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

Compare commits

base: rust:barrotsteindev-filter-collector
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:python-binding-changes
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

2 Commits
barrotstei ... python-bin

Author SHA1 Message Date
Paul Masurel
a7c579f5c9 Added method to convert named doc to doc 2019-08-06 08:00:32 +09:00
Paul Masurel
f2e546bdff Changes required for python binding 2019-08-01 17:23:49 +09:00
212 changed files with 8179 additions and 15100 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']

2
.gitignore vendored
View File

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

2
.travis.yml
View File

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

104
CHANGELOG.md
View File

@@ -1,111 +1,7 @@
Tantivy 0.14.0
=========================
- Remove dependency to atomicwrites #833 .Implemented by @pmasurel upon suggestion and research from @asafigan).
- Migrated tantivy error from the now deprecated `failure` crate to `thiserror` #760. (@hirevo)
- API Change. Accessing the typed value off a `Schema::Value` now returns an Option instead of panicking if the type does not match.
- Large API Change in the Directory API. Tantivy used to assume that all files could be somehow memory mapped. After this change, Directory return a `FileSlice` that can be reduced and eventually read into an `OwnedBytes` object. Long and blocking io operation are still required by they do not span over the entire file.
- Added support for Brotli compression in the DocStore. (@ppodolsky)
- Added helper for building intersections and unions in BooleanQuery (@guilload)
- Bugfix in `Query::explain`
- Removed dependency on `notify` #924. Replaced with `FileWatcher` struct that polls meta file every 500ms in background thread. (@halvorboe @guilload)
Tantivy 0.13.2
===================
Bugfix. Acquiring a facet reader on a segment that does not contain any
doc with this facet returns `None`. (#896)
Tantivy 0.13.1
===================
Made `Query` and `Collector` `Send + Sync`.
Updated misc dependency versions.
Tantivy 0.13.0
======================
Tantivy 0.13 introduce a change in the index format that will require
you to reindex your index (BlockWAND information are added in the skiplist).
The index size increase is minor as this information is only added for
full blocks.
If you have a massive index for which reindexing is not an option, please contact me
so that we can discuss possible solutions.
- Bugfix in `FuzzyTermQuery` not matching terms by prefix when it should (@Peachball)
- Relaxed constraints on the custom/tweak score functions. At the segment level, they can be mut, and they are not required to be Sync + Send.
- `MMapDirectory::open` does not return a `Result` anymore.
- Change in the DocSet and Scorer API. (@fulmicoton).
A freshly created DocSet point directly to their first doc. A sentinel value called TERMINATED marks the end of a DocSet.
`.advance()` returns the new DocId. `Scorer::skip(target)` has been replaced by `Scorer::seek(target)` and returns the resulting DocId.
As a result, iterating through DocSet now looks as follows
```rust
let mut doc = docset.doc();
while doc != TERMINATED {
// ...
doc = docset.advance();
}
```
The change made it possible to greatly simplify a lot of the docset's code.
- Misc internal optimization and introduction of the `Scorer::for_each_pruning` function. (@fulmicoton)
- Added an offset option to the Top(.*)Collectors. (@robyoung)
- Added Block WAND. Performance on TOP-K on term-unions should be greatly increased. (@fulmicoton, and special thanks
to the PISA team for answering all my questions!)
Tantivy 0.12.0
======================
- Removing static dispatch in tokenizers for simplicity. (#762)
- Added backward iteration for `TermDictionary` stream. (@halvorboe)
- Fixed a performance issue when searching for the posting lists of a missing term (@audunhalland)
- Added a configurable maximum number of docs (10M by default) for a segment to be considered for merge (@hntd187, landed by @halvorboe #713)
- Important Bugfix #777, causing tantivy to retain memory mapping. (diagnosed by @poljar)
- Added support for field boosting. (#547, @fulmicoton)
## How to update?
Crates relying on custom tokenizer, or registering tokenizer in the manager will require some
minor changes. Check https://github.com/tantivy-search/tantivy/blob/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
=====================

86
Cargo.toml
View File

@@ -1,11 +1,11 @@
[package]
name = "tantivy"
version = "0.14.0-dev"
version = "0.10.1"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://docs.rs/tantivy/"
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"
@@ -13,41 +13,47 @@ keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
base64 = "0.13"
byteorder = "1"
crc32fast = "1"
once_cell = "1"
regex ={version = "1", default-features = false, features = ["std"]}
tantivy-fst = "0.3"
base64 = "0.10.0"
byteorder = "1.0"
once_cell = "0.2"
regex = "1.0"
tantivy-fst = "0.1"
memmap = {version = "0.7", optional=true}
lz4 = {version="1", optional=true}
brotli = {version="3.3.0", optional=true}
snap = "1"
tempfile = {version="3", optional=true}
lz4 = {version="1.20", optional=true}
snap = {version="0.2"}
atomicwrites = {version="0.2.2", optional=true}
tempfile = "3.0"
log = "0.4"
serde = {version="1", features=["derive"]}
serde_json = "1"
num_cpus = "1"
combine = ">=3.6.0,<4.0.0"
tempdir = "0.3"
serde = "1.0"
serde_derive = "1.0"
serde_json = "1.0"
num_cpus = "1.2"
fs2={version="0.4", optional=true}
levenshtein_automata = "0.2"
uuid = { version = "0.8", features = ["v4", "serde"] }
crossbeam = "0.8"
futures = {version = "0.3", features=["thread-pool"] }
tantivy-query-grammar = { version="0.14.0-dev", path="./query-grammar" }
stable_deref_trait = "1"
rust-stemmers = "1"
downcast-rs = "1"
itertools = "0.8"
levenshtein_automata = {version="0.1", features=["fst_automaton"]}
notify = {version="4", optional=true}
bit-set = "0.5"
uuid = { version = "0.7.2", features = ["v4", "serde"] }
crossbeam = "0.5"
futures = "0.1"
futures-cpupool = "0.1"
owning_ref = "0.4"
stable_deref_trait = "1.0.0"
rust-stemmers = "1.1"
downcast-rs = { version="1.0" }
bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
census = "0.4"
fnv = "1"
thiserror = "1.0"
htmlescape = "0.3"
fail = "0.4"
census = "0.2"
fnv = "1.0.6"
owned-read = "0.4"
failure = "0.1"
htmlescape = "0.3.1"
fail = "0.3"
scoped-pool = "1.0"
murmurhash32 = "0.2"
chrono = "0.4"
smallvec = "1"
rayon = "1"
lru = "0.6"
smallvec = "0.6"
[target.'cfg(windows)'.dependencies]
winapi = "0.3"
@@ -56,11 +62,7 @@ winapi = "0.3"
rand = "0.7"
maplit = "1"
matches = "0.1.8"
proptest = "0.10"
[dev-dependencies.fail]
version = "0.4"
features = ["failpoints"]
time = "0.1.42"
[profile.release]
opt-level = 3
@@ -73,19 +75,19 @@ overflow-checks = true
[features]
default = ["mmap"]
mmap = ["fs2", "tempfile", "memmap"]
brotli-compression = ["brotli"]
mmap = ["atomicwrites", "fs2", "memmap", "notify"]
lz4-compression = ["lz4"]
failpoints = ["fail/failpoints"]
unstable = [] # useful for benches.
wasm-bindgen = ["uuid/wasm-bindgen"]
[workspace]
members = ["query-grammar"]
[badges]
travis-ci = { repository = "tantivy-search/tantivy" }
[dev-dependencies.fail]
features = ["failpoints"]
# Following the "fail" crate best practises, we isolate
# tests that define specific behavior in fail check points
# in a different binary.
@@ -96,4 +98,4 @@ travis-ci = { repository = "tantivy-search/tantivy" }
[[test]]
name = "failpoints"
path = "tests/failpoints/mod.rs"
required-features = ["fail/failpoints"]
required-features = ["fail/failpoints"]

3
Makefile
View File

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

68
README.md
View File

@@ -5,6 +5,7 @@
[![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)
@@ -20,9 +21,9 @@
[![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
**Tantivy** is a **full text search engine library** written in Rust.
**Tantivy** is a **full text search engine library** written in rust.
It is closer to [Apache Lucene](https://lucene.apache.org/) than to [Elasticsearch](https://www.elastic.co/products/elasticsearch) or [Apache Solr](https://lucene.apache.org/solr/) in the sense it is not
It is closer to [Apache Lucene](https://lucene.apache.org/) than to [Elasticsearch](https://www.elastic.co/products/elasticsearch) and [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.
@@ -30,70 +31,73 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark
Tantivy is typically faster than Lucene, but the results will depend on
the nature of the queries in your workload.
The following [benchmark](https://tantivy-search.github.io/bench/) break downs
performance for different type of queries / collection.
Your mileage WILL vary depending on the nature of queries and their load.
# Features
- Full-text search
- Configurable tokenizer (stemming available for 17 Latin languages 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))
- Configurable tokenizer. (stemming available for 17 latin languages. Third party support for Chinese ([tantivy-jieba](https://crates.io/crates/tantivy-jieba) and [cang-jie](https://crates.io/crates/cang-jie)) and [Japanese](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter)
- 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"`)
- BM25 scoring (the same as lucene)
- Natural query language `(michael AND jackson) OR "king of pop"`
- Phrase queries search (`"michael jackson"`)
- Incremental indexing
- Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop)
- Mmap directory
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set
- Single valued and multivalued u64, i64, and f64 fast fields (equivalent of doc values in Lucene)
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set.
- Single valued and multivalued u64, i64 and f64 fast fields (equivalent of doc values in Lucene)
- `&[u8]` fast fields
- Text, i64, u64, f64, dates, and hierarchical facet fields
- Text, i64, u64, f64, dates and hierarchical facet fields
- LZ4 compressed document store
- Range queries
- Faceted search
- Configurable indexing (optional term frequency and position indexing)
- Cheesy logo with a horse
## Non-features
# Non-features
- Distributed search is out of the scope of Tantivy. That being said, Tantivy is a
- Distributed search is out of the scope of tantivy. That being said, tantivy is meant as a
library upon which one could build a distributed search. Serializable/mergeable collector state for instance,
are within the scope of Tantivy.
are within the scope of tantivy.
# Supported OS and compiler
Tantivy works on stable rust (>= 1.27) and supports Linux, MacOS and Windows.
# Getting started
Tantivy works on stable Rust (>= 1.27) and supports Linux, MacOS, and Windows.
- [Tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html)
- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli) - `tantivy-cli` is an actual command line interface that makes it easy for you to create a search engine,
index documents, and search via the CLI or a small server with a REST API.
It walks you through getting a wikipedia search engine up and running in a few minutes.
- [Reference doc for the last released version](https://docs.rs/tantivy/)
- [tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html)
- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli).
`tantivy-cli` is an actual command line interface that makes it easy for you to create a search engine,
index documents and search via the CLI or a small server with a REST API.
It will walk you through getting a wikipedia search engine up and running in a few minutes.
- [reference doc for the last released version](https://docs.rs/tantivy/)
# How can I support this project?
There are many ways to support this project.
- Use Tantivy and tell us about your experience on [Gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
- Use tantivy and tell us about your experience on [gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
- Report bugs
- Write a blog post
- Help with documentation by asking questions or submitting PRs
- Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy))
- Talk about Tantivy around you
- [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
- Contribute code (you can join [our gitter](https://gitter.im/tantivy-search/tantivy) )
- Talk about tantivy around you
- Drop a word on on [![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton) or even [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
# Contributing code
We use the GitHub Pull Request workflow: reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
We use the GitHub Pull Request workflow - reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
## Clone and build locally
Tantivy compiles on stable Rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run:
Tantivy compiles on stable rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run :
```bash
git clone https://github.com/tantivy-search/tantivy.git
@@ -104,7 +108,7 @@ To check out and run tests, you can simply run:
## Run tests
Some tests will not run with just `cargo test` because of `fail-rs`.
To run the tests exhaustively, run `./run-tests.sh`.
To run the tests exhaustively, run `./run-tests.sh`
## Debug
@@ -112,13 +116,13 @@ You might find it useful to step through the programme with a debugger.
### A failing test
Make sure you haven't run `cargo clean` after the most recent `cargo test` or `cargo build` to guarantee that 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`:
Make sure you haven't run `cargo clean` after the most recent `cargo test` or `cargo build` to guarantee that `target/` dir exists. Use this bash script to find the most name of the most recent debug build of tantivy and run it under rust-gdb.
```bash
find target/debug/ -maxdepth 1 -executable -type f -name "tantivy*" -printf '%TY-%Tm-%Td %TT %p\n' | sort -r | cut -d " " -f 3 | xargs -I RECENT_DBG_TANTIVY rust-gdb RECENT_DBG_TANTIVY
```
Now that you are in `rust-gdb`, you can set breakpoints on lines and methods that match your source code and run the debug executable with flags that you normally pass to `cargo test` like this:
Now that you are in rust-gdb, you can set breakpoints on lines and methods that match your source-code and run the debug executable with flags that you normally pass to `cargo test` to like this
```bash
$gdb run --test-threads 1 --test $NAME_OF_TEST
@@ -126,7 +130,7 @@ $gdb run --test-threads 1 --test $NAME_OF_TEST
### An example
By default, `rustc` compiles everything in the `examples/` directory in debug mode. This makes it easy for you to make examples to reproduce bugs:
By default, rustc compiles everything in the `examples/` dir in debug mode. This makes it easy for you to make examples to reproduce bugs.
```bash
rust-gdb target/debug/examples/$EXAMPLE_NAME

2
appveyor.yml
View File

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

5
ci/script.sh
View File

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

52
examples/basic_search.rs
View File

@@ -5,23 +5,26 @@
//
// 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.
// = 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...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::{doc, Index, ReloadPolicy};
use tempfile::TempDir;
use tantivy::Index;
use tantivy::ReloadPolicy;
use tempdir::TempDir;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new()?;
let index_path = TempDir::new("tantivy_example_dir")?;
// # Defining the schema
//
@@ -30,7 +33,7 @@ fn main() -> tantivy::Result<()> {
// and for each field, its type and "the way it should
// be indexed".
// First we need to define a schema ...
// first we need to define a schema ...
let mut schema_builder = Schema::builder();
// Our first field is title.
@@ -45,7 +48,7 @@ fn main() -> tantivy::Result<()> {
//
// `STORED` means that the field will also be saved
// in a compressed, row-oriented key-value store.
// This store is useful for reconstructing the
// This store is useful to reconstruct the
// documents that were selected during the search phase.
schema_builder.add_text_field("title", TEXT | STORED);
@@ -54,7 +57,8 @@ fn main() -> tantivy::Result<()> {
// need to be able to be able to retrieve it
// for our application.
//
// We can make our index lighter by omitting the `STORED` flag.
// We can make our index lighter and
// by omitting `STORED` flag.
schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
@@ -67,7 +71,7 @@ fn main() -> tantivy::Result<()> {
// 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.
// To insert document we need an index writer.
// There must be only one writer at a time.
// This single `IndexWriter` is already
// multithreaded.
@@ -112,6 +116,18 @@ fn main() -> tantivy::Result<()> {
limbs and branches that arch over the pool"
));
index_writer.add_document(doc!(
title => "Of Mice and Men",
body => "A few miles south of Soledad, the Salinas River drops in close to the hillside \
bank and runs deep and green. The water is warm too, for it has slipped twinkling \
over the yellow sands in the sunlight before reaching the narrow pool. On one \
side of the river the golden foothill slopes curve up to the strong and rocky \
Gabilan Mountains, but on the valley side the water is lined with trees—willows \
fresh and green with every spring, carrying in their lower leaf junctures the \
debris of the winter’s flooding; and sycamores with mottled, white, recumbent \
limbs and branches that arch over the pool"
));
// Multivalued field just need to be repeated.
index_writer.add_document(doc!(
title => "Frankenstein",
@@ -133,8 +149,8 @@ fn main() -> tantivy::Result<()> {
// At this point our documents are not searchable.
//
//
// We need to call `.commit()` explicitly to force the
// `index_writer` to finish processing the documents in the queue,
// We need to call .commit() explicitly to force the
// index_writer to finish processing the documents in the queue,
// flush the current index to the disk, and advertise
// the existence of new documents.
//
@@ -146,14 +162,14 @@ fn main() -> tantivy::Result<()> {
// persistently indexed.
//
// In the scenario of a crash or a power failure,
// tantivy behaves as if it has rolled back to its last
// tantivy behaves as if has rolled back to its last
// commit.
// # Searching
//
// ### Searcher
//
// A reader is required first in order to search an index.
// A reader is required to get search the index.
// It acts as a `Searcher` pool that reloads itself,
// depending on a `ReloadPolicy`.
//
@@ -169,7 +185,7 @@ fn main() -> tantivy::Result<()> {
// We now need to acquire a searcher.
//
// A searcher points to a snapshotted, immutable version of the index.
// A searcher points to 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
@@ -189,7 +205,7 @@ fn main() -> tantivy::Result<()> {
// in both title and body.
let query_parser = QueryParser::for_index(&index, vec![title, body]);
// `QueryParser` may fail if the query is not in the right
// QueryParser may fail if the query is not in the right
// format. For user facing applications, this can be a problem.
// A ticket has been opened regarding this problem.
let query = query_parser.parse_query("sea whale")?;
@@ -205,7 +221,7 @@ fn main() -> tantivy::Result<()> {
//
// We are not interested in all of the documents but
// only in the top 10. Keeping track of our top 10 best documents
// is the role of the `TopDocs` collector.
// is the role of the TopDocs.
// We can now perform our query.
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

7
examples/custom_collector.rs
View File

@@ -9,12 +9,15 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::{Collector, SegmentCollector};
use tantivy::fastfield::FastFieldReader;
use tantivy::query::QueryParser;
use tantivy::schema::Field;
use tantivy::schema::{Schema, FAST, INDEXED, TEXT};
use tantivy::{doc, Index, Score, SegmentReader, TantivyError};
use tantivy::SegmentReader;
use tantivy::{Index, TantivyError};
#[derive(Default)]
struct Stats {
@@ -114,7 +117,7 @@ struct StatsSegmentCollector {
impl SegmentCollector for StatsSegmentCollector {
type Fruit = Option<Stats>;
fn collect(&mut self, doc: u32, _score: Score) {
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;

5
examples/custom_tokenizer.rs
View File

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

5
examples/deleting_updating_documents.rs
View File

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

112
examples/faceted_search.rs
View File

@@ -12,101 +12,67 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::FacetCollector;
use tantivy::query::{AllQuery, TermQuery};
use tantivy::query::AllQuery;
use tantivy::schema::*;
use tantivy::{doc, Index};
use tantivy::Index;
fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the sake of this example
// Let's create a temporary directory for the
// sake of this example
let index_path = TempDir::new("tantivy_facet_example_dir")?;
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");
schema_builder.add_text_field("name", TEXT | STORED);
// this is our faceted field
schema_builder.add_facet_field("tags");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer(30_000_000)?;
let index = Index::create_in_dir(&index_path, schema.clone())?;
let mut index_writer = index.writer(50_000_000)?;
let name = schema.get_field("name").unwrap();
let tags = schema.get_field("tags").unwrap();
// 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")
name => "the ditch",
tags => Facet::from("/pools/north")
));
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")
name => "little stacey",
tags => Facet::from("/pools/south")
));
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.
let mut facet_collector = FacetCollector::for_field(tags);
facet_collector.add_facet("/pools");
// 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),
]
);
}
let facet_counts = searcher.search(&AllQuery, &facet_collector).unwrap();
// This lists all of the facet counts
let facets: Vec<(&Facet, u64)> = facet_counts.get("/pools").collect();
assert_eq!(
facets,
vec![
(&Facet::from("/pools/north"), 1),
(&Facet::from("/pools/south"), 1),
]
);
Ok(())
}
use tempdir::TempDir;

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 ingredient_reader = segment_reader.facet_reader(ingredient).unwrap();
let facet_dict = ingredient_reader.facet_dict();
let query_ords: HashSet<u64> = facets
.iter()
.filter_map(|key| facet_dict.term_ord(key.encoded_str()))
.collect();
let mut facet_ords_buffer: Vec<u64> = Vec::with_capacity(20);
move |doc: DocId, original_score: Score| {
ingredient_reader.facet_ords(doc, &mut facet_ords_buffer);
let missing_ingredients = facet_ords_buffer
.iter()
.filter(|ord| !query_ords.contains(ord))
.count();
let tweak = 1.0 / 4_f32.powi(missing_ingredients as i32);
original_score * tweak
}
});
let top_docs = searcher.search(&query, &top_docs_by_custom_score)?;
let titles: Vec<String> = top_docs
.iter()
.map(|(_, doc_id)| {
searcher
.doc(*doc_id)
.unwrap()
.get_first(title)
.unwrap()
.text()
.unwrap()
.to_owned()
})
.collect();
assert_eq!(titles, vec!["Fried egg", "Egg rolls"]);
}
Ok(())
}

6
examples/integer_range_search.rs
View File

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

28
examples/iterating_docs_and_positions.rs
View File

@@ -9,8 +9,11 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::schema::*;
use tantivy::{doc, DocSet, Index, Postings, TERMINATED};
use tantivy::Index;
use tantivy::{DocId, DocSet, Postings};
fn main() -> tantivy::Result<()> {
// We first create a schema for the sake of the
@@ -45,7 +48,7 @@ fn main() -> tantivy::Result<()> {
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title)?;
let inverted_index = segment_reader.inverted_index(title);
// A `Term` is a text token associated with a field.
// Let's go through all docs containing the term `title:the` and access their position
@@ -58,15 +61,16 @@ fn main() -> tantivy::Result<()> {
// If you don't need all this information, you may get better performance by decompressing less
// information.
if let Some(mut segment_postings) =
inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)?
inverted_index.read_postings(&term_the, IndexRecordOption::WithFreqsAndPositions)
{
// this buffer will be used to request for positions
let mut positions: Vec<u32> = Vec::with_capacity(100);
let mut doc_id = segment_postings.doc();
while doc_id != TERMINATED {
while segment_postings.advance() {
// the number of time the term appears in the document.
let doc_id: DocId = segment_postings.doc(); //< do not try to access this before calling advance once.
// This MAY contains deleted documents as well.
if segment_reader.is_deleted(doc_id) {
doc_id = segment_postings.advance();
continue;
}
@@ -85,7 +89,6 @@ fn main() -> tantivy::Result<()> {
// Doc 2: TermFreq 1: [0]
// ```
println!("Doc {}: TermFreq {}: {:?}", doc_id, term_freq, positions);
doc_id = segment_postings.advance();
}
}
}
@@ -106,7 +109,7 @@ fn main() -> tantivy::Result<()> {
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title)?;
let inverted_index = segment_reader.inverted_index(title);
// This segment posting object is like a cursor over the documents matching the term.
// The `IndexRecordOption` arguments tells tantivy we will be interested in both term frequencies
@@ -115,18 +118,13 @@ fn main() -> tantivy::Result<()> {
// If you don't need all this information, you may get better performance by decompressing less
// information.
if let Some(mut block_segment_postings) =
inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)?
inverted_index.read_block_postings(&term_the, IndexRecordOption::Basic)
{
loop {
let docs = block_segment_postings.docs();
if docs.is_empty() {
break;
}
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);
block_segment_postings.advance();
}
}
}

15
examples/multiple_producer.rs
View File

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

139
examples/pre_tokenized_text.rs
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(())
}

9
examples/snippet.rs
View File

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

6
examples/stop_words.rs
View File

@@ -11,11 +11,13 @@
// ---
// Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs;
use tantivy::query::QueryParser;
use tantivy::schema::*;
use tantivy::tokenizer::*;
use tantivy::{doc, Index};
use tantivy::Index;
fn main() -> tantivy::Result<()> {
// this example assumes you understand the content in `basic_search`
@@ -50,7 +52,7 @@ fn main() -> tantivy::Result<()> {
// This tokenizer lowers all of the text (to help with stop word matching)
// then removes all instances of `the` and `and` from the corpus
let tokenizer = TextAnalyzer::from(SimpleTokenizer)
let tokenizer = SimpleTokenizer
.filter(LowerCaser)
.filter(StopWordFilter::remove(vec![
"the".to_string(),

16
query-grammar/Cargo.toml
View File

@@ -1,16 +0,0 @@
[package]
name = "tantivy-query-grammar"
version = "0.14.0-dev"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
homepage = "https://github.com/tantivy-search/tantivy"
repository = "https://github.com/tantivy-search/tantivy"
readme = "README.md"
keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
combine = {version="4", default-features=false, features=[] }

3
query-grammar/README.md
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)
}

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

@@ -1,72 +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, right) {
(Occur::Should, _) => right,
(Occur::Must, Occur::MustNot) => Occur::MustNot,
(Occur::Must, _) => Occur::Must,
(Occur::MustNot, Occur::MustNot) => Occur::Must,
(Occur::MustNot, _) => Occur::MustNot,
}
}
}
impl fmt::Display for Occur {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
f.write_char(self.to_char())
}
}
#[cfg(test)]
mod test {
use crate::Occur;
#[test]
fn test_occur_compose() {
assert_eq!(Occur::compose(Occur::Should, Occur::Should), Occur::Should);
assert_eq!(Occur::compose(Occur::Should, Occur::Must), Occur::Must);
assert_eq!(
Occur::compose(Occur::Should, Occur::MustNot),
Occur::MustNot
);
assert_eq!(Occur::compose(Occur::Must, Occur::Should), Occur::Must);
assert_eq!(Occur::compose(Occur::Must, Occur::Must), Occur::Must);
assert_eq!(Occur::compose(Occur::Must, Occur::MustNot), Occur::MustNot);
assert_eq!(
Occur::compose(Occur::MustNot, Occur::Should),
Occur::MustNot
);
assert_eq!(Occur::compose(Occur::MustNot, Occur::Must), Occur::MustNot);
assert_eq!(Occur::compose(Occur::MustNot, Occur::MustNot), Occur::Must);
}
}

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

@@ -1,534 +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().or(char('_'))),
many(satisfy(|c: char| {
c.is_alphanumeric() || c == '_' || c == '-'
})),
)
.skip(char(':'))
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
fn word<'a>() -> impl Parser<&'a str, Output = String> {
(
satisfy(|c: char| {
!c.is_whitespace()
&& !['-', '^', '`', ':', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
}),
many(satisfy(|c: char| {
!c.is_whitespace() && ![':', '^', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
})),
)
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
.and_then(|s: String| match s.as_str() {
"OR" | "AND " | "NOT" => Err(StringStreamError::UnexpectedParse),
_ => Ok(s),
})
}
fn term_val<'a>() -> impl Parser<&'a str, Output = String> {
let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
phrase.or(word())
}
fn term_query<'a>() -> impl Parser<&'a str, Output = UserInputLiteral> {
let term_val_with_field = negative_number().or(term_val());
(field(), term_val_with_field).map(|(field_name, phrase)| UserInputLiteral {
field_name: Some(field_name),
phrase,
})
}
fn literal<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let term_default_field = term_val().map(|phrase| UserInputLiteral {
field_name: None,
phrase,
});
attempt(term_query())
.or(term_default_field)
.map(UserInputLeaf::from)
}
fn negative_number<'a>() -> impl Parser<&'a str, Output = String> {
(
char('-'),
many1(digit()),
optional((char('.'), many1(digit()))),
)
.map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
if let Some(('.', s3)) = s3 {
format!("{}{}.{}", s1, s2, s3)
} else {
format!("{}{}", s1, s2)
}
})
}
fn spaces1<'a>() -> impl Parser<&'a str, Output = ()> {
skip_many1(space())
}
/// Function that parses a range out of a Stream
/// Supports ranges like:
/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
/// [a TO *], [a TO c], [abc TO bcd}
fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let range_term_val = || {
word()
.or(negative_number())
.or(char('*').with(value("*".to_string())))
};
// check for unbounded range in the form of <5, <=10, >5, >=5
let elastic_unbounded_range = (
choice([
attempt(string(">=")),
attempt(string("<=")),
attempt(string("<")),
attempt(string(">")),
])
.skip(spaces()),
range_term_val(),
)
.map(
|(comparison_sign, bound): (&str, String)| match comparison_sign {
">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
"<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
"<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
// default case
_ => (UserInputBound::Unbounded, UserInputBound::Unbounded),
},
);
let lower_bound = (one_of("{[".chars()), range_term_val()).map(
|(boundary_char, lower_bound): (char, String)| {
if lower_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '{' {
UserInputBound::Exclusive(lower_bound)
} else {
UserInputBound::Inclusive(lower_bound)
}
},
);
let upper_bound = (range_term_val(), one_of("}]".chars())).map(
|(higher_bound, boundary_char): (String, char)| {
if higher_bound == "*" {
UserInputBound::Unbounded
} else if boundary_char == '}' {
UserInputBound::Exclusive(higher_bound)
} else {
UserInputBound::Inclusive(higher_bound)
}
},
);
// return only lower and upper
let lower_to_upper = (
lower_bound.skip((spaces(), string("TO"), spaces())),
upper_bound,
);
(
optional(field()).skip(spaces()),
// try elastic first, if it matches, the range is unbounded
attempt(elastic_unbounded_range).or(lower_to_upper),
)
.map(|(field, (lower, upper))|
// Construct the leaf from extracted field (optional)
// and bounds
UserInputLeaf::Range {
field,
lower,
upper
})
}
fn negate(expr: UserInputAST) -> UserInputAST {
expr.unary(Occur::MustNot)
}
fn leaf<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
parser(|input| {
char('(')
.with(ast())
.skip(char(')'))
.or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All)))
.or(attempt(
string("NOT").skip(spaces1()).with(leaf()).map(negate),
))
.or(attempt(range().map(UserInputAST::from)))
.or(literal().map(UserInputAST::from))
.parse_stream(input)
.into_result()
})
}
fn occur_symbol<'a>() -> impl Parser<&'a str, Output = Occur> {
char('-')
.map(|_| Occur::MustNot)
.or(char('+').map(|_| Occur::Must))
}
fn occur_leaf<'a>() -> impl Parser<&'a str, Output = (Option<Occur>, UserInputAST)> {
(optional(occur_symbol()), boosted_leaf())
}
fn positive_float_number<'a>() -> impl Parser<&'a str, Output = f64> {
(many1(digit()), optional((char('.'), many1(digit())))).map(
|(int_part, decimal_part_opt): (String, Option<(char, String)>)| {
let mut float_str = int_part;
if let Some((chr, decimal_str)) = decimal_part_opt {
float_str.push(chr);
float_str.push_str(&decimal_str);
}
float_str.parse::<f64>().unwrap()
},
)
}
fn boost<'a>() -> impl Parser<&'a str, Output = f64> {
(char('^'), positive_float_number()).map(|(_, boost)| boost)
}
fn boosted_leaf<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
(leaf(), optional(boost())).map(|(leaf, boost_opt)| match boost_opt {
Some(boost) if (boost - 1.0).abs() > std::f64::EPSILON => {
UserInputAST::Boost(Box::new(leaf), boost)
}
_ => leaf,
})
}
#[derive(Clone, Copy)]
enum BinaryOperand {
Or,
And,
}
fn binary_operand<'a>() -> impl Parser<&'a str, Output = BinaryOperand> {
string("AND")
.with(value(BinaryOperand::And))
.or(string("OR").with(value(BinaryOperand::Or)))
}
fn aggregate_binary_expressions(
left: UserInputAST,
others: Vec<(BinaryOperand, UserInputAST)>,
) -> UserInputAST {
let mut dnf: Vec<Vec<UserInputAST>> = vec![vec![left]];
for (operator, operand_ast) in others {
match operator {
BinaryOperand::And => {
if let Some(last) = dnf.last_mut() {
last.push(operand_ast);
}
}
BinaryOperand::Or => {
dnf.push(vec![operand_ast]);
}
}
}
if dnf.len() == 1 {
UserInputAST::and(dnf.into_iter().next().unwrap()) //< safe
} else {
let conjunctions = dnf.into_iter().map(UserInputAST::and).collect();
UserInputAST::or(conjunctions)
}
}
fn operand_leaf<'a>() -> impl Parser<&'a str, Output = (BinaryOperand, UserInputAST)> {
(
binary_operand().skip(spaces()),
boosted_leaf().skip(spaces()),
)
}
pub fn ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
let boolean_expr = (boosted_leaf().skip(spaces()), many1(operand_leaf()))
.map(|(left, right)| aggregate_binary_expressions(left, right));
let whitespace_separated_leaves = many1(occur_leaf().skip(spaces().silent())).map(
|subqueries: Vec<(Option<Occur>, UserInputAST)>| {
if subqueries.len() == 1 {
let (occur_opt, ast) = subqueries.into_iter().next().unwrap();
match occur_opt.unwrap_or(Occur::Should) {
Occur::Must | Occur::Should => ast,
Occur::MustNot => UserInputAST::Clause(vec![(Some(Occur::MustNot), ast)]),
}
} else {
UserInputAST::Clause(subqueries.into_iter().collect())
}
},
);
let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
spaces().with(expr).skip(spaces())
}
pub fn parse_to_ast<'a>() -> impl Parser<&'a str, Output = UserInputAST> {
spaces()
.with(optional(ast()).skip(eof()))
.map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
}
#[cfg(test)]
mod test {
type TestParseResult = Result<(), StringStreamError>;
use super::*;
use combine::parser::Parser;
pub fn nearly_equals(a: f64, b: f64) -> bool {
(a - b).abs() < 0.0005 * (a + b).abs()
}
fn assert_nearly_equals(expected: f64, val: f64) {
assert!(
nearly_equals(val, expected),
"Got {}, expected {}.",
val,
expected
);
}
#[test]
fn test_occur_symbol() -> TestParseResult {
assert_eq!(super::occur_symbol().parse("-")?, (Occur::MustNot, ""));
assert_eq!(super::occur_symbol().parse("+")?, (Occur::Must, ""));
Ok(())
}
#[test]
fn test_positive_float_number() {
fn valid_parse(float_str: &str, expected_val: f64, expected_remaining: &str) {
let (val, remaining) = positive_float_number().parse(float_str).unwrap();
assert_eq!(remaining, expected_remaining);
assert_nearly_equals(val, expected_val);
}
fn error_parse(float_str: &str) {
assert!(positive_float_number().parse(float_str).is_err());
}
valid_parse("1.0", 1.0, "");
valid_parse("1", 1.0, "");
valid_parse("0.234234 aaa", 0.234234f64, " aaa");
error_parse(".3332");
error_parse("1.");
error_parse("-1.");
}
fn test_parse_query_to_ast_helper(query: &str, expected: &str) {
let query = parse_to_ast().parse(query).unwrap().0;
let query_str = format!("{:?}", query);
assert_eq!(query_str, expected);
}
fn test_is_parse_err(query: &str) {
assert!(parse_to_ast().parse(query).is_err());
}
#[test]
fn test_parse_empty_to_ast() {
test_parse_query_to_ast_helper("", "<emptyclause>");
}
#[test]
fn test_parse_query_to_ast_hyphen() {
test_parse_query_to_ast_helper("\"www-form-encoded\"", "\"www-form-encoded\"");
test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
test_parse_query_to_ast_helper("www-form-encoded", "\"www-form-encoded\"");
}
#[test]
fn test_parse_query_to_ast_not_op() {
assert_eq!(
format!("{:?}", parse_to_ast().parse("NOT")),
"Err(UnexpectedParse)"
);
test_parse_query_to_ast_helper("NOTa", "\"NOTa\"");
test_parse_query_to_ast_helper("NOT a", "(-\"a\")");
}
#[test]
fn test_boosting() {
assert!(parse_to_ast().parse("a^2^3").is_err());
assert!(parse_to_ast().parse("a^2^").is_err());
test_parse_query_to_ast_helper("a^3", "(\"a\")^3");
test_parse_query_to_ast_helper("a^3 b^2", "(*(\"a\")^3 *(\"b\")^2)");
test_parse_query_to_ast_helper("a^1", "\"a\"");
}
#[test]
fn test_parse_query_to_ast_binary_op() {
test_parse_query_to_ast_helper("a AND b", "(+\"a\" +\"b\")");
test_parse_query_to_ast_helper("a OR b", "(?\"a\" ?\"b\")");
test_parse_query_to_ast_helper("a OR b AND c", "(?\"a\" ?(+\"b\" +\"c\"))");
test_parse_query_to_ast_helper("a AND b AND c", "(+\"a\" +\"b\" +\"c\")");
assert_eq!(
format!("{:?}", parse_to_ast().parse("a OR b aaa")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("a AND b aaa")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("aaa a OR b ")),
"Err(UnexpectedParse)"
);
assert_eq!(
format!("{:?}", parse_to_ast().parse("aaa ccc a OR b ")),
"Err(UnexpectedParse)"
);
}
#[test]
fn test_parse_elastic_query_ranges() {
test_parse_query_to_ast_helper("title: >a", "title:{\"a\" TO \"*\"}");
test_parse_query_to_ast_helper("title:>=a", "title:[\"a\" TO \"*\"}");
test_parse_query_to_ast_helper("title: <a", "title:{\"*\" TO \"a\"}");
test_parse_query_to_ast_helper("title:<=a", "title:{\"*\" TO \"a\"]");
test_parse_query_to_ast_helper("title:<=bsd", "title:{\"*\" TO \"bsd\"]");
test_parse_query_to_ast_helper("weight: >70", "weight:{\"70\" TO \"*\"}");
test_parse_query_to_ast_helper("weight:>=70", "weight:[\"70\" TO \"*\"}");
test_parse_query_to_ast_helper("weight: <70", "weight:{\"*\" TO \"70\"}");
test_parse_query_to_ast_helper("weight:<=70", "weight:{\"*\" TO \"70\"]");
test_parse_query_to_ast_helper("weight: >60.7", "weight:{\"60.7\" TO \"*\"}");
test_parse_query_to_ast_helper("weight: <= 70", "weight:{\"*\" TO \"70\"]");
test_parse_query_to_ast_helper("weight: <= 70.5", "weight:{\"*\" TO \"70.5\"]");
}
#[test]
fn test_occur_leaf() {
let ((occur, ast), _) = super::occur_leaf().parse("+abc").unwrap();
assert_eq!(occur, Some(Occur::Must));
assert_eq!(format!("{:?}", ast), "\"abc\"");
}
#[test]
fn test_field_name() -> TestParseResult {
assert_eq!(
super::field().parse("my-field-name:a")?,
("my-field-name".to_string(), "a")
);
assert_eq!(
super::field().parse("my_field_name:a")?,
("my_field_name".to_string(), "a")
);
assert!(super::field().parse(":a").is_err());
assert!(super::field().parse("-my_field:a").is_err());
assert_eq!(
super::field().parse("_my_field:a")?,
("_my_field".to_string(), "a")
);
Ok(())
}
#[test]
fn test_range_parser() {
// testing the range() parser separately
let res = range().parse("title: <hello").unwrap().0;
let expected = UserInputLeaf::Range {
field: Some("title".to_string()),
lower: UserInputBound::Unbounded,
upper: UserInputBound::Exclusive("hello".to_string()),
};
let res2 = range().parse("title:{* TO hello}").unwrap().0;
assert_eq!(res, expected);
assert_eq!(res2, expected);
let expected_weight = UserInputLeaf::Range {
field: Some("weight".to_string()),
lower: UserInputBound::Inclusive("71.2".to_string()),
upper: UserInputBound::Unbounded,
};
let res3 = range().parse("weight: >=71.2").unwrap().0;
let res4 = range().parse("weight:[71.2 TO *}").unwrap().0;
assert_eq!(res3, expected_weight);
assert_eq!(res4, expected_weight);
}
#[test]
fn test_parse_query_to_triming_spaces() {
test_parse_query_to_ast_helper(" abc", "\"abc\"");
test_parse_query_to_ast_helper("abc ", "\"abc\"");
test_parse_query_to_ast_helper("( a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc)", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("a OR abc ", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc )", "(?\"a\" ?\"abc\")");
test_parse_query_to_ast_helper("(a OR abc) ", "(?\"a\" ?\"abc\")");
}
#[test]
fn test_parse_query_single_term() {
test_parse_query_to_ast_helper("abc", "\"abc\"");
}
#[test]
fn test_parse_query_default_clause() {
test_parse_query_to_ast_helper("a b", "(*\"a\" *\"b\")");
}
#[test]
fn test_parse_query_must_default_clause() {
test_parse_query_to_ast_helper("+(a b)", "(*\"a\" *\"b\")");
}
#[test]
fn test_parse_query_must_single_term() {
test_parse_query_to_ast_helper("+d", "\"d\"");
}
#[test]
fn test_single_term_with_field() {
test_parse_query_to_ast_helper("abc:toto", "abc:\"toto\"");
}
#[test]
fn test_single_term_with_float() {
test_parse_query_to_ast_helper("abc:1.1", "abc:\"1.1\"");
}
#[test]
fn test_must_clause() {
test_parse_query_to_ast_helper("(+a +b)", "(+\"a\" +\"b\")");
}
#[test]
fn test_parse_test_query_plus_a_b_plus_d() {
test_parse_query_to_ast_helper("+(a b) +d", "(+(*\"a\" *\"b\") +\"d\")");
}
#[test]
fn test_parse_test_query_other() {
test_parse_query_to_ast_helper("(+a +b) d", "(*(+\"a\" +\"b\") *\"d\")");
test_parse_query_to_ast_helper("+abc:toto", "abc:\"toto\"");
test_parse_query_to_ast_helper("(+abc:toto -titi)", "(+abc:\"toto\" -\"titi\")");
test_parse_query_to_ast_helper("-abc:toto", "(-abc:\"toto\")");
test_parse_query_to_ast_helper("abc:a b", "(*abc:\"a\" *\"b\")");
test_parse_query_to_ast_helper("abc:\"a b\"", "abc:\"a b\"");
test_parse_query_to_ast_helper("foo:[1 TO 5]", "foo:[\"1\" TO \"5\"]");
}
#[test]
fn test_parse_query_with_range() {
test_parse_query_to_ast_helper("[1 TO 5]", "[\"1\" TO \"5\"]");
test_parse_query_to_ast_helper("foo:{a TO z}", "foo:{\"a\" TO \"z\"}");
test_parse_query_to_ast_helper("foo:[1 TO toto}", "foo:[\"1\" TO \"toto\"}");
test_parse_query_to_ast_helper("foo:[* TO toto}", "foo:{\"*\" TO \"toto\"}");
test_parse_query_to_ast_helper("foo:[1 TO *}", "foo:[\"1\" TO \"*\"}");
test_parse_query_to_ast_helper("foo:[1.1 TO *}", "foo:[\"1.1\" TO \"*\"}");
test_is_parse_err("abc + ");
}
}

73
src/collector/count_collector.rs
View File

@@ -1,6 +1,7 @@
use super::Collector;
use crate::collector::SegmentCollector;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -9,32 +10,49 @@ use crate::SegmentReader;
/// documents match the query.
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::Count;
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index};
///
/// 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);
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer(3_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
///
/// let mut 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()?;
/// let searcher = reader.searcher();
///
/// 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")?;
/// let count = searcher.search(&query, &Count).unwrap();
///
/// // 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);
/// }
///
/// assert_eq!(count, 2);
/// Ok(())
/// }
/// ```
pub struct Count;
@@ -43,11 +61,7 @@ impl Collector for Count {
type Child = SegmentCountCollector;
fn for_segment(
&self,
_: SegmentLocalId,
_: &SegmentReader,
) -> crate::Result<SegmentCountCollector> {
fn for_segment(&self, _: SegmentLocalId, _: &SegmentReader) -> Result<SegmentCountCollector> {
Ok(SegmentCountCollector::default())
}
@@ -55,7 +69,7 @@ impl Collector for Count {
false
}
fn merge_fruits(&self, segment_counts: Vec<usize>) -> crate::Result<usize> {
fn merge_fruits(&self, segment_counts: Vec<usize>) -> Result<usize> {
Ok(segment_counts.into_iter().sum())
}
}
@@ -96,19 +110,20 @@ mod tests {
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1.0);
count_collector.collect(0u32, 1f32);
assert_eq!(count_collector.harvest(), 1);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1.0);
count_collector.collect(0u32, 1f32);
assert_eq!(count_collector.harvest(), 1);
}
{
let mut count_collector = SegmentCountCollector::default();
count_collector.collect(0u32, 1.0);
count_collector.collect(1u32, 1.0);
count_collector.collect(0u32, 1f32);
count_collector.collect(1u32, 1f32);
assert_eq!(count_collector.harvest(), 2);
}
}
}

25
src/collector/custom_score_top_collector.rs
View File

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

61
src/collector/docset_collector.rs
View File

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

130
src/collector/facet_collector.rs
View File

@@ -1,12 +1,15 @@
use crate::collector::Collector;
use crate::collector::SegmentCollector;
use crate::docset::SkipResult;
use crate::fastfield::FacetReader;
use crate::schema::Facet;
use crate::schema::Field;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
use crate::TantivyError;
use std::cmp::Ordering;
use std::collections::btree_map;
use std::collections::BTreeMap;
@@ -78,12 +81,15 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::FacetCollector;
/// use tantivy::query::AllQuery;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{doc, Index};
///
/// fn example() -> tantivy::Result<()> {
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = Schema::builder();
///
/// // Facet have their own specific type.
@@ -123,7 +129,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// let searcher = reader.searcher();
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/lang");
/// facet_collector.add_facet("/category");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
@@ -139,7 +145,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// }
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/category/fiction");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
///
@@ -154,8 +160,8 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// ]);
/// }
///
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// {
/// let mut facet_collector = FacetCollector::for_field(facet);
/// facet_collector.add_facet("/category/fiction");
/// let facet_counts = searcher.search(&AllQuery, &facet_collector)?;
///
@@ -168,7 +174,6 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
///
/// Ok(())
/// }
/// # assert!(example().is_ok());
/// ```
pub struct FacetCollector {
field: Field,
@@ -186,11 +191,6 @@ pub struct FacetSegmentCollector {
collapse_facet_ords: Vec<u64>,
}
enum SkipResult {
Found,
NotFound,
}
fn skip<'a, I: Iterator<Item = &'a Facet>>(
target: &[u8],
collapse_it: &mut Peekable<I>,
@@ -200,14 +200,14 @@ fn skip<'a, I: Iterator<Item = &'a Facet>>(
Some(facet_bytes) => match facet_bytes.encoded_str().as_bytes().cmp(target) {
Ordering::Less => {}
Ordering::Greater => {
return SkipResult::NotFound;
return SkipResult::OverStep;
}
Ordering::Equal => {
return SkipResult::Found;
return SkipResult::Reached;
}
},
None => {
return SkipResult::NotFound;
return SkipResult::End;
}
}
collapse_it.next();
@@ -264,8 +264,11 @@ impl Collector for FacetCollector {
&self,
_: SegmentLocalId,
reader: &SegmentReader,
) -> crate::Result<FacetSegmentCollector> {
let facet_reader = reader.facet_reader(self.field)?;
) -> 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();
@@ -281,7 +284,7 @@ impl Collector for FacetCollector {
// is positionned on a term that has not been processed yet.
let skip_result = skip(facet_streamer.key(), &mut collapse_facet_it);
match skip_result {
SkipResult::Found => {
SkipResult::Reached => {
// we reach a facet we decided to collapse.
let collapse_depth = facet_depth(facet_streamer.key());
let mut collapsed_id = 0;
@@ -301,7 +304,7 @@ impl Collector for FacetCollector {
}
break;
}
SkipResult::NotFound => {
SkipResult::End | SkipResult::OverStep => {
collapse_mapping.push(0);
if !facet_streamer.advance() {
break;
@@ -327,7 +330,7 @@ impl Collector for FacetCollector {
false
}
fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> crate::Result<FacetCounts> {
fn merge_fruits(&self, segments_facet_counts: Vec<FacetCounts>) -> 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 {
@@ -451,11 +454,9 @@ impl FacetCounts {
#[cfg(test)]
mod tests {
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 crate::query::AllQuery;
use crate::schema::{Document, Facet, Field, Schema};
use rand::distributions::Uniform;
use rand::prelude::SliceRandom;
use rand::{thread_rng, Rng};
@@ -468,7 +469,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let num_facets: usize = 3 * 4 * 5;
let facets: Vec<Facet> = (0..num_facets)
.map(|mut n| {
@@ -516,7 +517,7 @@ mod tests {
#[should_panic(expected = "Tried to add a facet which is a descendant of \
an already added facet.")]
fn test_misused_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::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"));
}
@@ -527,7 +528,7 @@ mod tests {
let facet_field = schema_builder.add_facet_field("facets");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
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"),
@@ -545,59 +546,9 @@ mod tests {
assert_eq!(facets[0].1, 1);
}
#[test]
fn test_doc_search_by_facet() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/B"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/A/C/A"),
));
index_writer.add_document(doc!(
facet_field => Facet::from_text(&"/D/C/A"),
));
index_writer.commit()?;
let reader = index.reader()?;
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 4);
let count_facet = |facet_str: &str| {
let term = Term::from_facet(facet_field, &Facet::from_text(facet_str));
searcher
.search(&TermQuery::new(term, IndexRecordOption::Basic), &Count)
.unwrap()
};
assert_eq!(count_facet("/"), 4);
assert_eq!(count_facet("/A"), 3);
assert_eq!(count_facet("/A/B"), 1);
assert_eq!(count_facet("/A/C"), 1);
assert_eq!(count_facet("/A/C/A"), 1);
assert_eq!(count_facet("/C/A"), 0);
let query_parser = QueryParser::for_index(&index, vec![]);
{
let query = query_parser.parse_query("facet:/A/B")?;
assert_eq!(1, searcher.search(&query, &Count).unwrap());
}
{
let query = query_parser.parse_query("facet:/A")?;
assert_eq!(3, searcher.search(&query, &Count)?);
}
Ok(())
}
#[test]
fn test_non_used_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::from_field_id(0));
let mut facet_collector = FacetCollector::for_field(Field(0));
facet_collector.add_facet(Facet::from("/country"));
facet_collector.add_facet(Facet::from("/countryeurope"));
}
@@ -627,7 +578,7 @@ mod tests {
.collect();
docs[..].shuffle(&mut thread_rng());
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for doc in docs {
index_writer.add_document(doc);
}
@@ -650,18 +601,19 @@ mod tests {
);
}
}
}
#[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 collector::FacetCollector;
use query::AllQuery;
use rand::{thread_rng, Rng};
use schema::Facet;
use schema::Schema;
use test::Bencher;
use Index;
#[bench]
fn bench_facet_collector(b: &mut Bencher) {
@@ -678,16 +630,16 @@ mod bench {
}
}
// 40425 docs
docs[..].shuffle(&mut thread_rng());
thread_rng().shuffle(&mut docs[..]);
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for doc in docs {
index_writer.add_document(doc);
}
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
b.iter(|| {
let searcher = reader.searcher();
let searcher = index.searcher();
let facet_collector = FacetCollector::for_field(facet_field);
searcher.search(&AllQuery, &facet_collector).unwrap();
});

148
src/collector/filter_collector_wrapper.rs
View File

@@ -1,148 +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 crate::collector::{Collector, SegmentCollector};
use crate::fastfield::FastFieldReader;
use crate::schema::Field;
use crate::{Score, SegmentReader, TantivyError};
/// The `FilterCollector` collector filters docs using a u64 fast field value and a predicate.
/// Only the documents for which the predicate returned "true" will be passed on to the next collector.
///
/// ```rust
/// use tantivy::collector::{TopDocs, FilterCollector};
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT, INDEXED, FAST};
/// use tantivy::{doc, DocAddress, Index};
///
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let price = schema_builder.add_u64_field("price", INDEXED | FAST);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
///
/// let mut index_writer = index.writer_with_num_threads(1, 10_000_000).unwrap();
/// index_writer.add_document(doc!(title => "The Name of the Wind", price => 30_200u64));
/// index_writer.add_document(doc!(title => "The Diary of Muadib", price => 29_240u64));
/// index_writer.add_document(doc!(title => "A Dairy Cow", price => 21_240u64));
/// index_writer.add_document(doc!(title => "The Diary of a Young Girl", price => 20_120u64));
/// assert!(index_writer.commit().is_ok());
///
/// let reader = index.reader().unwrap();
/// let searcher = reader.searcher();
///
/// let query_parser = QueryParser::for_index(&index, vec![title]);
/// let query = query_parser.parse_query("diary").unwrap();
/// let no_filter_collector = FilterCollector::new(price, &|value| true, TopDocs::with_limit(2));
/// let top_docs = searcher.search(&query, &no_filter_collector).unwrap();
///
/// assert_eq!(top_docs.len(), 2);
/// assert_eq!(top_docs[0].1, DocAddress(0, 1));
/// assert_eq!(top_docs[1].1, DocAddress(0, 3));
///
/// let filter_all_collector = FilterCollector::new(price, &|value| false, TopDocs::with_limit(2));
/// let filtered_top_docs = searcher.search(&query, &filter_all_collector).unwrap();
///
/// assert_eq!(filtered_top_docs.len(), 0);
/// ```
pub struct FilterCollector<TCollector> {
field: Field,
collector: TCollector,
predicate: &'static (dyn Fn(u64) -> bool + Send + Sync),
}
impl<TCollector> FilterCollector<TCollector>
where
TCollector: Collector + Send + Sync,
{
pub fn new(
field: Field,
predicate: &'static (dyn Fn(u64) -> bool + Send + Sync),
collector: TCollector,
) -> FilterCollector<TCollector> {
FilterCollector {
field,
predicate,
collector,
}
}
}
impl<TCollector> Collector for FilterCollector<TCollector>
where
TCollector: Collector + Send + Sync,
{
// That's the type of our result.
// Our standard deviation will be a float.
type Fruit = TCollector::Fruit;
type Child = FilterSegmentCollector<TCollector::Child>;
fn for_segment(
&self,
segment_local_id: u32,
segment_reader: &SegmentReader,
) -> crate::Result<FilterSegmentCollector<TCollector::Child>> {
let fast_field_reader = segment_reader
.fast_fields()
.u64(self.field)
.ok_or_else(|| {
let field_name = segment_reader.schema().get_field_name(self.field);
TantivyError::SchemaError(format!(
"Field {:?} is not a u64 fast field.",
field_name
))
})?;
let segment_collector = self
.collector
.for_segment(segment_local_id, segment_reader)?;
Ok(FilterSegmentCollector {
fast_field_reader,
segment_collector: segment_collector,
predicate: self.predicate,
})
}
fn requires_scoring(&self) -> bool {
self.collector.requires_scoring()
}
fn merge_fruits(
&self,
segment_fruits: Vec<<TCollector::Child as SegmentCollector>::Fruit>,
) -> crate::Result<TCollector::Fruit> {
self.collector.merge_fruits(segment_fruits)
}
}
pub struct FilterSegmentCollector<TSegmentCollector> {
fast_field_reader: FastFieldReader<u64>,
segment_collector: TSegmentCollector,
predicate: &'static (dyn Fn(u64) -> bool + Send + Sync),
}
impl<TSegmentCollector> SegmentCollector for FilterSegmentCollector<TSegmentCollector>
where
TSegmentCollector: SegmentCollector,
{
type Fruit = TSegmentCollector::Fruit;
fn collect(&mut self, doc: u32, score: Score) {
let value = self.fast_field_reader.get(doc);
if (self.predicate)(value) {
self.segment_collector.collect(doc, score)
}
}
fn harvest(self) -> <TSegmentCollector as SegmentCollector>::Fruit {
self.segment_collector.harvest()
}
}

127
src/collector/int_facet_collector.rs Normal file
View File

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

77
src/collector/mod.rs
View File

@@ -35,6 +35,7 @@ The resulting `Fruit` will then be a typed tuple with each collector's original
in their respective position.
```rust
# extern crate tantivy;
# use tantivy::schema::*;
# use tantivy::*;
# use tantivy::query::*;
@@ -85,6 +86,7 @@ See the `custom_collector` example.
*/
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -109,13 +111,6 @@ pub use self::tweak_score_top_collector::{ScoreSegmentTweaker, ScoreTweaker};
mod facet_collector;
pub use self::facet_collector::FacetCollector;
use crate::query::Weight;
mod docset_collector;
pub use self::docset_collector::DocSetCollector;
mod filter_collector_wrapper;
pub use self::filter_collector_wrapper::FilterCollector;
/// `Fruit` is the type for the result of our collection.
/// e.g. `usize` for the `Count` collector.
@@ -139,13 +134,13 @@ impl<T> Fruit for T where T: Send + downcast_rs::Downcast {}
/// The collection logic itself is in the `SegmentCollector`.
///
/// Segments are not guaranteed to be visited in any specific order.
pub trait Collector: Sync + Send {
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;
type Child: SegmentCollector<Fruit = Self::Fruit>;
/// `set_segment` is called before beginning to enumerate
/// on this segment.
@@ -153,40 +148,14 @@ pub trait Collector: Sync + Send {
&self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> crate::Result<Self::Child>;
) -> 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::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit>;
/// Created a segment collector and
fn collect_segment(
&self,
weight: &dyn Weight,
segment_ord: u32,
reader: &SegmentReader,
) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
let mut segment_collector = self.for_segment(segment_ord as u32, reader)?;
if let Some(delete_bitset) = reader.delete_bitset() {
weight.for_each(reader, &mut |doc, score| {
if delete_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
}
})?;
} else {
weight.for_each(reader, &mut |doc, score| {
segment_collector.collect(doc, score);
})?;
}
Ok(segment_collector.harvest())
}
fn merge_fruits(&self, segment_fruits: Vec<Self::Fruit>) -> Result<Self::Fruit>;
}
/// The `SegmentCollector` is the trait in charge of defining the
@@ -217,11 +186,7 @@ where
type Fruit = (Left::Fruit, Right::Fruit);
type Child = (Left::Child, Right::Child);
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> 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))
@@ -233,11 +198,11 @@ where
fn merge_fruits(
&self,
segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<(Left::Fruit, Right::Fruit)> {
children: Vec<(Left::Fruit, Right::Fruit)>,
) -> Result<(Left::Fruit, Right::Fruit)> {
let mut left_fruits = vec![];
let mut right_fruits = vec![];
for (left_fruit, right_fruit) in segment_fruits {
for (left_fruit, right_fruit) in children {
left_fruits.push(left_fruit);
right_fruits.push(right_fruit);
}
@@ -276,11 +241,7 @@ where
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit);
type Child = (One::Child, Two::Child, Three::Child);
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> 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)?;
@@ -291,10 +252,7 @@ where
self.0.requires_scoring() || self.1.requires_scoring() || self.2.requires_scoring()
}
fn merge_fruits(
&self,
children: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit> {
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];
@@ -342,11 +300,7 @@ where
type Fruit = (One::Fruit, Two::Fruit, Three::Fruit, Four::Fruit);
type Child = (One::Child, Two::Child, Three::Child, Four::Child);
fn for_segment(
&self,
segment_local_id: u32,
segment: &SegmentReader,
) -> crate::Result<Self::Child> {
fn for_segment(&self, segment_local_id: u32, segment: &SegmentReader) -> 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)?;
@@ -361,10 +315,7 @@ where
|| self.3.requires_scoring()
}
fn merge_fruits(
&self,
children: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit> {
fn merge_fruits(&self, children: Vec<Self::Fruit>) -> Result<Self::Fruit> {
let mut one_fruits = vec![];
let mut two_fruits = vec![];
let mut three_fruits = vec![];

94
src/collector/multi_collector.rs
View File

@@ -2,6 +2,7 @@ use super::Collector;
use super::SegmentCollector;
use crate::collector::Fruit;
use crate::DocId;
use crate::Result;
use crate::Score;
use crate::SegmentLocalId;
use crate::SegmentReader;
@@ -23,7 +24,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
&self,
segment_local_id: u32,
reader: &SegmentReader,
) -> crate::Result<Box<dyn BoxableSegmentCollector>> {
) -> Result<Box<dyn BoxableSegmentCollector>> {
let child = self.0.for_segment(segment_local_id, reader)?;
Ok(Box::new(SegmentCollectorWrapper(child)))
}
@@ -32,21 +33,18 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
self.0.requires_scoring()
}
fn merge_fruits(
&self,
children: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Box<dyn Fruit>> {
let typed_fruit: Vec<<TCollector::Child as SegmentCollector>::Fruit> = children
fn merge_fruits(&self, children: Vec<<Self as Collector>::Fruit>) -> Result<Box<dyn Fruit>> {
let typed_fruit: Vec<TCollector::Fruit> = children
.into_iter()
.map(|untyped_fruit| {
untyped_fruit
.downcast::<<TCollector::Child as SegmentCollector>::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<_>>()?;
.collect::<Result<_>>()?;
let merged_fruit = self.0.merge_fruits(typed_fruit)?;
Ok(Box::new(merged_fruit))
}
@@ -55,7 +53,7 @@ impl<TCollector: Collector> Collector for CollectorWrapper<TCollector> {
impl SegmentCollector for Box<dyn BoxableSegmentCollector> {
type Fruit = Box<dyn Fruit>;
fn collect(&mut self, doc: u32, score: Score) {
fn collect(&mut self, doc: u32, score: f32) {
self.as_mut().collect(doc, score);
}
@@ -65,7 +63,7 @@ impl SegmentCollector for Box<dyn BoxableSegmentCollector> {
}
pub trait BoxableSegmentCollector {
fn collect(&mut self, doc: u32, score: Score);
fn collect(&mut self, doc: u32, score: f32);
fn harvest_from_box(self: Box<Self>) -> Box<dyn Fruit>;
}
@@ -74,7 +72,7 @@ pub struct SegmentCollectorWrapper<TSegmentCollector: SegmentCollector>(TSegment
impl<TSegmentCollector: SegmentCollector> BoxableSegmentCollector
for SegmentCollectorWrapper<TSegmentCollector>
{
fn collect(&mut self, doc: u32, score: Score) {
fn collect(&mut self, doc: u32, score: f32) {
self.0.collect(doc, score);
}
@@ -107,38 +105,54 @@ impl<TFruit: Fruit> FruitHandle<TFruit> {
/// [Combining several collectors section of the collector documentation](./index.html#combining-several-collectors).
///
/// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::{Count, TopDocs, MultiCollector};
/// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index};
///
/// 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);
/// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer(3_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
///
/// let mut 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()?;
/// let searcher = reader.searcher();
///
/// 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")?;
/// let mut multi_fruit = searcher.search(&query, &collectors)?;
///
/// 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);
///
/// 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);
///
/// assert_eq!(count, 2);
/// assert_eq!(top_docs.len(), 2);
/// Ok(())
/// }
/// ```
#[allow(clippy::type_complexity)]
#[derive(Default)]
@@ -177,12 +191,12 @@ impl<'a> Collector for MultiCollector<'a> {
&self,
segment_local_id: SegmentLocalId,
segment: &SegmentReader,
) -> crate::Result<MultiCollectorChild> {
) -> Result<MultiCollectorChild> {
let children = self
.collector_wrappers
.iter()
.map(|collector_wrapper| collector_wrapper.for_segment(segment_local_id, segment))
.collect::<crate::Result<Vec<_>>>()?;
.collect::<Result<Vec<_>>>()?;
Ok(MultiCollectorChild { children })
}
@@ -193,7 +207,7 @@ impl<'a> Collector for MultiCollector<'a> {
.any(Collector::requires_scoring)
}
fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> crate::Result<MultiFruit> {
fn merge_fruits(&self, segments_multifruits: Vec<MultiFruit>) -> 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<_>>();
@@ -211,7 +225,7 @@ impl<'a> Collector for MultiCollector<'a> {
.map(|(child_collector, segment_fruits)| {
Ok(Some(child_collector.merge_fruits(segment_fruits)?))
})
.collect::<crate::Result<_>>()?;
.collect::<Result<_>>()?;
Ok(MultiFruit { sub_fruits })
}
}
@@ -259,7 +273,7 @@ mod tests {
let index = Index::create_in_ram(schema);
{
let mut index_writer = index.writer_for_tests().unwrap();
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"));

25
src/collector/tests.rs
View File

@@ -55,7 +55,7 @@ impl Collector for TestCollector {
&self,
segment_id: SegmentLocalId,
_reader: &SegmentReader,
) -> crate::Result<TestSegmentCollector> {
) -> Result<TestSegmentCollector> {
Ok(TestSegmentCollector {
segment_id,
fruit: TestFruit::default(),
@@ -66,7 +66,7 @@ impl Collector for TestCollector {
self.compute_score
}
fn merge_fruits(&self, mut children: Vec<TestFruit>) -> crate::Result<TestFruit> {
fn merge_fruits(&self, mut children: Vec<TestFruit>) -> Result<TestFruit> {
children.sort_by_key(|fruit| {
if fruit.docs().is_empty() {
0
@@ -124,7 +124,7 @@ impl Collector for FastFieldTestCollector {
&self,
_: SegmentLocalId,
segment_reader: &SegmentReader,
) -> crate::Result<FastFieldSegmentCollector> {
) -> Result<FastFieldSegmentCollector> {
let reader = segment_reader
.fast_fields()
.u64(self.field)
@@ -139,7 +139,7 @@ impl Collector for FastFieldTestCollector {
false
}
fn merge_fruits(&self, children: Vec<Vec<u64>>) -> crate::Result<Vec<u64>> {
fn merge_fruits(&self, children: Vec<Vec<u64>>) -> Result<Vec<u64>> {
Ok(children.into_iter().flat_map(|v| v.into_iter()).collect())
}
}
@@ -184,16 +184,13 @@ impl Collector for BytesFastFieldTestCollector {
&self,
_segment_local_id: u32,
segment_reader: &SegmentReader,
) -> crate::Result<BytesFastFieldSegmentCollector> {
let reader = segment_reader
.fast_fields()
.bytes(self.field)
.ok_or_else(|| {
crate::TantivyError::InvalidArgument("Field is not a bytes fast field.".to_string())
})?;
) -> Result<BytesFastFieldSegmentCollector> {
Ok(BytesFastFieldSegmentCollector {
vals: Vec::new(),
reader,
reader: segment_reader
.fast_fields()
.bytes(self.field)
.expect("Field is not a bytes fast field."),
})
}
@@ -201,7 +198,7 @@ impl Collector for BytesFastFieldTestCollector {
false
}
fn merge_fruits(&self, children: Vec<Vec<u8>>) -> crate::Result<Vec<u8>> {
fn merge_fruits(&self, children: Vec<Vec<u8>>) -> Result<Vec<u8>> {
Ok(children.into_iter().flat_map(|c| c.into_iter()).collect())
}
}
@@ -209,7 +206,7 @@ impl Collector for BytesFastFieldTestCollector {
impl SegmentCollector for BytesFastFieldSegmentCollector {
type Fruit = Vec<u8>;
fn collect(&mut self, doc: u32, _score: Score) {
fn collect(&mut self, doc: u32, _score: f32) {
let data = self.reader.get_bytes(doc);
self.vals.extend(data);
}

204
src/collector/top_collector.rs
View File

@@ -1,5 +1,6 @@
use crate::DocAddress;
use crate::DocId;
use crate::Result;
use crate::SegmentLocalId;
use crate::SegmentReader;
use serde::export::PhantomData;
@@ -11,53 +12,41 @@ use std::collections::BinaryHeap;
/// It has a custom implementation of `PartialOrd` that reverses the order. This is because the
/// default Rust heap is a max heap, whereas a min heap is needed.
///
/// Additionally, it guarantees stable sorting: in case of a tie on the feature, the document
/// address is used.
///
/// WARNING: equality is not what you would expect here.
/// Two elements are equal if their feature is equal, and regardless of whether `doc`
/// is equal. This should be perfectly fine for this usage, but let's make sure this
/// struct is never public.
pub(crate) struct ComparableDoc<T, D> {
pub feature: T,
pub doc: D,
struct ComparableDoc<T, D> {
feature: T,
doc: D,
}
impl<T: PartialOrd, D: PartialOrd> PartialOrd for ComparableDoc<T, D> {
impl<T: PartialOrd, D> PartialOrd for ComparableDoc<T, D> {
fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other))
}
}
impl<T: PartialOrd, D: PartialOrd> Ord for ComparableDoc<T, D> {
impl<T: PartialOrd, D> Ord for ComparableDoc<T, D> {
#[inline]
fn cmp(&self, other: &Self) -> Ordering {
// Reversed to make BinaryHeap work as a min-heap
let by_feature = other
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)
.unwrap_or_else(|| Ordering::Equal)
}
}
impl<T: PartialOrd, D: PartialOrd> PartialEq for ComparableDoc<T, D> {
impl<T: PartialOrd, D> PartialEq for ComparableDoc<T, D> {
fn eq(&self, other: &Self) -> bool {
self.cmp(other) == Ordering::Equal
}
}
impl<T: PartialOrd, D: PartialOrd> Eq for ComparableDoc<T, D> {}
impl<T: PartialOrd, D> Eq for ComparableDoc<T, D> {}
pub(crate) struct TopCollector<T> {
pub limit: usize,
pub offset: usize,
limit: usize,
_marker: PhantomData<T>,
}
@@ -73,33 +62,27 @@ where
if limit < 1 {
panic!("Limit must be strictly greater than 0.");
}
Self {
TopCollector {
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 limit(&self) -> usize {
self.limit
}
pub fn merge_fruits(
&self,
children: Vec<Vec<(T, DocAddress)>>,
) -> crate::Result<Vec<(T, DocAddress)>> {
) -> 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) {
if top_collector.len() < self.limit {
top_collector.push(ComparableDoc { feature, doc });
} else if let Some(mut head) = top_collector.peek_mut() {
if head.feature < feature {
@@ -111,7 +94,6 @@ where
Ok(top_collector
.into_sorted_vec()
.into_iter()
.skip(self.offset)
.map(|cdoc| (cdoc.feature, cdoc.doc))
.collect())
}
@@ -120,24 +102,8 @@ where
&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,
}
) -> Result<TopSegmentCollector<F>> {
Ok(TopSegmentCollector::new(segment_id, self.limit))
}
}
@@ -211,7 +177,7 @@ impl<T: PartialOrd + Clone> TopSegmentCollector<T> {
#[cfg(test)]
mod tests {
use super::{TopCollector, TopSegmentCollector};
use super::TopSegmentCollector;
use crate::DocAddress;
#[test]
@@ -248,136 +214,4 @@ mod tests {
]
);
}
#[test]
fn test_top_segment_collector_stable_ordering_for_equal_feature() {
// given that the documents are collected in ascending doc id order,
// when harvesting we have to guarantee stable sorting in case of a tie
// on the score
let doc_ids_collection = [4, 5, 6];
let score = 3.14;
let mut top_collector_limit_2 = TopSegmentCollector::new(0, 2);
for id in &doc_ids_collection {
top_collector_limit_2.collect(*id, score);
}
let mut top_collector_limit_3 = TopSegmentCollector::new(0, 3);
for id in &doc_ids_collection {
top_collector_limit_3.collect(*id, score);
}
assert_eq!(
top_collector_limit_2.harvest(),
top_collector_limit_3.harvest()[..2].to_vec(),
);
}
#[test]
fn test_top_collector_with_limit_and_offset() {
let collector = TopCollector::with_limit(2).and_offset(1);
let results = collector
.merge_fruits(vec![vec![
(0.9, DocAddress(0, 1)),
(0.8, DocAddress(0, 2)),
(0.7, DocAddress(0, 3)),
(0.6, DocAddress(0, 4)),
(0.5, DocAddress(0, 5)),
]])
.unwrap();
assert_eq!(
results,
vec![(0.8, DocAddress(0, 2)), (0.7, DocAddress(0, 3)),]
);
}
#[test]
fn test_top_collector_with_limit_larger_than_set_and_offset() {
let collector = TopCollector::with_limit(2).and_offset(1);
let results = collector
.merge_fruits(vec![vec![(0.9, DocAddress(0, 1)), (0.8, DocAddress(0, 2))]])
.unwrap();
assert_eq!(results, vec![(0.8, DocAddress(0, 2)),]);
}
#[test]
fn test_top_collector_with_limit_and_offset_larger_than_set() {
let collector = TopCollector::with_limit(2).and_offset(20);
let results = collector
.merge_fruits(vec![vec![(0.9, DocAddress(0, 1)), (0.8, DocAddress(0, 2))]])
.unwrap();
assert_eq!(results, vec![]);
}
}
#[cfg(all(test, feature = "unstable"))]
mod bench {
use super::TopSegmentCollector;
use test::Bencher;
#[bench]
fn bench_top_segment_collector_collect_not_at_capacity(b: &mut Bencher) {
let mut top_collector = TopSegmentCollector::new(0, 400);
b.iter(|| {
for i in 0..100 {
top_collector.collect(i, 0.8);
}
});
}
#[bench]
fn bench_top_segment_collector_collect_at_capacity(b: &mut Bencher) {
let mut top_collector = TopSegmentCollector::new(0, 100);
for i in 0..100 {
top_collector.collect(i, 0.8);
}
b.iter(|| {
for i in 0..100 {
top_collector.collect(i, 0.8);
}
});
}
#[bench]
fn bench_top_segment_collector_collect_and_harvest_many_ties(b: &mut Bencher) {
b.iter(|| {
let mut top_collector = TopSegmentCollector::new(0, 100);
for i in 0..100 {
top_collector.collect(i, 0.8);
}
// it would be nice to be able to do the setup N times but still
// measure only harvest(). We can't since harvest() consumes
// the top_collector.
top_collector.harvest()
});
}
#[bench]
fn bench_top_segment_collector_collect_and_harvest_no_tie(b: &mut Bencher) {
b.iter(|| {
let mut top_collector = TopSegmentCollector::new(0, 100);
let mut score = 1.0;
for i in 0..100 {
score += 1.0;
top_collector.collect(i, score);
}
// it would be nice to be able to do the setup N times but still
// measure only harvest(). We can't since harvest() consumes
// the top_collector.
top_collector.harvest()
});
}
}

767
src/collector/top_score_collector.rs
View File

File diff suppressed because it is too large Load Diff

12
src/collector/tweak_score_top_collector.rs
View File

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

24
src/common/bitpacker.rs
View File

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

29
src/common/bitset.rs
View File

@@ -33,10 +33,6 @@ impl TinySet {
TinySet(0u64)
}
pub fn clear(&mut self) {
self.0 = 0u64;
}
/// Returns the complement of the set in `[0, 64[`.
fn complement(self) -> TinySet {
TinySet(!self.0)
@@ -47,11 +43,6 @@ impl TinySet {
!self.intersect(TinySet::singleton(el)).is_empty()
}
/// Returns the number of elements in the TinySet.
pub fn len(self) -> u32 {
self.0.count_ones()
}
/// Returns the intersection of `self` and `other`
pub fn intersect(self, other: TinySet) -> TinySet {
TinySet(self.0 & other.0)
@@ -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,
}
@@ -203,7 +204,7 @@ mod tests {
use super::BitSet;
use super::TinySet;
use crate::docset::{DocSet, TERMINATED};
use crate::docset::DocSet;
use crate::query::BitSetDocSet;
use crate::tests;
use crate::tests::generate_nonunique_unsorted;
@@ -277,13 +278,11 @@ mod tests {
}
assert_eq!(btreeset.len(), bitset.len());
let mut bitset_docset = BitSetDocSet::from(bitset);
let mut remaining = true;
for el in btreeset.into_iter() {
assert!(remaining);
bitset_docset.advance();
assert_eq!(bitset_docset.doc(), el);
remaining = bitset_docset.advance() != TERMINATED;
}
assert!(!remaining);
assert!(!bitset_docset.advance());
}
#[test]

80
src/common/composite_file.rs
View File

@@ -1,15 +1,14 @@
use crate::common::BinarySerializable;
use crate::common::CountingWriter;
use crate::common::VInt;
use crate::directory::FileSlice;
use crate::directory::{TerminatingWrite, WritePtr};
use crate::directory::ReadOnlySource;
use crate::directory::WritePtr;
use crate::schema::Field;
use crate::space_usage::FieldUsage;
use crate::space_usage::PerFieldSpaceUsage;
use std::collections::HashMap;
use std::io::{self, Read, Write};
use super::HasLen;
use std::io::Write;
use std::io::{self, Read};
#[derive(Eq, PartialEq, Hash, Copy, Ord, PartialOrd, Clone, Debug)]
pub struct FileAddr {
@@ -43,7 +42,7 @@ pub struct CompositeWrite<W = WritePtr> {
offsets: HashMap<FileAddr, u64>,
}
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> {
@@ -92,7 +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(())
}
}
@@ -104,26 +104,25 @@ impl<W: TerminatingWrite + Write> CompositeWrite<W> {
/// for each field.
#[derive(Clone)]
pub struct CompositeFile {
data: FileSlice,
data: ReadOnlySource,
offsets_index: HashMap<FileAddr, (usize, usize)>,
}
impl CompositeFile {
/// Opens a composite file stored in a given
/// `FileSlice`.
pub fn open(data: &FileSlice) -> io::Result<CompositeFile> {
/// `ReadOnlySource`.
pub fn open(data: &ReadOnlySource) -> io::Result<CompositeFile> {
let end = data.len();
let footer_len_data = data.slice_from(end - 4).read_bytes()?;
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)
.read_bytes()?;
let footer_data = data.slice(footer_start, footer_start + footer_len);
let mut footer_buffer = footer_data.as_slice();
let num_fields = VInt::deserialize(&mut footer_buffer)?.0 as usize;
let mut file_addrs = vec![];
let mut offsets = vec![];
let mut field_index = HashMap::new();
let mut offset = 0;
@@ -152,19 +151,19 @@ impl CompositeFile {
pub fn empty() -> CompositeFile {
CompositeFile {
offsets_index: HashMap::new(),
data: FileSlice::empty(),
data: ReadOnlySource::empty(),
}
}
/// Returns the `FileSlice` associated
/// Returns the `ReadOnlySource` associated
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read(&self, field: Field) -> Option<FileSlice> {
pub fn open_read(&self, field: Field) -> Option<ReadOnlySource> {
self.open_read_with_idx(field, 0)
}
/// Returns the `FileSlice` associated
/// Returns the `ReadOnlySource` associated
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<FileSlice> {
pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<ReadOnlySource> {
self.offsets_index
.get(&FileAddr { field, idx })
.map(|&(from, to)| self.data.slice(from, to))
@@ -194,44 +193,43 @@ mod test {
use std::path::Path;
#[test]
fn test_composite_file() -> crate::Result<()> {
fn test_composite_file() {
let path = Path::new("test_path");
let directory = RAMDirectory::create();
let mut directory = RAMDirectory::create();
{
let w = directory.open_write(path).unwrap();
let mut composite_write = CompositeWrite::wrap(w);
let mut write_0 = composite_write.for_field(Field::from_field_id(0u32));
VInt(32431123u64).serialize(&mut write_0)?;
write_0.flush()?;
let mut write_4 = composite_write.for_field(Field::from_field_id(4u32));
VInt(2).serialize(&mut write_4)?;
write_4.flush()?;
composite_write.close()?;
{
let 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(4u32));
VInt(2).serialize(&mut write_4).unwrap();
write_4.flush().unwrap();
}
composite_write.close().unwrap();
}
{
let r = directory.open_read(path)?;
let composite_file = CompositeFile::open(&r)?;
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()
.read_bytes()?;
let file0 = composite_file.open_read(Field(0u32)).unwrap();
let mut file0_buf = file0.as_slice();
let payload_0 = VInt::deserialize(&mut file0_buf)?.0;
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()
.read_bytes()?;
let file4 = composite_file.open_read(Field(4u32)).unwrap();
let mut file4_buf = file4.as_slice();
let payload_4 = VInt::deserialize(&mut file4_buf)?.0;
let payload_4 = VInt::deserialize(&mut file4_buf).unwrap().0;
assert_eq!(file4_buf.len(), 0);
assert_eq!(payload_4, 2u64);
}
}
Ok(())
}
}

9
src/common/counting_writer.rs
View File

@@ -1,5 +1,3 @@
use crate::directory::AntiCallToken;
use crate::directory::TerminatingWrite;
use std::io;
use std::io::Write;
@@ -44,13 +42,6 @@ impl<W: Write> Write for CountingWriter<W> {
}
}
impl<W: TerminatingWrite> TerminatingWrite for CountingWriter<W> {
fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
self.flush()?;
self.underlying.terminate_ref(token)
}
}
#[cfg(test)]
mod test {

58
src/common/mod.rs
View File

@@ -10,9 +10,7 @@ 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, read_u32_vint_no_advance, serialize_vint_u32, write_u32_vint, VInt,
};
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`.
@@ -20,19 +18,6 @@ pub use byteorder::LittleEndian as Endianness;
/// We do not allow segments with more than
pub const MAX_DOC_LIMIT: u32 = 1 << 31;
pub fn minmax<I, T>(mut vals: I) -> Option<(T, T)>
where
I: Iterator<Item = T>,
T: Copy + Ord,
{
if let Some(first_el) = vals.next() {
return Some(vals.fold((first_el, first_el), |(min_val, max_val), el| {
(min_val.min(el), max_val.max(el))
}));
}
None
}
/// Computes the number of bits that will be used for bitpacking.
///
/// In general the target is the minimum number of bits
@@ -66,6 +51,10 @@ pub(crate) fn compute_num_bits(n: u64) -> u8 {
}
}
pub(crate) fn is_power_of_2(n: usize) -> bool {
(n > 0) && (n & (n - 1) == 0)
}
/// Has length trait
pub trait HasLen {
/// Return length
@@ -135,25 +124,26 @@ pub fn f64_to_u64(val: f64) -> u64 {
/// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html).
#[inline(always)]
pub fn u64_to_f64(val: u64) -> f64 {
f64::from_bits(if val & HIGHEST_BIT != 0 {
val ^ HIGHEST_BIT
} else {
!val
})
f64::from_bits(
if val & HIGHEST_BIT != 0 {
val ^ HIGHEST_BIT
} else {
!val
}
)
}
#[cfg(test)]
pub(crate) mod test {
pub use super::minmax;
pub use super::serialize::test::fixed_size_test;
use super::{compute_num_bits, f64_to_u64, i64_to_u64, u64_to_f64, u64_to_i64};
use super::{compute_num_bits, i64_to_u64, u64_to_i64, f64_to_u64, u64_to_f64};
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);
}
@@ -182,8 +172,7 @@ pub(crate) mod test {
#[test]
fn test_f64_order() {
assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY))
.contains(&f64_to_u64(f64::NAN))); //nan is not a number
assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY)).contains(&f64_to_u64(f64::NAN))); //nan is not a number
assert!(f64_to_u64(1.5) > f64_to_u64(1.0)); //same exponent, different mantissa
assert!(f64_to_u64(2.0) > f64_to_u64(1.0)); //same mantissa, different exponent
assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa
@@ -211,21 +200,4 @@ pub(crate) mod test {
assert!(((super::MAX_DOC_LIMIT - 1) as i32) >= 0);
assert!((super::MAX_DOC_LIMIT as i32) < 0);
}
#[test]
fn test_minmax_empty() {
let vals: Vec<u32> = vec![];
assert_eq!(minmax(vals.into_iter()), None);
}
#[test]
fn test_minmax_one() {
assert_eq!(minmax(vec![1].into_iter()), Some((1, 1)));
}
#[test]
fn test_minmax_two() {
assert_eq!(minmax(vec![1, 2].into_iter()), Some((1, 2)));
assert_eq!(minmax(vec![2, 1].into_iter()), Some((1, 2)));
}
}

18
src/common/serialize.rs
View File

@@ -89,19 +89,6 @@ impl FixedSize for u64 {
const SIZE_IN_BYTES: usize = 8;
}
impl BinarySerializable for f32 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_f32::<Endianness>(*self)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
reader.read_f32::<Endianness>()
}
}
impl FixedSize for f32 {
const SIZE_IN_BYTES: usize = 4;
}
impl BinarySerializable for i64 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_i64::<Endianness>(*self)
@@ -212,7 +199,10 @@ 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]

38
src/common/vint.rs
View File

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

39
src/core/executor.rs
View File

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

230
src/core/index.rs
View File

@@ -1,3 +1,4 @@
use super::segment::create_segment;
use super::segment::Segment;
use crate::core::Executor;
use crate::core::IndexMeta;
@@ -5,7 +6,6 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SegmentMetaInventory;
use crate::core::META_FILEPATH;
use crate::directory::error::OpenReadError;
use crate::directory::ManagedDirectory;
#[cfg(feature = "mmap")]
use crate::directory::MmapDirectory;
@@ -20,20 +20,18 @@ use crate::reader::IndexReaderBuilder;
use crate::schema::Field;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::tokenizer::{TextAnalyzer, TokenizerManager};
use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::TokenizerManager;
use crate::IndexWriter;
use std::collections::HashSet;
use crate::Result;
use num_cpus;
use std::borrow::BorrowMut;
use std::fmt;
#[cfg(feature = "mmap")]
use std::path::Path;
use std::path::PathBuf;
use std::sync::Arc;
fn load_metas(
directory: &dyn Directory,
inventory: &SegmentMetaInventory,
) -> crate::Result<IndexMeta> {
fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> {
let meta_data = directory.atomic_read(&META_FILEPATH)?;
let meta_string = String::from_utf8_lossy(&meta_data);
IndexMeta::deserialize(&meta_string, &inventory)
@@ -57,10 +55,8 @@ pub struct Index {
}
impl Index {
/// Examines the directory to see if it contains an index.
///
/// Effectively, it only checks for the presence of the `meta.json` file.
pub fn exists<Dir: Directory>(dir: &Dir) -> Result<bool, OpenReadError> {
/// Examines the director to see if it contains an index
pub fn exists<Dir: Directory>(dir: &Dir) -> bool {
dir.exists(&META_FILEPATH)
}
@@ -76,16 +72,15 @@ impl Index {
/// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads.
pub fn set_multithread_executor(&mut self, num_threads: usize) -> crate::Result<()> {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")?);
Ok(())
pub fn set_multithread_executor(&mut self, num_threads: usize) {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-"));
}
/// 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<()> {
pub fn set_default_multithread_executor(&mut self) {
let default_num_threads = num_cpus::get();
self.set_multithread_executor(default_num_threads)
self.set_multithread_executor(default_num_threads);
}
/// Creates a new index using the `RAMDirectory`.
@@ -102,29 +97,28 @@ impl Index {
///
/// If a previous index was in this directory, then its meta file will be destroyed.
#[cfg(feature = "mmap")]
pub fn create_in_dir<P: AsRef<Path>>(
directory_path: P,
schema: Schema,
) -> crate::Result<Index> {
pub fn create_in_dir<P: AsRef<Path>>(directory_path: P, schema: Schema) -> Result<Index> {
let mmap_directory = MmapDirectory::open(directory_path)?;
if Index::exists(&mmap_directory)? {
if Index::exists(&mmap_directory) {
return Err(TantivyError::IndexAlreadyExists);
}
Index::create(mmap_directory, schema)
}
/// Opens or creates a new index in the provided directory
pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
if !Index::exists(&dir)? {
return Index::create(dir, schema);
}
let index = Index::open(dir)?;
if index.schema() == schema {
Ok(index)
pub fn open_or_create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
if Index::exists(&dir) {
let index = Index::open(dir)?;
if index.schema() == schema {
Ok(index)
} else {
Err(TantivyError::SchemaError(
"An index exists but the schema does not match.".to_string(),
))
}
} else {
Err(TantivyError::SchemaError(
"An index exists but the schema does not match.".to_string(),
))
Index::create(dir, schema)
}
}
@@ -137,15 +131,13 @@ impl Index {
/// The temp directory is only used for testing the `MmapDirectory`.
/// For other unit tests, prefer the `RAMDirectory`, see: `create_in_ram`.
#[cfg(feature = "mmap")]
pub fn create_from_tempdir(schema: Schema) -> crate::Result<Index> {
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`.
///
/// If a directory previously existed, it will be erased.
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> crate::Result<Index> {
/// Creates a new index given an implementation of the trait `Directory`
pub fn create<Dir: Directory>(dir: Dir, schema: Schema) -> Result<Index> {
let directory = ManagedDirectory::wrap(dir)?;
Index::from_directory(directory, schema)
}
@@ -153,8 +145,8 @@ impl Index {
/// Create a new index from a directory.
///
/// This will overwrite existing meta.json
fn from_directory(directory: ManagedDirectory, schema: Schema) -> crate::Result<Index> {
save_new_metas(schema.clone(), &directory)?;
fn from_directory(mut directory: ManagedDirectory, schema: Schema) -> Result<Index> {
save_new_metas(schema.clone(), directory.borrow_mut())?;
let metas = IndexMeta::with_schema(schema);
Index::create_from_metas(directory, &metas, SegmentMetaInventory::default())
}
@@ -164,7 +156,7 @@ impl Index {
directory: ManagedDirectory,
metas: &IndexMeta,
inventory: SegmentMetaInventory,
) -> crate::Result<Index> {
) -> Result<Index> {
let schema = metas.schema.clone();
Ok(Index {
directory,
@@ -181,11 +173,11 @@ impl Index {
}
/// Helper to access the tokenizer associated to a specific field.
pub fn tokenizer_for_field(&self, field: Field) -> crate::Result<TextAnalyzer> {
pub fn tokenizer_for_field(&self, field: Field) -> Result<Box<dyn BoxedTokenizer>> {
let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type();
let tokenizer_manager: &TokenizerManager = self.tokenizers();
let tokenizer_name_opt: Option<TextAnalyzer> = match field_type {
let tokenizer_name_opt: Option<Box<dyn BoxedTokenizer>> = match field_type {
FieldType::Str(text_options) => text_options
.get_indexing_options()
.map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -204,7 +196,7 @@ impl Index {
/// Create a default `IndexReader` for the given index.
///
/// See [`Index.reader_builder()`](#method.reader_builder).
pub fn reader(&self) -> crate::Result<IndexReader> {
pub fn reader(&self) -> Result<IndexReader> {
self.reader_builder().try_into()
}
@@ -219,31 +211,17 @@ impl Index {
/// 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> {
pub fn open_in_dir<P: AsRef<Path>>(directory_path: P) -> Result<Index> {
let mmap_directory = MmapDirectory::open(directory_path)?;
Index::open(mmap_directory)
}
/// Returns the list of the segment metas tracked by the index.
///
/// Such segments can of course be part of the index,
/// but also they could be segments being currently built or in the middle of a merge
/// operation.
pub fn list_all_segment_metas(&self) -> Vec<SegmentMeta> {
self.inventory.all()
}
/// Creates a new segment_meta (Advanced user only).
///
/// As long as the `SegmentMeta` lives, the files associated with the
/// `SegmentMeta` are guaranteed to not be garbage collected, regardless of
/// whether the segment is recorded as part of the index or not.
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
self.inventory.new_segment_meta(segment_id, max_doc)
pub(crate) fn inventory(&self) -> &SegmentMetaInventory {
&self.inventory
}
/// Open the index using the provided directory
pub fn open<D: Directory>(directory: D) -> crate::Result<Index> {
pub fn open<D: Directory>(directory: D) -> Result<Index> {
let directory = ManagedDirectory::wrap(directory)?;
let inventory = SegmentMetaInventory::default();
let metas = load_metas(&directory, &inventory)?;
@@ -251,7 +229,7 @@ impl Index {
}
/// Reads the index meta file from the directory.
pub fn load_metas(&self) -> crate::Result<IndexMeta> {
pub fn load_metas(&self) -> Result<IndexMeta> {
load_metas(self.directory(), &self.inventory)
}
@@ -279,7 +257,7 @@ impl Index {
&self,
num_threads: usize,
overall_heap_size_in_bytes: usize,
) -> crate::Result<IndexWriter> {
) -> Result<IndexWriter> {
let directory_lock = self
.directory
.acquire_lock(&INDEX_WRITER_LOCK)
@@ -287,7 +265,7 @@ impl Index {
TantivyError::LockFailure(
err,
Some(
"Failed to acquire index lock. If you are using \
"Failed to acquire index lock. If you are using\
a regular directory, this means there is already an \
`IndexWriter` working on this `Directory`, in this process \
or in a different process."
@@ -304,15 +282,6 @@ impl Index {
)
}
/// Helper to create an index writer for tests.
///
/// That index writer only simply has a single thread and a heap of 5 MB.
/// Using a single thread gives us a deterministic allocation of DocId.
#[cfg(test)]
pub fn writer_for_tests(&self) -> crate::Result<IndexWriter> {
self.writer_with_num_threads(1, 10_000_000)
}
/// Creates a multithreaded writer
///
/// Tantivy will automatically define the number of threads to use.
@@ -323,7 +292,7 @@ impl Index {
/// If the lockfile already exists, returns `Error::FileAlreadyExists`.
/// # Panics
/// If the heap size per thread is too small, panics.
pub fn writer(&self, overall_heap_size_in_bytes: usize) -> crate::Result<IndexWriter> {
pub fn writer(&self, overall_heap_size_in_bytes: usize) -> 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 {
@@ -340,7 +309,7 @@ impl Index {
}
/// Returns the list of segments that are searchable
pub fn searchable_segments(&self) -> crate::Result<Vec<Segment>> {
pub fn searchable_segments(&self) -> Result<Vec<Segment>> {
Ok(self
.searchable_segment_metas()?
.into_iter()
@@ -350,7 +319,7 @@ 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.
@@ -373,23 +342,18 @@ 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>> {
pub fn searchable_segment_ids(&self) -> Result<Vec<SegmentId>> {
Ok(self
.searchable_segment_metas()?
.iter()
.map(SegmentMeta::id)
.collect())
}
/// Returns the set of corrupted files
pub fn validate_checksum(&self) -> crate::Result<HashSet<PathBuf>> {
self.directory.list_damaged().map_err(Into::into)
}
}
impl fmt::Debug for Index {
@@ -400,12 +364,15 @@ impl fmt::Debug for Index {
#[cfg(test)]
mod tests {
use crate::directory::{RAMDirectory, WatchCallback};
use crate::directory::RAMDirectory;
use crate::schema::Field;
use crate::schema::{Schema, INDEXED, TEXT};
use crate::Index;
use crate::IndexReader;
use crate::IndexWriter;
use crate::ReloadPolicy;
use crate::{Directory, Index};
use std::thread;
use std::time::Duration;
#[test]
fn test_indexer_for_field() {
@@ -424,24 +391,24 @@ mod tests {
#[test]
fn test_index_exists() {
let directory = RAMDirectory::create();
assert!(!Index::exists(&directory).unwrap());
assert!(!Index::exists(&directory));
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory).unwrap());
assert!(Index::exists(&directory));
}
#[test]
fn open_or_create_should_create() {
let directory = RAMDirectory::create();
assert!(!Index::exists(&directory).unwrap());
assert!(!Index::exists(&directory));
assert!(Index::open_or_create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory).unwrap());
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).unwrap());
assert!(Index::exists(&directory));
assert!(Index::open_or_create(directory, throw_away_schema()).is_ok());
}
@@ -449,7 +416,7 @@ mod tests {
fn create_should_wipeoff_existing() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory).unwrap());
assert!(Index::exists(&directory));
assert!(Index::create(directory.clone(), Schema::builder().build()).is_ok());
}
@@ -457,7 +424,7 @@ mod tests {
fn open_or_create_exists_but_schema_does_not_match() {
let directory = RAMDirectory::create();
assert!(Index::create(directory.clone(), throw_away_schema()).is_ok());
assert!(Index::exists(&directory).unwrap());
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!(
@@ -483,39 +450,41 @@ mod tests {
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
}
#[cfg(feature = "mmap")]
mod mmap_specific {
use super::*;
use crate::Directory;
use std::path::PathBuf;
use tempfile::TempDir;
use tempdir::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 = TempDir::new("index").unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &index, &reader);
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
}
#[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_for_tests().unwrap();
let index = Index::create_from_tempdir(schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
writer.commit().unwrap();
let reader = index
.reader_builder()
@@ -524,12 +493,8 @@ mod tests {
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = index.directory_mut().watch(WatchCallback::new(move || {
let _ = sender.send(());
}));
writer.commit().unwrap();
assert!(receiver.recv().is_ok());
thread::sleep(Duration::from_millis(500));
assert_eq!(reader.searcher().num_docs(), 0);
reader.reload().unwrap();
assert_eq!(reader.searcher().num_docs(), 1);
@@ -539,7 +504,7 @@ mod tests {
fn test_index_on_commit_reload_policy_different_directories() {
let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap();
let tempdir = TempDir::new().unwrap();
let tempdir = TempDir::new("index").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();
@@ -549,38 +514,39 @@ mod tests {
.try_into()
.unwrap();
assert_eq!(reader.searcher().num_docs(), 0);
test_index_on_commit_reload_policy_aux(field, &write_index, &reader);
let mut writer = write_index.writer_with_num_threads(1, 3_000_000).unwrap();
test_index_on_commit_reload_policy_aux(field, &mut writer, &reader);
}
}
fn test_index_on_commit_reload_policy_aux(field: Field, index: &Index, reader: &IndexReader) {
let mut reader_index = reader.index();
let (sender, receiver) = crossbeam::channel::unbounded();
let _watch_handle = reader_index
.directory_mut()
.watch(WatchCallback::new(move || {
let _ = sender.send(());
}));
let mut writer = index.writer_for_tests().unwrap();
fn test_index_on_commit_reload_policy_aux(
field: Field,
writer: &mut IndexWriter,
reader: &IndexReader,
) {
assert_eq!(reader.searcher().num_docs(), 0);
writer.add_document(doc!(field=>1u64));
writer.commit().unwrap();
// We need a loop here because it is possible for notify to send more than
// one modify event. It was observed on CI on MacOS.
loop {
assert!(receiver.recv().is_ok());
if reader.searcher().num_docs() == 1 {
let mut count = 0;
for _ in 0..100 {
count = reader.searcher().num_docs();
if count > 0 {
break;
}
thread::sleep(Duration::from_millis(100));
}
assert_eq!(count, 1);
writer.add_document(doc!(field=>2u64));
writer.commit().unwrap();
// ... Same as above
loop {
assert!(receiver.recv().is_ok());
if reader.searcher().num_docs() == 2 {
let mut count = 0;
for _ in 0..10 {
count = reader.searcher().num_docs();
if count > 1 {
break;
}
thread::sleep(Duration::from_millis(100));
}
assert_eq!(count, 2);
}
// This test will not pass on windows, because windows
@@ -597,13 +563,9 @@ mod tests {
for i in 0u64..8_000u64 {
writer.add_document(doc!(field => i));
}
let (sender, receiver) = crossbeam::channel::unbounded();
let _handle = directory.watch(WatchCallback::new(move || {
let _ = sender.send(());
}));
writer.commit().unwrap();
let mem_right_after_commit = directory.total_mem_usage();
assert!(receiver.recv().is_ok());
thread::sleep(Duration::from_millis(1_000));
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
@@ -617,11 +579,7 @@ mod tests {
reader.reload().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 8_000);
assert!(
mem_right_after_merge_finished < mem_right_after_commit,
"(mem after merge){} is expected < (mem before merge){}",
mem_right_after_merge_finished,
mem_right_after_commit
);
assert!(mem_right_after_merge_finished < mem_right_after_commit);
}
}

26
src/core/index_meta.rs
View File

@@ -3,7 +3,8 @@ use crate::core::SegmentId;
use crate::schema::Schema;
use crate::Opstamp;
use census::{Inventory, TrackedObject};
use serde::{Deserialize, Serialize};
use serde;
use serde_json;
use std::collections::HashSet;
use std::fmt;
use std::path::PathBuf;
@@ -29,6 +30,7 @@ impl SegmentMetaInventory {
.collect::<Vec<_>>()
}
#[doc(hidden)]
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
let inner = InnerSegmentMeta {
segment_id,
@@ -149,21 +151,6 @@ impl SegmentMeta {
self.num_deleted_docs() > 0
}
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> SegmentMeta {
assert_eq!(self.tracked.max_doc, 0);
assert!(self.tracked.deletes.is_none());
let tracked = self.tracked.map(move |inner_meta| InnerSegmentMeta {
segment_id: inner_meta.segment_id,
max_doc,
deletes: None,
});
SegmentMeta { tracked }
}
#[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta {
let delete_meta = DeleteMeta {
@@ -213,7 +200,7 @@ pub struct IndexMeta {
#[serde(skip_serializing_if = "Option::is_none")]
/// Payload associated to the last commit.
///
/// Upon commit, clients can optionally add a small `String` payload to their 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>,
@@ -299,9 +286,6 @@ mod tests {
payload: None,
};
let json = serde_json::ser::to_string(&index_metas).expect("serialization failed");
assert_eq!(
json,
r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#
);
assert_eq!(json, r#"{"segments":[],"schema":[{"name":"text","type":"text","options":{"indexing":{"record":"position","tokenizer":"default"},"stored":false}}],"opstamp":0}"#);
}
}

112
src/core/inverted_index_reader.rs
View File

@@ -1,13 +1,13 @@
use std::io;
use crate::common::BinarySerializable;
use crate::directory::FileSlice;
use crate::directory::ReadOnlySource;
use crate::positions::PositionReader;
use crate::postings::TermInfo;
use crate::postings::{BlockSegmentPostings, SegmentPostings};
use crate::schema::FieldType;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::termdict::TermDictionary;
use owned_read::OwnedRead;
/// The inverted index reader is in charge of accessing
/// the inverted index associated to a specific field.
@@ -16,7 +16,7 @@ use crate::termdict::TermDictionary;
///
/// It is safe to delete the segment associated to
/// an `InvertedIndexReader`. As long as it is open,
/// the `FileSlice` it is relying on should
/// the `ReadOnlySource` it is relying on should
/// stay available.
///
///
@@ -24,9 +24,9 @@ use crate::termdict::TermDictionary;
/// the `SegmentReader`'s [`.inverted_index(...)`] method
pub struct InvertedIndexReader {
termdict: TermDictionary,
postings_file_slice: FileSlice,
positions_file_slice: FileSlice,
positions_idx_file_slice: FileSlice,
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
record_option: IndexRecordOption,
total_num_tokens: u64,
}
@@ -35,31 +35,35 @@ impl InvertedIndexReader {
#[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))] // for symmetry
pub(crate) fn new(
termdict: TermDictionary,
postings_file_slice: FileSlice,
positions_file_slice: FileSlice,
positions_idx_file_slice: FileSlice,
postings_source: ReadOnlySource,
positions_source: ReadOnlySource,
positions_idx_source: ReadOnlySource,
record_option: IndexRecordOption,
) -> io::Result<InvertedIndexReader> {
let (total_num_tokens_slice, postings_body) = postings_file_slice.split(8);
let total_num_tokens = u64::deserialize(&mut total_num_tokens_slice.read_bytes()?)?;
Ok(InvertedIndexReader {
) -> InvertedIndexReader {
let total_num_tokens_data = postings_source.slice(0, 8);
let mut total_num_tokens_cursor = total_num_tokens_data.as_slice();
let total_num_tokens = u64::deserialize(&mut total_num_tokens_cursor).unwrap_or(0u64);
InvertedIndexReader {
termdict,
postings_file_slice: postings_body,
positions_file_slice,
positions_idx_file_slice,
postings_source: postings_source.slice_from(8),
positions_source,
positions_idx_source,
record_option,
total_num_tokens,
})
}
}
/// Creates an empty `InvertedIndexReader` object, which
/// contains no terms at all.
pub fn empty(record_option: IndexRecordOption) -> 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(),
postings_file_slice: FileSlice::empty(),
positions_file_slice: FileSlice::empty(),
positions_idx_file_slice: FileSlice::empty(),
termdict: TermDictionary::empty(&field_type),
postings_source: ReadOnlySource::empty(),
positions_source: ReadOnlySource::empty(),
positions_idx_source: ReadOnlySource::empty(),
record_option,
total_num_tokens: 0u64,
}
@@ -89,12 +93,12 @@ impl InvertedIndexReader {
&self,
term_info: &TermInfo,
block_postings: &mut BlockSegmentPostings,
) -> io::Result<()> {
let start_offset = term_info.postings_start_offset as usize;
let stop_offset = term_info.postings_stop_offset as usize;
let postings_slice = self.postings_file_slice.slice(start_offset, stop_offset);
block_postings.reset(term_info.doc_freq, postings_slice.read_bytes()?);
Ok(())
) {
let offset = term_info.postings_offset as usize;
let end_source = self.postings_source.len();
let postings_slice = self.postings_source.slice(offset, end_source);
let postings_reader = OwnedRead::new(postings_slice);
block_postings.reset(term_info.doc_freq, postings_reader);
}
/// Returns a block postings given a `Term`.
@@ -105,11 +109,9 @@ impl InvertedIndexReader {
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<BlockSegmentPostings>> {
Ok(self
.get_term_info(term)
) -> Option<BlockSegmentPostings> {
self.get_term_info(term)
.map(move |term_info| self.read_block_postings_from_terminfo(&term_info, option))
.transpose()?)
}
/// Returns a block postings given a `term_info`.
@@ -120,14 +122,12 @@ impl InvertedIndexReader {
&self,
term_info: &TermInfo,
requested_option: IndexRecordOption,
) -> io::Result<BlockSegmentPostings> {
let postings_data = self.postings_file_slice.slice(
term_info.postings_start_offset as usize,
term_info.postings_stop_offset as usize,
);
BlockSegmentPostings::open(
) -> BlockSegmentPostings {
let offset = term_info.postings_offset as usize;
let postings_data = self.postings_source.slice_from(offset);
BlockSegmentPostings::from_data(
term_info.doc_freq,
postings_data,
OwnedRead::new(postings_data),
self.record_option,
requested_option,
)
@@ -141,23 +141,20 @@ impl InvertedIndexReader {
&self,
term_info: &TermInfo,
option: IndexRecordOption,
) -> io::Result<SegmentPostings> {
let block_postings = self.read_block_postings_from_terminfo(term_info, option)?;
) -> SegmentPostings {
let block_postings = self.read_block_postings_from_terminfo(term_info, option);
let position_stream = {
if option.has_positions() {
let position_reader = self.positions_file_slice.clone();
let skip_reader = self.positions_idx_file_slice.clone();
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)?;
PositionReader::new(position_reader, skip_reader, term_info.positions_idx);
Some(position_reader)
} else {
None
}
};
Ok(SegmentPostings::from_block_postings(
block_postings,
position_stream,
))
SegmentPostings::from_block_postings(block_postings, position_stream)
}
/// Returns the total number of tokens recorded for all documents
@@ -176,31 +173,24 @@ impl InvertedIndexReader {
/// For instance, requesting `IndexRecordOption::Freq` for a
/// `TextIndexingOptions` that does not index position will return a `SegmentPostings`
/// with `DocId`s and frequencies.
pub fn read_postings(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
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))
.transpose()
}
pub(crate) fn read_postings_no_deletes(
&self,
term: &Term,
option: IndexRecordOption,
) -> io::Result<Option<SegmentPostings>> {
) -> Option<SegmentPostings> {
self.get_term_info(term)
.map(|term_info| self.read_postings_from_terminfo(&term_info, option))
.transpose()
}
/// Returns the number of documents containing the term.
pub fn doc_freq(&self, term: &Term) -> io::Result<u32> {
Ok(self
.get_term_info(term)
pub fn doc_freq(&self, term: &Term) -> u32 {
self.get_term_info(term)
.map(|term_info| term_info.doc_freq)
.unwrap_or(0u32))
.unwrap_or(0u32)
}
}

2
src/core/mod.rs
View File

@@ -12,7 +12,7 @@ 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::{FieldSearcher, Searcher};
pub use self::searcher::Searcher;
pub use self::segment::Segment;
pub use self::segment::SerializableSegment;
pub use self::segment_component::SegmentComponent;

91
src/core/searcher.rs
View File

@@ -1,8 +1,11 @@
use crate::collector::Collector;
use crate::collector::SegmentCollector;
use crate::core::Executor;
use crate::core::InvertedIndexReader;
use crate::core::SegmentReader;
use crate::query::Query;
use crate::query::Scorer;
use crate::query::Weight;
use crate::schema::Document;
use crate::schema::Schema;
use crate::schema::{Field, Term};
@@ -11,8 +14,29 @@ use crate::store::StoreReader;
use crate::termdict::TermMerger;
use crate::DocAddress;
use crate::Index;
use crate::Result;
use std::fmt;
use std::sync::Arc;
use std::{fmt, io};
fn collect_segment<C: Collector>(
collector: &C,
weight: &dyn Weight,
segment_ord: u32,
segment_reader: &SegmentReader,
) -> Result<C::Fruit> {
let mut scorer = weight.scorer(segment_reader)?;
let mut segment_collector = collector.for_segment(segment_ord as u32, segment_reader)?;
if let Some(delete_bitset) = segment_reader.delete_bitset() {
scorer.for_each(&mut |doc, score| {
if delete_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
}
});
} else {
scorer.for_each(&mut |doc, score| segment_collector.collect(doc, score));
}
Ok(segment_collector.harvest())
}
/// Holds a list of `SegmentReader`s ready for search.
///
@@ -32,17 +56,17 @@ impl Searcher {
schema: Schema,
index: Index,
segment_readers: Vec<SegmentReader>,
) -> io::Result<Searcher> {
let store_readers: Vec<StoreReader> = segment_readers
) -> Searcher {
let store_readers = segment_readers
.iter()
.map(SegmentReader::get_store_reader)
.collect::<io::Result<Vec<_>>>()?;
Ok(Searcher {
.collect();
Searcher {
schema,
index,
segment_readers,
store_readers,
})
}
}
/// Returns the `Index` associated to the `Searcher`
@@ -54,7 +78,7 @@ impl Searcher {
///
/// The searcher uses the segment ordinal to route the
/// the request to the right `Segment`.
pub fn doc(&self, doc_address: DocAddress) -> crate::Result<Document> {
pub fn doc(&self, doc_address: DocAddress) -> 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)
@@ -75,14 +99,13 @@ impl Searcher {
/// Return the overall number of documents containing
/// the given term.
pub fn doc_freq(&self, term: &Term) -> crate::Result<u64> {
let mut total_doc_freq = 0;
for segment_reader in &self.segment_readers {
let inverted_index = segment_reader.inverted_index(term.field())?;
let doc_freq = inverted_index.doc_freq(term)?;
total_doc_freq += u64::from(doc_freq);
}
Ok(total_doc_freq)
pub fn doc_freq(&self, term: &Term) -> u64 {
self.segment_readers
.iter()
.map(|segment_reader| {
u64::from(segment_reader.inverted_index(term.field()).doc_freq(term))
})
.sum::<u64>()
}
/// Return the list of segment readers
@@ -109,11 +132,7 @@ impl Searcher {
///
/// Finally, the Collector merges each of the child collectors into itself for result usability
/// by the caller.
pub fn search<C: Collector>(
&self,
query: &dyn Query,
collector: &C,
) -> crate::Result<C::Fruit> {
pub fn search<C: Collector>(&self, query: &dyn Query, collector: &C) -> Result<C::Fruit> {
let executor = self.index.search_executor();
self.search_with_executor(query, collector, executor)
}
@@ -135,13 +154,18 @@ impl Searcher {
query: &dyn Query,
collector: &C,
executor: &Executor,
) -> crate::Result<C::Fruit> {
) -> 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)
collect_segment(
collector,
weight.as_ref(),
segment_ord as u32,
segment_reader,
)
},
segment_readers.iter().enumerate(),
)?;
@@ -149,26 +173,25 @@ impl Searcher {
}
/// Return the field searcher associated to a `Field`.
pub fn field(&self, field: Field) -> crate::Result<FieldSearcher> {
let inv_index_readers: Vec<Arc<InvertedIndexReader>> = self
pub fn field(&self, field: Field) -> FieldSearcher {
let inv_index_readers = self
.segment_readers
.iter()
.map(|segment_reader| segment_reader.inverted_index(field))
.collect::<crate::Result<Vec<_>>>()?;
Ok(FieldSearcher::new(inv_index_readers))
.collect::<Vec<_>>();
FieldSearcher::new(inv_index_readers)
}
/// Summarize total space usage of this searcher.
pub fn space_usage(&self) -> io::Result<SearcherSpaceUsage> {
pub fn space_usage(&self) -> SearcherSpaceUsage {
let mut space_usage = SearcherSpaceUsage::new();
for segment_reader in &self.segment_readers {
space_usage.add_segment(segment_reader.space_usage()?);
for segment_reader in self.segment_readers.iter() {
space_usage.add_segment(segment_reader.space_usage());
}
Ok(space_usage)
space_usage
}
}
/// **Experimental API** `FieldSearcher` only gives access to a stream over the terms of a field.
pub struct FieldSearcher {
inv_index_readers: Vec<Arc<InvertedIndexReader>>,
}
@@ -180,11 +203,7 @@ impl FieldSearcher {
/// Returns a Stream over all of the sorted unique terms of
/// for the given field.
///
/// This method does not take into account which documents are deleted, so
/// in presence of deletes some terms may not actually exist in any document
/// anymore.
pub fn terms(&self) -> TermMerger {
pub fn terms(&self) -> TermMerger<'_> {
let term_streamers: Vec<_> = self
.inv_index_readers
.iter()

43
src/core/segment.rs
View File

@@ -4,12 +4,14 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::directory::error::{OpenReadError, OpenWriteError};
use crate::directory::Directory;
use crate::directory::{FileSlice, WritePtr};
use crate::directory::{ReadOnlySource, WritePtr};
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::schema::Schema;
use crate::Opstamp;
use crate::Result;
use std::fmt;
use std::path::PathBuf;
use std::result;
/// A segment is a piece of the index.
#[derive(Clone)]
@@ -24,12 +26,15 @@ impl fmt::Debug for Segment {
}
}
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`.
/// #[doc(hidden)]
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
@@ -45,17 +50,6 @@ 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 {
@@ -78,13 +72,20 @@ impl Segment {
}
/// Open one of the component file for a *regular* read.
pub fn open_read(&self, component: SegmentComponent) -> Result<FileSlice, OpenReadError> {
pub fn open_read(
&self,
component: SegmentComponent,
) -> result::Result<ReadOnlySource, OpenReadError> {
let path = self.relative_path(component);
self.index.directory().open_read(&path)
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)
@@ -97,5 +98,5 @@ 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>;
}

2
src/core/segment_component.rs
View File

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

56
src/core/segment_id.rs
View File

@@ -4,9 +4,6 @@ use uuid::Uuid;
#[cfg(test)]
use once_cell::sync::Lazy;
use serde::{Deserialize, Serialize};
use std::error::Error;
use std::str::FromStr;
#[cfg(test)]
use std::sync::atomic;
@@ -55,51 +52,15 @@ 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()
}
/// Returns a segment uuid string.
///
/// It consists in 32 lowercase hexadecimal chars
/// (e.g. a5c4dfcbdfe645089129e308e26d5523)
pub fn uuid_string(&self) -> String {
self.0.to_simple_ref().to_string()
}
/// Build a `SegmentId` string from the full uuid string.
///
/// E.g. "a5c4dfcbdfe645089129e308e26d5523"
pub fn from_uuid_string(uuid_string: &str) -> Result<SegmentId, SegmentIdParseError> {
FromStr::from_str(uuid_string)
}
}
/// Error type used when parsing a `SegmentId` from a string fails.
pub struct SegmentIdParseError(uuid::Error);
impl Error for SegmentIdParseError {}
impl fmt::Debug for SegmentIdParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.0.fmt(f)
}
}
impl fmt::Display for SegmentIdParseError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
self.0.fmt(f)
}
}
impl FromStr for SegmentId {
type Err = SegmentIdParseError;
fn from_str(uuid_string: &str) -> Result<Self, SegmentIdParseError> {
let uuid = Uuid::parse_str(uuid_string).map_err(SegmentIdParseError)?;
Ok(SegmentId(uuid))
}
}
impl fmt::Debug for SegmentId {
@@ -119,18 +80,3 @@ 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());
}
}

208
src/core/segment_reader.rs
View File

@@ -1,26 +1,27 @@
use crate::common::CompositeFile;
use crate::common::HasLen;
use crate::core::InvertedIndexReader;
use crate::core::Segment;
use crate::core::SegmentComponent;
use crate::core::SegmentId;
use crate::directory::FileSlice;
use crate::directory::ReadOnlySource;
use crate::fastfield::DeleteBitSet;
use crate::fastfield::FacetReader;
use crate::fastfield::FastFieldReaders;
use crate::fieldnorm::{FieldNormReader, FieldNormReaders};
use crate::fieldnorm::FieldNormReader;
use crate::schema::Field;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::schema::{Field, IndexRecordOption};
use crate::space_usage::SegmentSpaceUsage;
use crate::store::StoreReader;
use crate::termdict::TermDictionary;
use crate::DocId;
use crate::{common::CompositeFile, error::DataCorruption};
use crate::Result;
use fail::fail_point;
use std::collections::HashMap;
use std::fmt;
use std::sync::Arc;
use std::sync::RwLock;
use std::{collections::HashMap, io};
/// Entry point to access all of the datastructures of the `Segment`
///
@@ -48,9 +49,9 @@ pub struct SegmentReader {
positions_composite: CompositeFile,
positions_idx_composite: CompositeFile,
fast_fields_readers: Arc<FastFieldReaders>,
fieldnorm_readers: FieldNormReaders,
fieldnorms_composite: CompositeFile,
store_file: FileSlice,
store_source: ReadOnlySource,
delete_bitset_opt: Option<DeleteBitSet>,
schema: Schema,
}
@@ -106,26 +107,16 @@ impl SegmentReader {
}
/// Accessor to the `FacetReader` associated to a given `Field`.
pub fn facet_reader(&self, field: Field) -> crate::Result<FacetReader> {
pub fn facet_reader(&self, field: Field) -> Option<FacetReader> {
let field_entry = self.schema.get_field_entry(field);
if field_entry.field_type() != &FieldType::HierarchicalFacet {
return Err(crate::TantivyError::InvalidArgument(format!(
"Field {:?} is not a facet field.",
field_entry.name()
)));
return None;
}
let term_ords_reader = self.fast_fields().u64s(field).ok_or_else(|| {
DataCorruption::comment_only(format!(
"Cannot find data for hierarchical facet {:?}",
field_entry.name()
))
})?;
let termdict = self
.termdict_composite
.open_read(field)
.map(TermDictionary::open)
.unwrap_or_else(|| Ok(TermDictionary::empty()))?;
Ok(FacetReader::new(term_ords_reader, termdict))
let term_ords_reader = self.fast_fields().u64s(field)?;
let termdict_source = self.termdict_composite.open_read(field)?;
let termdict = TermDictionary::from_source(&termdict_source);
let facet_reader = FacetReader::new(term_ords_reader, termdict);
Some(facet_reader)
}
/// Accessor to the segment's `Field norms`'s reader.
@@ -135,45 +126,47 @@ impl SegmentReader {
///
/// They are simply stored as a fast field, serialized in
/// the `.fieldnorm` file of the segment.
pub fn get_fieldnorms_reader(&self, field: Field) -> crate::Result<FieldNormReader> {
self.fieldnorm_readers.get_field(field)?.ok_or_else(|| {
pub fn get_fieldnorms_reader(&self, field: Field) -> FieldNormReader {
if let Some(fieldnorm_source) = self.fieldnorms_composite.open_read(field) {
FieldNormReader::open(fieldnorm_source)
} else {
let field_name = self.schema.get_field_name(field);
let err_msg = format!(
"Field norm not found for field {:?}. Was it marked as indexed during indexing?",
"Field norm not found for field {:?}. Was it market as indexed during indexing.",
field_name
);
crate::TantivyError::SchemaError(err_msg)
})
panic!(err_msg);
}
}
/// Accessor to the segment's `StoreReader`.
pub fn get_store_reader(&self) -> io::Result<StoreReader> {
StoreReader::open(self.store_file.clone())
pub fn get_store_reader(&self) -> StoreReader {
StoreReader::from_source(self.store_source.clone())
}
/// Open a new segment for reading.
pub fn open(segment: &Segment) -> crate::Result<SegmentReader> {
let termdict_file = segment.open_read(SegmentComponent::TERMS)?;
let termdict_composite = CompositeFile::open(&termdict_file)?;
pub fn open(segment: &Segment) -> Result<SegmentReader> {
let termdict_source = segment.open_read(SegmentComponent::TERMS)?;
let termdict_composite = CompositeFile::open(&termdict_source)?;
let store_file = segment.open_read(SegmentComponent::STORE)?;
let store_source = segment.open_read(SegmentComponent::STORE)?;
fail_point!("SegmentReader::open#middle");
let postings_file = segment.open_read(SegmentComponent::POSTINGS)?;
let postings_composite = CompositeFile::open(&postings_file)?;
let postings_source = segment.open_read(SegmentComponent::POSTINGS)?;
let postings_composite = CompositeFile::open(&postings_source)?;
let positions_composite = {
if let Ok(positions_file) = segment.open_read(SegmentComponent::POSITIONS) {
CompositeFile::open(&positions_file)?
if let Ok(source) = segment.open_read(SegmentComponent::POSITIONS) {
CompositeFile::open(&source)?
} else {
CompositeFile::empty()
}
};
let positions_idx_composite = {
if let Ok(positions_skip_file) = segment.open_read(SegmentComponent::POSITIONSSKIP) {
CompositeFile::open(&positions_skip_file)?
if let Ok(source) = segment.open_read(SegmentComponent::POSITIONSSKIP) {
CompositeFile::open(&source)?
} else {
CompositeFile::empty()
}
@@ -186,27 +179,26 @@ impl SegmentReader {
let fast_field_readers =
Arc::new(FastFieldReaders::load_all(&schema, &fast_fields_composite)?);
let fieldnorm_data = segment.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
let fieldnorms_data = segment.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorms_composite = CompositeFile::open(&fieldnorms_data)?;
let delete_bitset_opt = if segment.meta().has_deletes() {
let delete_data = segment.open_read(SegmentComponent::DELETE)?;
let delete_bitset = DeleteBitSet::open(delete_data)?;
Some(delete_bitset)
Some(DeleteBitSet::open(delete_data))
} else {
None
};
Ok(SegmentReader {
inv_idx_reader_cache: Default::default(),
inv_idx_reader_cache: Arc::new(RwLock::new(HashMap::new())),
max_doc: segment.meta().max_doc(),
num_docs: segment.meta().num_docs(),
termdict_composite,
postings_composite,
fast_fields_readers: fast_field_readers,
fieldnorm_readers,
fieldnorms_composite,
segment_id: segment.id(),
store_file,
store_source,
delete_bitset_opt,
positions_composite,
positions_idx_composite,
@@ -221,64 +213,58 @@ impl SegmentReader {
/// The field reader is in charge of iterating through the
/// term dictionary associated to a specific field,
/// and opening the posting list associated to any term.
///
/// If the field is marked as index, a warn is logged and an empty `InvertedIndexReader`
/// is returned.
/// Similarly if the field is marked as indexed but no term has been indexed for the given
/// index. an empty `InvertedIndexReader` is returned (but no warning is logged).
pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
pub fn inverted_index(&self, field: Field) -> Arc<InvertedIndexReader> {
if let Some(inv_idx_reader) = self
.inv_idx_reader_cache
.read()
.expect("Lock poisoned. This should never happen")
.get(&field)
{
return Ok(Arc::clone(inv_idx_reader));
return Arc::clone(inv_idx_reader);
}
let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type();
let record_option_opt = field_type.get_index_record_option();
if record_option_opt.is_none() {
warn!("Field {:?} does not seem indexed.", field_entry.name());
panic!("Field {:?} does not seem indexed.", field_entry.name());
}
let postings_file_opt = self.postings_composite.open_read(field);
let record_option = record_option_opt.unwrap();
if postings_file_opt.is_none() || record_option_opt.is_none() {
let postings_source_opt = self.postings_composite.open_read(field);
if postings_source_opt.is_none() {
// no documents in the segment contained this field.
// As a result, no data is associated to the inverted index.
//
// Returns an empty inverted index.
let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);
return Ok(Arc::new(InvertedIndexReader::empty(record_option)));
return Arc::new(InvertedIndexReader::empty(field_type));
}
let record_option = record_option_opt.unwrap();
let postings_file = postings_file_opt.unwrap();
let postings_source = postings_source_opt.unwrap();
let termdict_file: FileSlice = self.termdict_composite.open_read(field)
.ok_or_else(||
DataCorruption::comment_only(format!("Failed to open field {:?}'s term dictionary in the composite file. Has the schema been modified?", field_entry.name()))
)?;
let termdict_source = self.termdict_composite.open_read(field).expect(
"Failed to open field term dictionary in composite file. Is the field indexed?",
);
let positions_file = self
let positions_source = self
.positions_composite
.open_read(field)
.expect("Index corrupted. Failed to open field positions in composite file.");
let positions_idx_file = self
let positions_idx_source = self
.positions_idx_composite
.open_read(field)
.expect("Index corrupted. Failed to open field positions in composite file.");
let inv_idx_reader = Arc::new(InvertedIndexReader::new(
TermDictionary::open(termdict_file)?,
postings_file,
positions_file,
positions_idx_file,
TermDictionary::from_source(&termdict_source),
postings_source,
positions_source,
positions_idx_source,
record_option,
)?);
));
// by releasing the lock in between, we may end up opening the inverting index
// twice, but this is fine.
@@ -287,7 +273,7 @@ impl SegmentReader {
.expect("Field reader cache lock poisoned. This should never happen.")
.insert(field, Arc::clone(&inv_idx_reader));
Ok(inv_idx_reader)
inv_idx_reader
}
/// Returns the segment id
@@ -310,26 +296,26 @@ impl SegmentReader {
}
/// Returns an iterator that will iterate over the alive document ids
pub fn doc_ids_alive<'a>(&'a self) -> impl Iterator<Item = DocId> + 'a {
(0u32..self.max_doc).filter(move |doc| !self.is_deleted(*doc))
pub fn doc_ids_alive(&self) -> SegmentReaderAliveDocsIterator<'_> {
SegmentReaderAliveDocsIterator::new(&self)
}
/// Summarize total space usage of this segment.
pub fn space_usage(&self) -> io::Result<SegmentSpaceUsage> {
Ok(SegmentSpaceUsage::new(
pub fn space_usage(&self) -> SegmentSpaceUsage {
SegmentSpaceUsage::new(
self.num_docs(),
self.termdict_composite.space_usage(),
self.postings_composite.space_usage(),
self.positions_composite.space_usage(),
self.positions_idx_composite.space_usage(),
self.fast_fields_readers.space_usage(),
self.fieldnorm_readers.space_usage(),
self.get_store_reader()?.space_usage(),
self.fieldnorms_composite.space_usage(),
self.get_store_reader().space_usage(),
self.delete_bitset_opt
.as_ref()
.map(DeleteBitSet::space_usage)
.unwrap_or(0),
))
)
}
}
@@ -339,6 +325,52 @@ impl fmt::Debug for SegmentReader {
}
}
/// Implements the iterator trait to allow easy iteration
/// over non-deleted ("alive") DocIds in a SegmentReader
pub struct SegmentReaderAliveDocsIterator<'a> {
reader: &'a SegmentReader,
max_doc: DocId,
current: DocId,
}
impl<'a> SegmentReaderAliveDocsIterator<'a> {
pub fn new(reader: &'a SegmentReader) -> SegmentReaderAliveDocsIterator<'a> {
SegmentReaderAliveDocsIterator {
reader,
max_doc: reader.max_doc(),
current: 0,
}
}
}
impl<'a> Iterator for SegmentReaderAliveDocsIterator<'a> {
type Item = DocId;
fn next(&mut self) -> Option<Self::Item> {
// TODO: Use TinySet (like in BitSetDocSet) to speed this process up
if self.current >= self.max_doc {
return None;
}
// find the next alive doc id
while self.reader.is_deleted(self.current) {
self.current += 1;
if self.current >= self.max_doc {
return None;
}
}
// capture the current alive DocId
let result = Some(self.current);
// move down the chain
self.current += 1;
result
}
}
#[cfg(test)]
mod test {
use crate::core::Index;
@@ -346,7 +378,7 @@ mod test {
use crate::DocId;
#[test]
fn test_alive_docs_iterator() -> crate::Result<()> {
fn test_alive_docs_iterator() {
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("name", TEXT | STORED);
let schema = schema_builder.build();
@@ -354,26 +386,26 @@ mod test {
let name = schema.get_field("name").unwrap();
{
let mut index_writer = index.writer_for_tests()?;
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(name => "tantivy"));
index_writer.add_document(doc!(name => "horse"));
index_writer.add_document(doc!(name => "jockey"));
index_writer.add_document(doc!(name => "cap"));
// we should now have one segment with two docs
index_writer.commit()?;
index_writer.commit().unwrap();
}
{
let mut index_writer2 = index.writer(50_000_000)?;
let mut index_writer2 = index.writer(50_000_000).unwrap();
index_writer2.delete_term(Term::from_field_text(name, "horse"));
index_writer2.delete_term(Term::from_field_text(name, "cap"));
// ok, now we should have a deleted doc
index_writer2.commit()?;
index_writer2.commit().unwrap();
}
let searcher = index.reader()?.searcher();
let searcher = index.reader().unwrap().searcher();
let docs: Vec<DocId> = searcher.segment_reader(0).doc_ids_alive().collect();
assert_eq!(vec![0u32, 2u32], docs);
Ok(())
}
}

31
src/directory/directory.rs
View File

@@ -3,7 +3,7 @@ use crate::directory::error::LockError;
use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
use crate::directory::WatchCallback;
use crate::directory::WatchHandle;
use crate::directory::{FileSlice, WritePtr};
use crate::directory::{ReadOnlySource, WritePtr};
use std::fmt;
use std::io;
use std::io::Write;
@@ -11,6 +11,7 @@ use std::marker::Send;
use std::marker::Sync;
use std::path::Path;
use std::path::PathBuf;
use std::result;
use std::thread;
use std::time::Duration;
@@ -47,14 +48,14 @@ impl RetryPolicy {
///
/// It is transparently associated to a lock file, that gets deleted
/// on `Drop.` The lock is released automatically on `Drop`.
pub struct DirectoryLock(Box<dyn Send + Sync + 'static>);
pub struct DirectoryLock(Box<dyn Drop + Send + Sync + 'static>);
struct DirectoryLockGuard {
directory: Box<dyn Directory>,
path: PathBuf,
}
impl<T: Send + Sync + 'static> From<Box<T>> for DirectoryLock {
impl<T: Drop + Send + Sync + 'static> From<Box<T>> for DirectoryLock {
fn from(underlying: Box<T>) -> Self {
DirectoryLock(underlying)
}
@@ -79,7 +80,7 @@ fn try_acquire_lock(
) -> Result<DirectoryLock, TryAcquireLockError> {
let mut write = directory.open_write(filepath).map_err(|e| match e {
OpenWriteError::FileAlreadyExists(_) => TryAcquireLockError::FileExists,
OpenWriteError::IOError { io_error, .. } => TryAcquireLockError::IOError(io_error),
OpenWriteError::IOError(io_error) => TryAcquireLockError::IOError(io_error.into()),
})?;
write.flush().map_err(TryAcquireLockError::IOError)?;
Ok(DirectoryLock::from(Box::new(DirectoryLockGuard {
@@ -116,29 +117,27 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// change.
///
/// Specifically, subsequent writes or flushes should
/// have no effect on the returned `FileSlice` object.
///
/// You should only use this to read files create with [Directory::open_write].
fn open_read(&self, path: &Path) -> Result<FileSlice, OpenReadError>;
/// have no effect on the returned `ReadOnlySource` object.
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
/// Removes a file
///
/// Removing a file will not affect an eventual
/// existing FileSlice pointing to it.
/// existing ReadOnlySource pointing to it.
///
/// Removing a nonexistent file, yields a
/// `DeleteError::DoesNotExist`.
fn delete(&self, path: &Path) -> Result<(), DeleteError>;
fn delete(&self, path: &Path) -> result::Result<(), DeleteError>;
/// Returns true iff the file exists
fn exists(&self, path: &Path) -> Result<bool, OpenReadError>;
fn exists(&self, path: &Path) -> bool;
/// Opens a writer for the *virtual file* associated with
/// a Path.
///
/// Right after this call, the file should be created
/// and any subsequent call to `open_read` for the
/// same path should return a `FileSlice`.
/// same path should return a `ReadOnlySource`.
///
/// Write operations may be aggressively buffered.
/// The client of this trait is responsible for calling flush
@@ -152,14 +151,12 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// was not called.
///
/// The file may not previously exist.
fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError>;
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError>;
/// Reads the full content file that has been written using
/// atomic_write.
///
/// This should only be used for small files.
///
/// You should only use this to read files create with [Directory::atomic_write].
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
/// Atomically replace the content of a file with data.
@@ -168,7 +165,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// a partially written file.
///
/// The file may or may not previously exist.
fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()>;
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()>;
/// Acquire a lock in the given directory.
///
@@ -196,7 +193,7 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// Registers a callback that will be called whenever a change on the `meta.json`
/// using the `atomic_write` API is detected.
///
/// The behavior when using `.watch()` on a file using [Directory::open_write] is, on the other
/// The behavior when using `.watch()` on a file using `.open_write(...)` is, on the other
/// hand, undefined.
///
/// The file will be watched for the lifetime of the returned `WatchHandle`. The caller is

312
src/directory/error.rs
View File

@@ -1,171 +1,243 @@
use crate::Version;
use std::error::Error as StdError;
use std::fmt;
use std::io;
use std::path::PathBuf;
/// Error while trying to acquire a directory lock.
#[derive(Debug, Error)]
#[derive(Debug, Fail)]
pub enum LockError {
/// Failed to acquired a lock as it is already held by another
/// client.
/// - In the context of a blocking lock, this means the lock was not released within some `timeout` period.
/// - In the context of a non-blocking lock, this means the lock was busy at the moment of the call.
#[error("Could not acquire lock as it is already held, possibly by a different process.")]
#[fail(
display = "Could not acquire lock as it is already held, possibly by a different process."
)]
LockBusy,
/// Trying to acquire a lock failed with an `IOError`
#[error("Failed to acquire the lock due to an io:Error.")]
#[fail(display = "Failed to acquire the lock due to an io:Error.")]
IOError(io::Error),
}
/// General IO error with an optional path to the offending file.
#[derive(Debug)]
pub struct IOError {
path: Option<PathBuf>,
err: io::Error,
}
impl Into<io::Error> for IOError {
fn into(self) -> io::Error {
self.err
}
}
impl fmt::Display for IOError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self.path {
Some(ref path) => write!(f, "io error occurred on path '{:?}': '{}'", path, self.err),
None => write!(f, "io error occurred: '{}'", self.err),
}
}
}
impl StdError for IOError {
fn description(&self) -> &str {
"io error occurred"
}
fn cause(&self) -> Option<&dyn StdError> {
Some(&self.err)
}
}
impl IOError {
pub(crate) fn with_path(path: PathBuf, err: io::Error) -> Self {
IOError {
path: Some(path),
err,
}
}
}
impl From<io::Error> for IOError {
fn from(err: io::Error) -> IOError {
IOError { path: None, err }
}
}
/// Error that may occur when opening a directory
#[derive(Debug, Error)]
#[derive(Debug)]
pub enum OpenDirectoryError {
/// The underlying directory does not exists.
#[error("Directory does not exist: '{0}'.")]
DoesNotExist(PathBuf),
/// The path exists but is not a directory.
#[error("Path exists but is not a directory: '{0}'.")]
NotADirectory(PathBuf),
/// Failed to create a temp directory.
#[error("Failed to create a temporary directory: '{0}'.")]
FailedToCreateTempDir(io::Error),
/// IoError
#[error("IOError '{io_error:?}' while create directory in: '{directory_path:?}'.")]
IoError {
/// underlying io Error.
io_error: io::Error,
/// directory we tried to open.
directory_path: PathBuf,
},
IoError(io::Error),
}
impl From<io::Error> for OpenDirectoryError {
fn from(io_err: io::Error) -> Self {
OpenDirectoryError::IoError(io_err)
}
}
impl fmt::Display for OpenDirectoryError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
OpenDirectoryError::DoesNotExist(ref path) => {
write!(f, "the underlying directory '{:?}' does not exist", path)
}
OpenDirectoryError::NotADirectory(ref path) => {
write!(f, "the path '{:?}' exists but is not a directory", path)
}
OpenDirectoryError::IoError(ref err) => write!(
f,
"IOError while trying to open/create the directory. {:?}",
err
),
}
}
}
impl StdError for OpenDirectoryError {
fn description(&self) -> &str {
"error occurred while opening a directory"
}
fn cause(&self) -> Option<&dyn StdError> {
None
}
}
/// Error that may occur when starting to write in a file
#[derive(Debug, Error)]
#[derive(Debug)]
pub enum OpenWriteError {
/// Our directory is WORM, writing an existing file is forbidden.
/// Checkout the `Directory` documentation.
#[error("File already exists: '{0}'")]
FileAlreadyExists(PathBuf),
/// Any kind of IO error that happens when
/// writing in the underlying IO device.
#[error("IOError '{io_error:?}' while opening file for write: '{filepath}'.")]
IOError {
/// The underlying `io::Error`.
io_error: io::Error,
/// File path of the file that tantivy failed to open for write.
filepath: PathBuf,
},
IOError(IOError),
}
impl OpenWriteError {
pub(crate) fn wrap_io_error(io_error: io::Error, filepath: PathBuf) -> Self {
Self::IOError { io_error, filepath }
impl From<IOError> for OpenWriteError {
fn from(err: IOError) -> OpenWriteError {
OpenWriteError::IOError(err)
}
}
/// Type of index incompatibility between the library and the index found on disk
/// Used to catch and provide a hint to solve this incompatibility issue
pub enum Incompatibility {
/// This library cannot decompress the index found on disk
CompressionMismatch {
/// Compression algorithm used by the current version of tantivy
library_compression_format: String,
/// Compression algorithm that was used to serialise the index
index_compression_format: String,
},
/// The index format found on disk isn't supported by this version of the library
IndexMismatch {
/// Version used by the library
library_version: Version,
/// Version the index was built with
index_version: Version,
},
impl fmt::Display for OpenWriteError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
OpenWriteError::FileAlreadyExists(ref path) => {
write!(f, "the file '{:?}' already exists", path)
}
OpenWriteError::IOError(ref err) => write!(
f,
"an io error occurred while opening a file for writing: '{}'",
err
),
}
}
}
impl fmt::Debug for Incompatibility {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
match self {
Incompatibility::CompressionMismatch {
library_compression_format,
index_compression_format,
} => {
let err = format!(
"Library was compiled with {:?} compression, index was compressed with {:?}",
library_compression_format, index_compression_format
);
let advice = format!(
"Change the feature flag to {:?} and rebuild the library",
index_compression_format
);
write!(f, "{}. {}", err, advice)?;
}
Incompatibility::IndexMismatch {
library_version,
index_version,
} => {
let err = format!(
"Library version: {}, index version: {}",
library_version.index_format_version, index_version.index_format_version
);
// TODO make a more useful error message
// include the version range that supports this index_format_version
let advice = format!(
"Change tantivy to a version compatible with index format {} (e.g. {}.{}.x) \
and rebuild your project.",
index_version.index_format_version, index_version.major, index_version.minor
);
write!(f, "{}. {}", err, advice)?;
}
}
impl StdError for OpenWriteError {
fn description(&self) -> &str {
"error occurred while opening a file for writing"
}
Ok(())
fn cause(&self) -> Option<&dyn StdError> {
match *self {
OpenWriteError::FileAlreadyExists(_) => None,
OpenWriteError::IOError(ref err) => Some(err),
}
}
}
/// Error that may occur when accessing a file read
#[derive(Debug, Error)]
#[derive(Debug)]
pub enum OpenReadError {
/// The file does not exists.
#[error("Files does not exists: {0:?}")]
FileDoesNotExist(PathBuf),
/// Any kind of io::Error.
#[error(
"IOError: '{io_error:?}' happened while opening the following file for Read: {filepath}."
)]
IOError {
/// The underlying `io::Error`.
io_error: io::Error,
/// File path of the file that tantivy failed to open for read.
filepath: PathBuf,
},
/// This library does not support the index version found in file footer.
#[error("Index version unsupported: {0:?}")]
IncompatibleIndex(Incompatibility),
}
impl OpenReadError {
pub(crate) fn wrap_io_error(io_error: io::Error, filepath: PathBuf) -> Self {
Self::IOError { io_error, filepath }
}
}
/// Error that may occur when trying to delete a file
#[derive(Debug, Error)]
pub enum DeleteError {
/// The file does not exists.
#[error("File does not exists: '{0}'.")]
FileDoesNotExist(PathBuf),
/// Any kind of IO error that happens when
/// interacting with the underlying IO device.
#[error("The following IO error happened while deleting file '{filepath}': '{io_error:?}'.")]
IOError {
/// The underlying `io::Error`.
io_error: io::Error,
/// File path of the file that tantivy failed to delete.
filepath: PathBuf,
},
IOError(IOError),
}
impl From<Incompatibility> for OpenReadError {
fn from(incompatibility: Incompatibility) -> Self {
OpenReadError::IncompatibleIndex(incompatibility)
impl From<IOError> for OpenReadError {
fn from(err: IOError) -> OpenReadError {
OpenReadError::IOError(err)
}
}
impl fmt::Display for OpenReadError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
OpenReadError::FileDoesNotExist(ref path) => {
write!(f, "the file '{:?}' does not exist", path)
}
OpenReadError::IOError(ref err) => write!(
f,
"an io error occurred while opening a file for reading: '{}'",
err
),
}
}
}
impl StdError for OpenReadError {
fn description(&self) -> &str {
"error occurred while opening a file for reading"
}
fn cause(&self) -> Option<&dyn StdError> {
match *self {
OpenReadError::FileDoesNotExist(_) => None,
OpenReadError::IOError(ref err) => Some(err),
}
}
}
/// Error that may occur when trying to delete a file
#[derive(Debug)]
pub enum DeleteError {
/// The file does not exists.
FileDoesNotExist(PathBuf),
/// Any kind of IO error that happens when
/// interacting with the underlying IO device.
IOError(IOError),
}
impl From<IOError> for DeleteError {
fn from(err: IOError) -> DeleteError {
DeleteError::IOError(err)
}
}
impl fmt::Display for DeleteError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match *self {
DeleteError::FileDoesNotExist(ref path) => {
write!(f, "the file '{:?}' does not exist", path)
}
DeleteError::IOError(ref err) => {
write!(f, "an io error occurred while deleting a file: '{}'", err)
}
}
}
}
impl StdError for DeleteError {
fn description(&self) -> &str {
"error occurred while deleting a file"
}
fn cause(&self) -> Option<&dyn StdError> {
match *self {
DeleteError::FileDoesNotExist(_) => None,
DeleteError::IOError(ref err) => Some(err),
}
}
}

237
src/directory/file_slice.rs
View File

@@ -1,237 +0,0 @@
use stable_deref_trait::StableDeref;
use crate::common::HasLen;
use crate::directory::OwnedBytes;
use std::sync::Arc;
use std::{io, ops::Deref};
pub type BoxedData = Box<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
/// Objects that represents files sections in tantivy.
///
/// By contract, whatever happens to the directory file, as long as a FileHandle
/// is alive, the data associated with it cannot be altered or destroyed.
///
/// The underlying behavior is therefore specific to the `Directory` that created it.
/// Despite its name, a `FileSlice` may or may not directly map to an actual file
/// on the filesystem.
pub trait FileHandle: 'static + Send + Sync + HasLen {
/// Reads a slice of bytes.
///
/// This method may panic if the range requested is invalid.
fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes>;
}
impl FileHandle for &'static [u8] {
fn read_bytes(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
let bytes = &self[from..to];
Ok(OwnedBytes::new(bytes))
}
}
impl<T: Deref<Target = [u8]>> HasLen for T {
fn len(&self) -> usize {
self.as_ref().len()
}
}
impl<B> From<B> for FileSlice
where
B: StableDeref + Deref<Target = [u8]> + 'static + Send + Sync,
{
fn from(bytes: B) -> FileSlice {
FileSlice::new(OwnedBytes::new(bytes))
}
}
/// Logical slice of read only file in tantivy.
//
/// It can be cloned and sliced cheaply.
///
#[derive(Clone)]
pub struct FileSlice {
data: Arc<Box<dyn FileHandle>>,
start: usize,
stop: usize,
}
impl FileSlice {
/// Wraps a FileHandle.
pub fn new<D>(data: D) -> Self
where
D: FileHandle,
{
let len = data.len();
FileSlice {
data: Arc::new(Box::new(data)),
start: 0,
stop: len,
}
}
/// Creates a fileslice that is just a view over a slice of the data.
///
/// # Panics
///
/// Panics if `to < from` or if `to` exceeds the filesize.
pub fn slice(&self, from: usize, to: usize) -> FileSlice {
assert!(to <= self.len());
assert!(to >= from);
FileSlice {
data: self.data.clone(),
start: self.start + from,
stop: self.start + to,
}
}
/// Creates an empty FileSlice
pub fn empty() -> FileSlice {
const EMPTY_SLICE: &[u8] = &[];
FileSlice::from(EMPTY_SLICE)
}
/// Returns a `OwnedBytes` with all of the data in the `FileSlice`.
///
/// The behavior is strongly dependant on the implementation of the underlying
/// `Directory` and the `FileSliceTrait` it creates.
/// In particular, it is up to the `Directory` implementation
/// to handle caching if needed.
pub fn read_bytes(&self) -> io::Result<OwnedBytes> {
self.data.read_bytes(self.start, self.stop)
}
/// Reads a specific slice of data.
///
/// This is equivalent to running `file_slice.slice(from, to).read_bytes()`.
pub fn read_bytes_slice(&self, from: usize, to: usize) -> io::Result<OwnedBytes> {
assert!(from <= to);
assert!(
self.start + to <= self.stop,
"`to` exceeds the fileslice length"
);
self.data.read_bytes(self.start + from, self.start + to)
}
/// Splits the FileSlice at the given offset and return two file slices.
/// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
///
/// This operation is cheap and must not copy any underlying data.
pub fn split(self, left_len: usize) -> (FileSlice, FileSlice) {
let left = self.slice_to(left_len);
let right = self.slice_from(left_len);
(left, right)
}
/// Splits the file slice at the given offset and return two file slices.
/// `file_slice[..split_offset]` and `file_slice[split_offset..]`.
pub fn split_from_end(self, right_len: usize) -> (FileSlice, FileSlice) {
let left_len = self.len() - right_len;
self.split(left_len)
}
/// Like `.slice(...)` but enforcing only the `from`
/// boundary.
///
/// Equivalent to `.slice(from_offset, self.len())`
pub fn slice_from(&self, from_offset: usize) -> FileSlice {
self.slice(from_offset, self.len())
}
/// Like `.slice(...)` but enforcing only the `to`
/// boundary.
///
/// Equivalent to `.slice(0, to_offset)`
pub fn slice_to(&self, to_offset: usize) -> FileSlice {
self.slice(0, to_offset)
}
}
impl HasLen for FileSlice {
fn len(&self) -> usize {
self.stop - self.start
}
}
#[cfg(test)]
mod tests {
use super::{FileHandle, FileSlice};
use crate::common::HasLen;
use std::io;
#[test]
fn test_file_slice() -> io::Result<()> {
let file_slice = FileSlice::new(b"abcdef".as_ref());
assert_eq!(file_slice.len(), 6);
assert_eq!(file_slice.slice_from(2).read_bytes()?.as_slice(), b"cdef");
assert_eq!(file_slice.slice_to(2).read_bytes()?.as_slice(), b"ab");
assert_eq!(
file_slice
.slice_from(1)
.slice_to(2)
.read_bytes()?
.as_slice(),
b"bc"
);
{
let (left, right) = file_slice.clone().split(0);
assert_eq!(left.read_bytes()?.as_slice(), b"");
assert_eq!(right.read_bytes()?.as_slice(), b"abcdef");
}
{
let (left, right) = file_slice.clone().split(2);
assert_eq!(left.read_bytes()?.as_slice(), b"ab");
assert_eq!(right.read_bytes()?.as_slice(), b"cdef");
}
{
let (left, right) = file_slice.clone().split_from_end(0);
assert_eq!(left.read_bytes()?.as_slice(), b"abcdef");
assert_eq!(right.read_bytes()?.as_slice(), b"");
}
{
let (left, right) = file_slice.clone().split_from_end(2);
assert_eq!(left.read_bytes()?.as_slice(), b"abcd");
assert_eq!(right.read_bytes()?.as_slice(), b"ef");
}
Ok(())
}
#[test]
fn test_file_slice_trait_slice_len() {
let blop: &'static [u8] = b"abc";
let owned_bytes: Box<dyn FileHandle> = Box::new(blop);
assert_eq!(owned_bytes.len(), 3);
}
#[test]
fn test_slice_simple_read() -> io::Result<()> {
let slice = FileSlice::new(&b"abcdef"[..]);
assert_eq!(slice.len(), 6);
assert_eq!(slice.read_bytes()?.as_ref(), b"abcdef");
assert_eq!(slice.slice(1, 4).read_bytes()?.as_ref(), b"bcd");
Ok(())
}
#[test]
fn test_slice_read_slice() -> io::Result<()> {
let slice_deref = FileSlice::new(&b"abcdef"[..]);
assert_eq!(slice_deref.read_bytes_slice(1, 4)?.as_ref(), b"bcd");
Ok(())
}
#[test]
#[should_panic(expected = "assertion failed: from <= to")]
fn test_slice_read_slice_invalid_range() {
let slice_deref = FileSlice::new(&b"abcdef"[..]);
assert_eq!(slice_deref.read_bytes_slice(1, 0).unwrap().as_ref(), b"bcd");
}
#[test]
#[should_panic(expected = "`to` exceeds the fileslice length")]
fn test_slice_read_slice_invalid_range_exceeds() {
let slice_deref = FileSlice::new(&b"abcdef"[..]);
assert_eq!(
slice_deref.read_bytes_slice(0, 10).unwrap().as_ref(),
b"bcd"
);
}
}

178
src/directory/file_watcher.rs
View File

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

393
src/directory/footer.rs
View File

@@ -1,393 +0,0 @@
use crate::common::{BinarySerializable, CountingWriter, FixedSize, HasLen, VInt};
use crate::directory::error::Incompatibility;
use crate::directory::FileSlice;
use crate::directory::{AntiCallToken, TerminatingWrite};
use crate::Version;
use crc32fast::Hasher;
use std::io;
use std::io::Write;
const FOOTER_MAX_LEN: usize = 10_000;
type CrcHashU32 = u32;
#[derive(Debug, Clone, PartialEq)]
pub struct Footer {
pub version: Version,
pub meta: String,
pub versioned_footer: VersionedFooter,
}
/// Serialises the footer to a byte-array
/// - versioned_footer_len : 4 bytes
///- versioned_footer: variable bytes
/// - meta_len: 4 bytes
/// - meta: variable bytes
/// - version_len: 4 bytes
/// - version json: variable bytes
impl BinarySerializable for Footer {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
BinarySerializable::serialize(&self.versioned_footer, writer)?;
BinarySerializable::serialize(&self.meta, writer)?;
let version_string =
serde_json::to_string(&self.version).map_err(|_err| io::ErrorKind::InvalidInput)?;
BinarySerializable::serialize(&version_string, writer)?;
Ok(())
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let versioned_footer = VersionedFooter::deserialize(reader)?;
let meta = String::deserialize(reader)?;
let version_json = String::deserialize(reader)?;
let version = serde_json::from_str(&version_json)?;
Ok(Footer {
version,
meta,
versioned_footer,
})
}
}
impl Footer {
pub fn new(versioned_footer: VersionedFooter) -> Self {
let version = crate::VERSION.clone();
let meta = version.to_string();
Footer {
version,
meta,
versioned_footer,
}
}
pub fn append_footer<W: io::Write>(&self, mut write: &mut W) -> io::Result<()> {
let mut counting_write = CountingWriter::wrap(&mut write);
self.serialize(&mut counting_write)?;
let written_len = counting_write.written_bytes();
(written_len as u32).serialize(write)?;
Ok(())
}
pub fn extract_footer(file: FileSlice) -> io::Result<(Footer, FileSlice)> {
if file.len() < 4 {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The file is smaller than 4 bytes (len={}).",
file.len()
),
));
}
let (body_footer, footer_len_file) = file.split_from_end(u32::SIZE_IN_BYTES);
let mut footer_len_bytes = footer_len_file.read_bytes()?;
let footer_len = u32::deserialize(&mut footer_len_bytes)? as usize;
let (body, footer) = body_footer.split_from_end(footer_len);
let mut footer_bytes = footer.read_bytes()?;
let footer = Footer::deserialize(&mut footer_bytes)?;
Ok((footer, body))
}
/// Confirms that the index will be read correctly by this version of tantivy
/// Has to be called after `extract_footer` to make sure it's not accessing uninitialised memory
pub fn is_compatible(&self) -> Result<(), Incompatibility> {
let library_version = crate::version();
match &self.versioned_footer {
VersionedFooter::V1 {
crc32: _crc,
store_compression,
} => {
if &library_version.store_compression != store_compression {
return Err(Incompatibility::CompressionMismatch {
library_compression_format: library_version.store_compression.to_string(),
index_compression_format: store_compression.to_string(),
});
}
Ok(())
}
VersionedFooter::V2 {
crc32: _crc,
store_compression,
} => {
if &library_version.store_compression != store_compression {
return Err(Incompatibility::CompressionMismatch {
library_compression_format: library_version.store_compression.to_string(),
index_compression_format: store_compression.to_string(),
});
}
Ok(())
}
VersionedFooter::UnknownVersion => Err(Incompatibility::IndexMismatch {
library_version: library_version.clone(),
index_version: self.version.clone(),
}),
}
}
}
/// Footer that includes a crc32 hash that enables us to checksum files in the index
#[derive(Debug, Clone, PartialEq)]
pub enum VersionedFooter {
UnknownVersion,
V1 {
crc32: CrcHashU32,
store_compression: String,
},
// Introduction of the Block WAND information.
V2 {
crc32: CrcHashU32,
store_compression: String,
},
}
impl BinarySerializable for VersionedFooter {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
let mut buf = Vec::new();
match self {
VersionedFooter::V2 {
crc32,
store_compression: compression,
} => {
// Serializes a valid `VersionedFooter` or panics if the version is unknown
// [ version | crc_hash | compression_mode ]
// [ 0..4 | 4..8 | variable ]
BinarySerializable::serialize(&2u32, &mut buf)?;
BinarySerializable::serialize(crc32, &mut buf)?;
BinarySerializable::serialize(compression, &mut buf)?;
}
VersionedFooter::V1 { .. } | VersionedFooter::UnknownVersion => {
return Err(io::Error::new(
io::ErrorKind::InvalidInput,
"Cannot serialize an unknown versioned footer ",
));
}
}
BinarySerializable::serialize(&VInt(buf.len() as u64), writer)?;
assert!(buf.len() <= FOOTER_MAX_LEN);
writer.write_all(&buf[..])?;
Ok(())
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let len = VInt::deserialize(reader)?.0 as usize;
if len > FOOTER_MAX_LEN {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
format!(
"Footer seems invalid as it suggests a footer len of {}. File is corrupted, \
or the index was created with a different & old version of tantivy.",
len
),
));
}
let mut buf = vec![0u8; len];
reader.read_exact(&mut buf[..])?;
let mut cursor = &buf[..];
let version = u32::deserialize(&mut cursor)?;
if version != 1 && version != 2 {
return Ok(VersionedFooter::UnknownVersion);
}
let crc32 = u32::deserialize(&mut cursor)?;
let store_compression = String::deserialize(&mut cursor)?;
Ok(if version == 1 {
VersionedFooter::V1 {
crc32,
store_compression,
}
} else {
assert_eq!(version, 2);
VersionedFooter::V2 {
crc32,
store_compression,
}
})
}
}
impl VersionedFooter {
pub fn crc(&self) -> Option<CrcHashU32> {
match self {
VersionedFooter::V2 { crc32, .. } => Some(*crc32),
VersionedFooter::V1 { crc32, .. } => Some(*crc32),
VersionedFooter::UnknownVersion { .. } => None,
}
}
}
pub(crate) struct FooterProxy<W: TerminatingWrite> {
/// always Some except after terminate call
hasher: Option<Hasher>,
/// always Some except after terminate call
writer: Option<W>,
}
impl<W: TerminatingWrite> FooterProxy<W> {
pub fn new(writer: W) -> Self {
FooterProxy {
hasher: Some(Hasher::new()),
writer: Some(writer),
}
}
}
impl<W: TerminatingWrite> Write for FooterProxy<W> {
fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
let count = self.writer.as_mut().unwrap().write(buf)?;
self.hasher.as_mut().unwrap().update(&buf[..count]);
Ok(count)
}
fn flush(&mut self) -> io::Result<()> {
self.writer.as_mut().unwrap().flush()
}
}
impl<W: TerminatingWrite> TerminatingWrite for FooterProxy<W> {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
let crc32 = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V2 {
crc32,
store_compression: crate::store::COMPRESSION.to_string(),
});
let mut writer = self.writer.take().unwrap();
footer.append_footer(&mut writer)?;
writer.terminate()
}
}
#[cfg(test)]
mod tests {
use super::CrcHashU32;
use super::FooterProxy;
use crate::common::{BinarySerializable, VInt};
use crate::directory::footer::{Footer, VersionedFooter};
use crate::directory::TerminatingWrite;
use byteorder::{ByteOrder, LittleEndian};
use regex::Regex;
use std::io;
#[test]
fn test_versioned_footer() {
let mut vec = Vec::new();
let footer_proxy = FooterProxy::new(&mut vec);
assert!(footer_proxy.terminate().is_ok());
if crate::store::COMPRESSION == "lz4" {
assert_eq!(vec.len(), 158);
} else {
assert_eq!(vec.len(), 167);
}
let footer = Footer::deserialize(&mut &vec[..]).unwrap();
assert!(matches!(
footer.versioned_footer,
VersionedFooter::V2 { store_compression, .. }
if store_compression == crate::store::COMPRESSION
));
assert_eq!(&footer.version, crate::version());
}
#[test]
fn test_serialize_deserialize_footer() {
let mut buffer = Vec::new();
let crc32 = 123456u32;
let footer: Footer = Footer::new(VersionedFooter::V2 {
crc32,
store_compression: "lz4".to_string(),
});
footer.serialize(&mut buffer).unwrap();
let footer_deser = Footer::deserialize(&mut &buffer[..]).unwrap();
assert_eq!(footer_deser, footer);
}
#[test]
fn footer_length() {
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V2 {
crc32,
store_compression: "lz4".to_string(),
};
let mut buf = Vec::new();
versioned_footer.serialize(&mut buf).unwrap();
assert_eq!(buf.len(), 13);
let footer = Footer::new(versioned_footer);
let regex_ptn = Regex::new(
"tantivy v[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.{0,10}, index_format v[0-9]{1,5}",
)
.unwrap();
assert!(regex_ptn.is_match(&footer.meta));
}
#[test]
fn versioned_footer_from_bytes() {
let v_footer_bytes = vec![
// versionned footer length
12 | 128,
// index format version
2,
0,
0,
0,
// crc 32
12,
35,
89,
18,
// compression format
3 | 128,
b'l',
b'z',
b'4',
];
let mut cursor = &v_footer_bytes[..];
let versioned_footer = VersionedFooter::deserialize(&mut cursor).unwrap();
assert!(cursor.is_empty());
let expected_crc: u32 = LittleEndian::read_u32(&v_footer_bytes[5..9]) as CrcHashU32;
let expected_versioned_footer: VersionedFooter = VersionedFooter::V2 {
crc32: expected_crc,
store_compression: "lz4".to_string(),
};
assert_eq!(versioned_footer, expected_versioned_footer);
let mut buffer = Vec::new();
assert!(versioned_footer.serialize(&mut buffer).is_ok());
assert_eq!(&v_footer_bytes[..], &buffer[..]);
}
#[test]
fn versioned_footer_panic() {
let v_footer_bytes = vec![6u8 | 128u8, 3u8, 0u8, 0u8, 1u8, 0u8, 0u8];
let mut b = &v_footer_bytes[..];
let versioned_footer = VersionedFooter::deserialize(&mut b).unwrap();
assert!(b.is_empty());
let expected_versioned_footer = VersionedFooter::UnknownVersion;
assert_eq!(versioned_footer, expected_versioned_footer);
let mut buf = Vec::new();
assert!(versioned_footer.serialize(&mut buf).is_err());
}
#[test]
#[cfg(not(feature = "lz4"))]
fn compression_mismatch() {
let crc32 = 1111111u32;
let versioned_footer = VersionedFooter::V1 {
crc32,
store_compression: "lz4".to_string(),
};
let footer = Footer::new(versioned_footer);
let res = footer.is_compatible();
assert!(res.is_err());
}
#[test]
fn test_deserialize_too_large_footer() {
let mut buf = vec![];
assert!(FooterProxy::new(&mut buf).terminate().is_ok());
let mut long_len_buf = [0u8; 10];
let num_bytes = VInt(super::FOOTER_MAX_LEN as u64 + 1u64).serialize_into(&mut long_len_buf);
buf[0..num_bytes].copy_from_slice(&long_len_buf[..num_bytes]);
let err = Footer::deserialize(&mut &buf[..]).unwrap_err();
assert_eq!(err.kind(), io::ErrorKind::InvalidData);
assert_eq!(
err.to_string(),
"Footer seems invalid as it suggests a footer len of 10001. File is corrupted, \
or the index was created with a different & old version of tantivy."
);
}
}

224
src/directory/managed_directory.rs
View File

@@ -1,16 +1,14 @@
use crate::core::{MANAGED_FILEPATH, META_FILEPATH};
use crate::directory::error::{DeleteError, LockError, OpenReadError, OpenWriteError};
use crate::directory::footer::{Footer, FooterProxy};
use crate::core::MANAGED_FILEPATH;
use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError};
use crate::directory::DirectoryLock;
use crate::directory::GarbageCollectionResult;
use crate::directory::Lock;
use crate::directory::META_LOCK;
use crate::directory::{FileSlice, WritePtr};
use crate::directory::{ReadOnlySource, WritePtr};
use crate::directory::{WatchCallback, WatchHandle};
use crate::error::DataCorruption;
use crate::Directory;
use crc32fast::Hasher;
use crate::Result;
use serde_json;
use std::collections::HashSet;
use std::io;
use std::io::Write;
@@ -53,7 +51,7 @@ struct MetaInformation {
/// Saves the file containing the list of existing files
/// that were created by tantivy.
fn save_managed_paths(
directory: &dyn Directory,
directory: &mut dyn Directory,
wlock: &RwLockWriteGuard<'_, MetaInformation>,
) -> io::Result<()> {
let mut w = serde_json::to_vec(&wlock.managed_paths)?;
@@ -64,7 +62,7 @@ fn save_managed_paths(
impl ManagedDirectory {
/// Wraps a directory as managed directory.
pub fn wrap<Dir: Directory>(directory: Dir) -> crate::Result<ManagedDirectory> {
pub fn wrap<Dir: Directory>(directory: Dir) -> Result<ManagedDirectory> {
match directory.atomic_read(&MANAGED_FILEPATH) {
Ok(data) => {
let managed_files_json = String::from_utf8_lossy(&data);
@@ -86,12 +84,7 @@ impl ManagedDirectory {
directory: Box::new(directory),
meta_informations: Arc::default(),
}),
io_err @ Err(OpenReadError::IOError { .. }) => Err(io_err.err().unwrap().into()),
Err(OpenReadError::IncompatibleIndex(incompatibility)) => {
// For the moment, this should never happen `meta.json`
// do not have any footer and cannot detect incompatibility.
Err(crate::TantivyError::IncompatibleIndex(incompatibility))
}
Err(OpenReadError::IOError(e)) => Err(From::from(e)),
}
}
@@ -109,10 +102,7 @@ impl ManagedDirectory {
/// If a file cannot be deleted (for permission reasons for instance)
/// an error is simply logged, and the file remains in the list of managed
/// files.
pub fn garbage_collect<L: FnOnce() -> HashSet<PathBuf>>(
&mut self,
get_living_files: L,
) -> crate::Result<GarbageCollectionResult> {
pub fn garbage_collect<L: FnOnce() -> HashSet<PathBuf>>(&mut self, get_living_files: L) {
info!("Garbage collect");
let mut files_to_delete = vec![];
@@ -138,25 +128,19 @@ impl ManagedDirectory {
// 2) writer change meta.json (for instance after a merge or a commit)
// 3) gc kicks in.
// 4) gc removes a file that was useful for process B, before process B opened it.
match self.acquire_lock(&META_LOCK) {
Ok(_meta_lock) => {
let living_files = get_living_files();
for managed_path in &meta_informations_rlock.managed_paths {
if !living_files.contains(managed_path) {
files_to_delete.push(managed_path.clone());
}
if let Ok(_meta_lock) = self.acquire_lock(&META_LOCK) {
let living_files = get_living_files();
for managed_path in &meta_informations_rlock.managed_paths {
if !living_files.contains(managed_path) {
files_to_delete.push(managed_path.clone());
}
}
Err(err) => {
error!("Failed to acquire lock for GC");
return Err(crate::TantivyError::from(err));
}
} else {
error!("Failed to acquire lock for GC");
}
}
let mut failed_to_delete_files = vec![];
let mut deleted_files = vec![];
for file_to_delete in files_to_delete {
match self.delete(&file_to_delete) {
Ok(_) => {
@@ -166,10 +150,9 @@ impl ManagedDirectory {
Err(file_error) => {
match file_error {
DeleteError::FileDoesNotExist(_) => {
deleted_files.push(file_to_delete.clone());
deleted_files.push(file_to_delete);
}
DeleteError::IOError { .. } => {
failed_to_delete_files.push(file_to_delete.clone());
DeleteError::IOError(_) => {
if !cfg!(target_os = "windows") {
// On windows, delete is expected to fail if the file
// is mmapped.
@@ -192,13 +175,10 @@ impl ManagedDirectory {
for delete_file in &deleted_files {
managed_paths_write.remove(delete_file);
}
save_managed_paths(self.directory.as_mut(), &meta_informations_wlock)?;
if save_managed_paths(self.directory.as_mut(), &meta_informations_wlock).is_err() {
error!("Failed to save the list of managed files.");
}
}
Ok(GarbageCollectionResult {
deleted_files,
failed_to_delete_files,
})
}
/// Registers a file as managed
@@ -212,7 +192,7 @@ impl ManagedDirectory {
/// File starting by "." are reserved to locks.
/// They are not managed and cannot be subjected
/// to garbage collection.
fn register_file_as_managed(&self, filepath: &Path) -> io::Result<()> {
fn register_file_as_managed(&mut self, filepath: &Path) -> io::Result<()> {
// Files starting by "." (e.g. lock files) are not managed.
if !is_managed(filepath) {
return Ok(());
@@ -223,78 +203,24 @@ impl ManagedDirectory {
.expect("Managed file lock poisoned");
let has_changed = meta_wlock.managed_paths.insert(filepath.to_owned());
if has_changed {
save_managed_paths(self.directory.as_ref(), &meta_wlock)?;
save_managed_paths(self.directory.as_mut(), &meta_wlock)?;
}
Ok(())
}
/// Verify checksum of a managed file
pub fn validate_checksum(&self, path: &Path) -> result::Result<bool, OpenReadError> {
let reader = self.directory.open_read(path)?;
let (footer, data) =
Footer::extract_footer(reader).map_err(|io_error| OpenReadError::IOError {
io_error,
filepath: path.to_path_buf(),
})?;
let bytes = data
.read_bytes()
.map_err(|io_error| OpenReadError::IOError {
filepath: path.to_path_buf(),
io_error,
})?;
let mut hasher = Hasher::new();
hasher.update(bytes.as_slice());
let crc = hasher.finalize();
Ok(footer
.versioned_footer
.crc()
.map(|v| v == crc)
.unwrap_or(false))
}
/// List files for which checksum does not match content
pub fn list_damaged(&self) -> result::Result<HashSet<PathBuf>, OpenReadError> {
let mut managed_paths = self
.meta_informations
.read()
.expect("Managed directory rlock poisoned in list damaged.")
.managed_paths
.clone();
managed_paths.remove(*META_FILEPATH);
let mut damaged_files = HashSet::new();
for path in managed_paths {
if !self.validate_checksum(&path)? {
damaged_files.insert(path);
}
}
Ok(damaged_files)
}
}
impl Directory for ManagedDirectory {
fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
let file_slice = self.directory.open_read(path)?;
let (footer, reader) = Footer::extract_footer(file_slice)
.map_err(|io_error| OpenReadError::wrap_io_error(io_error, path.to_path_buf()))?;
footer.is_compatible()?;
Ok(reader)
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
self.directory.open_read(path)
}
fn open_write(&self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
self.register_file_as_managed(path)
.map_err(|io_error| OpenWriteError::wrap_io_error(io_error, path.to_path_buf()))?;
Ok(io::BufWriter::new(Box::new(FooterProxy::new(
self.directory
.open_write(path)?
.into_inner()
.map_err(|_| ())
.expect("buffer should be empty"),
))))
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
self.directory.open_write(path)
}
fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()> {
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
self.register_file_as_managed(path)?;
self.directory.atomic_write(path, data)
}
@@ -307,7 +233,7 @@ impl Directory for ManagedDirectory {
self.directory.delete(path)
}
fn exists(&self, path: &Path) -> Result<bool, OpenReadError> {
fn exists(&self, path: &Path) -> bool {
self.directory.exists(path)
}
@@ -333,16 +259,15 @@ impl Clone for ManagedDirectory {
#[cfg(test)]
mod tests_mmap_specific {
use crate::directory::{Directory, ManagedDirectory, MmapDirectory, TerminatingWrite};
use crate::directory::{Directory, ManagedDirectory, MmapDirectory};
use std::collections::HashSet;
use std::fs::OpenOptions;
use std::io::Write;
use std::path::{Path, PathBuf};
use tempfile::TempDir;
use tempdir::TempDir;
#[test]
fn test_managed_directory() {
let tempdir = TempDir::new().unwrap();
let tempdir = TempDir::new("tantivy-test").unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let test_path1: &'static Path = Path::new("some_path_for_test");
@@ -350,27 +275,28 @@ mod tests_mmap_specific {
{
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let write_file = managed_directory.open_write(test_path1).unwrap();
write_file.terminate().unwrap();
let mut write_file = managed_directory.open_write(test_path1).unwrap();
write_file.flush().unwrap();
managed_directory
.atomic_write(test_path2, &[0u8, 1u8])
.unwrap();
assert!(managed_directory.exists(test_path1).unwrap());
assert!(managed_directory.exists(test_path2).unwrap());
let living_files: HashSet<PathBuf> = [test_path1.to_owned()].iter().cloned().collect();
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path2).unwrap());
assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path2));
let living_files: HashSet<PathBuf> =
[test_path1.to_owned()].into_iter().cloned().collect();
managed_directory.garbage_collect(|| living_files);
assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
}
{
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
assert!(managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path2).unwrap());
assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
let living_files: HashSet<PathBuf> = HashSet::new();
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(!managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path2).unwrap());
managed_directory.garbage_collect(|| living_files);
assert!(!managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2));
}
}
@@ -378,67 +304,31 @@ mod tests_mmap_specific {
fn test_managed_directory_gc_while_mmapped() {
let test_path1: &'static Path = Path::new("some_path_for_test");
let tempdir = TempDir::new().unwrap();
let tempdir = TempDir::new("index").unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let living_files = HashSet::new();
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let mut write = managed_directory.open_write(test_path1).unwrap();
write.write_all(&[0u8, 1u8]).unwrap();
write.terminate().unwrap();
assert!(managed_directory.exists(test_path1).unwrap());
managed_directory
.atomic_write(test_path1, &vec![0u8, 1u8])
.unwrap();
assert!(managed_directory.exists(test_path1));
let _mmap_read = managed_directory.open_read(test_path1).unwrap();
assert!(managed_directory
.garbage_collect(|| living_files.clone())
.is_ok());
managed_directory.garbage_collect(|| living_files.clone());
if cfg!(target_os = "windows") {
// On Windows, gc should try and fail the file as it is mmapped.
assert!(managed_directory.exists(test_path1).unwrap());
assert!(managed_directory.exists(test_path1));
// unmap should happen here.
drop(_mmap_read);
// The file should still be in the list of managed file and
// eventually be deleted once mmap is released.
assert!(managed_directory.garbage_collect(|| living_files).is_ok());
assert!(!managed_directory.exists(test_path1).unwrap());
managed_directory.garbage_collect(|| living_files);
assert!(!managed_directory.exists(test_path1));
} else {
assert!(!managed_directory.exists(test_path1).unwrap());
assert!(!managed_directory.exists(test_path1));
}
}
#[test]
fn test_checksum() -> crate::Result<()> {
let test_path1: &'static Path = Path::new("some_path_for_test");
let test_path2: &'static Path = Path::new("other_test_path");
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let mmap_directory = MmapDirectory::open(&tempdir_path)?;
let managed_directory = ManagedDirectory::wrap(mmap_directory)?;
let mut write = managed_directory.open_write(test_path1)?;
write.write_all(&[0u8, 1u8])?;
write.terminate()?;
let mut write = managed_directory.open_write(test_path2)?;
write.write_all(&[3u8, 4u8, 5u8])?;
write.terminate()?;
let read_file = managed_directory.open_read(test_path2)?.read_bytes()?;
assert_eq!(read_file.as_slice(), &[3u8, 4u8, 5u8]);
assert!(managed_directory.list_damaged().unwrap().is_empty());
let mut corrupted_path = tempdir_path.clone();
corrupted_path.push(test_path2);
let mut file = OpenOptions::new().write(true).open(&corrupted_path)?;
file.write_all(&[255u8])?;
file.flush()?;
drop(file);
let damaged = managed_directory.list_damaged()?;
assert_eq!(damaged.len(), 1);
assert!(damaged.contains(test_path2));
Ok(())
}
}

323
src/directory/mmap_directory.rs
View File

@@ -1,20 +1,27 @@
use fs2;
use notify;
use self::fs2::FileExt;
use self::notify::RawEvent;
use self::notify::RecursiveMode;
use self::notify::Watcher;
use crate::core::META_FILEPATH;
use crate::directory::error::LockError;
use crate::directory::error::{DeleteError, OpenDirectoryError, OpenReadError, OpenWriteError};
use crate::directory::file_watcher::FileWatcher;
use crate::directory::AntiCallToken;
use crate::directory::BoxedData;
use crate::directory::error::{
DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
};
use crate::directory::read_only_source::BoxedData;
use crate::directory::Directory;
use crate::directory::DirectoryLock;
use crate::directory::FileSlice;
use crate::directory::Lock;
use crate::directory::ReadOnlySource;
use crate::directory::WatchCallback;
use crate::directory::WatchCallbackList;
use crate::directory::WatchHandle;
use crate::directory::{TerminatingWrite, WritePtr};
use fs2::FileExt;
use crate::directory::WritePtr;
use atomicwrites;
use memmap::Mmap;
use serde::{Deserialize, Serialize};
use stable_deref_trait::StableDeref;
use std::collections::HashMap;
use std::convert::From;
use std::fmt;
use std::fs::OpenOptions;
@@ -23,11 +30,13 @@ use std::io::{self, Seek, SeekFrom};
use std::io::{BufWriter, Read, Write};
use std::path::{Path, PathBuf};
use std::result;
use std::sync::mpsc::{channel, Receiver, Sender};
use std::sync::Arc;
use std::sync::Mutex;
use std::sync::RwLock;
use std::sync::Weak;
use std::{collections::HashMap, ops::Deref};
use tempfile::TempDir;
use std::thread;
use tempdir::TempDir;
/// Create a default io error given a string.
pub(crate) fn make_io_err(msg: String) -> io::Error {
@@ -37,17 +46,17 @@ pub(crate) fn make_io_err(msg: String) -> io::Error {
/// Returns None iff the file exists, can be read, but is empty (and hence
/// cannot be mmapped)
fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
let file = File::open(full_path).map_err(|io_err| {
if io_err.kind() == io::ErrorKind::NotFound {
OpenReadError::FileDoesNotExist(full_path.to_path_buf())
let file = File::open(full_path).map_err(|e| {
if e.kind() == io::ErrorKind::NotFound {
OpenReadError::FileDoesNotExist(full_path.to_owned())
} else {
OpenReadError::wrap_io_error(io_err, full_path.to_path_buf())
OpenReadError::IOError(IOError::with_path(full_path.to_owned(), e))
}
})?;
let meta_data = file
.metadata()
.map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_owned()))?;
.map_err(|e| IOError::with_path(full_path.to_owned(), e))?;
if meta_data.len() == 0 {
// if the file size is 0, it will not be possible
// to mmap the file, so we return None
@@ -57,7 +66,7 @@ fn open_mmap(full_path: &Path) -> result::Result<Option<Mmap>, OpenReadError> {
unsafe {
memmap::Mmap::map(&file)
.map(Some)
.map_err(|io_err| OpenReadError::wrap_io_error(io_err, full_path.to_path_buf()))
.map_err(|e| From::from(IOError::with_path(full_path.to_owned(), e)))
}
}
@@ -121,13 +130,83 @@ impl MmapCache {
}
self.cache.remove(full_path);
self.counters.miss += 1;
let mmap_opt = open_mmap(full_path)?;
Ok(mmap_opt.map(|mmap| {
Ok(if let Some(mmap) = open_mmap(full_path)? {
let mmap_arc: Arc<BoxedData> = Arc::new(Box::new(mmap));
let mmap_weak = Arc::downgrade(&mmap_arc);
self.cache.insert(full_path.to_owned(), mmap_weak);
mmap_arc
}))
Some(mmap_arc)
} else {
None
})
}
}
struct InnerWatcherWrapper {
_watcher: Mutex<notify::RecommendedWatcher>,
watcher_router: WatchCallbackList,
}
impl InnerWatcherWrapper {
pub fn new(path: &Path) -> Result<(Self, Receiver<notify::RawEvent>), notify::Error> {
let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel();
// We need to initialize the
let mut watcher = notify::raw_watcher(tx)?;
watcher.watch(path, RecursiveMode::Recursive)?;
let inner = InnerWatcherWrapper {
_watcher: Mutex::new(watcher),
watcher_router: Default::default(),
};
Ok((inner, watcher_recv))
}
}
#[derive(Clone)]
struct WatcherWrapper {
inner: Arc<InnerWatcherWrapper>,
}
impl WatcherWrapper {
pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
let (inner, watcher_recv) = InnerWatcherWrapper::new(path).map_err(|err| match err {
notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()),
_ => {
panic!("Unknown error while starting watching directory {:?}", path);
}
})?;
let watcher_wrapper = WatcherWrapper {
inner: Arc::new(inner),
};
let watcher_wrapper_clone = watcher_wrapper.clone();
thread::Builder::new()
.name("meta-file-watch-thread".to_string())
.spawn(move || {
loop {
match watcher_recv.recv().map(|evt| evt.path) {
Ok(Some(changed_path)) => {
// ... Actually subject to false positive.
// We might want to be more accurate than this at one point.
if let Some(filename) = changed_path.file_name() {
if filename == *META_FILEPATH {
watcher_wrapper_clone.inner.watcher_router.broadcast();
}
}
}
Ok(None) => {
// not an event we are interested in.
}
Err(_e) => {
// the watch send channel was dropped
break;
}
}
}
})
.expect("Failed to spawn thread to watch meta.json");
Ok(watcher_wrapper)
}
pub fn watch(&mut self, watch_callback: WatchCallback) -> WatchHandle {
self.inner.watcher_router.subscribe(watch_callback)
}
}
@@ -152,21 +231,44 @@ struct MmapDirectoryInner {
root_path: PathBuf,
mmap_cache: RwLock<MmapCache>,
_temp_directory: Option<TempDir>,
watcher: FileWatcher,
watcher: RwLock<Option<WatcherWrapper>>,
}
impl MmapDirectoryInner {
fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectoryInner {
MmapDirectoryInner {
fn new(
root_path: PathBuf,
temp_directory: Option<TempDir>,
) -> Result<MmapDirectoryInner, OpenDirectoryError> {
let mmap_directory_inner = MmapDirectoryInner {
root_path,
mmap_cache: Default::default(),
_temp_directory: temp_directory,
watcher: FileWatcher::new(&root_path.join(*META_FILEPATH)),
root_path: root_path,
}
watcher: RwLock::new(None),
};
Ok(mmap_directory_inner)
}
fn watch(&self, callback: WatchCallback) -> crate::Result<WatchHandle> {
Ok(self.watcher.watch(callback))
fn watch(&self, watch_callback: WatchCallback) -> crate::Result<WatchHandle> {
// a lot of juggling here, to ensure we don't do anything that panics
// while the rwlock is held. That way we ensure that the rwlock cannot
// be poisoned.
//
// The downside is that we might create a watch wrapper that is not useful.
let need_initialization = self.watcher.read().unwrap().is_none();
if need_initialization {
let watch_wrapper = WatcherWrapper::new(&self.root_path)?;
let mut watch_wlock = self.watcher.write().unwrap();
// the watcher could have been initialized when we released the lock, and
// we do not want to lose the watched files that were set.
if watch_wlock.is_none() {
*watch_wlock = Some(watch_wrapper);
}
}
if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() {
return Ok(watch_wrapper.watch(watch_callback));
} else {
unreachable!("At this point, watch wrapper is supposed to be initialized");
}
}
}
@@ -177,11 +279,14 @@ impl fmt::Debug for MmapDirectory {
}
impl MmapDirectory {
fn new(root_path: PathBuf, temp_directory: Option<TempDir>) -> MmapDirectory {
let inner = MmapDirectoryInner::new(root_path, temp_directory);
MmapDirectory {
fn new(
root_path: PathBuf,
temp_directory: Option<TempDir>,
) -> Result<MmapDirectory, OpenDirectoryError> {
let inner = MmapDirectoryInner::new(root_path, temp_directory)?;
Ok(MmapDirectory {
inner: Arc::new(inner),
}
})
}
/// Creates a new MmapDirectory in a temporary directory.
@@ -189,11 +294,9 @@ impl MmapDirectory {
/// This is mostly useful to test the MmapDirectory itself.
/// For your unit tests, prefer the RAMDirectory.
pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> {
let tempdir = TempDir::new().map_err(OpenDirectoryError::FailedToCreateTempDir)?;
Ok(MmapDirectory::new(
tempdir.path().to_path_buf(),
Some(tempdir),
))
let tempdir = TempDir::new("index").map_err(OpenDirectoryError::IoError)?;
let tempdir_path = PathBuf::from(tempdir.path());
MmapDirectory::new(tempdir_path, Some(tempdir))
}
/// Opens a MmapDirectory in a directory.
@@ -211,7 +314,7 @@ impl MmapDirectory {
directory_path,
)))
} else {
Ok(MmapDirectory::new(PathBuf::from(directory_path), None))
Ok(MmapDirectory::new(PathBuf::from(directory_path), None)?)
}
}
@@ -309,44 +412,8 @@ impl Seek for SafeFileWriter {
}
}
impl TerminatingWrite for SafeFileWriter {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
#[derive(Clone)]
struct MmapArc(Arc<Box<dyn Deref<Target = [u8]> + Send + Sync>>);
impl Deref for MmapArc {
type Target = [u8];
fn deref(&self) -> &[u8] {
self.0.deref()
}
}
unsafe impl StableDeref for MmapArc {}
/// Writes a file in an atomic manner.
pub(crate) fn atomic_write(path: &Path, content: &[u8]) -> io::Result<()> {
// We create the temporary file in the same directory as the target file.
// Indeed the canonical temp directory and the target file might sit in different
// filesystem, in which case the atomic write may actually not work.
let parent_path = path.parent().ok_or_else(|| {
io::Error::new(
io::ErrorKind::InvalidInput,
"Path {:?} does not have parent directory.",
)
})?;
let mut tempfile = tempfile::Builder::new().tempfile_in(&parent_path)?;
tempfile.write_all(content)?;
tempfile.flush()?;
tempfile.into_temp_path().persist(path)?;
Ok(())
}
impl Directory for MmapDirectory {
fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
debug!("Open Read {:?}", path);
let full_path = self.resolve_path(path);
@@ -356,14 +423,12 @@ impl Directory for MmapDirectory {
on mmap cache while reading {:?}",
path
);
let io_err = make_io_err(msg);
OpenReadError::wrap_io_error(io_err, path.to_path_buf())
IOError::with_path(path.to_owned(), make_io_err(msg))
})?;
if let Some(mmap_arc) = mmap_cache.get_mmap(&full_path)? {
Ok(FileSlice::from(MmapArc(mmap_arc)))
} else {
Ok(FileSlice::empty())
}
Ok(mmap_cache
.get_mmap(&full_path)?
.map(ReadOnlySource::from)
.unwrap_or_else(ReadOnlySource::empty))
}
/// Any entry associated to the path in the mmap will be
@@ -371,29 +436,25 @@ impl Directory for MmapDirectory {
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
let full_path = self.resolve_path(path);
match fs::remove_file(&full_path) {
Ok(_) => self.sync_directory().map_err(|e| DeleteError::IOError {
io_error: e,
filepath: path.to_path_buf(),
}),
Ok(_) => self
.sync_directory()
.map_err(|e| IOError::with_path(path.to_owned(), e).into()),
Err(e) => {
if e.kind() == io::ErrorKind::NotFound {
Err(DeleteError::FileDoesNotExist(path.to_owned()))
} else {
Err(DeleteError::IOError {
io_error: e,
filepath: path.to_path_buf(),
})
Err(IOError::with_path(path.to_owned(), e).into())
}
}
}
}
fn exists(&self, path: &Path) -> Result<bool, OpenReadError> {
fn exists(&self, path: &Path) -> bool {
let full_path = self.resolve_path(path);
Ok(full_path.exists())
full_path.exists()
}
fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
debug!("Open Write {:?}", path);
let full_path = self.resolve_path(path);
@@ -402,22 +463,22 @@ impl Directory for MmapDirectory {
.create_new(true)
.open(full_path);
let mut file = open_res.map_err(|io_err| {
if io_err.kind() == io::ErrorKind::AlreadyExists {
OpenWriteError::FileAlreadyExists(path.to_path_buf())
let mut file = open_res.map_err(|err| {
if err.kind() == io::ErrorKind::AlreadyExists {
OpenWriteError::FileAlreadyExists(path.to_owned())
} else {
OpenWriteError::wrap_io_error(io_err, path.to_path_buf())
IOError::with_path(path.to_owned(), err).into()
}
})?;
// making sure the file is created.
file.flush()
.map_err(|io_error| OpenWriteError::wrap_io_error(io_error, path.to_path_buf()))?;
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
// Apparetntly, on some filesystem syncing the parent
// directory is required.
self.sync_directory()
.map_err(|io_err| OpenWriteError::wrap_io_error(io_err, path.to_path_buf()))?;
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
let writer = SafeFileWriter::new(file);
Ok(BufWriter::new(Box::new(writer)))
@@ -428,25 +489,26 @@ impl Directory for MmapDirectory {
let mut buffer = Vec::new();
match File::open(&full_path) {
Ok(mut file) => {
file.read_to_end(&mut buffer).map_err(|io_error| {
OpenReadError::wrap_io_error(io_error, path.to_path_buf())
})?;
file.read_to_end(&mut buffer)
.map_err(|e| IOError::with_path(path.to_owned(), e))?;
Ok(buffer)
}
Err(io_error) => {
if io_error.kind() == io::ErrorKind::NotFound {
Err(e) => {
if e.kind() == io::ErrorKind::NotFound {
Err(OpenReadError::FileDoesNotExist(path.to_owned()))
} else {
Err(OpenReadError::wrap_io_error(io_error, path.to_path_buf()))
Err(IOError::with_path(path.to_owned(), e).into())
}
}
}
}
fn atomic_write(&self, path: &Path, content: &[u8]) -> io::Result<()> {
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
debug!("Atomic Write {:?}", path);
let full_path = self.resolve_path(path);
atomic_write(&full_path, content)
let meta_file = atomicwrites::AtomicFile::new(full_path, atomicwrites::AllowOverwrite);
meta_file.write(|f| f.write_all(data))?;
Ok(())
}
fn acquire_lock(&self, lock: &Lock) -> Result<DirectoryLock, LockError> {
@@ -484,10 +546,13 @@ mod tests {
use crate::schema::{Schema, SchemaBuilder, TEXT};
use crate::Index;
use crate::ReloadPolicy;
use crate::{common::HasLen, indexer::LogMergePolicy};
use std::fs;
use std::sync::atomic::{AtomicUsize, Ordering};
use std::thread;
use std::time::Duration;
#[test]
fn test_open_non_existent_path() {
fn test_open_non_existant_path() {
assert!(MmapDirectory::open(PathBuf::from("./nowhere")).is_err());
}
@@ -497,7 +562,7 @@ mod tests {
// cannot be mmapped.
//
// In that case the directory returns a SharedVecSlice.
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let path = PathBuf::from("test");
{
let mut w = mmap_directory.open_write(&path).unwrap();
@@ -513,7 +578,7 @@ mod tests {
// here we test if the cache releases
// mmaps correctly.
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let num_paths = 10;
let paths: Vec<PathBuf> = (0..num_paths)
.map(|i| PathBuf::from(&*format!("file_{}", i)))
@@ -573,48 +638,56 @@ mod tests {
assert_eq!(mmap_directory.get_cache_info().mmapped.len(), 0);
}
#[test]
fn test_watch_wrapper() {
let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone();
let tmp_dir: TempDir = tempdir::TempDir::new("test_watch_wrapper").unwrap();
let tmp_dirpath = tmp_dir.path().to_owned();
let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath).unwrap();
let tmp_file = tmp_dirpath.join("coucou");
let _handle = watch_wrapper.watch(Box::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
}));
assert_eq!(counter.load(Ordering::SeqCst), 0);
fs::write(&tmp_file, b"whateverwilldo").unwrap();
thread::sleep(Duration::new(0, 1_000u32));
}
#[test]
fn test_mmap_released() {
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
let mut schema_builder: SchemaBuilder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
{
let index = Index::create(mmap_directory.clone(), schema).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let mut log_merge_policy = LogMergePolicy::default();
log_merge_policy.set_min_merge_size(3);
index_writer.set_merge_policy(Box::new(log_merge_policy));
for _num_commits in 0..10 {
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for _num_commits in 0..16 {
for _ in 0..10 {
index_writer.add_document(doc!(text_field=>"abc"));
}
index_writer.commit().unwrap();
}
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
for _ in 0..4 {
for _ in 0..30 {
index_writer.add_document(doc!(text_field=>"abc"));
index_writer.commit().unwrap();
reader.reload().unwrap();
}
index_writer.wait_merging_threads().unwrap();
reader.reload().unwrap();
let num_segments = reader.searcher().segment_readers().len();
assert!(num_segments <= 4);
assert_eq!(num_segments, 4);
assert_eq!(
num_segments * 7,
mmap_directory.get_cache_info().mmapped.len()
);
}
assert!(mmap_directory.get_cache_info().mmapped.is_empty());
assert_eq!(mmap_directory.get_cache_info().mmapped.len(), 0);
}
}

72
src/directory/mod.rs
View File

@@ -9,12 +9,9 @@ mod mmap_directory;
mod directory;
mod directory_lock;
mod file_slice;
mod file_watcher;
mod footer;
mod managed_directory;
mod owned_bytes;
mod ram_directory;
mod read_only_source;
mod watch_event_router;
/// Errors specific to the directory module.
@@ -23,79 +20,22 @@ pub mod error;
pub use self::directory::DirectoryLock;
pub use self::directory::{Directory, DirectoryClone};
pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
pub(crate) use self::file_slice::BoxedData;
pub use self::file_slice::{FileHandle, FileSlice};
pub use self::owned_bytes::OwnedBytes;
pub use self::ram_directory::RAMDirectory;
pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};
use std::io::{self, BufWriter, Write};
use std::path::PathBuf;
/// Outcome of the Garbage collection
pub struct GarbageCollectionResult {
/// List of files that were deleted in this cycle
pub deleted_files: Vec<PathBuf>,
/// List of files that were schedule to be deleted in this cycle,
/// but deletion did not work. This typically happens on windows,
/// as deleting a memory mapped file is forbidden.
///
/// If a searcher is still held, a file cannot be deleted.
/// This is not considered a bug, the file will simply be deleted
/// in the next GC.
pub failed_to_delete_files: Vec<PathBuf>,
}
pub use self::read_only_source::ReadOnlySource;
pub(crate) use self::watch_event_router::WatchCallbackList;
pub use self::watch_event_router::{WatchCallback, WatchHandle};
use std::io::{BufWriter, Write};
#[cfg(feature = "mmap")]
pub use self::mmap_directory::MmapDirectory;
pub use self::managed_directory::ManagedDirectory;
/// Struct used to prevent from calling [`terminate_ref`](trait.TerminatingWrite#method.terminate_ref) directly
///
/// The point is that while the type is public, it cannot be built by anyone
/// outside of this module.
pub struct AntiCallToken(());
/// Trait used to indicate when no more write need to be done on a writer
pub trait TerminatingWrite: Write {
/// Indicate that the writer will no longer be used. Internally call terminate_ref.
fn terminate(mut self) -> io::Result<()>
where
Self: Sized,
{
self.terminate_ref(AntiCallToken(()))
}
/// You should implement this function to define custom behavior.
/// This function should flush any buffer it may hold.
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()>;
}
impl<W: TerminatingWrite + ?Sized> TerminatingWrite for Box<W> {
fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
self.as_mut().terminate_ref(token)
}
}
impl<W: TerminatingWrite> TerminatingWrite for BufWriter<W> {
fn terminate_ref(&mut self, a: AntiCallToken) -> io::Result<()> {
self.flush()?;
self.get_mut().terminate_ref(a)
}
}
#[cfg(test)]
impl<'a> TerminatingWrite for &'a mut Vec<u8> {
fn terminate_ref(&mut self, _a: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
/// Write object for Directory.
///
/// `WritePtr` are required to implement both Write
/// and Seek.
pub type WritePtr = BufWriter<Box<dyn TerminatingWrite>>;
pub type WritePtr = BufWriter<Box<dyn Write>>;
#[cfg(test)]
mod tests;

255
src/directory/owned_bytes.rs
View File

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

99
src/directory/ram_directory.rs
View File

@@ -1,9 +1,8 @@
use crate::core::META_FILEPATH;
use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
use crate::directory::AntiCallToken;
use crate::directory::WatchCallbackList;
use crate::directory::{Directory, FileSlice, WatchCallback, WatchHandle};
use crate::directory::{TerminatingWrite, WritePtr};
use crate::{common::HasLen, core::META_FILEPATH};
use crate::directory::WritePtr;
use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
use fail::fail_point;
use std::collections::HashMap;
use std::fmt;
@@ -72,25 +71,19 @@ impl Write for VecWriter {
}
}
impl TerminatingWrite for VecWriter {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
#[derive(Default)]
struct InnerDirectory {
fs: HashMap<PathBuf, FileSlice>,
fs: HashMap<PathBuf, ReadOnlySource>,
watch_router: WatchCallbackList,
}
impl InnerDirectory {
fn write(&mut self, path: PathBuf, data: &[u8]) -> bool {
let data = FileSlice::from(data.to_vec());
let data = ReadOnlySource::new(Vec::from(data));
self.fs.insert(path, data).is_some()
}
fn open_read(&self, path: &Path) -> Result<FileSlice, OpenReadError> {
fn open_read(&self, path: &Path) -> Result<ReadOnlySource, OpenReadError> {
self.fs
.get(path)
.ok_or_else(|| OpenReadError::FileDoesNotExist(PathBuf::from(path)))
@@ -144,51 +137,27 @@ impl RAMDirectory {
pub fn total_mem_usage(&self) -> usize {
self.fs.read().unwrap().total_mem_usage()
}
/// Write a copy of all of the files saved in the RAMDirectory in the target `Directory`.
///
/// Files are all written using the `Directory::write` meaning, even if they were
/// written using the `atomic_write` api.
///
/// If an error is encounterred, files may be persisted partially.
pub fn persist(&self, dest: &dyn Directory) -> crate::Result<()> {
let wlock = self.fs.write().unwrap();
for (path, file) in wlock.fs.iter() {
let mut dest_wrt = dest.open_write(path)?;
dest_wrt.write_all(file.read_bytes()?.as_slice())?;
dest_wrt.terminate()?;
}
Ok(())
}
}
impl Directory for RAMDirectory {
fn open_read(&self, path: &Path) -> result::Result<FileSlice, OpenReadError> {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
self.fs.read().unwrap().open_read(path)
}
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
fail_point!("RAMDirectory::delete", |_| {
Err(DeleteError::IOError {
io_error: io::Error::from(io::ErrorKind::Other),
filepath: path.to_path_buf(),
})
use crate::directory::error::IOError;
let io_error = IOError::from(io::Error::from(io::ErrorKind::Other));
Err(DeleteError::from(io_error))
});
self.fs.write().unwrap().delete(path)
}
fn exists(&self, path: &Path) -> Result<bool, OpenReadError> {
Ok(self
.fs
.read()
.map_err(|e| OpenReadError::IOError {
io_error: io::Error::new(io::ErrorKind::Other, e.to_string()),
filepath: path.to_path_buf(),
})?
.exists(path))
fn exists(&self, path: &Path) -> bool {
self.fs.read().unwrap().exists(path)
}
fn open_write(&self, path: &Path) -> Result<WritePtr, OpenWriteError> {
fn open_write(&mut self, path: &Path) -> Result<WritePtr, OpenWriteError> {
let mut fs = self.fs.write().unwrap();
let path_buf = PathBuf::from(path);
let vec_writer = VecWriter::new(path_buf.clone(), self.clone());
@@ -202,31 +171,24 @@ impl Directory for RAMDirectory {
}
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError> {
let bytes =
self.open_read(path)?
.read_bytes()
.map_err(|io_error| OpenReadError::IOError {
io_error,
filepath: path.to_path_buf(),
})?;
Ok(bytes.as_slice().to_owned())
Ok(self.open_read(path)?.as_slice().to_owned())
}
fn atomic_write(&self, path: &Path, data: &[u8]) -> io::Result<()> {
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
io::ErrorKind::Other,
msg.unwrap_or_else(|| "Undefined".to_string())
msg.unwrap_or("Undefined".to_string())
)));
let path_buf = PathBuf::from(path);
// Reserve the path to prevent calls to .write() to succeed.
self.fs.write().unwrap().write(path_buf.clone(), &[]);
let mut vec_writer = VecWriter::new(path_buf, self.clone());
let mut vec_writer = VecWriter::new(path_buf.clone(), self.clone());
vec_writer.write_all(data)?;
vec_writer.flush()?;
if path == Path::new(&*META_FILEPATH) {
let _ = self.fs.write().unwrap().watch_router.broadcast();
self.fs.write().unwrap().watch_router.broadcast();
}
Ok(())
}
@@ -235,28 +197,3 @@ impl Directory for RAMDirectory {
Ok(self.fs.write().unwrap().watch(watch_callback))
}
}
#[cfg(test)]
mod tests {
use super::RAMDirectory;
use crate::Directory;
use std::io::Write;
use std::path::Path;
#[test]
fn test_persist() {
let msg_atomic: &'static [u8] = b"atomic is the way";
let msg_seq: &'static [u8] = b"sequential is the way";
let path_atomic: &'static Path = Path::new("atomic");
let path_seq: &'static Path = Path::new("seq");
let directory = RAMDirectory::create();
assert!(directory.atomic_write(path_atomic, msg_atomic).is_ok());
let mut wrt = directory.open_write(path_seq).unwrap();
assert!(wrt.write_all(msg_seq).is_ok());
assert!(wrt.flush().is_ok());
let directory_copy = RAMDirectory::create();
assert!(directory.persist(&directory_copy).is_ok());
assert_eq!(directory_copy.atomic_read(path_atomic).unwrap(), msg_atomic);
assert_eq!(directory_copy.atomic_read(path_seq).unwrap(), msg_seq);
}
}

131
src/directory/read_only_source.rs Normal file
View File

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

268
src/directory/tests.rs
View File

@@ -1,182 +1,93 @@
use super::*;
use futures::channel::oneshot;
use futures::executor::block_on;
use std::io::Write;
use std::mem;
use std::path::{Path, PathBuf};
use std::sync::atomic::Ordering::SeqCst;
use std::sync::atomic::{AtomicBool, AtomicUsize};
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering;
use std::sync::Arc;
use std::thread;
use std::time;
use std::time::Duration;
#[cfg(feature = "mmap")]
mod mmap_directory_tests {
use crate::directory::MmapDirectory;
type DirectoryImpl = MmapDirectory;
fn make_directory() -> DirectoryImpl {
MmapDirectory::create_from_tempdir().unwrap()
}
#[test]
fn test_simple() -> crate::Result<()> {
let directory = make_directory();
super::test_simple(&directory)
}
#[test]
fn test_write_create_the_file() {
let directory = make_directory();
super::test_write_create_the_file(&directory);
}
#[test]
fn test_rewrite_forbidden() -> crate::Result<()> {
let directory = make_directory();
super::test_rewrite_forbidden(&directory)?;
Ok(())
}
#[test]
fn test_directory_delete() -> crate::Result<()> {
let directory = make_directory();
super::test_directory_delete(&directory)?;
Ok(())
}
#[test]
fn test_lock_non_blocking() {
let directory = make_directory();
super::test_lock_non_blocking(&directory);
}
#[test]
fn test_lock_blocking() {
let directory = make_directory();
super::test_lock_blocking(&directory);
}
#[test]
fn test_watch() {
let directory = make_directory();
super::test_watch(&directory);
}
#[test]
fn test_ram_directory() {
let mut ram_directory = RAMDirectory::create();
test_directory(&mut ram_directory);
}
mod ram_directory_tests {
use crate::directory::RAMDirectory;
type DirectoryImpl = RAMDirectory;
fn make_directory() -> DirectoryImpl {
RAMDirectory::default()
}
#[test]
fn test_simple() -> crate::Result<()> {
let directory = make_directory();
super::test_simple(&directory)
}
#[test]
fn test_write_create_the_file() {
let directory = make_directory();
super::test_write_create_the_file(&directory);
}
#[test]
fn test_rewrite_forbidden() -> crate::Result<()> {
let directory = make_directory();
super::test_rewrite_forbidden(&directory)?;
Ok(())
}
#[test]
fn test_directory_delete() -> crate::Result<()> {
let directory = make_directory();
super::test_directory_delete(&directory)?;
Ok(())
}
#[test]
fn test_lock_non_blocking() {
let directory = make_directory();
super::test_lock_non_blocking(&directory);
}
#[test]
fn test_lock_blocking() {
let directory = make_directory();
super::test_lock_blocking(&directory);
}
#[test]
fn test_watch() {
let directory = make_directory();
super::test_watch(&directory);
}
#[test]
#[cfg(feature = "mmap")]
fn test_mmap_directory() {
let mut mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
test_directory(&mut mmap_directory);
}
#[test]
#[should_panic]
fn ram_directory_panics_if_flush_forgotten() {
let test_path: &'static Path = Path::new("some_path_for_test");
let ram_directory = RAMDirectory::create();
let mut ram_directory = RAMDirectory::create();
let mut write_file = ram_directory.open_write(test_path).unwrap();
assert!(write_file.write_all(&[4]).is_ok());
}
fn test_simple(directory: &dyn Directory) -> crate::Result<()> {
fn test_simple(directory: &mut dyn Directory) {
let test_path: &'static Path = Path::new("some_path_for_test");
let mut write_file = directory.open_write(test_path)?;
assert!(directory.exists(test_path).unwrap());
write_file.write_all(&[4])?;
write_file.write_all(&[3])?;
write_file.write_all(&[7, 3, 5])?;
write_file.flush()?;
let read_file = directory.open_read(test_path)?.read_bytes()?;
assert_eq!(read_file.as_slice(), &[4u8, 3u8, 7u8, 3u8, 5u8]);
mem::drop(read_file);
{
let mut write_file = directory.open_write(test_path).unwrap();
assert!(directory.exists(test_path));
write_file.write_all(&[4]).unwrap();
write_file.write_all(&[3]).unwrap();
write_file.write_all(&[7, 3, 5]).unwrap();
write_file.flush().unwrap();
}
{
let read_file = directory.open_read(test_path).unwrap();
let data: &[u8] = &*read_file;
assert_eq!(data, &[4u8, 3u8, 7u8, 3u8, 5u8]);
}
assert!(directory.delete(test_path).is_ok());
assert!(!directory.exists(test_path).unwrap());
Ok(())
assert!(!directory.exists(test_path));
}
fn test_rewrite_forbidden(directory: &dyn Directory) -> crate::Result<()> {
fn test_rewrite_forbidden(directory: &mut dyn Directory) {
let test_path: &'static Path = Path::new("some_path_for_test");
directory.open_write(test_path)?;
assert!(directory.exists(test_path).unwrap());
assert!(directory.open_write(test_path).is_err());
{
directory.open_write(test_path).unwrap();
assert!(directory.exists(test_path));
}
{
assert!(directory.open_write(test_path).is_err());
}
assert!(directory.delete(test_path).is_ok());
Ok(())
}
fn test_write_create_the_file(directory: &dyn Directory) {
fn test_write_create_the_file(directory: &mut dyn Directory) {
let test_path: &'static Path = Path::new("some_path_for_test");
{
assert!(directory.open_read(test_path).is_err());
let _w = directory.open_write(test_path).unwrap();
assert!(directory.exists(test_path).unwrap());
assert!(directory.exists(test_path));
assert!(directory.open_read(test_path).is_ok());
assert!(directory.delete(test_path).is_ok());
}
}
fn test_directory_delete(directory: &dyn Directory) -> crate::Result<()> {
fn test_directory_delete(directory: &mut dyn Directory) {
let test_path: &'static Path = Path::new("some_path_for_test");
assert!(directory.open_read(test_path).is_err());
let mut write_file = directory.open_write(&test_path)?;
write_file.write_all(&[1, 2, 3, 4])?;
write_file.flush()?;
let mut write_file = directory.open_write(&test_path).unwrap();
write_file.write_all(&[1, 2, 3, 4]).unwrap();
write_file.flush().unwrap();
{
let read_handle = directory.open_read(&test_path)?.read_bytes()?;
assert_eq!(read_handle.as_slice(), &[1u8, 2u8, 3u8, 4u8]);
let read_handle = directory.open_read(&test_path).unwrap();
assert_eq!(&*read_handle, &[1u8, 2u8, 3u8, 4u8]);
// Mapped files can't be deleted on Windows
if !cfg!(windows) {
assert!(directory.delete(&test_path).is_ok());
assert_eq!(read_handle.as_slice(), &[1u8, 2u8, 3u8, 4u8]);
assert_eq!(&*read_handle, &[1u8, 2u8, 3u8, 4u8]);
}
assert!(directory.delete(Path::new("SomeOtherPath")).is_err());
}
@@ -186,40 +97,53 @@ fn test_directory_delete(directory: &dyn Directory) -> crate::Result<()> {
assert!(directory.open_read(&test_path).is_err());
assert!(directory.delete(&test_path).is_err());
Ok(())
}
fn test_watch(directory: &dyn Directory) {
fn test_directory(directory: &mut dyn Directory) {
test_simple(directory);
test_rewrite_forbidden(directory);
test_write_create_the_file(directory);
test_directory_delete(directory);
test_lock_non_blocking(directory);
test_lock_blocking(directory);
test_watch(directory);
}
fn test_watch(directory: &mut dyn Directory) {
let counter: Arc<AtomicUsize> = Default::default();
let (tx, rx) = crossbeam::channel::unbounded();
let timeout = Duration::from_millis(500);
let handle = directory
.watch(WatchCallback::new(move || {
let val = counter.fetch_add(1, SeqCst);
tx.send(val + 1).unwrap();
}))
.unwrap();
let counter_clone = counter.clone();
let watch_callback = Box::new(move || {
counter_clone.fetch_add(1, Ordering::SeqCst);
});
assert!(directory
.atomic_write(Path::new("meta.json"), b"foo")
.atomic_write(Path::new("meta.json"), b"random_test_data")
.is_ok());
assert_eq!(rx.recv_timeout(timeout), Ok(1));
thread::sleep(Duration::new(0, 10_000));
assert_eq!(0, counter.load(Ordering::SeqCst));
let watch_handle = directory.watch(watch_callback).unwrap();
for i in 0..10 {
assert_eq!(i, counter.load(Ordering::SeqCst));
assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data_2")
.is_ok());
for _ in 0..100 {
if counter.load(Ordering::SeqCst) > i {
break;
}
thread::sleep(Duration::from_millis(10));
}
assert_eq!(i + 1, counter.load(Ordering::SeqCst));
}
mem::drop(watch_handle);
assert!(directory
.atomic_write(Path::new("meta.json"), b"bar")
.atomic_write(Path::new("meta.json"), b"random_test_data")
.is_ok());
assert_eq!(rx.recv_timeout(timeout), Ok(2));
mem::drop(handle);
assert!(directory
.atomic_write(Path::new("meta.json"), b"qux")
.is_ok());
assert!(rx.recv_timeout(timeout).is_err());
thread::sleep(Duration::from_millis(200));
assert_eq!(10, counter.load(Ordering::SeqCst));
}
fn test_lock_non_blocking(directory: &dyn Directory) {
fn test_lock_non_blocking(directory: &mut dyn Directory) {
{
let lock_a_res = directory.acquire_lock(&Lock {
filepath: PathBuf::from("a.lock"),
@@ -244,19 +168,15 @@ fn test_lock_non_blocking(directory: &dyn Directory) {
assert!(lock_a_res.is_ok());
}
fn test_lock_blocking(directory: &dyn Directory) {
fn test_lock_blocking(directory: &mut dyn Directory) {
let lock_a_res = directory.acquire_lock(&Lock {
filepath: PathBuf::from("a.lock"),
is_blocking: true,
});
assert!(lock_a_res.is_ok());
let in_thread = Arc::new(AtomicBool::default());
let in_thread_clone = in_thread.clone();
let (sender, receiver) = oneshot::channel();
std::thread::spawn(move || {
//< lock_a_res is sent to the thread.
in_thread_clone.store(true, SeqCst);
let _just_sync = block_on(receiver);
std::thread::sleep(time::Duration::from_millis(10));
// explicitely droping lock_a_res. It would have been sufficient to just force it
// to be part of the move, but the intent seems clearer that way.
drop(lock_a_res);
@@ -269,18 +189,14 @@ fn test_lock_blocking(directory: &dyn Directory) {
});
assert!(lock_a_res.is_err());
}
let directory_clone = directory.box_clone();
let (sender2, receiver2) = oneshot::channel();
let join_handle = std::thread::spawn(move || {
assert!(sender2.send(()).is_ok());
let lock_a_res = directory_clone.acquire_lock(&Lock {
{
// the blocking call should wait for at least 10ms.
let start = time::Instant::now();
let lock_a_res = directory.acquire_lock(&Lock {
filepath: PathBuf::from("a.lock"),
is_blocking: true,
});
assert!(in_thread.load(SeqCst));
assert!(lock_a_res.is_ok());
});
assert!(block_on(receiver2).is_ok());
assert!(sender.send(()).is_ok());
assert!(join_handle.join().is_ok());
assert!(start.elapsed().subsec_millis() >= 10);
}
}

119
src/directory/watch_event_router.rs
View File

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

131
src/docset.rs
View File

@@ -1,48 +1,58 @@
use crate::common::BitSet;
use crate::fastfield::DeleteBitSet;
use crate::DocId;
use std::borrow::Borrow;
use std::borrow::BorrowMut;
use std::cmp::Ordering;
/// Sentinel value returned when a DocSet has been entirely consumed.
///
/// This is not u32::MAX as one would have expected, due to the lack of SSE2 instructions
/// to compare [u32; 4].
pub const TERMINATED: DocId = std::i32::MAX as u32;
/// Expresses the outcome of a call to `DocSet`'s `.skip_next(...)`.
#[derive(PartialEq, Eq, Debug)]
pub enum SkipResult {
/// target was in the docset
Reached,
/// target was not in the docset, skipping stopped as a greater element was found
OverStep,
/// the docset was entirely consumed without finding the target, nor any
/// element greater than the target.
End,
}
/// Represents an iterable set of sorted doc ids.
pub trait DocSet {
/// Goes to the next element.
///
/// The DocId of the next element is returned.
/// In other words we should always have :
/// ```ignore
/// let doc = docset.advance();
/// assert_eq!(doc, docset.doc());
/// ```
///
/// If we reached the end of the DocSet, TERMINATED should be returned.
///
/// Calling `.advance()` on a terminated DocSet should be supported, and TERMINATED should
/// be returned.
/// TODO Test existing docsets.
fn advance(&mut self) -> DocId;
/// `.advance(...)` needs to be called a first time to point to the correct
/// element.
fn advance(&mut self) -> bool;
/// Advances the DocSet forward until reaching the target, or going to the
/// lowest DocId greater than the target.
/// After skipping, position the iterator in such a way that `.doc()`
/// will return a value greater than or equal to target.
///
/// If the end of the DocSet is reached, TERMINATED is returned.
/// SkipResult expresses whether the `target value` was reached, overstepped,
/// or if the `DocSet` was entirely consumed without finding any value
/// greater or equal to the `target`.
///
/// Calling `.seek(target)` on a terminated DocSet is legal. Implementation
/// of DocSet should support it.
/// WARNING: Calling skip always advances the docset.
/// More specifically, if the docset is already positionned on the target
/// skipping will advance to the next position and return SkipResult::Overstep.
///
/// Calling `seek(TERMINATED)` is also legal and is the normal way to consume a DocSet.
fn seek(&mut self, target: DocId) -> DocId {
let mut doc = self.doc();
debug_assert!(doc <= target);
while doc < target {
doc = self.advance();
/// If `.skip_next()` oversteps, then the docset must be positionned correctly
/// on an existing document. In other words, `.doc()` should return the first document
/// greater than `DocId`.
fn skip_next(&mut self, target: DocId) -> SkipResult {
if !self.advance() {
return SkipResult::End;
}
loop {
match self.doc().cmp(&target) {
Ordering::Less => {
if !self.advance() {
return SkipResult::End;
}
}
Ordering::Equal => return SkipResult::Reached,
Ordering::Greater => return SkipResult::OverStep,
}
}
doc
}
/// Fills a given mutable buffer with the next doc ids from the
@@ -61,38 +71,38 @@ pub trait DocSet {
/// use case where batching. The normal way to
/// go through the `DocId`'s is to call `.advance()`.
fn fill_buffer(&mut self, buffer: &mut [DocId]) -> usize {
if self.doc() == TERMINATED {
return 0;
}
for (i, buffer_val) in buffer.iter_mut().enumerate() {
*buffer_val = self.doc();
if self.advance() == TERMINATED {
return i + 1;
if self.advance() {
*buffer_val = self.doc();
} else {
return i;
}
}
buffer.len()
}
/// Returns the current document
/// Right after creating a new DocSet, the docset points to the first document.
///
/// If the DocSet is empty, .doc() should return `TERMINATED`.
fn doc(&self) -> DocId;
/// Returns a best-effort hint of the
/// length of the docset.
fn size_hint(&self) -> u32;
/// Appends all docs to a `bitset`.
fn append_to_bitset(&mut self, bitset: &mut BitSet) {
while self.advance() {
bitset.insert(self.doc());
}
}
/// Returns the number documents matching.
/// Calling this method consumes the `DocSet`.
fn count(&mut self, delete_bitset: &DeleteBitSet) -> u32 {
let mut count = 0u32;
let mut doc = self.doc();
while doc != TERMINATED {
if !delete_bitset.is_deleted(doc) {
while self.advance() {
if !delete_bitset.is_deleted(self.doc()) {
count += 1u32;
}
doc = self.advance();
}
count
}
@@ -104,42 +114,22 @@ pub trait DocSet {
/// given by `count()`.
fn count_including_deleted(&mut self) -> u32 {
let mut count = 0u32;
let mut doc = self.doc();
while doc != TERMINATED {
while self.advance() {
count += 1u32;
doc = self.advance();
}
count
}
}
impl<'a> DocSet for &'a mut dyn DocSet {
fn advance(&mut self) -> u32 {
(**self).advance()
}
fn seek(&mut self, target: DocId) -> DocId {
(**self).seek(target)
}
fn doc(&self) -> u32 {
(**self).doc()
}
fn size_hint(&self) -> u32 {
(**self).size_hint()
}
}
impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
fn advance(&mut self) -> DocId {
fn advance(&mut self) -> bool {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.advance()
}
fn seek(&mut self, target: DocId) -> DocId {
fn skip_next(&mut self, target: DocId) -> SkipResult {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.seek(target)
unboxed.skip_next(target)
}
fn doc(&self) -> DocId {
@@ -161,4 +151,9 @@ impl<TDocSet: DocSet + ?Sized> DocSet for Box<TDocSet> {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.count_including_deleted()
}
fn append_to_bitset(&mut self, bitset: &mut BitSet) {
let unboxed: &mut TDocSet = self.borrow_mut();
unboxed.append_to_bitset(bitset);
}
}

115
src/error.rs
View File

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

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

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

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

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

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

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

108
src/fastfield/delete.rs
View File

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

4
src/fastfield/error.rs
View File

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

56
src/fastfield/facet_reader.rs
View File

@@ -73,61 +73,7 @@ impl FacetReader {
}
/// Return the list of facet ordinals associated to a document.
pub fn facet_ords(&self, doc: DocId, output: &mut Vec<u64>) {
pub fn facet_ords(&mut self, doc: DocId, output: &mut Vec<u64>) {
self.term_ords.get_vals(doc, output);
}
}
#[cfg(test)]
mod tests {
use crate::Index;
use crate::{
schema::{Facet, SchemaBuilder},
Document,
};
#[test]
fn test_facet_not_populated_for_all_docs() -> crate::Result<()> {
let mut schema_builder = SchemaBuilder::default();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(doc!(facet_field=>Facet::from_text("/a/b")));
index_writer.add_document(Document::default());
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let facet_reader = searcher
.segment_reader(0u32)
.facet_reader(facet_field)
.unwrap();
let mut facet_ords = Vec::new();
facet_reader.facet_ords(0u32, &mut facet_ords);
assert_eq!(&facet_ords, &[2u64]);
facet_reader.facet_ords(1u32, &mut facet_ords);
assert!(facet_ords.is_empty());
Ok(())
}
#[test]
fn test_facet_not_populated_for_any_docs() -> crate::Result<()> {
let mut schema_builder = SchemaBuilder::default();
let facet_field = schema_builder.add_facet_field("facet");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests()?;
index_writer.add_document(Document::default());
index_writer.add_document(Document::default());
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let facet_reader = searcher
.segment_reader(0u32)
.facet_reader(facet_field)
.unwrap();
let mut facet_ords = Vec::new();
facet_reader.facet_ords(0u32, &mut facet_ords);
assert!(facet_ords.is_empty());
facet_reader.facet_ords(1u32, &mut facet_ords);
assert!(facet_ords.is_empty());
Ok(())
}
}

301
src/fastfield/mod.rs
View File

@@ -37,10 +37,6 @@ use crate::common;
use crate::schema::Cardinality;
use crate::schema::FieldType;
use crate::schema::Value;
use crate::{
chrono::{NaiveDateTime, Utc},
schema::Type,
};
mod bytes;
mod delete;
@@ -53,7 +49,7 @@ mod serializer;
mod writer;
/// Trait for types that are allowed for fast fields: (u64, i64 and f64).
pub trait FastValue: Clone + Copy + Send + Sync + PartialOrd {
pub trait FastValue: Default + Clone + Copy + Send + Sync + PartialOrd {
/// Converts a value from u64
///
/// Internally all fast field values are encoded as u64.
@@ -73,15 +69,6 @@ pub trait FastValue: Clone + Copy + Send + Sync + PartialOrd {
/// Cast value to `u64`.
/// The value is just reinterpreted in memory.
fn as_u64(&self) -> u64;
/// Build a default value. This default value is never used, so the value does not
/// really matter.
fn make_zero() -> Self {
Self::from_u64(0i64.to_u64())
}
/// Returns the `schema::Type` for this FastValue.
fn to_type() -> Type;
}
impl FastValue for u64 {
@@ -104,10 +91,6 @@ impl FastValue for u64 {
fn as_u64(&self) -> u64 {
*self
}
fn to_type() -> Type {
Type::U64
}
}
impl FastValue for i64 {
@@ -129,10 +112,6 @@ impl FastValue for i64 {
fn as_u64(&self) -> u64 {
*self as u64
}
fn to_type() -> Type {
Type::I64
}
}
impl FastValue for f64 {
@@ -154,36 +133,6 @@ impl FastValue for f64 {
fn as_u64(&self) -> u64 {
self.to_bits()
}
fn to_type() -> Type {
Type::F64
}
}
impl FastValue for crate::DateTime {
fn from_u64(timestamp_u64: u64) -> Self {
let timestamp_i64 = i64::from_u64(timestamp_u64);
crate::DateTime::from_utc(NaiveDateTime::from_timestamp(timestamp_i64, 0), Utc)
}
fn to_u64(&self) -> u64 {
self.timestamp().to_u64()
}
fn fast_field_cardinality(field_type: &FieldType) -> Option<Cardinality> {
match *field_type {
FieldType::Date(ref integer_options) => integer_options.get_fastfield_cardinality(),
_ => None,
}
}
fn as_u64(&self) -> u64 {
self.timestamp().as_u64()
}
fn to_type() -> Type {
Type::Date
}
}
fn value_to_u64(value: &Value) -> u64 {
@@ -191,7 +140,6 @@ fn value_to_u64(value: &Value) -> u64 {
Value::U64(ref val) => *val,
Value::I64(ref val) => common::i64_to_u64(*val),
Value::F64(ref val) => common::f64_to_u64(*val),
Value::Date(ref datetime) => common::i64_to_u64(datetime.timestamp()),
_ => panic!("Expected a u64/i64/f64 field, got {:?} ", value),
}
}
@@ -203,13 +151,10 @@ mod tests {
use crate::common::CompositeFile;
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::FastFieldReader;
use crate::merge_policy::NoMergePolicy;
use crate::schema::Document;
use crate::schema::Field;
use crate::schema::Schema;
use crate::schema::FAST;
use crate::schema::{Document, IntOptions};
use crate::{Index, SegmentId, SegmentReader};
use common::HasLen;
use once_cell::sync::Lazy;
use rand::prelude::SliceRandom;
use rand::rngs::StdRng;
@@ -234,15 +179,9 @@ mod tests {
}
#[test]
pub fn test_fastfield_i64_u64() {
let datetime = crate::DateTime::from_utc(NaiveDateTime::from_timestamp(0i64, 0), Utc);
assert_eq!(i64::from_u64(datetime.to_u64()), 0i64);
}
#[test]
fn test_intfastfield_small() -> crate::Result<()> {
fn test_intfastfield_small() {
let path = Path::new("test");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -255,24 +194,27 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 36 as usize);
let composite_file = CompositeFile::open(&file)?;
let file = composite_file.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(file)?;
assert_eq!(fast_field_reader.get(0), 13u64);
assert_eq!(fast_field_reader.get(1), 14u64);
assert_eq!(fast_field_reader.get(2), 2u64);
Ok(())
let source = directory.open_read(&path).unwrap();
{
assert_eq!(source.len(), 36 as usize);
}
{
let composite_file = CompositeFile::open(&source).unwrap();
let field_source = composite_file.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(field_source);
assert_eq!(fast_field_reader.get(0), 13u64);
assert_eq!(fast_field_reader.get(1), 14u64);
assert_eq!(fast_field_reader.get(2), 2u64);
}
}
#[test]
fn test_intfastfield_large() -> crate::Result<()> {
fn test_intfastfield_large() {
let path = Path::new("test");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test"))?;
let mut serializer = FastFieldSerializer::from_write(write)?;
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
fast_field_writers.add_document(&doc!(*FIELD=>4u64));
fast_field_writers.add_document(&doc!(*FIELD=>14_082_001u64));
@@ -283,15 +225,19 @@ mod tests {
fast_field_writers.add_document(&doc!(*FIELD=>1_002u64));
fast_field_writers.add_document(&doc!(*FIELD=>1_501u64));
fast_field_writers.add_document(&doc!(*FIELD=>215u64));
fast_field_writers.serialize(&mut serializer, &HashMap::new())?;
serializer.close()?;
fast_field_writers
.serialize(&mut serializer, &HashMap::new())
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path)?;
assert_eq!(file.len(), 61 as usize);
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file)?;
assert_eq!(source.len(), 61 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
let fast_field_reader = FastFieldReader::<u64>::open(data);
assert_eq!(fast_field_reader.get(0), 4u64);
assert_eq!(fast_field_reader.get(1), 14_082_001u64);
assert_eq!(fast_field_reader.get(2), 3_052u64);
@@ -302,13 +248,12 @@ mod tests {
assert_eq!(fast_field_reader.get(7), 1_501u64);
assert_eq!(fast_field_reader.get(8), 215u64);
}
Ok(())
}
#[test]
fn test_intfastfield_null_amplitude() -> crate::Result<()> {
fn test_intfastfield_null_amplitude() {
let path = Path::new("test");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
@@ -322,23 +267,24 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 34 as usize);
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file).unwrap();
assert_eq!(source.len(), 34 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
let fast_field_reader = FastFieldReader::<u64>::open(data);
for doc in 0..10_000 {
assert_eq!(fast_field_reader.get(doc), 100_000u64);
}
}
Ok(())
}
#[test]
fn test_intfastfield_large_numbers() -> crate::Result<()> {
fn test_intfastfield_large_numbers() {
let path = Path::new("test");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
@@ -354,12 +300,14 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 80042 as usize);
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file)?;
assert_eq!(source.len(), 80042 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
let fast_field_reader = FastFieldReader::<u64>::open(data);
assert_eq!(fast_field_reader.get(0), 0u64);
for doc in 1..10_001 {
assert_eq!(
@@ -368,13 +316,12 @@ mod tests {
);
}
}
Ok(())
}
#[test]
fn test_signed_intfastfield() -> crate::Result<()> {
fn test_signed_intfastfield() {
let path = Path::new("test");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
let mut schema_builder = Schema::builder();
let i64_field = schema_builder.add_i64_field("field", FAST);
@@ -393,12 +340,14 @@ mod tests {
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
assert_eq!(file.len(), 17709 as usize);
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file)?;
assert_eq!(source.len(), 17709 as usize);
}
{
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(i64_field).unwrap();
let fast_field_reader = FastFieldReader::<i64>::open(data)?;
let fast_field_reader = FastFieldReader::<i64>::open(data);
assert_eq!(fast_field_reader.min_value(), -100i64);
assert_eq!(fast_field_reader.max_value(), 9_999i64);
@@ -411,13 +360,12 @@ mod tests {
assert_eq!(buffer[i], -100i64 + 53i64 + i as i64);
}
}
Ok(())
}
#[test]
fn test_signed_intfastfield_default_val() -> crate::Result<()> {
fn test_signed_intfastfield_default_val() {
let path = Path::new("test");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
let mut schema_builder = Schema::builder();
let i64_field = schema_builder.add_i64_field("field", FAST);
let schema = schema_builder.build();
@@ -434,14 +382,13 @@ mod tests {
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(i64_field).unwrap();
let fast_field_reader = FastFieldReader::<i64>::open(data)?;
let fast_field_reader = FastFieldReader::<i64>::open(data);
assert_eq!(fast_field_reader.get(0u32), 0i64);
}
Ok(())
}
// Warning: this generates the same permutation at each call
@@ -452,26 +399,28 @@ mod tests {
}
#[test]
fn test_intfastfield_permutation() -> crate::Result<()> {
fn test_intfastfield_permutation() {
let path = Path::new("test");
let permutation = generate_permutation();
let n = permutation.len();
let directory = RAMDirectory::create();
let mut directory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test"))?;
let mut serializer = FastFieldSerializer::from_write(write)?;
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
for &x in &permutation {
fast_field_writers.add_document(&doc!(*FIELD=>x));
}
fast_field_writers.serialize(&mut serializer, &HashMap::new())?;
serializer.close()?;
fast_field_writers
.serialize(&mut serializer, &HashMap::new())
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path)?;
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file)?;
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data)?;
let fast_field_reader = FastFieldReader::<u64>::open(data);
let mut a = 0u64;
for _ in 0..n {
@@ -479,95 +428,8 @@ mod tests {
a = fast_field_reader.get(a as u32);
}
}
Ok(())
}
#[test]
fn test_merge_missing_date_fast_field() {
let mut schema_builder = Schema::builder();
let date_field = schema_builder.add_date_field("date", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(date_field =>crate::chrono::prelude::Utc::now()));
index_writer.commit().unwrap();
index_writer.add_document(doc!());
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let segment_ids: Vec<SegmentId> = reader
.searcher()
.segment_readers()
.iter()
.map(SegmentReader::segment_id)
.collect();
assert_eq!(segment_ids.len(), 2);
let merge_future = index_writer.merge(&segment_ids[..]);
let merge_res = futures::executor::block_on(merge_future);
assert!(merge_res.is_ok());
assert!(reader.reload().is_ok());
assert_eq!(reader.searcher().segment_readers().len(), 1);
}
#[test]
fn test_default_datetime() {
assert_eq!(crate::DateTime::make_zero().timestamp(), 0i64);
}
#[test]
fn test_datefastfield() {
use crate::fastfield::FastValue;
let mut schema_builder = Schema::builder();
let date_field = schema_builder.add_date_field("date", FAST);
let multi_date_field = schema_builder.add_date_field(
"multi_date",
IntOptions::default().set_fast(Cardinality::MultiValues),
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(1i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(2i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(3i64.to_u64())
));
index_writer.add_document(doc!(
date_field => crate::DateTime::from_u64(4i64.to_u64())
));
index_writer.add_document(doc!(
multi_date_field => crate::DateTime::from_u64(5i64.to_u64()),
multi_date_field => crate::DateTime::from_u64(6i64.to_u64())
));
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
let segment_reader = searcher.segment_reader(0);
let fast_fields = segment_reader.fast_fields();
let date_fast_field = fast_fields.date(date_field).unwrap();
let dates_fast_field = fast_fields.dates(multi_date_field).unwrap();
let mut dates = vec![];
{
assert_eq!(date_fast_field.get(0u32).timestamp(), 1i64);
dates_fast_field.get_vals(0u32, &mut dates);
assert_eq!(dates.len(), 2);
assert_eq!(dates[0].timestamp(), 2i64);
assert_eq!(dates[1].timestamp(), 3i64);
}
{
assert_eq!(date_fast_field.get(1u32).timestamp(), 4i64);
dates_fast_field.get_vals(1u32, &mut dates);
assert!(dates.is_empty());
}
{
assert_eq!(date_fast_field.get(2u32).timestamp(), 0i64);
dates_fast_field.get_vals(2u32, &mut dates);
assert_eq!(dates.len(), 2);
assert_eq!(dates[0].timestamp(), 5i64);
assert_eq!(dates[1].timestamp(), 6i64);
}
}
}
#[cfg(all(test, feature = "unstable"))]
@@ -575,9 +437,9 @@ mod bench {
use super::tests::FIELD;
use super::tests::{generate_permutation, SCHEMA};
use super::*;
use crate::common::CompositeFile;
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::FastFieldReader;
use common::CompositeFile;
use directory::{Directory, RAMDirectory, WritePtr};
use fastfield::FastFieldReader;
use std::collections::HashMap;
use std::path::Path;
use test::{self, Bencher};
@@ -612,7 +474,7 @@ mod bench {
fn bench_intfastfield_linear_fflookup(b: &mut Bencher) {
let path = Path::new("test");
let permutation = generate_permutation();
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -625,11 +487,11 @@ mod bench {
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
b.iter(|| {
let n = test::black_box(7000u32);
@@ -646,7 +508,7 @@ mod bench {
fn bench_intfastfield_fflookup(b: &mut Bencher) {
let path = Path::new("test");
let permutation = generate_permutation();
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = FastFieldSerializer::from_write(write).unwrap();
@@ -659,11 +521,11 @@ mod bench {
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(&path).unwrap();
let source = directory.open_read(&path).unwrap();
{
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let fast_fields_composite = CompositeFile::open(&source).unwrap();
let data = fast_fields_composite.open_read(*FIELD).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data).unwrap();
let fast_field_reader = FastFieldReader::<u64>::open(data);
b.iter(|| {
let n = test::black_box(1000u32);
@@ -675,4 +537,5 @@ mod bench {
});
}
}
}

42
src/fastfield/multivalued/mod.rs
View File

@@ -7,6 +7,9 @@ pub use self::writer::MultiValueIntFastFieldWriter;
#[cfg(test)]
mod tests {
use time;
use self::time::Duration;
use crate::collector::TopDocs;
use crate::query::QueryParser;
use crate::schema::Cardinality;
@@ -14,7 +17,6 @@ mod tests {
use crate::schema::IntOptions;
use crate::schema::Schema;
use crate::Index;
use chrono::Duration;
#[test]
fn test_multivalued_u64() {
@@ -25,7 +27,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(field=>1u64, field=>3u64));
index_writer.add_document(doc!());
index_writer.add_document(doc!(field=>4u64));
@@ -64,7 +66,7 @@ mod tests {
schema_builder.add_i64_field("time_stamp_i", IntOptions::default().set_stored());
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let first_time_stamp = chrono::Utc::now();
index_writer.add_document(
doc!(date_field=>first_time_stamp, date_field=>first_time_stamp, time_i=>1i64),
@@ -100,7 +102,6 @@ mod tests {
.get_first(date_field)
.expect("cannot find value")
.date_value()
.unwrap()
.timestamp(),
first_time_stamp.timestamp()
);
@@ -109,7 +110,7 @@ mod tests {
.get_first(time_i)
.expect("cannot find value")
.i64_value(),
Some(1i64)
1i64
);
}
}
@@ -132,7 +133,6 @@ mod tests {
.get_first(date_field)
.expect("cannot find value")
.date_value()
.unwrap()
.timestamp(),
two_secs_ahead.timestamp()
);
@@ -141,7 +141,7 @@ mod tests {
.get_first(time_i)
.expect("cannot find value")
.i64_value(),
Some(3i64)
3i64
);
}
}
@@ -188,7 +188,7 @@ mod tests {
);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.add_document(doc!(field=> 1i64, field => 3i64));
index_writer.add_document(doc!());
index_writer.add_document(doc!(field=> -4i64));
@@ -199,14 +199,22 @@ mod tests {
let segment_reader = searcher.segment_reader(0);
let mut vals = Vec::new();
let multi_value_reader = segment_reader.fast_fields().i64s(field).unwrap();
multi_value_reader.get_vals(2, &mut vals);
assert_eq!(&vals, &[-4i64]);
multi_value_reader.get_vals(0, &mut vals);
assert_eq!(&vals, &[1i64, 3i64]);
multi_value_reader.get_vals(1, &mut vals);
assert!(vals.is_empty());
multi_value_reader.get_vals(3, &mut vals);
assert_eq!(&vals, &[-5i64, -20i64, 1i64]);
{
multi_value_reader.get_vals(2, &mut vals);
assert_eq!(&vals, &[-4i64]);
}
{
multi_value_reader.get_vals(0, &mut vals);
assert_eq!(&vals, &[1i64, 3i64]);
}
{
multi_value_reader.get_vals(1, &mut vals);
assert!(vals.is_empty());
}
{
multi_value_reader.get_vals(3, &mut vals);
assert_eq!(&vals, &[-5i64, -20i64, 1i64]);
}
}
#[test]
#[ignore]
@@ -215,7 +223,7 @@ mod tests {
let field = schema_builder.add_facet_field("facetfield");
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for i in 0..100_000 {
index_writer.add_document(doc!(field=> Facet::from(format!("/lang/{}", i).as_str())));
}

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

@@ -45,7 +45,7 @@ impl<Item: FastValue> MultiValueIntFastFieldReader<Item> {
pub fn get_vals(&self, doc: DocId, vals: &mut Vec<Item>) {
let (start, stop) = self.range(doc);
let len = (stop - start) as usize;
vals.resize(len, Item::make_zero());
vals.resize(len, Item::default());
self.vals_reader.get_range_u64(start, &mut vals[..]);
}
@@ -74,7 +74,7 @@ mod tests {
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index
.writer_for_tests()
.writer_with_num_threads(1, 30_000_000)
.expect("Failed to create index writer.");
index_writer.add_document(doc!(
facet_field => Facet::from("/category/cat2"),

11
src/fastfield/multivalued/writer.rs
View File

@@ -5,7 +5,8 @@ use crate::postings::UnorderedTermId;
use crate::schema::{Document, Field};
use crate::termdict::TermOrdinal;
use crate::DocId;
use fnv::FnvHashMap;
use itertools::Itertools;
use std::collections::HashMap;
use std::io;
/// Writer for multi-valued (as in, more than one value per document)
@@ -101,7 +102,7 @@ impl MultiValueIntFastFieldWriter {
pub fn serialize(
&self,
serializer: &mut FastFieldSerializer,
mapping_opt: Option<&FnvHashMap<UnorderedTermId, TermOrdinal>>,
mapping_opt: Option<&HashMap<UnorderedTermId, TermOrdinal>>,
) -> io::Result<()> {
{
// writing the offset index
@@ -143,15 +144,15 @@ impl MultiValueIntFastFieldWriter {
.iter()
.map(|val| *mapping.get(val).expect("Missing term ordinal"));
doc_vals.extend(remapped_vals);
doc_vals.sort_unstable();
doc_vals.sort();
for &val in &doc_vals {
value_serializer.add_val(val)?;
}
}
}
None => {
let val_min_max = crate::common::minmax(self.vals.iter().cloned());
let (val_min, val_max) = val_min_max.unwrap_or((0u64, 0u64));
let val_min_max = self.vals.iter().cloned().minmax();
let (val_min, val_max) = val_min_max.into_option().unwrap_or((0u64, 0u64));
value_serializer =
serializer.new_u64_fast_field_with_idx(self.field, val_min, val_max, 1)?;
for &val in &self.vals {

39
src/fastfield/reader.rs
View File

@@ -3,12 +3,13 @@ use crate::common::bitpacker::BitUnpacker;
use crate::common::compute_num_bits;
use crate::common::BinarySerializable;
use crate::common::CompositeFile;
use crate::directory::FileSlice;
use crate::directory::ReadOnlySource;
use crate::directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::{FastFieldSerializer, FastFieldsWriter};
use crate::schema::Schema;
use crate::schema::FAST;
use crate::DocId;
use owning_ref::OwningRef;
use std::collections::HashMap;
use std::marker::PhantomData;
use std::path::Path;
@@ -19,27 +20,34 @@ use std::path::Path;
/// fast field is required.
#[derive(Clone)]
pub struct FastFieldReader<Item: FastValue> {
bit_unpacker: BitUnpacker,
bit_unpacker: BitUnpacker<OwningRef<ReadOnlySource, [u8]>>,
min_value_u64: u64,
max_value_u64: u64,
_phantom: PhantomData<Item>,
}
impl<Item: FastValue> FastFieldReader<Item> {
/// Opens a fast field given a file.
pub fn open(file: FileSlice) -> crate::Result<Self> {
let mut bytes = file.read_bytes()?;
let min_value = u64::deserialize(&mut bytes)?;
let amplitude = u64::deserialize(&mut bytes)?;
/// Opens a fast field given a source.
pub fn open(data: ReadOnlySource) -> Self {
let min_value: u64;
let amplitude: u64;
{
let mut cursor = data.as_slice();
min_value =
u64::deserialize(&mut cursor).expect("Failed to read the min_value of fast field.");
amplitude =
u64::deserialize(&mut cursor).expect("Failed to read the amplitude of fast field.");
}
let max_value = min_value + amplitude;
let num_bits = compute_num_bits(amplitude);
let bit_unpacker = BitUnpacker::new(bytes, num_bits);
Ok(FastFieldReader {
let owning_ref = OwningRef::new(data).map(|data| &data[16..]);
let bit_unpacker = BitUnpacker::new(owning_ref, num_bits);
FastFieldReader {
min_value_u64: min_value,
max_value_u64: max_value,
bit_unpacker,
_phantom: PhantomData,
})
}
}
pub(crate) fn into_u64_reader(self) -> FastFieldReader<u64> {
@@ -127,7 +135,7 @@ impl<Item: FastValue> From<Vec<Item>> for FastFieldReader<Item> {
let field = schema_builder.add_u64_field("field", FAST);
let schema = schema_builder.build();
let path = Path::new("__dummy__");
let directory: RAMDirectory = RAMDirectory::create();
let mut directory: RAMDirectory = RAMDirectory::create();
{
let write: WritePtr = directory
.open_write(path)
@@ -149,11 +157,12 @@ impl<Item: FastValue> From<Vec<Item>> for FastFieldReader<Item> {
serializer.close().unwrap();
}
let file = directory.open_read(path).expect("Failed to open the file");
let composite_file = CompositeFile::open(&file).expect("Failed to read the composite file");
let field_file = composite_file
let source = directory.open_read(path).expect("Failed to open the file");
let composite_file =
CompositeFile::open(&source).expect("Failed to read the composite file");
let field_source = composite_file
.open_read(field)
.expect("File component not found");
FastFieldReader::open(field_file).unwrap()
FastFieldReader::open(field_source)
}
}

96
src/fastfield/readers.rs
View File

@@ -4,6 +4,7 @@ use crate::fastfield::MultiValueIntFastFieldReader;
use crate::fastfield::{FastFieldNotAvailableError, FastFieldReader};
use crate::schema::{Cardinality, Field, FieldType, Schema};
use crate::space_usage::PerFieldSpaceUsage;
use crate::Result;
use std::collections::HashMap;
/// Provides access to all of the FastFieldReader.
@@ -14,11 +15,9 @@ pub struct FastFieldReaders {
fast_field_i64: HashMap<Field, FastFieldReader<i64>>,
fast_field_u64: HashMap<Field, FastFieldReader<u64>>,
fast_field_f64: HashMap<Field, FastFieldReader<f64>>,
fast_field_date: HashMap<Field, FastFieldReader<crate::DateTime>>,
fast_field_i64s: HashMap<Field, MultiValueIntFastFieldReader<i64>>,
fast_field_u64s: HashMap<Field, MultiValueIntFastFieldReader<u64>>,
fast_field_f64s: HashMap<Field, MultiValueIntFastFieldReader<f64>>,
fast_field_dates: HashMap<Field, MultiValueIntFastFieldReader<crate::DateTime>>,
fast_bytes: HashMap<Field, BytesFastFieldReader>,
fast_fields_composite: CompositeFile,
}
@@ -27,7 +26,6 @@ enum FastType {
I64,
U64,
F64,
Date,
}
fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality)> {
@@ -41,9 +39,6 @@ fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType, Cardinality
FieldType::F64(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::F64, cardinality)),
FieldType::Date(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::Date, cardinality)),
FieldType::HierarchicalFacet => Some((FastType::U64, Cardinality::MultiValues)),
_ => None,
}
@@ -53,67 +48,53 @@ impl FastFieldReaders {
pub(crate) fn load_all(
schema: &Schema,
fast_fields_composite: &CompositeFile,
) -> crate::Result<FastFieldReaders> {
) -> Result<FastFieldReaders> {
let mut fast_field_readers = FastFieldReaders {
fast_field_i64: Default::default(),
fast_field_u64: Default::default(),
fast_field_f64: Default::default(),
fast_field_date: Default::default(),
fast_field_i64s: Default::default(),
fast_field_u64s: Default::default(),
fast_field_f64s: Default::default(),
fast_field_dates: Default::default(),
fast_bytes: Default::default(),
fast_fields_composite: fast_fields_composite.clone(),
};
for (field, field_entry) in schema.fields() {
for (field_id, field_entry) in schema.fields().iter().enumerate() {
let field = Field(field_id as u32);
let field_type = field_entry.field_type();
if let FieldType::Bytes(bytes_option) = field_type {
if !bytes_option.is_fast() {
continue;
}
let fast_field_idx_file = fast_fields_composite
if field_type == &FieldType::Bytes {
let idx_reader = fast_fields_composite
.open_read_with_idx(field, 0)
.ok_or_else(|| FastFieldNotAvailableError::new(field_entry))?;
let idx_reader = FastFieldReader::open(fast_field_idx_file)?;
.ok_or_else(|| FastFieldNotAvailableError::new(field_entry))
.map(FastFieldReader::open)?;
let data = fast_fields_composite
.open_read_with_idx(field, 1)
.ok_or_else(|| FastFieldNotAvailableError::new(field_entry))?;
let bytes_fast_field_reader = BytesFastFieldReader::open(idx_reader, data)?;
fast_field_readers
.fast_bytes
.insert(field, bytes_fast_field_reader);
.insert(field, BytesFastFieldReader::open(idx_reader, data));
} else if let Some((fast_type, cardinality)) = type_and_cardinality(field_type) {
match cardinality {
Cardinality::SingleValue => {
if let Some(fast_field_data) = fast_fields_composite.open_read(field) {
match fast_type {
FastType::U64 => {
let fast_field_reader = FastFieldReader::open(fast_field_data)?;
let fast_field_reader = FastFieldReader::open(fast_field_data);
fast_field_readers
.fast_field_u64
.insert(field, fast_field_reader);
}
FastType::I64 => {
let fast_field_reader =
FastFieldReader::open(fast_field_data.clone())?;
fast_field_readers
.fast_field_i64
.insert(field, fast_field_reader);
fast_field_readers.fast_field_i64.insert(
field,
FastFieldReader::open(fast_field_data.clone()),
);
}
FastType::F64 => {
let fast_field_reader =
FastFieldReader::open(fast_field_data.clone())?;
fast_field_readers
.fast_field_f64
.insert(field, fast_field_reader);
}
FastType::Date => {
let fast_field_reader =
FastFieldReader::open(fast_field_data.clone())?;
fast_field_readers
.fast_field_date
.insert(field, fast_field_reader);
fast_field_readers.fast_field_f64.insert(
field,
FastFieldReader::open(fast_field_data.clone()),
);
}
}
} else {
@@ -124,10 +105,10 @@ impl FastFieldReaders {
let idx_opt = fast_fields_composite.open_read_with_idx(field, 0);
let data_opt = fast_fields_composite.open_read_with_idx(field, 1);
if let (Some(fast_field_idx), Some(fast_field_data)) = (idx_opt, data_opt) {
let idx_reader = FastFieldReader::open(fast_field_idx)?;
let idx_reader = FastFieldReader::open(fast_field_idx);
match fast_type {
FastType::I64 => {
let vals_reader = FastFieldReader::open(fast_field_data)?;
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
@@ -135,7 +116,7 @@ impl FastFieldReaders {
.insert(field, multivalued_int_fast_field);
}
FastType::U64 => {
let vals_reader = FastFieldReader::open(fast_field_data)?;
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
@@ -143,21 +124,13 @@ impl FastFieldReaders {
.insert(field, multivalued_int_fast_field);
}
FastType::F64 => {
let vals_reader = FastFieldReader::open(fast_field_data)?;
let vals_reader = FastFieldReader::open(fast_field_data);
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_f64s
.insert(field, multivalued_int_fast_field);
}
FastType::Date => {
let vals_reader = FastFieldReader::open(fast_field_data)?;
let multivalued_int_fast_field =
MultiValueIntFastFieldReader::open(idx_reader, vals_reader);
fast_field_readers
.fast_field_dates
.insert(field, multivalued_int_fast_field);
}
}
} else {
return Err(From::from(FastFieldNotAvailableError::new(field_entry)));
@@ -184,6 +157,8 @@ impl FastFieldReaders {
/// If the field is a i64-fast field, return the associated u64 reader. Values are
/// mapped from i64 to u64 using a (well the, it is unique) monotonic mapping. ///
///
///TODO should it also be lenient with f64?
///
/// This method is useful when merging segment reader.
pub(crate) fn u64_lenient(&self, field: Field) -> Option<FastFieldReader<u64>> {
if let Some(u64_ff_reader) = self.u64(field) {
@@ -192,12 +167,6 @@ impl FastFieldReaders {
if let Some(i64_ff_reader) = self.i64(field) {
return Some(i64_ff_reader.into_u64_reader());
}
if let Some(f64_ff_reader) = self.f64(field) {
return Some(f64_ff_reader.into_u64_reader());
}
if let Some(date_ff_reader) = self.date(field) {
return Some(date_ff_reader.into_u64_reader());
}
None
}
@@ -208,13 +177,6 @@ impl FastFieldReaders {
self.fast_field_i64.get(&field).cloned()
}
/// Returns the `i64` fast field reader reader associated to `field`.
///
/// If `field` is not a i64 fast field, this method returns `None`.
pub fn date(&self, field: Field) -> Option<FastFieldReader<crate::DateTime>> {
self.fast_field_date.get(&field).cloned()
}
/// Returns the `f64` fast field reader reader associated to `field`.
///
/// If `field` is not a f64 fast field, this method returns `None`.
@@ -241,9 +203,6 @@ impl FastFieldReaders {
if let Some(i64s_ff_reader) = self.i64s(field) {
return Some(i64s_ff_reader.into_u64s_reader());
}
if let Some(f64s_ff_reader) = self.f64s(field) {
return Some(f64s_ff_reader.into_u64s_reader());
}
None
}
@@ -261,13 +220,6 @@ impl FastFieldReaders {
self.fast_field_f64s.get(&field).cloned()
}
/// Returns a `crate::DateTime` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a `crate::DateTime` multi-valued fast field, this method returns `None`.
pub fn dates(&self, field: Field) -> Option<MultiValueIntFastFieldReader<crate::DateTime>> {
self.fast_field_dates.get(&field).cloned()
}
/// Returns the `bytes` fast field reader associated to `field`.
///
/// If `field` is not a bytes fast field, returns `None`.

38
src/fastfield/writer.rs
View File

@@ -4,9 +4,8 @@ use crate::common::BinarySerializable;
use crate::common::VInt;
use crate::fastfield::{BytesFastFieldWriter, FastFieldSerializer};
use crate::postings::UnorderedTermId;
use crate::schema::{Cardinality, Document, Field, FieldEntry, FieldType, Schema};
use crate::schema::{Cardinality, Document, Field, FieldType, Schema};
use crate::termdict::TermOrdinal;
use fnv::FnvHashMap;
use std::collections::HashMap;
use std::io;
@@ -17,14 +16,6 @@ pub struct FastFieldsWriter {
bytes_value_writers: Vec<BytesFastFieldWriter>,
}
fn fast_field_default_value(field_entry: &FieldEntry) -> u64 {
match *field_entry.field_type() {
FieldType::I64(_) | FieldType::Date(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
}
}
impl FastFieldsWriter {
/// Create all `FastFieldWriter` required by the schema.
pub fn from_schema(schema: &Schema) -> FastFieldsWriter {
@@ -32,16 +23,18 @@ impl FastFieldsWriter {
let mut multi_values_writers = Vec::new();
let mut bytes_value_writers = Vec::new();
for (field, field_entry) in schema.fields() {
match field_entry.field_type() {
FieldType::I64(ref int_options)
| FieldType::U64(ref int_options)
| FieldType::F64(ref int_options)
| FieldType::Date(ref int_options) => {
for (field_id, field_entry) in schema.fields().iter().enumerate() {
let field = Field(field_id as u32);
let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64,
};
match *field_entry.field_type() {
FieldType::I64(ref int_options) | FieldType::U64(ref int_options) | FieldType::F64(ref int_options) => {
match int_options.get_fastfield_cardinality() {
Some(Cardinality::SingleValue) => {
let mut fast_field_writer = IntFastFieldWriter::new(field);
let default_value = fast_field_default_value(field_entry);
fast_field_writer.set_val_if_missing(default_value);
single_value_writers.push(fast_field_writer);
}
@@ -56,11 +49,9 @@ impl FastFieldsWriter {
let fast_field_writer = MultiValueIntFastFieldWriter::new(field, true);
multi_values_writers.push(fast_field_writer);
}
FieldType::Bytes(bytes_option) => {
if bytes_option.is_fast() {
let fast_field_writer = BytesFastFieldWriter::new(field);
bytes_value_writers.push(fast_field_writer);
}
FieldType::Bytes => {
let fast_field_writer = BytesFastFieldWriter::new(field);
bytes_value_writers.push(fast_field_writer);
}
_ => {}
}
@@ -123,12 +114,11 @@ impl FastFieldsWriter {
pub fn serialize(
&self,
serializer: &mut FastFieldSerializer,
mapping: &HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>,
mapping: &HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>>,
) -> io::Result<()> {
for field_writer in &self.single_value_writers {
field_writer.serialize(serializer)?;
}
for field_writer in &self.multi_values_writers {
let field = field_writer.field();
field_writer.serialize(serializer, mapping.get(&field))?;

2
src/fieldnorm/mod.rs
View File

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

98
src/fieldnorm/reader.rs
View File

@@ -1,47 +1,6 @@
use super::{fieldnorm_to_id, id_to_fieldnorm};
use crate::common::CompositeFile;
use crate::directory::FileSlice;
use crate::directory::OwnedBytes;
use crate::schema::Field;
use crate::space_usage::PerFieldSpaceUsage;
use crate::directory::ReadOnlySource;
use crate::DocId;
use std::sync::Arc;
/// Reader for the fieldnorm (for each document, the number of tokens indexed in the
/// field) of all indexed fields in the index.
///
/// Each fieldnorm is approximately compressed over one byte. We refer to this byte as
/// `fieldnorm_id`.
/// The mapping from `fieldnorm` to `fieldnorm_id` is given by monotonic.
#[derive(Clone)]
pub struct FieldNormReaders {
data: Arc<CompositeFile>,
}
impl FieldNormReaders {
/// Creates a field norm reader.
pub fn open(file: FileSlice) -> crate::Result<FieldNormReaders> {
let data = CompositeFile::open(&file)?;
Ok(FieldNormReaders {
data: Arc::new(data),
})
}
/// Returns the FieldNormReader for a specific field.
pub fn get_field(&self, field: Field) -> crate::Result<Option<FieldNormReader>> {
if let Some(file) = self.data.open_read(field) {
let fieldnorm_reader = FieldNormReader::open(file)?;
Ok(Some(fieldnorm_reader))
} else {
Ok(None)
}
}
/// Return a break down of the space usage per field.
pub fn space_usage(&self) -> PerFieldSpaceUsage {
self.data.space_usage()
}
}
/// Reads the fieldnorm associated to a document.
/// The fieldnorm represents the length associated to
@@ -60,34 +19,16 @@ impl FieldNormReaders {
/// Apart from compression, this scale also makes it possible to
/// precompute computationally expensive functions of the fieldnorm
/// in a very short array.
#[derive(Clone)]
pub struct FieldNormReader {
data: OwnedBytes,
data: ReadOnlySource,
}
impl FieldNormReader {
/// Creates a `FieldNormReader` with a constant fieldnorm.
pub fn constant(num_docs: u32, fieldnorm: u32) -> FieldNormReader {
let fieldnorm_id = fieldnorm_to_id(fieldnorm);
let field_norms_data = OwnedBytes::new(vec![fieldnorm_id; num_docs as usize]);
FieldNormReader::new(field_norms_data)
}
/// Opens a field norm reader given its file.
pub fn open(fieldnorm_file: FileSlice) -> crate::Result<Self> {
let data = fieldnorm_file.read_bytes()?;
Ok(FieldNormReader::new(data))
}
fn new(data: OwnedBytes) -> Self {
/// Opens a field norm reader given its data source.
pub fn open(data: ReadOnlySource) -> Self {
FieldNormReader { data }
}
/// Returns the number of documents in this segment.
pub fn num_docs(&self) -> u32 {
self.data.len() as u32
}
/// Returns the `fieldnorm` associated to a doc id.
/// The fieldnorm is a value approximating the number
/// of tokens in a given field of the `doc_id`.
@@ -105,7 +46,8 @@ impl FieldNormReader {
/// Returns the `fieldnorm_id` associated to a document.
#[inline(always)]
pub fn fieldnorm_id(&self, doc_id: DocId) -> u8 {
self.data.as_slice()[doc_id as usize]
let fielnorms_data = self.data.as_slice();
fielnorms_data[doc_id as usize]
}
/// Converts a `fieldnorm_id` into a fieldnorm.
@@ -120,34 +62,18 @@ impl FieldNormReader {
pub fn fieldnorm_to_id(fieldnorm: u32) -> u8 {
fieldnorm_to_id(fieldnorm)
}
}
#[cfg(test)]
pub fn for_test(field_norms: &[u32]) -> FieldNormReader {
#[cfg(test)]
impl From<Vec<u32>> for FieldNormReader {
fn from(field_norms: Vec<u32>) -> FieldNormReader {
let field_norms_id = field_norms
.iter()
.cloned()
.into_iter()
.map(FieldNormReader::fieldnorm_to_id)
.collect::<Vec<u8>>();
let field_norms_data = OwnedBytes::new(field_norms_id);
let field_norms_data = ReadOnlySource::from(field_norms_id);
FieldNormReader {
data: field_norms_data,
}
}
}
#[cfg(test)]
mod tests {
use crate::fieldnorm::FieldNormReader;
#[test]
fn test_from_fieldnorms_array() {
let fieldnorms = &[1, 2, 3, 4, 1_000_000];
let fieldnorm_reader = FieldNormReader::for_test(fieldnorms);
assert_eq!(fieldnorm_reader.num_docs(), 5);
assert_eq!(fieldnorm_reader.fieldnorm(0), 1);
assert_eq!(fieldnorm_reader.fieldnorm(1), 2);
assert_eq!(fieldnorm_reader.fieldnorm(2), 3);
assert_eq!(fieldnorm_reader.fieldnorm(3), 4);
assert_eq!(fieldnorm_reader.fieldnorm(4), 983_064);
}
}

32
src/fieldnorm/writer.rs
View File

@@ -4,7 +4,7 @@ use super::fieldnorm_to_id;
use super::FieldNormsSerializer;
use crate::schema::Field;
use crate::schema::Schema;
use std::{io, iter};
use std::io;
/// The `FieldNormsWriter` is in charge of tracking the fieldnorm byte
/// of each document for each field with field norms.
@@ -22,14 +22,11 @@ impl FieldNormsWriter {
pub(crate) fn fields_with_fieldnorm(schema: &Schema) -> Vec<Field> {
schema
.fields()
.filter_map(|(field, field_entry)| {
if field_entry.is_indexed() {
Some(field)
} else {
None
}
})
.collect::<Vec<_>>()
.iter()
.enumerate()
.filter(|&(_, field_entry)| field_entry.is_indexed())
.map(|(field, _)| Field(field as u32))
.collect::<Vec<Field>>()
}
/// Initialize with state for tracking the field norm fields
@@ -38,15 +35,13 @@ impl FieldNormsWriter {
let fields = FieldNormsWriter::fields_with_fieldnorm(schema);
let max_field = fields
.iter()
.map(Field::field_id)
.map(|field| field.0)
.max()
.map(|max_field_id| max_field_id as usize + 1)
.unwrap_or(0);
FieldNormsWriter {
fields,
fieldnorms_buffer: iter::repeat_with(Vec::new)
.take(max_field)
.collect::<Vec<_>>(),
fieldnorms_buffer: (0..max_field).map(|_| Vec::new()).collect::<Vec<_>>(),
}
}
@@ -55,8 +50,8 @@ impl FieldNormsWriter {
///
/// Will extend with 0-bytes for documents that have not been seen.
pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) {
for field in self.fields.iter() {
self.fieldnorms_buffer[field.field_id() as usize].resize(max_doc as usize, 0u8);
for &field in self.fields.iter() {
self.fieldnorms_buffer[field.0 as usize].resize(max_doc as usize, 0u8);
}
}
@@ -69,7 +64,7 @@ impl FieldNormsWriter {
/// * field - the field being set
/// * fieldnorm - the number of terms present in document `doc` in field `field`
pub fn record(&mut self, doc: DocId, field: Field, fieldnorm: u32) {
let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.field_id() as usize];
let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.0 as usize];
assert!(
fieldnorm_buffer.len() <= doc as usize,
"Cannot register a given fieldnorm twice"
@@ -80,12 +75,11 @@ impl FieldNormsWriter {
}
/// Serialize the seen fieldnorm values to the serializer for all fields.
pub fn serialize(&self, mut fieldnorms_serializer: FieldNormsSerializer) -> io::Result<()> {
pub fn serialize(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> io::Result<()> {
for &field in self.fields.iter() {
let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.field_id() as usize][..];
let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.0 as usize][..];
fieldnorms_serializer.serialize_field(field, fieldnorm_values)?;
}
fieldnorms_serializer.close()?;
Ok(())
}
}

81
src/indexer/delete_queue.rs
View File

@@ -2,7 +2,7 @@ use super::operation::DeleteOperation;
use crate::Opstamp;
use std::mem;
use std::ops::DerefMut;
use std::sync::{Arc, RwLock, Weak};
use std::sync::{Arc, RwLock};
// The DeleteQueue is similar in conceptually to a multiple
// consumer single producer broadcast channel.
@@ -14,15 +14,14 @@ use std::sync::{Arc, RwLock, Weak};
//
// New consumer can be created in two ways
// - calling `delete_queue.cursor()` returns a cursor, that
// will include all future delete operation (and some or none
// of the past operations... The client is in charge of checking the opstamps.).
// will include all future delete operation (and no past operations).
// - cloning an existing cursor returns a new cursor, that
// is at the exact same position, and can now advance independently
// from the original cursor.
#[derive(Default)]
struct InnerDeleteQueue {
writer: Vec<DeleteOperation>,
last_block: Weak<Block>,
last_block: Option<Arc<Block>>,
}
#[derive(Clone)]
@@ -33,31 +32,21 @@ pub struct DeleteQueue {
impl DeleteQueue {
// Creates a new delete queue.
pub fn new() -> DeleteQueue {
DeleteQueue {
let delete_queue = DeleteQueue {
inner: Arc::default(),
}
}
};
let next_block = NextBlock::from(delete_queue.clone());
fn get_last_block(&self) -> Arc<Block> {
{
// try get the last block with simply acquiring the read lock.
let rlock = self.inner.read().unwrap();
if let Some(block) = rlock.last_block.upgrade() {
return block;
}
let mut delete_queue_wlock = delete_queue.inner.write().unwrap();
delete_queue_wlock.last_block = Some(Arc::new(Block {
operations: Arc::default(),
next: next_block,
}));
}
// It failed. Let's double check after acquiring the write, as someone could have called
// `get_last_block` right after we released the rlock.
let mut wlock = self.inner.write().unwrap();
if let Some(block) = wlock.last_block.upgrade() {
return block;
}
let block = Arc::new(Block {
operations: Arc::default(),
next: NextBlock::from(self.clone()),
});
wlock.last_block = Arc::downgrade(&block);
block
delete_queue
}
// Creates a new cursor that makes it possible to
@@ -65,7 +54,17 @@ impl DeleteQueue {
//
// Past delete operations are not accessible.
pub fn cursor(&self) -> DeleteCursor {
let last_block = self.get_last_block();
let last_block = self
.inner
.read()
.expect("Read lock poisoned when opening delete queue cursor")
.last_block
.clone()
.expect(
"Failed to unwrap last_block. This should never happen
as the Option<> is only here to make
initialization possible",
);
let operations_len = last_block.operations.len();
DeleteCursor {
block: last_block,
@@ -101,19 +100,23 @@ impl DeleteQueue {
.write()
.expect("Failed to acquire write lock on delete queue writer");
if self_wlock.writer.is_empty() {
return None;
let delete_operations;
{
let writer: &mut Vec<DeleteOperation> = &mut self_wlock.writer;
if writer.is_empty() {
return None;
}
delete_operations = mem::replace(writer, vec![]);
}
let delete_operations = mem::replace(&mut self_wlock.writer, vec![]);
let new_block = Arc::new(Block {
operations: Arc::new(delete_operations.into_boxed_slice()),
next: NextBlock::from(self.clone()),
});
self_wlock.last_block = Arc::downgrade(&new_block);
Some(new_block)
let next_block = NextBlock::from(self.clone());
{
self_wlock.last_block = Some(Arc::new(Block {
operations: Arc::new(delete_operations),
next: next_block,
}));
}
self_wlock.last_block.clone()
}
}
@@ -167,7 +170,7 @@ impl NextBlock {
}
struct Block {
operations: Arc<Box<[DeleteOperation]>>,
operations: Arc<Vec<DeleteOperation>>,
next: NextBlock,
}
@@ -255,7 +258,7 @@ mod tests {
let delete_queue = DeleteQueue::new();
let make_op = |i: usize| {
let field = Field::from_field_id(1u32);
let field = Field(1u32);
DeleteOperation {
opstamp: i as u64,
term: Term::from_field_u64(field, i as u64),

319
src/indexer/index_writer.rs
View File

@@ -1,16 +1,14 @@
use super::operation::{AddOperation, UserOperation};
use super::segment_updater::SegmentUpdater;
use super::PreparedCommit;
use crate::common::BitSet;
use crate::core::Index;
use crate::core::Segment;
use crate::core::SegmentComponent;
use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SegmentReader;
use crate::directory::TerminatingWrite;
use crate::directory::{DirectoryLock, GarbageCollectionResult};
use crate::docset::{DocSet, TERMINATED};
use crate::directory::DirectoryLock;
use crate::docset::DocSet;
use crate::error::TantivyError;
use crate::fastfield::write_delete_bitset;
use crate::indexer::delete_queue::{DeleteCursor, DeleteQueue};
@@ -24,9 +22,10 @@ use crate::schema::Document;
use crate::schema::IndexRecordOption;
use crate::schema::Term;
use crate::Opstamp;
use crate::Result;
use bit_set::BitSet;
use crossbeam::channel;
use futures::executor::block_on;
use futures::future::Future;
use futures::{Canceled, Future};
use smallvec::smallvec;
use smallvec::SmallVec;
use std::mem;
@@ -72,7 +71,7 @@ pub struct IndexWriter {
heap_size_in_bytes_per_thread: usize,
workers_join_handle: Vec<JoinHandle<crate::Result<()>>>,
workers_join_handle: Vec<JoinHandle<Result<()>>>,
operation_receiver: OperationReceiver,
operation_sender: OperationSender,
@@ -95,7 +94,7 @@ fn compute_deleted_bitset(
delete_cursor: &mut DeleteCursor,
doc_opstamps: &DocToOpstampMapping,
target_opstamp: Opstamp,
) -> crate::Result<bool> {
) -> Result<bool> {
let mut might_have_changed = false;
while let Some(delete_op) = delete_cursor.get() {
if delete_op.opstamp > target_opstamp {
@@ -108,96 +107,82 @@ fn compute_deleted_bitset(
// Limit doc helps identify the first document
// that may be affected by the delete operation.
let limit_doc = doc_opstamps.compute_doc_limit(delete_op.opstamp);
let inverted_index = segment_reader.inverted_index(delete_op.term.field())?;
let inverted_index = segment_reader.inverted_index(delete_op.term.field());
if let Some(mut docset) =
inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)?
inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)
{
let mut deleted_doc = docset.doc();
while deleted_doc != TERMINATED {
while docset.advance() {
let deleted_doc = docset.doc();
if deleted_doc < limit_doc {
delete_bitset.insert(deleted_doc);
delete_bitset.insert(deleted_doc as usize);
might_have_changed = true;
}
deleted_doc = docset.advance();
}
}
delete_cursor.advance();
}
Ok(might_have_changed)
}
/// Advance delete for the given segment up to the target opstamp.
///
/// Note that there are no guarantee that the resulting `segment_entry` delete_opstamp
/// is `==` target_opstamp.
/// For instance, there was no delete operation between the state of the `segment_entry` and
/// the `target_opstamp`, `segment_entry` is not updated.
/// Advance delete for the given segment up
/// to the target opstamp.
pub(crate) fn advance_deletes(
mut segment: Segment,
segment_entry: &mut SegmentEntry,
target_opstamp: Opstamp,
) -> crate::Result<()> {
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
return Ok(());
}
) -> Result<()> {
{
if segment_entry.meta().delete_opstamp() == Some(target_opstamp) {
// We are already up-to-date here.
return Ok(());
}
if segment_entry.delete_bitset().is_none() && segment_entry.delete_cursor().get().is_none() {
// There has been no `DeleteOperation` between the segment status and `target_opstamp`.
return Ok(());
}
let segment_reader = SegmentReader::open(&segment)?;
let segment_reader = SegmentReader::open(&segment)?;
let max_doc = segment_reader.max_doc();
let mut delete_bitset: BitSet = match segment_entry.delete_bitset() {
Some(previous_delete_bitset) => (*previous_delete_bitset).clone(),
None => BitSet::with_capacity(max_doc as usize),
};
let max_doc = segment_reader.max_doc();
let mut delete_bitset: BitSet = match segment_entry.delete_bitset() {
Some(previous_delete_bitset) => (*previous_delete_bitset).clone(),
None => BitSet::with_max_value(max_doc),
};
let delete_cursor = segment_entry.delete_cursor();
let num_deleted_docs_before = segment.meta().num_deleted_docs();
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
delete_cursor,
&DocToOpstampMapping::None,
target_opstamp,
)?;
compute_deleted_bitset(
&mut delete_bitset,
&segment_reader,
segment_entry.delete_cursor(),
&DocToOpstampMapping::None,
target_opstamp,
)?;
// TODO optimize
// It should be possible to do something smarter by manipulation bitsets directly
// to compute this union.
if let Some(seg_delete_bitset) = segment_reader.delete_bitset() {
// TODO optimize
for doc in 0u32..max_doc {
if seg_delete_bitset.is_deleted(doc) {
delete_bitset.insert(doc);
if segment_reader.is_deleted(doc) {
delete_bitset.insert(doc as usize);
}
}
}
let num_deleted_docs: u32 = delete_bitset.len() as u32;
if num_deleted_docs > num_deleted_docs_before {
// There are new deletes. We need to write a new delete file.
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, max_doc, &mut delete_file)?;
delete_file.terminate()?;
let num_deleted_docs = delete_bitset.len();
if num_deleted_docs > 0 {
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, &mut delete_file)?;
}
}
segment_entry.set_meta(segment.meta().clone());
Ok(())
}
fn index_documents(
memory_budget: usize,
segment: Segment,
segment: &Segment,
grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>,
segment_updater: &mut SegmentUpdater,
mut delete_cursor: DeleteCursor,
) -> crate::Result<bool> {
) -> Result<bool> {
let schema = segment.schema();
let segment_id = segment.id();
let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?;
for document_group in grouped_document_iterator {
for doc in document_group {
@@ -217,32 +202,25 @@ fn index_documents(
return Ok(false);
}
let max_doc = segment_writer.max_doc();
let num_docs = segment_writer.max_doc();
// this is ensured by the call to peek before starting
// the worker thread.
assert!(max_doc > 0);
assert!(num_docs > 0);
let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?;
let segment_with_max_doc = segment.with_max_doc(max_doc);
let segment_meta = segment
.index()
.inventory()
.new_segment_meta(segment_id, num_docs);
let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
let delete_bitset_opt = apply_deletes(
&segment_with_max_doc,
&mut delete_cursor,
&doc_opstamps,
last_docstamp,
)?;
let delete_bitset_opt =
apply_deletes(&segment, &mut delete_cursor, &doc_opstamps, last_docstamp)?;
let segment_entry = SegmentEntry::new(
segment_with_max_doc.meta().clone(),
delete_cursor,
delete_bitset_opt,
);
block_on(segment_updater.schedule_add_segment(segment_entry))?;
Ok(true)
let segment_entry = SegmentEntry::new(segment_meta, delete_cursor, delete_bitset_opt);
Ok(segment_updater.add_segment(segment_entry))
}
fn apply_deletes(
@@ -250,7 +228,7 @@ fn apply_deletes(
mut delete_cursor: &mut DeleteCursor,
doc_opstamps: &[Opstamp],
last_docstamp: Opstamp,
) -> crate::Result<Option<BitSet>> {
) -> Result<Option<BitSet<u32>>> {
if delete_cursor.get().is_none() {
// if there are no delete operation in the queue, no need
// to even open the segment.
@@ -258,9 +236,7 @@ fn apply_deletes(
}
let segment_reader = SegmentReader::open(segment)?;
let doc_to_opstamps = DocToOpstampMapping::from(doc_opstamps);
let max_doc = segment.meta().max_doc();
let mut deleted_bitset = BitSet::with_max_value(max_doc);
let mut deleted_bitset = BitSet::with_capacity(segment_reader.max_doc() as usize);
let may_have_deletes = compute_deleted_bitset(
&mut deleted_bitset,
&segment_reader,
@@ -295,7 +271,7 @@ impl IndexWriter {
num_threads: usize,
heap_size_in_bytes_per_thread: usize,
directory_lock: DirectoryLock,
) -> crate::Result<IndexWriter> {
) -> Result<IndexWriter> {
if heap_size_in_bytes_per_thread < HEAP_SIZE_MIN {
let err_msg = format!(
"The heap size per thread needs to be at least {}.",
@@ -344,17 +320,12 @@ impl IndexWriter {
Ok(index_writer)
}
fn drop_sender(&mut self) {
let (sender, _receiver) = channel::bounded(1);
self.operation_sender = sender;
}
/// If there are some merging threads, blocks until they all finish their work and
/// then drop the `IndexWriter`.
pub fn wait_merging_threads(mut self) -> crate::Result<()> {
pub fn wait_merging_threads(mut self) -> Result<()> {
// this will stop the indexing thread,
// dropping the last reference to the segment_updater.
self.drop_sender();
drop(self.operation_sender);
let former_workers_handles = mem::replace(&mut self.workers_join_handle, vec![]);
for join_handle in former_workers_handles {
@@ -365,6 +336,7 @@ impl IndexWriter {
TantivyError::ErrorInThread("Error in indexing worker thread.".into())
})?;
}
drop(self.workers_join_handle);
let result = self
.segment_updater
@@ -379,10 +351,10 @@ impl IndexWriter {
}
#[doc(hidden)]
pub fn add_segment(&self, segment_meta: SegmentMeta) -> crate::Result<()> {
pub fn add_segment(&mut self, segment_meta: SegmentMeta) {
let delete_cursor = self.delete_queue.cursor();
let segment_entry = SegmentEntry::new(segment_meta, delete_cursor, None);
block_on(self.segment_updater.schedule_add_segment(segment_entry))
self.segment_updater.add_segment(segment_entry);
}
/// Creates a new segment.
@@ -399,7 +371,7 @@ impl IndexWriter {
/// Spawns a new worker thread for indexing.
/// The thread consumes documents from the pipeline.
fn add_indexing_worker(&mut self) -> crate::Result<()> {
fn add_indexing_worker(&mut self) -> Result<()> {
let document_receiver_clone = self.operation_receiver.clone();
let mut segment_updater = self.segment_updater.clone();
@@ -407,7 +379,7 @@ impl IndexWriter {
let mem_budget = self.heap_size_in_bytes_per_thread;
let index = self.index.clone();
let join_handle: JoinHandle<crate::Result<()>> = thread::Builder::new()
let join_handle: JoinHandle<Result<()>> = thread::Builder::new()
.name(format!("thrd-tantivy-index{}", self.worker_id))
.spawn(move || {
loop {
@@ -436,7 +408,7 @@ impl IndexWriter {
let segment = index.new_segment();
index_documents(
mem_budget,
segment,
&segment,
&mut document_iterator,
&mut segment_updater,
delete_cursor.clone(),
@@ -453,23 +425,22 @@ impl IndexWriter {
self.segment_updater.get_merge_policy()
}
/// Setter for the merge policy.
/// Set the merge policy.
pub fn set_merge_policy(&self, merge_policy: Box<dyn MergePolicy>) {
self.segment_updater.set_merge_policy(merge_policy);
}
fn start_workers(&mut self) -> crate::Result<()> {
fn start_workers(&mut self) -> Result<()> {
for _ in 0..self.num_threads {
self.add_indexing_worker()?;
}
Ok(())
}
/// Detects and removes the files that are not used by the index anymore.
pub fn garbage_collect_files(
&self,
) -> impl Future<Output = crate::Result<GarbageCollectionResult>> {
self.segment_updater.schedule_garbage_collect()
/// Detects and removes the files that
/// are not used by the index anymore.
pub fn garbage_collect_files(&mut self) -> Result<()> {
self.segment_updater.garbage_collect_files().wait()
}
/// Deletes all documents from the index
@@ -479,10 +450,12 @@ impl IndexWriter {
/// by clearing and resubmitting necessary documents
///
/// ```rust
/// use tantivy::collector::TopDocs;
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::query::QueryParser;
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::*;
/// use tantivy::{doc, Index};
/// use tantivy::Index;
///
/// fn main() -> tantivy::Result<()> {
/// let mut schema_builder = Schema::builder();
@@ -508,7 +481,7 @@ impl IndexWriter {
/// Ok(())
/// }
/// ```
pub fn delete_all_documents(&self) -> crate::Result<Opstamp> {
pub fn delete_all_documents(&mut self) -> Result<Opstamp> {
// Delete segments
self.segment_updater.remove_all_segments();
// Return new stamp - reverted stamp
@@ -522,10 +495,8 @@ impl IndexWriter {
pub fn merge(
&mut self,
segment_ids: &[SegmentId],
) -> impl Future<Output = crate::Result<SegmentMeta>> {
let merge_operation = self.segment_updater.make_merge_operation(segment_ids);
let segment_updater = self.segment_updater.clone();
async move { segment_updater.start_merge(merge_operation)?.await }
) -> Result<impl Future<Item = SegmentMeta, Error = Canceled>> {
self.segment_updater.start_merge(segment_ids)
}
/// Closes the current document channel send.
@@ -536,7 +507,6 @@ impl IndexWriter {
/// when no documents are remaining.
///
/// Returns the former segment_ready channel.
#[allow(unused_must_use)]
fn recreate_document_channel(&mut self) -> OperationReceiver {
let (document_sender, document_receiver): (OperationSender, OperationReceiver) =
channel::bounded(PIPELINE_MAX_SIZE_IN_DOCS);
@@ -552,8 +522,13 @@ impl IndexWriter {
/// state as it was after the last commit.
///
/// The opstamp at the last commit is returned.
pub fn rollback(&mut self) -> crate::Result<Opstamp> {
pub fn rollback(&mut self) -> Result<Opstamp> {
info!("Rolling back to opstamp {}", self.committed_opstamp);
self.rollback_impl()
}
/// Private, implementation of rollback
fn rollback_impl(&mut self) -> Result<Opstamp> {
// marks the segment updater as killed. From now on, all
// segment updates will be ignored.
self.segment_updater.kill();
@@ -576,7 +551,7 @@ impl IndexWriter {
//
// This will drop the document queue, and the thread
// should terminate.
*self = new_index_writer;
mem::replace(self, new_index_writer);
// Drains the document receiver pipeline :
// Workers don't need to index the pending documents.
@@ -609,7 +584,7 @@ impl IndexWriter {
/// It is also possible to add a payload to the `commit`
/// using this API.
/// See [`PreparedCommit::set_payload()`](PreparedCommit.html)
pub fn prepare_commit(&mut self) -> crate::Result<PreparedCommit> {
pub fn prepare_commit(&mut self) -> Result<PreparedCommit<'_>> {
// Here, because we join all of the worker threads,
// all of the segment update for this commit have been
// sent.
@@ -656,7 +631,7 @@ impl IndexWriter {
/// Commit returns the `opstamp` of the last document
/// that made it in the commit.
///
pub fn commit(&mut self) -> crate::Result<Opstamp> {
pub fn commit(&mut self) -> Result<Opstamp> {
self.prepare_commit()?.commit()
}
@@ -697,6 +672,9 @@ impl IndexWriter {
/// The opstamp is an increasing `u64` that can
/// be used by the client to align commits with its own
/// document queue.
///
/// Currently it represents the number of documents that
/// have been added since the creation of the index.
pub fn add_document(&self, document: Document) -> Opstamp {
let opstamp = self.stamper.stamp();
let add_operation = AddOperation { opstamp, document };
@@ -770,16 +748,6 @@ impl IndexWriter {
}
}
impl Drop for IndexWriter {
fn drop(&mut self) {
self.segment_updater.kill();
self.drop_sender();
for work in self.workers_join_handle.drain(..) {
let _ = work.join();
}
}
}
#[cfg(test)]
mod tests {
@@ -789,10 +757,11 @@ mod tests {
use crate::error::*;
use crate::indexer::NoMergePolicy;
use crate::query::TermQuery;
use crate::schema::{self, IndexRecordOption, STRING};
use crate::schema::{self, IndexRecordOption};
use crate::Index;
use crate::ReloadPolicy;
use crate::Term;
use fail;
#[test]
fn test_operations_group() {
@@ -800,7 +769,7 @@ mod tests {
let mut schema_builder = schema::Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_in_ram(schema_builder.build());
let index_writer = index.writer_for_tests().unwrap();
let index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let operations = vec![
UserOperation::Add(doc!(text_field=>"a")),
UserOperation::Add(doc!(text_field=>"b")),
@@ -809,46 +778,6 @@ mod tests {
assert_eq!(batch_opstamp1, 2u64);
}
#[test]
fn test_no_need_to_rewrite_delete_file_if_no_new_deletes() {
let mut schema_builder = schema::Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(text_field => "hello1"));
index_writer.add_document(doc!(text_field => "hello2"));
assert!(index_writer.commit().is_ok());
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
assert_eq!(searcher.segment_reader(0u32).num_deleted_docs(), 0);
index_writer.delete_term(Term::from_field_text(text_field, "hello1"));
assert!(index_writer.commit().is_ok());
assert!(reader.reload().is_ok());
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
assert_eq!(searcher.segment_reader(0u32).num_deleted_docs(), 1);
let previous_delete_opstamp = index.load_metas().unwrap().segments[0].delete_opstamp();
// All docs containing hello1 have been already removed.
// We should not update the delete meta.
index_writer.delete_term(Term::from_field_text(text_field, "hello1"));
assert!(index_writer.commit().is_ok());
assert!(reader.reload().is_ok());
let searcher = reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
assert_eq!(searcher.segment_reader(0u32).num_deleted_docs(), 1);
let after_delete_opstamp = index.load_metas().unwrap().segments[0].delete_opstamp();
assert_eq!(after_delete_opstamp, previous_delete_opstamp);
}
#[test]
fn test_ordered_batched_operations() {
// * one delete for `doc!(field=>"a")`
@@ -864,7 +793,7 @@ mod tests {
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
let a_term = Term::from_field_text(text_field, "a");
let b_term = Term::from_field_text(text_field, "b");
let operations = vec![
@@ -926,8 +855,8 @@ mod tests {
fn test_lockfile_already_exists_error_msg() {
let schema_builder = schema::Schema::builder();
let index = Index::create_in_ram(schema_builder.build());
let _index_writer = index.writer_for_tests().unwrap();
match index.writer_for_tests() {
let _index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
match index.writer_with_num_threads(1, 3_000_000) {
Err(err) => {
let err_msg = err.to_string();
assert!(err_msg.contains("already an `IndexWriter`"));
@@ -943,7 +872,7 @@ mod tests {
let index_writer = index.writer(3_000_000).unwrap();
assert_eq!(
format!("{:?}", index_writer.get_merge_policy()),
"LogMergePolicy { min_merge_size: 8, max_merge_size: 10000000, min_layer_size: 10000, \
"LogMergePolicy { min_merge_size: 8, min_layer_size: 10000, \
level_log_size: 0.75 }"
);
let merge_policy = Box::new(NoMergePolicy::default());
@@ -979,7 +908,7 @@ mod tests {
let num_docs_containing = |s: &str| {
let searcher = reader.searcher();
let term = Term::from_field_text(text_field, s);
searcher.doc_freq(&term).unwrap()
searcher.doc_freq(&term)
};
{
@@ -1015,7 +944,7 @@ mod tests {
.unwrap();
let num_docs_containing = |s: &str| {
let term_a = Term::from_field_text(text_field, s);
reader.searcher().doc_freq(&term_a).unwrap()
reader.searcher().doc_freq(&term_a)
};
{
// writing the segment
@@ -1110,7 +1039,6 @@ mod tests {
.unwrap()
.searcher()
.doc_freq(&term_a)
.unwrap()
};
assert_eq!(num_docs_containing("a"), 0);
assert_eq!(num_docs_containing("b"), 100);
@@ -1130,7 +1058,7 @@ mod tests {
reader.reload().unwrap();
let searcher = reader.searcher();
let term = Term::from_field_text(text_field, s);
searcher.doc_freq(&term).unwrap()
searcher.doc_freq(&term)
};
let mut index_writer = index.writer_with_num_threads(4, 12_000_000).unwrap();
@@ -1181,15 +1109,7 @@ mod tests {
// working with an empty index == no documents
let term_b = Term::from_field_text(text_field, "b");
assert_eq!(
index
.reader()
.unwrap()
.searcher()
.doc_freq(&term_b)
.unwrap(),
0
);
assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_b), 0);
}
#[test]
@@ -1209,15 +1129,7 @@ mod tests {
let term_a = Term::from_field_text(text_field, "a");
// expect the document with that term to be in the index
assert_eq!(
index
.reader()
.unwrap()
.searcher()
.doc_freq(&term_a)
.unwrap(),
1
);
assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_a), 1);
}
#[test]
@@ -1243,15 +1155,7 @@ mod tests {
// Find original docs in the index
let term_a = Term::from_field_text(text_field, "a");
// expect the document with that term to be in the index
assert_eq!(
index
.reader()
.unwrap()
.searcher()
.doc_freq(&term_a)
.unwrap(),
1
);
assert_eq!(index.reader().unwrap().searcher().doc_freq(&term_a), 1);
}
#[test]
@@ -1280,15 +1184,4 @@ mod tests {
assert!(commit_again.is_ok());
}
#[test]
fn test_index_doc_missing_field() {
let mut schema_builder = schema::Schema::builder();
let idfield = schema_builder.add_text_field("id", STRING);
schema_builder.add_text_field("optfield", STRING);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests().unwrap();
index_writer.add_document(doc!(idfield=>"myid"));
let commit = index_writer.commit();
assert!(commit.is_ok());
}
}

88
src/indexer/log_merge_policy.rs
View File

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

19
src/indexer/merge_operation.rs
View File

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

719
src/indexer/merger.rs
View File

File diff suppressed because it is too large Load Diff

26
src/indexer/mod.rs
View File

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

2
src/indexer/operation.rs
View File

@@ -19,8 +19,6 @@ pub struct AddOperation {
/// UserOperation is an enum type that encapsulates other operation types.
#[derive(Eq, PartialEq, Debug)]
pub enum UserOperation {
/// Add operation
Add(Document),
/// Delete operation
Delete(Term),
}

14
src/indexer/prepared_commit.rs
View File

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

2
src/indexer/segment_entry.rs
View File

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

63
src/indexer/segment_manager.rs
View File

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

1
src/indexer/segment_register.rs
View File

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

30
src/indexer/segment_serializer.rs
View File

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

478
src/indexer/segment_updater.rs
View File

@@ -6,33 +6,39 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta;
use crate::core::SerializableSegment;
use crate::core::META_FILEPATH;
use crate::directory::{Directory, DirectoryClone, GarbageCollectionResult};
use crate::directory::{Directory, DirectoryClone};
use crate::error::TantivyError;
use crate::indexer::delete_queue::DeleteCursor;
use crate::indexer::index_writer::advance_deletes;
use crate::indexer::merge_operation::MergeOperationInventory;
use crate::indexer::merger::IndexMerger;
use crate::indexer::segment_manager::SegmentsStatus;
use crate::indexer::stamper::Stamper;
use crate::indexer::MergeOperation;
use crate::indexer::SegmentEntry;
use crate::indexer::SegmentSerializer;
use crate::indexer::{DefaultMergePolicy, MergePolicy};
use crate::indexer::{MergeCandidate, MergeOperation};
use crate::schema::Schema;
use crate::Opstamp;
use futures::channel::oneshot;
use futures::executor::{ThreadPool, ThreadPoolBuilder};
use futures::future::Future;
use futures::future::TryFutureExt;
use crate::Result;
use futures::oneshot;
use futures::sync::oneshot::Receiver;
use futures::Future;
use futures_cpupool::Builder as CpuPoolBuilder;
use futures_cpupool::CpuFuture;
use futures_cpupool::CpuPool;
use serde_json;
use std::borrow::BorrowMut;
use std::collections::HashMap;
use std::collections::HashSet;
use std::io::Write;
use std::ops::Deref;
use std::mem;
use std::ops::DerefMut;
use std::path::PathBuf;
use std::sync::atomic::{AtomicBool, Ordering};
use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering};
use std::sync::Arc;
use std::sync::RwLock;
const NUM_MERGE_THREADS: usize = 4;
use std::thread;
use std::thread::JoinHandle;
/// Save the index meta file.
/// This operation is atomic :
@@ -43,7 +49,7 @@ const NUM_MERGE_THREADS: usize = 4;
/// and flushed.
///
/// This method is not part of tantivy's public API
pub fn save_new_metas(schema: Schema, directory: &dyn Directory) -> crate::Result<()> {
pub fn save_new_metas(schema: Schema, directory: &mut dyn Directory) -> Result<()> {
save_metas(
&IndexMeta {
segments: Vec::new(),
@@ -64,7 +70,7 @@ pub fn save_new_metas(schema: Schema, directory: &dyn Directory) -> crate::Resul
/// and flushed.
///
/// This method is not part of tantivy's public API
fn save_metas(metas: &IndexMeta, directory: &dyn Directory) -> crate::Result<()> {
fn save_metas(metas: &IndexMeta, directory: &mut dyn Directory) -> Result<()> {
info!("save metas");
let mut buffer = serde_json::to_vec_pretty(metas)?;
// Just adding a new line at the end of the buffer.
@@ -83,38 +89,21 @@ fn save_metas(metas: &IndexMeta, directory: &dyn Directory) -> crate::Result<()>
// We voluntarily pass a merge_operation ref to guarantee that
// the merge_operation is alive during the process
#[derive(Clone)]
pub(crate) struct SegmentUpdater(Arc<InnerSegmentUpdater>);
pub struct SegmentUpdater(Arc<InnerSegmentUpdater>);
impl Deref for SegmentUpdater {
type Target = InnerSegmentUpdater;
#[inline]
fn deref(&self) -> &Self::Target {
&self.0
}
}
async fn garbage_collect_files(
segment_updater: SegmentUpdater,
) -> crate::Result<GarbageCollectionResult> {
info!("Running garbage collection");
let mut index = segment_updater.index.clone();
index
.directory_mut()
.garbage_collect(move || segment_updater.list_files())
}
/// Merges a list of segments the list of segment givens in the `segment_entries`.
/// This function happens in the calling thread and is computationally expensive.
fn merge(
fn perform_merge(
merge_operation: &MergeOperation,
index: &Index,
mut segment_entries: Vec<SegmentEntry>,
target_opstamp: Opstamp,
) -> crate::Result<SegmentEntry> {
// first we need to apply deletes to our segment.
let merged_segment = index.new_segment();
) -> Result<SegmentEntry> {
let target_opstamp = merge_operation.target_opstamp();
// first we need to apply deletes to our segment.
let mut merged_segment = index.new_segment();
// TODO add logging
let schema = index.schema();
// First we apply all of the delet to the merged segment, up to the target opstamp.
for segment_entry in &mut segment_entries {
let segment = index.segment(segment_entry.meta().clone());
advance_deletes(segment, segment_entry, target_opstamp)?;
@@ -128,20 +117,24 @@ fn merge(
.collect();
// An IndexMerger is like a "view" of our merged segments.
let merger: IndexMerger = IndexMerger::open(index.schema(), &segments[..])?;
let merger: IndexMerger = IndexMerger::open(schema, &segments[..])?;
// ... we just serialize this index merger in our new segment to merge the two segments.
let segment_serializer = SegmentSerializer::for_segment(merged_segment.clone())?;
// ... we just serialize this index merger in our new segment
// to merge the two segments.
let segment_serializer = SegmentSerializer::for_segment(&mut merged_segment)?;
let num_docs = merger.write(segment_serializer)?;
let merged_segment_id = merged_segment.id();
let segment_meta = index
.inventory()
.new_segment_meta(merged_segment.id(), num_docs);
let segment_meta = index.new_segment_meta(merged_segment_id, num_docs);
Ok(SegmentEntry::new(segment_meta, delete_cursor, None))
let after_merge_segment_entry = SegmentEntry::new(segment_meta.clone(), delete_cursor, None);
Ok(after_merge_segment_entry)
}
pub(crate) struct InnerSegmentUpdater {
struct InnerSegmentUpdater {
// we keep a copy of the current active IndexMeta to
// avoid loading the file everytime we need it in the
// `SegmentUpdater`.
@@ -149,12 +142,12 @@ pub(crate) struct InnerSegmentUpdater {
// This should be up to date as all update happen through
// the unique active `SegmentUpdater`.
active_metas: RwLock<Arc<IndexMeta>>,
pool: ThreadPool,
merge_thread_pool: ThreadPool,
pool: CpuPool,
index: Index,
segment_manager: SegmentManager,
merge_policy: RwLock<Arc<Box<dyn MergePolicy>>>,
merging_thread_id: AtomicUsize,
merging_threads: RwLock<HashMap<usize, JoinHandle<Result<()>>>>,
killed: AtomicBool,
stamper: Stamper,
merge_operations: MergeOperationInventory,
@@ -165,35 +158,22 @@ impl SegmentUpdater {
index: Index,
stamper: Stamper,
delete_cursor: &DeleteCursor,
) -> crate::Result<SegmentUpdater> {
) -> Result<SegmentUpdater> {
let segments = index.searchable_segment_metas()?;
let segment_manager = SegmentManager::from_segments(segments, delete_cursor);
let pool = ThreadPoolBuilder::new()
let pool = CpuPoolBuilder::new()
.name_prefix("segment_updater")
.pool_size(1)
.create()
.map_err(|_| {
crate::TantivyError::SystemError(
"Failed to spawn segment updater thread".to_string(),
)
})?;
let merge_thread_pool = ThreadPoolBuilder::new()
.name_prefix("merge_thread")
.pool_size(NUM_MERGE_THREADS)
.create()
.map_err(|_| {
crate::TantivyError::SystemError(
"Failed to spawn segment merging thread".to_string(),
)
})?;
.create();
let index_meta = index.load_metas()?;
Ok(SegmentUpdater(Arc::new(InnerSegmentUpdater {
active_metas: RwLock::new(Arc::new(index_meta)),
pool,
merge_thread_pool,
index,
segment_manager,
merge_policy: RwLock::new(Arc::new(Box::new(DefaultMergePolicy::default()))),
merging_thread_id: AtomicUsize::default(),
merging_threads: RwLock::new(HashMap::new()),
killed: AtomicBool::new(false),
stamper,
merge_operations: Default::default(),
@@ -201,82 +181,67 @@ impl SegmentUpdater {
}
pub fn get_merge_policy(&self) -> Arc<Box<dyn MergePolicy>> {
self.merge_policy.read().unwrap().clone()
self.0.merge_policy.read().unwrap().clone()
}
pub fn set_merge_policy(&self, merge_policy: Box<dyn MergePolicy>) {
let arc_merge_policy = Arc::new(merge_policy);
*self.merge_policy.write().unwrap() = arc_merge_policy;
*self.0.merge_policy.write().unwrap() = arc_merge_policy;
}
fn schedule_future<T: 'static + Send, F: Future<Output = crate::Result<T>> + 'static + Send>(
fn get_merging_thread_id(&self) -> usize {
self.0.merging_thread_id.fetch_add(1, Ordering::SeqCst)
}
fn run_async<T: 'static + Send, F: 'static + Send + FnOnce(SegmentUpdater) -> T>(
&self,
f: F,
) -> impl Future<Output = crate::Result<T>> {
let (sender, receiver) = oneshot::channel();
if self.is_alive() {
self.pool.spawn_ok(async move {
let _ = sender.send(f.await);
});
} else {
let _ = sender.send(Err(crate::TantivyError::SystemError(
"Segment updater killed".to_string(),
)));
}
receiver.unwrap_or_else(|_| {
let err_msg =
"A segment_updater future did not success. This should never happen.".to_string();
Err(crate::TantivyError::SystemError(err_msg))
})
) -> CpuFuture<T, TantivyError> {
let me_clone = self.clone();
self.0.pool.spawn_fn(move || Ok(f(me_clone)))
}
pub fn schedule_add_segment(
&self,
segment_entry: SegmentEntry,
) -> impl Future<Output = crate::Result<()>> {
let segment_updater = self.clone();
self.schedule_future(async move {
segment_updater.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options().await;
Ok(())
pub fn add_segment(&self, segment_entry: SegmentEntry) -> bool {
self.run_async(|segment_updater| {
segment_updater.0.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options();
true
})
.forget();
true
}
/// Orders `SegmentManager` to remove all segments
pub(crate) fn remove_all_segments(&self) {
self.segment_manager.remove_all_segments();
self.0.segment_manager.remove_all_segments();
}
pub fn kill(&mut self) {
self.killed.store(true, Ordering::Release);
self.0.killed.store(true, Ordering::Release);
}
pub fn is_alive(&self) -> bool {
!self.killed.load(Ordering::Acquire)
!self.0.killed.load(Ordering::Acquire)
}
/// Apply deletes up to the target opstamp to all segments.
///
/// The method returns copies of the segment entries,
/// updated with the delete information.
fn purge_deletes(&self, target_opstamp: Opstamp) -> crate::Result<Vec<SegmentEntry>> {
let mut segment_entries = self.segment_manager.segment_entries();
fn purge_deletes(&self, target_opstamp: Opstamp) -> Result<Vec<SegmentEntry>> {
let mut segment_entries = self.0.segment_manager.segment_entries();
for segment_entry in &mut segment_entries {
let segment = self.index.segment(segment_entry.meta().clone());
let segment = self.0.index.segment(segment_entry.meta().clone());
advance_deletes(segment, segment_entry, target_opstamp)?;
}
Ok(segment_entries)
}
pub fn save_metas(
&self,
opstamp: Opstamp,
commit_message: Option<String>,
) -> crate::Result<()> {
pub fn save_metas(&self, opstamp: Opstamp, commit_message: Option<String>) {
if self.is_alive() {
let index = &self.index;
let index = &self.0.index;
let directory = index.directory();
let mut commited_segment_metas = self.segment_manager.committed_segment_metas();
let mut commited_segment_metas = self.0.segment_manager.committed_segment_metas();
// We sort segment_readers by number of documents.
// This is an heuristic to make multithreading more efficient.
@@ -298,18 +263,16 @@ impl SegmentUpdater {
opstamp,
payload: commit_message,
};
// TODO add context to the error.
save_metas(&index_meta, directory.box_clone().borrow_mut())?;
save_metas(&index_meta, directory.box_clone().borrow_mut())
.expect("Could not save metas.");
self.store_meta(&index_meta);
}
Ok(())
}
pub fn schedule_garbage_collect(
&self,
) -> impl Future<Output = crate::Result<GarbageCollectionResult>> {
let garbage_collect_future = garbage_collect_files(self.clone());
self.schedule_future(garbage_collect_future)
pub fn garbage_collect_files(&self) -> CpuFuture<(), TantivyError> {
self.run_async(move |segment_updater| {
segment_updater.garbage_collect_files_exec();
})
}
/// List the files that are useful to the index.
@@ -317,130 +280,148 @@ impl SegmentUpdater {
/// This does not include lock files, or files that are obsolete
/// but have not yet been deleted by the garbage collector.
fn list_files(&self) -> HashSet<PathBuf> {
let mut files: HashSet<PathBuf> = self
.index
.list_all_segment_metas()
.into_iter()
.flat_map(|segment_meta| segment_meta.list_files())
.collect();
let mut files = HashSet::new();
files.insert(META_FILEPATH.to_path_buf());
for segment_meta in self.0.index.inventory().all() {
files.extend(segment_meta.list_files());
}
files
}
pub fn schedule_commit(
&self,
opstamp: Opstamp,
payload: Option<String>,
) -> impl Future<Output = crate::Result<()>> {
let segment_updater: SegmentUpdater = self.clone();
self.schedule_future(async move {
let segment_entries = segment_updater.purge_deletes(opstamp)?;
segment_updater.segment_manager.commit(segment_entries);
segment_updater.save_metas(opstamp, payload)?;
let _ = garbage_collect_files(segment_updater.clone()).await;
segment_updater.consider_merge_options().await;
Ok(())
fn garbage_collect_files_exec(&self) {
info!("Running garbage collection");
let mut index = self.0.index.clone();
index.directory_mut().garbage_collect(|| self.list_files());
}
pub fn commit(&self, opstamp: Opstamp, payload: Option<String>) -> Result<()> {
self.run_async(move |segment_updater| {
if segment_updater.is_alive() {
let segment_entries = segment_updater
.purge_deletes(opstamp)
.expect("Failed purge deletes");
segment_updater.0.segment_manager.commit(segment_entries);
segment_updater.save_metas(opstamp, payload);
segment_updater.garbage_collect_files_exec();
segment_updater.consider_merge_options();
}
})
.wait()
}
pub fn start_merge(&self, segment_ids: &[SegmentId]) -> Result<Receiver<SegmentMeta>> {
let commit_opstamp = self.load_metas().opstamp;
let merge_operation = MergeOperation::new(
&self.0.merge_operations,
commit_opstamp,
segment_ids.to_vec(),
);
self.run_async(move |segment_updater| segment_updater.start_merge_impl(merge_operation))
.wait()?
}
fn store_meta(&self, index_meta: &IndexMeta) {
*self.active_metas.write().unwrap() = Arc::new(index_meta.clone());
*self.0.active_metas.write().unwrap() = Arc::new(index_meta.clone());
}
fn load_metas(&self) -> Arc<IndexMeta> {
self.active_metas.read().unwrap().clone()
self.0.active_metas.read().unwrap().clone()
}
pub(crate) fn make_merge_operation(&self, segment_ids: &[SegmentId]) -> MergeOperation {
let commit_opstamp = self.load_metas().opstamp;
MergeOperation::new(&self.merge_operations, commit_opstamp, segment_ids.to_vec())
}
// Starts a merge operation. This function will block until the merge operation is effectively
// started. Note that it does not wait for the merge to terminate.
// The calling thread should not be block for a long time, as this only involve waiting for the
// `SegmentUpdater` queue which in turns only contains lightweight operations.
//
// The merge itself happens on a different thread.
//
// When successful, this function returns a `Future` for a `Result<SegmentMeta>` that represents
// the actual outcome of the merge operation.
//
// It returns an error if for some reason the merge operation could not be started.
//
// At this point an error is not necessarily the sign of a malfunction.
// (e.g. A rollback could have happened, between the instant when the merge operaiton was
// suggested and the moment when it ended up being executed.)
//
// `segment_ids` is required to be non-empty.
pub fn start_merge(
&self,
merge_operation: MergeOperation,
) -> crate::Result<impl Future<Output = crate::Result<SegmentMeta>>> {
fn start_merge_impl(&self, merge_operation: MergeOperation) -> Result<Receiver<SegmentMeta>> {
assert!(
!merge_operation.segment_ids().is_empty(),
"Segment_ids cannot be empty."
);
let segment_updater = self.clone();
let segment_updater_clone = self.clone();
let segment_entries: Vec<SegmentEntry> = self
.0
.segment_manager
.start_merge(merge_operation.segment_ids())?;
info!("Starting merge - {:?}", merge_operation.segment_ids());
// let segment_ids_vec = merge_operation.segment_ids.to_vec();
let (merging_future_send, merging_future_recv) =
oneshot::channel::<crate::Result<SegmentMeta>>();
let merging_thread_id = self.get_merging_thread_id();
info!(
"Starting merge thread #{} - {:?}",
merging_thread_id,
merge_operation.segment_ids()
);
let (merging_future_send, merging_future_recv) = oneshot();
self.merge_thread_pool.spawn_ok(async move {
// The fact that `merge_operation` is moved here is important.
// Its lifetime is used to track how many merging thread are currently running,
// as well as which segment is currently in merge and therefore should not be
// candidate for another merge.
match merge(
&segment_updater.index,
segment_entries,
merge_operation.target_opstamp(),
) {
Ok(after_merge_segment_entry) => {
let segment_meta = segment_updater
.end_merge(merge_operation, after_merge_segment_entry)
.await;
let _send_result = merging_future_send.send(segment_meta);
}
Err(e) => {
warn!(
"Merge of {:?} was cancelled: {:?}",
merge_operation.segment_ids().to_vec(),
e
);
// ... cancel merge
if cfg!(test) {
panic!("Merge failed.");
// first we need to apply deletes to our segment.
let merging_join_handle = thread::Builder::new()
.name(format!("mergingthread-{}", merging_thread_id))
.spawn(move || {
// first we need to apply deletes to our segment.
let merge_result = perform_merge(
&merge_operation,
&segment_updater_clone.0.index,
segment_entries,
);
match merge_result {
Ok(after_merge_segment_entry) => {
let merged_segment_meta = after_merge_segment_entry.meta().clone();
segment_updater_clone
.end_merge(merge_operation, after_merge_segment_entry)
.expect("Segment updater thread is corrupted.");
// the future may fail if the listener of the oneshot future
// has been destroyed.
//
// This is not a problem here, so we just ignore any
// possible error.
let _merging_future_res = merging_future_send.send(merged_segment_meta);
}
Err(e) => {
warn!(
"Merge of {:?} was cancelled: {:?}",
merge_operation.segment_ids(),
e
);
// ... cancel merge
if cfg!(test) {
panic!("Merge failed.");
}
// As `merge_operation` will be dropped, the segment in merge state will
// be available for merge again.
// `merging_future_send` will be dropped, sending an error to the future.
}
}
}
});
Ok(merging_future_recv
.unwrap_or_else(|_| Err(crate::TantivyError::SystemError("Merge failed".to_string()))))
segment_updater_clone
.0
.merging_threads
.write()
.unwrap()
.remove(&merging_thread_id);
Ok(())
})
.expect("Failed to spawn a thread.");
self.0
.merging_threads
.write()
.unwrap()
.insert(merging_thread_id, merging_join_handle);
Ok(merging_future_recv)
}
async fn consider_merge_options(&self) {
let merge_segment_ids: HashSet<SegmentId> = self.merge_operations.segment_in_merge();
fn consider_merge_options(&self) {
let merge_segment_ids: HashSet<SegmentId> = self.0.merge_operations.segment_in_merge();
let (committed_segments, uncommitted_segments) =
get_mergeable_segments(&merge_segment_ids, &self.segment_manager);
get_mergeable_segments(&merge_segment_ids, &self.0.segment_manager);
// Committed segments cannot be merged with uncommitted_segments.
// We therefore consider merges using these two sets of segments independently.
let merge_policy = self.get_merge_policy();
let current_opstamp = self.stamper.stamp();
let current_opstamp = self.0.stamper.stamp();
let mut merge_candidates: Vec<MergeOperation> = merge_policy
.compute_merge_candidates(&uncommitted_segments)
.into_iter()
.map(|merge_candidate| {
MergeOperation::new(&self.merge_operations, current_opstamp, merge_candidate.0)
MergeOperation::new(&self.0.merge_operations, current_opstamp, merge_candidate.0)
})
.collect();
@@ -448,17 +429,25 @@ impl SegmentUpdater {
let committed_merge_candidates = merge_policy
.compute_merge_candidates(&committed_segments)
.into_iter()
.map(|merge_candidate: MergeCandidate| {
MergeOperation::new(&self.merge_operations, commit_opstamp, merge_candidate.0)
});
merge_candidates.extend(committed_merge_candidates);
.map(|merge_candidate| {
MergeOperation::new(&self.0.merge_operations, commit_opstamp, merge_candidate.0)
})
.collect::<Vec<_>>();
merge_candidates.extend(committed_merge_candidates.into_iter());
for merge_operation in merge_candidates {
if let Err(err) = self.start_merge(merge_operation) {
warn!(
"Starting the merge failed for the following reason. This is not fatal. {}",
err
);
match self.start_merge_impl(merge_operation) {
Ok(merge_future) => {
if let Err(e) = merge_future.fuse().poll() {
error!("The merge task failed quickly after starting: {:?}", e);
}
}
Err(err) => {
warn!(
"Starting the merge failed for the following reason. This is not fatal. {}",
err
);
}
}
}
}
@@ -467,17 +456,15 @@ impl SegmentUpdater {
&self,
merge_operation: MergeOperation,
mut after_merge_segment_entry: SegmentEntry,
) -> impl Future<Output = crate::Result<SegmentMeta>> {
let segment_updater = self.clone();
let after_merge_segment_meta = after_merge_segment_entry.meta().clone();
let end_merge_future = self.schedule_future(async move {
) -> Result<()> {
self.run_async(move |segment_updater| {
info!("End merge {:?}", after_merge_segment_entry.meta());
{
let mut delete_cursor = after_merge_segment_entry.delete_cursor().clone();
if let Some(delete_operation) = delete_cursor.get() {
let committed_opstamp = segment_updater.load_metas().opstamp;
if delete_operation.opstamp < committed_opstamp {
let index = &segment_updater.index;
let index = &segment_updater.0.index;
let segment = index.segment(after_merge_segment_entry.meta().clone());
if let Err(e) = advance_deletes(
segment,
@@ -495,33 +482,28 @@ impl SegmentUpdater {
// ... cancel merge
// `merge_operations` are tracked. As it is dropped, the
// the segment_ids will be available again for merge.
return Err(e);
return;
}
}
}
let previous_metas = segment_updater.load_metas();
let segments_status = segment_updater
segment_updater
.0
.segment_manager
.end_merge(merge_operation.segment_ids(), after_merge_segment_entry)?;
if segments_status == SegmentsStatus::Committed {
segment_updater
.save_metas(previous_metas.opstamp, previous_metas.payload.clone())?;
}
segment_updater.consider_merge_options().await;
.end_merge(merge_operation.segment_ids(), after_merge_segment_entry);
segment_updater.consider_merge_options();
segment_updater.save_metas(previous_metas.opstamp, previous_metas.payload.clone());
} // we drop all possible handle to a now useless `SegmentMeta`.
let _ = garbage_collect_files(segment_updater).await;
Ok(())
});
end_merge_future.map_ok(|_| after_merge_segment_meta)
segment_updater.garbage_collect_files_exec();
})
.wait()
}
/// Wait for current merging threads.
///
/// Upon termination of the current merging threads,
/// merge opportunity may appear.
///
//
/// We keep waiting until the merge policy judges that
/// no opportunity is available.
///
@@ -532,9 +514,26 @@ impl SegmentUpdater {
///
/// Obsolete files will eventually be cleaned up
/// by the directory garbage collector.
pub fn wait_merging_thread(&self) -> crate::Result<()> {
self.merge_operations.wait_until_empty();
Ok(())
pub fn wait_merging_thread(&self) -> Result<()> {
loop {
let merging_threads: HashMap<usize, JoinHandle<Result<()>>> = {
let mut merging_threads = self.0.merging_threads.write().unwrap();
mem::replace(merging_threads.deref_mut(), HashMap::new())
};
if merging_threads.is_empty() {
return Ok(());
}
debug!("wait merging thread {}", merging_threads.len());
for (_, merging_thread_handle) in merging_threads {
merging_thread_handle
.join()
.map(|_| ())
.map_err(|_| TantivyError::ErrorInThread("Merging thread failed.".into()))?;
}
// Our merging thread may have queued their completed merged segment.
// Let's wait for that too.
self.run_async(move |_| {}).wait()?;
}
}
}
@@ -554,7 +553,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
index_writer.set_merge_policy(Box::new(MergeWheneverPossible));
{
@@ -607,7 +606,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
{
for _ in 0..100 {
@@ -678,7 +677,7 @@ mod tests {
let index = Index::create_in_ram(schema);
// writing the segment
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
{
for _ in 0..100 {
@@ -690,6 +689,7 @@ mod tests {
index_writer.segment_updater().remove_all_segments();
let seg_vec = index_writer
.segment_updater()
.0
.segment_manager
.segment_entries();
assert!(seg_vec.is_empty());

241
src/indexer/segment_writer.rs
View File

@@ -2,25 +2,29 @@ use super::operation::AddOperation;
use crate::core::Segment;
use crate::core::SerializableSegment;
use crate::fastfield::FastFieldsWriter;
use crate::fieldnorm::{FieldNormReaders, FieldNormsWriter};
use crate::fieldnorm::FieldNormsWriter;
use crate::indexer::segment_serializer::SegmentSerializer;
use crate::postings::compute_table_size;
use crate::postings::MultiFieldPostingsWriter;
use crate::schema::FieldEntry;
use crate::schema::FieldType;
use crate::schema::Schema;
use crate::schema::Term;
use crate::schema::Value;
use crate::schema::{Field, FieldEntry};
use crate::tokenizer::{BoxTokenStream, PreTokenizedStream};
use crate::tokenizer::{FacetTokenizer, TextAnalyzer};
use crate::tokenizer::{TokenStreamChain, Tokenizer};
use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::FacetTokenizer;
use crate::tokenizer::{TokenStream, Tokenizer};
use crate::DocId;
use crate::Opstamp;
use crate::{DocId, SegmentComponent};
use crate::Result;
use crate::TantivyError;
use std::io;
use std::str;
/// Computes the initial size of the hash table.
///
/// Returns a number of bit `b`, such that the recommended initial table size is 2^b.
fn initial_table_size(per_thread_memory_budget: usize) -> crate::Result<usize> {
fn initial_table_size(per_thread_memory_budget: usize) -> Result<usize> {
let table_memory_upper_bound = per_thread_memory_budget / 3;
if let Some(limit) = (10..)
.take_while(|num_bits: &usize| compute_table_size(*num_bits) < table_memory_upper_bound)
@@ -28,7 +32,7 @@ fn initial_table_size(per_thread_memory_budget: usize) -> crate::Result<usize> {
{
Ok(limit.min(19)) // we cap it at 2^19 = 512K.
} else {
Err(crate::TantivyError::InvalidArgument(
Err(TantivyError::InvalidArgument(
format!("per thread memory budget (={}) is too small. Raise the memory budget or lower the number of threads.", per_thread_memory_budget)))
}
}
@@ -45,8 +49,7 @@ pub struct SegmentWriter {
fast_field_writers: FastFieldsWriter,
fieldnorms_writer: FieldNormsWriter,
doc_opstamps: Vec<Opstamp>,
tokenizers: Vec<Option<TextAnalyzer>>,
term_buffer: Term,
tokenizers: Vec<Option<Box<dyn BoxedTokenizer>>>,
}
impl SegmentWriter {
@@ -61,27 +64,27 @@ impl SegmentWriter {
/// - schema
pub fn for_segment(
memory_budget: usize,
segment: Segment,
mut segment: Segment,
schema: &Schema,
) -> crate::Result<SegmentWriter> {
let tokenizer_manager = segment.index().tokenizers().clone();
) -> Result<SegmentWriter> {
let table_num_bits = initial_table_size(memory_budget)?;
let segment_serializer = SegmentSerializer::for_segment(segment)?;
let segment_serializer = SegmentSerializer::for_segment(&mut segment)?;
let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits);
let tokenizers = schema
.fields()
.map(
|(_, field_entry): (Field, &FieldEntry)| match field_entry.field_type() {
let tokenizers =
schema
.fields()
.iter()
.map(FieldEntry::field_type)
.map(|field_type| match *field_type {
FieldType::Str(ref text_options) => text_options
.get_indexing_options()
.and_then(|text_index_option| {
let tokenizer_name = &text_index_option.tokenizer();
tokenizer_manager.get(tokenizer_name)
segment.index().tokenizers().get(tokenizer_name)
}),
_ => None,
},
)
.collect();
})
.collect();
Ok(SegmentWriter {
max_doc: 0,
multifield_postings,
@@ -90,7 +93,6 @@ impl SegmentWriter {
fast_field_writers: FastFieldsWriter::from_schema(schema),
doc_opstamps: Vec::with_capacity(1_000),
tokenizers,
term_buffer: Term::new(),
})
}
@@ -98,7 +100,7 @@ impl SegmentWriter {
///
/// Finalize consumes the `SegmentWriter`, so that it cannot
/// be used afterwards.
pub fn finalize(mut self) -> crate::Result<Vec<u64>> {
pub fn finalize(mut self) -> Result<Vec<u64>> {
self.fieldnorms_writer.fill_up_to_max_doc(self.max_doc);
write(
&self.multifield_postings,
@@ -116,11 +118,7 @@ impl SegmentWriter {
/// Indexes a new document
///
/// As a user, you should rather use `IndexWriter`'s add_document.
pub fn add_document(
&mut self,
add_operation: AddOperation,
schema: &Schema,
) -> crate::Result<()> {
pub fn add_document(&mut self, add_operation: AddOperation, schema: &Schema) -> io::Result<()> {
let doc_id = self.max_doc;
let mut doc = add_operation.document;
self.doc_opstamps.push(add_operation.opstamp);
@@ -128,160 +126,111 @@ impl SegmentWriter {
self.fast_field_writers.add_document(&doc);
for (field, field_values) in doc.get_sorted_field_values() {
let field_entry = schema.get_field_entry(field);
let make_schema_error = || {
crate::TantivyError::SchemaError(format!(
"Expected a {:?} for field {:?}",
field_entry.field_type().value_type(),
field_entry.name()
))
};
if !field_entry.is_indexed() {
let field_options = schema.get_field_entry(field);
if !field_options.is_indexed() {
continue;
}
let (term_buffer, multifield_postings) =
(&mut self.term_buffer, &mut self.multifield_postings);
match *field_entry.field_type() {
match *field_options.field_type() {
FieldType::HierarchicalFacet => {
term_buffer.set_field(field);
let facets =
field_values
.iter()
.flat_map(|field_value| match *field_value.value() {
Value::Facet(ref facet) => Some(facet.encoded_str()),
_ => {
panic!("Expected hierarchical facet");
}
});
for facet_str in facets {
let facets: Vec<&str> = field_values
.iter()
.flat_map(|field_value| match *field_value.value() {
Value::Facet(ref facet) => Some(facet.encoded_str()),
_ => {
panic!("Expected hierarchical facet");
}
})
.collect();
let mut term = Term::for_field(field); // we set the Term
for fake_str in facets {
let mut unordered_term_id_opt = None;
FacetTokenizer
.token_stream(facet_str)
.process(&mut |token| {
term_buffer.set_text(&token.text);
let unordered_term_id =
multifield_postings.subscribe(doc_id, &term_buffer);
unordered_term_id_opt = Some(unordered_term_id);
});
FacetTokenizer.token_stream(fake_str).process(&mut |token| {
term.set_text(&token.text);
let unordered_term_id =
self.multifield_postings.subscribe(doc_id, &term);
unordered_term_id_opt = Some(unordered_term_id);
});
if let Some(unordered_term_id) = unordered_term_id_opt {
self.fast_field_writers
.get_multivalue_writer(field)
.expect("writer for facet missing")
.expect("multified writer for facet missing")
.add_val(unordered_term_id);
}
}
}
FieldType::Str(_) => {
let mut token_streams: Vec<BoxTokenStream> = vec![];
let mut offsets = vec![];
let mut total_offset = 0;
for field_value in field_values {
match field_value.value() {
Value::PreTokStr(tok_str) => {
offsets.push(total_offset);
if let Some(last_token) = tok_str.tokens.last() {
total_offset += last_token.offset_to;
}
token_streams
.push(PreTokenizedStream::from(tok_str.clone()).into());
}
Value::Str(ref text) => {
if let Some(ref mut tokenizer) =
self.tokenizers[field.field_id() as usize]
{
offsets.push(total_offset);
total_offset += text.len();
token_streams.push(tokenizer.token_stream(text));
}
}
_ => (),
let num_tokens = if let Some(ref mut tokenizer) =
self.tokenizers[field.0 as usize]
{
let texts: Vec<&str> = field_values
.iter()
.flat_map(|field_value| match *field_value.value() {
Value::Str(ref text) => Some(text.as_str()),
_ => None,
})
.collect();
if texts.is_empty() {
0
} else {
let mut token_stream = tokenizer.token_stream_texts(&texts[..]);
self.multifield_postings
.index_text(doc_id, field, &mut token_stream)
}
}
let num_tokens = if token_streams.is_empty() {
0
} else {
let mut token_stream = TokenStreamChain::new(offsets, token_streams);
multifield_postings.index_text(
doc_id,
field,
&mut token_stream,
term_buffer,
)
0
};
self.fieldnorms_writer.record(doc_id, field, num_tokens);
}
FieldType::U64(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
term_buffer.set_field(field_value.field());
let u64_val = field_value
.value()
.u64_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_u64(u64_val);
multifield_postings.subscribe(doc_id, &term_buffer);
let term = Term::from_field_u64(
field_value.field(),
field_value.value().u64_value(),
);
self.multifield_postings.subscribe(doc_id, &term);
}
}
}
FieldType::Date(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
term_buffer.set_field(field_value.field());
let date_val = field_value
.value()
.date_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_i64(date_val.timestamp());
multifield_postings.subscribe(doc_id, &term_buffer);
let term = Term::from_field_i64(
field_value.field(),
field_value.value().date_value().timestamp(),
);
self.multifield_postings.subscribe(doc_id, &term);
}
}
}
FieldType::I64(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
term_buffer.set_field(field_value.field());
let i64_val = field_value
.value()
.i64_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_i64(i64_val);
multifield_postings.subscribe(doc_id, &term_buffer);
let term = Term::from_field_i64(
field_value.field(),
field_value.value().i64_value(),
);
self.multifield_postings.subscribe(doc_id, &term);
}
}
}
FieldType::F64(ref int_option) => {
if int_option.is_indexed() {
for field_value in field_values {
term_buffer.set_field(field_value.field());
let f64_val = field_value
.value()
.f64_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_f64(f64_val);
multifield_postings.subscribe(doc_id, &term_buffer);
let term = Term::from_field_f64(
field_value.field(),
field_value.value().f64_value(),
);
self.multifield_postings.subscribe(doc_id, &term);
}
}
}
FieldType::Bytes(ref option) => {
if option.is_indexed() {
for field_value in field_values {
term_buffer.set_field(field_value.field());
let bytes = field_value
.value()
.bytes_value()
.ok_or_else(make_schema_error)?;
term_buffer.set_bytes(bytes);
self.multifield_postings.subscribe(doc_id, &term_buffer);
}
}
FieldType::Bytes => {
// Do nothing. Bytes only supports fast fields.
}
}
}
doc.filter_fields(|field| schema.get_field_entry(field).is_stored());
doc.prepare_for_store();
let doc_writer = self.segment_serializer.get_store_writer();
doc_writer.store(&doc)?;
self.max_doc += 1;
@@ -315,23 +264,16 @@ fn write(
fast_field_writers: &FastFieldsWriter,
fieldnorms_writer: &FieldNormsWriter,
mut serializer: SegmentSerializer,
) -> crate::Result<()> {
if let Some(fieldnorms_serializer) = serializer.extract_fieldnorms_serializer() {
fieldnorms_writer.serialize(fieldnorms_serializer)?;
}
let fieldnorm_data = serializer
.segment()
.open_read(SegmentComponent::FIELDNORMS)?;
let fieldnorm_readers = FieldNormReaders::open(fieldnorm_data)?;
let term_ord_map =
multifield_postings.serialize(serializer.get_postings_serializer(), fieldnorm_readers)?;
) -> Result<()> {
let term_ord_map = multifield_postings.serialize(serializer.get_postings_serializer())?;
fast_field_writers.serialize(serializer.get_fast_field_serializer(), &term_ord_map)?;
fieldnorms_writer.serialize(serializer.get_fieldnorms_serializer())?;
serializer.close()?;
Ok(())
}
impl SerializableSegment for SegmentWriter {
fn write(&self, serializer: SegmentSerializer) -> crate::Result<u32> {
fn write(&self, serializer: SegmentSerializer) -> Result<u32> {
let max_doc = self.max_doc;
write(
&self.multifield_postings,
@@ -354,4 +296,5 @@ mod tests {
assert_eq!(initial_table_size(10_000_000).unwrap(), 17);
assert_eq!(initial_table_size(1_000_000_000).unwrap(), 19);
}
}

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