub opstamp: Opstamp,
#[serde(skip_serializing_if = "Option::is_none")]
/// Payload associated to the last commit.
///
/// Upon commit, clients can optionally add a small `Striing` payload to their commit
/// to help identify this commit.
/// This payload is entirely unused by tantivy.
pub payload: Option<String>,
}
#[derive(Deserialize)]
struct UntrackedIndexMeta {
pub segments: Vec<InnerSegmentMeta>,
pub schema: Schema,
pub opstamp: Opstamp,
pub opstamp: u64,
#[serde(skip_serializing_if = "Option::is_none")]
pub payload: Option<String>,
}
impl UntrackedIndexMeta {
pub fn track(self, inventory: &SegmentMetaInventory) -> IndexMeta {
IndexMeta {
segments: self
.segments
.into_iter()
.map(|inner_seg_meta| inner_seg_meta.track(inventory))
.collect::<Vec<SegmentMeta>>(),
schema: self.schema,
opstamp: self.opstamp,
payload: self.payload,
}
}
}
impl IndexMeta {
/// Create an `IndexMeta` object representing a brand new `Index`
/// with the given index.
///
/// This new index does not contains any segments.
/// Opstamp will the value `0u64`.
pub fn with_schema(schema: Schema) -> IndexMeta {
IndexMeta {
segments: vec![],
@@ -257,18 +29,10 @@ impl IndexMeta {
payload: None,
}
}
pub(crate) fn deserialize(
meta_json: &str,
inventory: &SegmentMetaInventory,
) -> serde_json::Result<IndexMeta> {
let untracked_meta_json: UntrackedIndexMeta = serde_json::from_str(meta_json)?;
Ok(untracked_meta_json.track(inventory))
}
}
impl fmt::Debug for IndexMeta {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(
f,
"{}",
@@ -281,27 +45,24 @@ impl fmt::Debug for IndexMeta {
#[cfg(test)]
mod tests {
use super::IndexMeta;
use crate::schema::{Schema, TEXT};
use serde_json;
use super::IndexMeta;
use schema::{SchemaBuilder, TEXT};
#[test]
fn test_serialize_metas() {
let schema = {
let mut schema_builder = Schema::builder();
let mut schema_builder = SchemaBuilder::new();
schema_builder.add_text_field("text", TEXT);
schema_builder.build()
};
let index_metas = IndexMeta {
segments: Vec::new(),
schema,
schema: schema,
opstamp: 0u64,
payload: None,
};
let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
assert_eq!(
json,
r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#
);
assert_eq!(json, r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#);
}
}

98
src/core/inverted_index_reader.rs
View File

@@ -1,12 +1,13 @@
use crate::common::BinarySerializable;
use crate::directory::ReadOnlySource;
use crate::positions::PositionReader;
use crate::postings::TermInfo;
use crate::postings::{BlockSegmentPostings, SegmentPostings};
use crate::schema::FieldType;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::termdict::TermDictionary;
use directory::{ReadOnlySource, SourceRead};
use termdict::{TermDictionary, TermDictionaryImpl};
use postings::{BlockSegmentPostings, SegmentPostings};
use postings::TermInfo;
use schema::IndexRecordOption;
use schema::Term;
use compression::CompressedIntStream;
use postings::FreqReadingOption;
use common::BinarySerializable;
use schema::FieldType;
/// The inverted index reader is in charge of accessing
/// the inverted index associated to a specific field.
@@ -22,21 +23,18 @@ use crate::termdict::TermDictionary;
/// `InvertedIndexReader` are created by calling
/// the `SegmentReader`'s [`.inverted_index(...)`] method
pub struct InvertedIndexReader {
termdict: TermDictionary,
termdict: TermDictionaryImpl,
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
record_option: IndexRecordOption,
total_num_tokens: u64,
total_num_tokens: u64
}
impl InvertedIndexReader {
#[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))] // for symmetry
pub(crate) fn new(
termdict: TermDictionary,
termdict: TermDictionaryImpl,
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
record_option: IndexRecordOption,
) -> InvertedIndexReader {
let total_num_tokens_data = postings_source.slice(0, 8);
@@ -46,25 +44,23 @@ impl InvertedIndexReader {
termdict,
postings_source: postings_source.slice_from(8),
positions_source,
positions_idx_source,
record_option,
total_num_tokens,
total_num_tokens
}
}
/// Creates an empty `InvertedIndexReader` object, which
/// contains no terms at all.
pub fn empty(field_type: &FieldType) -> InvertedIndexReader {
pub fn empty(field_type: FieldType) -> InvertedIndexReader {
let record_option = field_type
.get_index_record_option()
.unwrap_or(IndexRecordOption::Basic);
InvertedIndexReader {
termdict: TermDictionary::empty(),
termdict: TermDictionaryImpl::empty(field_type),
postings_source: ReadOnlySource::empty(),
positions_source: ReadOnlySource::empty(),
positions_idx_source: ReadOnlySource::empty(),
record_option,
total_num_tokens: 0u64,
total_num_tokens: 0u64
}
}
@@ -74,7 +70,7 @@ impl InvertedIndexReader {
}
/// Return the term dictionary datastructure.
pub fn terms(&self) -> &TermDictionary {
pub fn terms(&self) -> &TermDictionaryImpl {
&self.termdict
}
@@ -96,20 +92,8 @@ impl InvertedIndexReader {
let offset = term_info.postings_offset as usize;
let end_source = self.postings_source.len();
let postings_slice = self.postings_source.slice(offset, end_source);
block_postings.reset(term_info.doc_freq, postings_slice);
}
/// Returns a block postings given a `Term`.
/// This method is for an advanced usage only.
///
/// Most user should prefer using `read_postings` instead.
pub fn read_block_postings(
&self,
term: &Term,
option: IndexRecordOption,
) -> Option<BlockSegmentPostings> {
self.get_term_info(term)
.map(move |term_info| self.read_block_postings_from_terminfo(&term_info, option))
let postings_reader = SourceRead::from(postings_slice);
block_postings.reset(term_info.doc_freq as usize, postings_reader);
}
/// Returns a block postings given a `term_info`.
@@ -123,11 +107,15 @@ impl InvertedIndexReader {
) -> BlockSegmentPostings {
let offset = term_info.postings_offset as usize;
let postings_data = self.postings_source.slice_from(offset);
let freq_reading_option = match (self.record_option, requested_option) {
(IndexRecordOption::Basic, _) => FreqReadingOption::NoFreq,
(_, IndexRecordOption::Basic) => FreqReadingOption::SkipFreq,
(_, _) => FreqReadingOption::ReadFreq,
};
BlockSegmentPostings::from_data(
term_info.doc_freq,
postings_data,
self.record_option,
requested_option,
term_info.doc_freq as usize,
SourceRead::from(postings_data),
freq_reading_option,
)
}
@@ -143,11 +131,11 @@ impl InvertedIndexReader {
let block_postings = self.read_block_postings_from_terminfo(term_info, option);
let position_stream = {
if option.has_positions() {
let position_reader = self.positions_source.clone();
let skip_reader = self.positions_idx_source.clone();
let position_reader =
PositionReader::new(position_reader, skip_reader, term_info.positions_idx);
Some(position_reader)
let position_offset = term_info.positions_offset;
let positions_source = self.positions_source.slice_from(position_offset as usize);
let mut stream = CompressedIntStream::wrap(positions_source);
stream.skip(term_info.positions_inner_offset as usize);
Some(stream)
} else {
None
}
@@ -161,6 +149,8 @@ impl InvertedIndexReader {
self.total_num_tokens
}
/// Returns the segment postings associated with the term, and with the given option,
/// or `None` if the term has never been encountered and indexed.
///
@@ -172,19 +162,16 @@ impl InvertedIndexReader {
/// `TextIndexingOptions` that does not index position will return a `SegmentPostings`
/// with `DocId`s and frequencies.
pub fn read_postings(&self, term: &Term, option: IndexRecordOption) -> Option<SegmentPostings> {
self.get_term_info(term)
.map(move |term_info| self.read_postings_from_terminfo(&term_info, option))
let term_info = get!(self.get_term_info(term));
Some(self.read_postings_from_terminfo(&term_info, option))
}
pub(crate) fn read_postings_no_deletes(
&self,
term: &Term,
option: IndexRecordOption,
) -> Option<SegmentPostings> {
self.get_term_info(term)
.map(|term_info| self.read_postings_from_terminfo(&term_info, option))
pub(crate) fn read_postings_no_deletes(&self, term: &Term, option: IndexRecordOption) -> Option<SegmentPostings> {
let term_info = get!(self.get_term_info(term));
Some(self.read_postings_from_terminfo(&term_info, option))
}
/// Returns the number of documents containing the term.
pub fn doc_freq(&self, term: &Term) -> u32 {
self.get_term_info(term)
@@ -192,3 +179,6 @@ impl InvertedIndexReader {
.unwrap_or(0u32)
}
}

54
src/core/mod.rs
View File

@@ -1,34 +1,42 @@
mod executor;
pub mod index;
mod index_meta;
mod inverted_index_reader;
pub mod searcher;
mod segment;
mod segment_component;
mod segment_id;
pub mod index;
mod segment_reader;
mod segment_id;
mod segment_component;
mod segment;
mod index_meta;
mod pool;
mod segment_meta;
mod inverted_index_reader;
pub use self::executor::Executor;
pub use self::index::Index;
pub use self::index_meta::{IndexMeta, SegmentMeta, SegmentMetaInventory};
pub use self::inverted_index_reader::InvertedIndexReader;
pub use self::searcher::Searcher;
pub use self::segment::Segment;
pub use self::segment::SerializableSegment;
pub use self::segment_component::SegmentComponent;
pub use self::segment_id::SegmentId;
pub use self::segment_reader::SegmentReader;
pub use self::segment::Segment;
pub use self::segment::SerializableSegment;
pub use self::index::Index;
pub use self::segment_meta::SegmentMeta;
pub use self::index_meta::IndexMeta;
use once_cell::sync::Lazy;
use std::path::Path;
use std::path::PathBuf;
/// The meta file contains all the information about the list of segments and the schema
/// of the index.
pub static META_FILEPATH: Lazy<&'static Path> = Lazy::new(|| Path::new("meta.json"));
lazy_static! {
/// The meta file contains all the information about the list of segments and the schema
/// of the index.
pub static ref META_FILEPATH: PathBuf = PathBuf::from("meta.json");
/// The managed file contains a list of files that were created by the tantivy
/// and will therefore be garbage collected when they are deemed useless by tantivy.
///
/// Removing this file is safe, but will prevent the garbage collection of all of the file that
/// are currently in the directory
pub static MANAGED_FILEPATH: Lazy<&'static Path> = Lazy::new(|| Path::new(".managed.json"));
/// The managed file contains a list of files that were created by the tantivy
/// and will therefore be garbage collected when they are deemed useless by tantivy.
///
/// Removing this file is safe, but will prevent the garbage collection of all of the file that
/// are currently in the directory
pub static ref MANAGED_FILEPATH: PathBuf = PathBuf::from(".managed.json");
/// Only one process should be able to write tantivy's index at a time.
/// This file, when present, is in charge of preventing other processes to open an IndexWriter.
///
/// If the process is killed and this file remains, it is safe to remove it manually.
pub static ref LOCKFILE_FILEPATH: PathBuf = PathBuf::from(".tantivy-indexer.lock");
}

134
src/core/pool.rs Normal file
View File

@@ -0,0 +1,134 @@
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering;
use std::mem;
use std::ops::{Deref, DerefMut};
use crossbeam::sync::MsQueue;
use std::sync::Arc;
pub struct GenerationItem<T> {
generation: usize,
item: T,
}
pub struct Pool<T> {
queue: Arc<MsQueue<GenerationItem<T>>>,
freshest_generation: AtomicUsize,
next_generation: AtomicUsize,
}
impl<T> Pool<T> {
pub fn new() -> Pool<T> {
let queue = Arc::new(MsQueue::new());
Pool {
queue,
freshest_generation: AtomicUsize::default(),
next_generation: AtomicUsize::default(),
}
}
pub fn publish_new_generation(&self, items: Vec<T>) {
let next_generation = self.next_generation.fetch_add(1, Ordering::SeqCst) + 1;
for item in items {
let gen_item = GenerationItem {
item,
generation: next_generation,
};
self.queue.push(gen_item);
}
self.advertise_generation(next_generation);
}
/// At the exit of this method,
/// - freshest_generation has a value greater or equal than generation
/// - freshest_generation has a value that has been advertised
/// - freshest_generation has)
fn advertise_generation(&self, generation: usize) {
// not optimal at all but the easiest to read proof.
loop {
let former_generation = self.freshest_generation.load(Ordering::Acquire);
if former_generation >= generation {
break;
}
self.freshest_generation.compare_and_swap(
former_generation,
generation,
Ordering::SeqCst,
);
}
}
fn generation(&self) -> usize {
self.freshest_generation.load(Ordering::Acquire)
}
pub fn acquire(&self) -> LeasedItem<T> {
let generation = self.generation();
loop {
let gen_item = self.queue.pop();
if gen_item.generation >= generation {
return LeasedItem {
gen_item: Some(gen_item),
recycle_queue: Arc::clone(&self.queue),
};
} else {
// this searcher is obsolete,
// removing it from the pool.
}
}
}
}
pub struct LeasedItem<T> {
gen_item: Option<GenerationItem<T>>,
recycle_queue: Arc<MsQueue<GenerationItem<T>>>,
}
impl<T> Deref for LeasedItem<T> {
type Target = T;
fn deref(&self) -> &T {
&self.gen_item
.as_ref()
.expect("Unwrapping a leased item should never fail")
.item // unwrap is safe here
}
}
impl<T> DerefMut for LeasedItem<T> {
fn deref_mut(&mut self) -> &mut T {
&mut self.gen_item
.as_mut()
.expect("Unwrapping a mut leased item should never fail")
.item // unwrap is safe here
}
}
impl<T> Drop for LeasedItem<T> {
fn drop(&mut self) {
let gen_item: GenerationItem<T> = mem::replace(&mut self.gen_item, None)
.expect("Unwrapping a leased item should never fail");
self.recycle_queue.push(gen_item);
}
}
#[cfg(test)]
mod tests {
use std::iter;
use super::Pool;
#[test]
fn test_pool() {
let items10: Vec<usize> = iter::repeat(10).take(10).collect();
let pool = Pool::new();
pool.publish_new_generation(items10);
for _ in 0..20 {
assert_eq!(*pool.acquire(), 10);
}
let items11: Vec<usize> = iter::repeat(11).take(10).collect();
pool.publish_new_generation(items11);
for _ in 0..20 {
assert_eq!(*pool.acquire(), 11);
}
}
}

153
src/core/searcher.rs
View File

@@ -1,18 +1,14 @@
use crate::collector::Collector;
use crate::core::Executor;
use crate::core::InvertedIndexReader;
use crate::core::SegmentReader;
use crate::query::Query;
use crate::schema::Document;
use crate::schema::Schema;
use crate::schema::{Field, Term};
use crate::space_usage::SearcherSpaceUsage;
use crate::store::StoreReader;
use crate::termdict::TermMerger;
use crate::DocAddress;
use crate::Index;
use std::fmt;
use Result;
use core::SegmentReader;
use schema::Document;
use collector::Collector;
use query::Query;
use DocAddress;
use schema::{Field, Term};
use termdict::{TermDictionary, TermMerger};
use std::sync::Arc;
use std::fmt;
use core::InvertedIndexReader;
/// Holds a list of `SegmentReader`s ready for search.
///
@@ -20,56 +16,25 @@ use std::sync::Arc;
/// the destruction of the `Searcher`.
///
pub struct Searcher {
schema: Schema,
index: Index,
segment_readers: Vec<SegmentReader>,
store_readers: Vec<StoreReader>,
}
impl Searcher {
/// Creates a new `Searcher`
pub(crate) fn new(
schema: Schema,
index: Index,
segment_readers: Vec<SegmentReader>,
) -> Searcher {
let store_readers = segment_readers
.iter()
.map(SegmentReader::get_store_reader)
.collect();
Searcher {
schema,
index,
segment_readers,
store_readers,
}
}
/// Returns the `Index` associated to the `Searcher`
pub fn index(&self) -> &Index {
&self.index
}
/// Fetches a document from tantivy's store given a `DocAddress`.
///
/// The searcher uses the segment ordinal to route the
/// the request to the right `Segment`.
pub fn doc(&self, doc_address: DocAddress) -> crate::Result<Document> {
let DocAddress(segment_local_id, doc_id) = doc_address;
let store_reader = &self.store_readers[segment_local_id as usize];
store_reader.get(doc_id)
}
/// Access the schema associated to the index of this searcher.
pub fn schema(&self) -> &Schema {
&self.schema
pub fn doc(&self, doc_address: &DocAddress) -> Result<Document> {
let DocAddress(segment_local_id, doc_id) = *doc_address;
let segment_reader = &self.segment_readers[segment_local_id as usize];
segment_reader.doc(doc_id)
}
/// Returns the overall number of documents in the index.
pub fn num_docs(&self) -> u64 {
self.segment_readers
.iter()
.map(|segment_reader| u64::from(segment_reader.num_docs()))
.map(|segment_reader| segment_reader.num_docs() as u64)
.sum::<u64>()
}
@@ -78,9 +43,7 @@ impl Searcher {
pub fn doc_freq(&self, term: &Term) -> u64 {
self.segment_readers
.iter()
.map(|segment_reader| {
u64::from(segment_reader.inverted_index(term.field()).doc_freq(term))
})
.map(|segment_reader| segment_reader.inverted_index(term.field()).doc_freq(term) as u64)
.sum::<u64>()
}
@@ -94,77 +57,19 @@ impl Searcher {
&self.segment_readers[segment_ord as usize]
}
/// Runs a query on the segment readers wrapped by the searcher.
///
/// Search works as follows :
///
/// First the weight object associated to the query is created.
///
/// Then, the query loops over the segments and for each segment :
/// - setup the collector and informs it that the segment being processed has changed.
/// - creates a SegmentCollector for collecting documents associated to the segment
/// - creates a `Scorer` object associated for this segment
/// - iterate through the matched documents and push them to the segment collector.
///
/// Finally, the Collector merges each of the child collectors into itself for result usability
/// by the caller.
pub fn search<C: Collector>(
&self,
query: &dyn Query,
collector: &C,
) -> crate::Result<C::Fruit> {
let executor = self.index.search_executor();
self.search_with_executor(query, collector, executor)
}
/// Same as [`search(...)`](#method.search) but multithreaded.
///
/// The current implementation is rather naive :
/// multithreading is by splitting search into as many task
/// as there are segments.
///
/// It is powerless at making search faster if your index consists in
/// one large segment.
///
/// Also, keep in my multithreading a single query on several
/// threads will not improve your throughput. It can actually
/// hurt it. It will however, decrease the average response time.
pub fn search_with_executor<C: Collector>(
&self,
query: &dyn Query,
collector: &C,
executor: &Executor,
) -> crate::Result<C::Fruit> {
let scoring_enabled = collector.requires_scoring();
let weight = query.weight(self, scoring_enabled)?;
let segment_readers = self.segment_readers();
let fruits = executor.map(
|(segment_ord, segment_reader)| {
collector.collect_segment(weight.as_ref(), segment_ord as u32, segment_reader)
},
segment_readers.iter().enumerate(),
)?;
collector.merge_fruits(fruits)
/// Runs a query on the segment readers wrapped by the searcher
pub fn search<C: Collector>(&self, query: &Query, collector: &mut C) -> Result<()> {
query.search(self, collector)
}
/// Return the field searcher associated to a `Field`.
pub fn field(&self, field: Field) -> FieldSearcher {
let inv_index_readers = self
.segment_readers
let inv_index_readers = self.segment_readers
.iter()
.map(|segment_reader| segment_reader.inverted_index(field))
.collect::<Vec<_>>();
FieldSearcher::new(inv_index_readers)
}
/// Summarize total space usage of this searcher.
pub fn space_usage(&self) -> SearcherSpaceUsage {
let mut space_usage = SearcherSpaceUsage::new();
for segment_reader in self.segment_readers.iter() {
space_usage.add_segment(segment_reader.space_usage());
}
space_usage
}
}
pub struct FieldSearcher {
@@ -178,9 +83,8 @@ impl FieldSearcher {
/// Returns a Stream over all of the sorted unique terms of
/// for the given field.
pub fn terms(&self) -> TermMerger<'_> {
let term_streamers: Vec<_> = self
.inv_index_readers
pub fn terms(&self) -> TermMerger {
let term_streamers: Vec<_> = self.inv_index_readers
.iter()
.map(|inverted_index| inverted_index.terms().stream())
.collect();
@@ -188,12 +92,17 @@ impl FieldSearcher {
}
}
impl From<Vec<SegmentReader>> for Searcher {
fn from(segment_readers: Vec<SegmentReader>) -> Searcher {
Searcher { segment_readers }
}
}
impl fmt::Debug for Searcher {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
let segment_ids = self
.segment_readers
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
let segment_ids = self.segment_readers
.iter()
.map(SegmentReader::segment_id)
.map(|segment_reader| segment_reader.segment_id())
.collect::<Vec<_>>();
write!(f, "Searcher({:?})", segment_ids)
}

109
src/core/segment.rs
View File

@@ -1,15 +1,16 @@
use super::SegmentComponent;
use crate::core::Index;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::directory::error::{OpenReadError, OpenWriteError};
use crate::directory::Directory;
use crate::directory::{ReadOnlySource, WritePtr};
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::schema::Schema;
use crate::Opstamp;
use std::fmt;
use Result;
use std::path::PathBuf;
use schema::Schema;
use std::fmt;
use core::SegmentId;
use directory::{FileProtection, ReadOnlySource, WritePtr};
use indexer::segment_serializer::SegmentSerializer;
use super::SegmentComponent;
use core::Index;
use std::result;
use directory::Directory;
use core::SegmentMeta;
use directory::error::{OpenReadError, OpenWriteError};
/// A segment is a piece of the index.
#[derive(Clone)]
@@ -19,17 +20,19 @@ pub struct Segment {
}
impl fmt::Debug for Segment {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "Segment({:?})", self.id().uuid_string())
}
}
impl Segment {
/// Creates a new segment given an `Index` and a `SegmentId`
pub(crate) fn for_index(index: Index, meta: SegmentMeta) -> Segment {
Segment { index, meta }
}
/// Creates a new segment given an `Index` and a `SegmentId`
///
/// The function is here to make it private outside `tantivy`.
pub fn create_segment(index: Index, meta: SegmentMeta) -> Segment {
Segment { index, meta }
}
impl Segment {
/// Returns the index the segment belongs to.
pub fn index(&self) -> &Index {
&self.index
@@ -45,23 +48,9 @@ impl Segment {
&self.meta
}
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> Segment {
Segment {
index: self.index,
meta: self.meta.with_max_doc(max_doc),
}
}
#[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment {
Segment {
index: self.index,
meta: self.meta.with_delete_meta(num_deleted_docs, opstamp),
}
pub fn set_delete_meta(&mut self, num_deleted_docs: u32, opstamp: u64) {
self.meta.set_delete_meta(num_deleted_docs, opstamp);
}
/// Returns the segment's id.
@@ -77,15 +66,31 @@ impl Segment {
self.meta.relative_path(component)
}
/// Protects a specific component file from being deleted.
///
/// Returns a FileProtection object. The file is guaranteed
/// to not be garbage collected as long as this `FileProtection` object
/// lives.
pub fn protect_from_delete(&self, component: SegmentComponent) -> FileProtection {
let path = self.relative_path(component);
self.index.directory().protect_file_from_delete(&path)
}
/// Open one of the component file for a *regular* read.
pub fn open_read(&self, component: SegmentComponent) -> Result<ReadOnlySource, OpenReadError> {
pub fn open_read(
&self,
component: SegmentComponent,
) -> result::Result<ReadOnlySource, OpenReadError> {
let path = self.relative_path(component);
let source = self.index.directory().open_read(&path)?;
Ok(source)
}
/// Open one of the component file for *regular* write.
pub fn open_write(&mut self, component: SegmentComponent) -> Result<WritePtr, OpenWriteError> {
pub fn open_write(
&mut self,
component: SegmentComponent,
) -> result::Result<WritePtr, OpenWriteError> {
let path = self.relative_path(component);
let write = self.index.directory_mut().open_write(&path)?;
Ok(write)
@@ -98,5 +103,37 @@ pub trait SerializableSegment {
///
/// # Returns
/// The number of documents in the segment.
fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32>;
fn write(&self, serializer: SegmentSerializer) -> Result<u32>;
}
#[cfg(test)]
mod tests {
use core::SegmentComponent;
use directory::Directory;
use std::collections::HashSet;
use schema::SchemaBuilder;
use Index;
#[test]
fn test_segment_protect_component() {
let mut index = Index::create_in_ram(SchemaBuilder::new().build());
let segment = index.new_segment();
let path = segment.relative_path(SegmentComponent::POSTINGS);
let directory = index.directory_mut();
directory.atomic_write(&*path, &vec![0u8]).unwrap();
let living_files = HashSet::new();
{
let _file_protection = segment.protect_from_delete(SegmentComponent::POSTINGS);
assert!(directory.exists(&*path));
directory.garbage_collect(|| living_files.clone());
assert!(directory.exists(&*path));
}
directory.garbage_collect(|| living_files);
assert!(!directory.exists(&*path));
}
}

11
src/core/segment_component.rs
View File

@@ -1,5 +1,3 @@
use std::slice;
/// Enum describing each component of a tantivy segment.
/// Each component is stored in its own file,
/// using the pattern `segment_uuid`.`component_extension`,
@@ -10,8 +8,6 @@ pub enum SegmentComponent {
POSTINGS,
/// Positions of terms in each document.
POSITIONS,
/// Index to seek within the position file
POSITIONSSKIP,
/// Column-oriented random-access storage of fields.
FASTFIELDS,
/// Stores the sum of the length (in terms) of each field for each document.
@@ -30,17 +26,16 @@ pub enum SegmentComponent {
impl SegmentComponent {
/// Iterates through the components.
pub fn iterator() -> slice::Iter<'static, SegmentComponent> {
static SEGMENT_COMPONENTS: [SegmentComponent; 8] = [
pub fn iterator() -> impl Iterator<Item = &'static SegmentComponent> {
static SEGMENT_COMPONENTS: [SegmentComponent; 7] = [
SegmentComponent::POSTINGS,
SegmentComponent::POSITIONS,
SegmentComponent::POSITIONSSKIP,
SegmentComponent::FASTFIELDS,
SegmentComponent::FIELDNORMS,
SegmentComponent::TERMS,
SegmentComponent::STORE,
SegmentComponent::DELETE,
];
SEGMENT_COMPONENTS.iter()
SEGMENT_COMPONENTS.into_iter()
}
}

78
src/core/segment_id.rs
View File

@@ -1,12 +1,7 @@
use std::cmp::{Ord, Ordering};
use std::fmt;
use uuid::Uuid;
use std::fmt;
use std::cmp::{Ord, Ordering};
#[cfg(test)]
use once_cell::sync::Lazy;
use serde::{Deserialize, Serialize};
use std::error::Error;
use std::str::FromStr;
#[cfg(test)]
use std::sync::atomic;
@@ -22,10 +17,10 @@ use std::sync::atomic;
pub struct SegmentId(Uuid);
#[cfg(test)]
static AUTO_INC_COUNTER: Lazy<atomic::AtomicUsize> = Lazy::new(|| atomic::AtomicUsize::default());
#[cfg(test)]
const ZERO_ARRAY: [u8; 8] = [0u8; 8];
lazy_static! {
static ref AUTO_INC_COUNTER: atomic::AtomicUsize = atomic::AtomicUsize::default();
static ref EMPTY_ARR: [u8; 8] = [0u8; 8];
}
// During tests, we generate the segment id in a autoincrement manner
// for consistency of segment id between run.
@@ -35,7 +30,7 @@ const ZERO_ARRAY: [u8; 8] = [0u8; 8];
#[cfg(test)]
fn create_uuid() -> Uuid {
let new_auto_inc_id = (*AUTO_INC_COUNTER).fetch_add(1, atomic::Ordering::SeqCst);
Uuid::from_fields(new_auto_inc_id as u32, 0, 0, &ZERO_ARRAY).unwrap()
Uuid::from_fields(new_auto_inc_id as u32, 0, 0, &*EMPTY_ARR).unwrap()
}
#[cfg(not(test))]
@@ -55,55 +50,19 @@ impl SegmentId {
/// and the rest is random.
///
/// Picking the first 8 chars is ok to identify
/// segments in a display message (e.g. a5c4dfcb).
/// segments in a display message.
pub fn short_uuid_string(&self) -> String {
(&self.0.to_simple_ref().to_string()[..8]).to_string()
(&self.0.simple().to_string()[..8]).to_string()
}
/// Returns a segment uuid string.
///
/// It consists in 32 lowercase hexadecimal chars
/// (e.g. a5c4dfcbdfe645089129e308e26d5523)
pub fn uuid_string(&self) -> String {
self.0.to_simple_ref().to_string()
}
/// Build a `SegmentId` string from the full uuid string.
///
/// E.g. "a5c4dfcbdfe645089129e308e26d5523"
pub fn from_uuid_string(uuid_string: &str) -> Result<SegmentId, SegmentIdParseError> {
FromStr::from_str(uuid_string)
}
}
/// Error type used when parsing a `SegmentId` from a string fails.
pub struct SegmentIdParseError(uuid::Error);
impl Error for SegmentIdParseError {}
impl fmt::Debug for SegmentIdParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.0.fmt(f)
}
}
impl fmt::Display for SegmentIdParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.0.fmt(f)
}
}
impl FromStr for SegmentId {
type Err = SegmentIdParseError;
fn from_str(uuid_string: &str) -> Result<Self, SegmentIdParseError> {
let uuid = Uuid::parse_str(uuid_string).map_err(SegmentIdParseError)?;
Ok(SegmentId(uuid))
self.0.simple().to_string()
}
}
impl fmt::Debug for SegmentId {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "Seg({:?})", self.short_uuid_string())
}
}
@@ -119,18 +78,3 @@ impl Ord for SegmentId {
self.0.as_bytes().cmp(other.0.as_bytes())
}
}
#[cfg(test)]
mod tests {
use super::SegmentId;
#[test]
fn test_to_uuid_string() {
let full_uuid = "a5c4dfcbdfe645089129e308e26d5523";
let segment_id = SegmentId::from_uuid_string(full_uuid).unwrap();
assert_eq!(segment_id.uuid_string(), full_uuid);
assert_eq!(segment_id.short_uuid_string(), "a5c4dfcb");
// one extra char
assert!(SegmentId::from_uuid_string("a5c4dfcbdfe645089129e308e26d5523b").is_err());
}
}

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