rust/tantivy
1
0
Fork 0
mirror of https://github.com/quickwit-oss/tantivy.git synced 2025-12-31 22:42:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

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

2 Commits
0.1 ... 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
117 changed files with 1193 additions and 2599 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
.travis.yml
View File

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

23
CHANGELOG.md
View File

@@ -2,29 +2,6 @@ Tantivy 0.11.0
===================== =====================
- Added f64 field. Internally reuse u64 code the same way i64 does (@fdb-hiroshima) - 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)
- TopDocs collector: ensure stable sorting on equal score. #671 (@brainlock)
- Added handling of pre-tokenized text fields (#642), which will enable users to
load tokens created outside tantivy. See usage in examples/pre_tokenized_text. (@kkoziara)
- Fix crash when committing multiple times with deleted documents. #681 (@brainlock)
## How to update?
- `Box<dyn BoxableTokenizer>` has been replaced by a `BoxedTokenizer` struct.
- Regex are now compiled when the `RegexQuery` instance is built. As a result, it can now return
an error and handling the `Result` is required.
Tantivy 0.10.2
=====================
- Closes #656. Solving memory leak.
Tantivy 0.10.1 Tantivy 0.10.1
===================== =====================

33
Cargo.toml
View File

@@ -1,6 +1,6 @@
[package] [package]
name = "tantivy" name = "tantivy"
version = "0.11.0" version = "0.10.1"
authors = ["Paul Masurel <paul.masurel@gmail.com>"] authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT" license = "MIT"
categories = ["database-implementations", "data-structures"] categories = ["database-implementations", "data-structures"]
@@ -13,11 +13,10 @@ keywords = ["search", "information", "retrieval"]
edition = "2018" edition = "2018"
[dependencies] [dependencies]
base64 = "0.11.0" base64 = "0.10.0"
byteorder = "1.0" byteorder = "1.0"
crc32fast = "1.2.0" once_cell = "0.2"
once_cell = "1.0" regex = "1.0"
regex ={version = "1.3.0", default-features = false, features = ["std"]}
tantivy-fst = "0.1" tantivy-fst = "0.1"
memmap = {version = "0.7", optional=true} memmap = {version = "0.7", optional=true}
lz4 = {version="1.20", optional=true} lz4 = {version="1.20", optional=true}
@@ -25,6 +24,8 @@ snap = {version="0.2"}
atomicwrites = {version="0.2.2", optional=true} atomicwrites = {version="0.2.2", optional=true}
tempfile = "3.0" tempfile = "3.0"
log = "0.4" log = "0.4"
combine = ">=3.6.0,<4.0.0"
tempdir = "0.3"
serde = "1.0" serde = "1.0"
serde_derive = "1.0" serde_derive = "1.0"
serde_json = "1.0" serde_json = "1.0"
@@ -34,15 +35,14 @@ itertools = "0.8"
levenshtein_automata = {version="0.1", features=["fst_automaton"]} levenshtein_automata = {version="0.1", features=["fst_automaton"]}
notify = {version="4", optional=true} notify = {version="4", optional=true}
bit-set = "0.5" bit-set = "0.5"
uuid = { version = "0.8", features = ["v4", "serde"] } uuid = { version = "0.7.2", features = ["v4", "serde"] }
crossbeam = "0.7" crossbeam = "0.5"
futures = "0.1" futures = "0.1"
futures-cpupool = "0.1" futures-cpupool = "0.1"
owning_ref = "0.4" owning_ref = "0.4"
stable_deref_trait = "1.0.0" stable_deref_trait = "1.0.0"
rust-stemmers = "1.1" rust-stemmers = "1.1"
downcast-rs = { version="1.0" } downcast-rs = { version="1.0" }
tantivy-query-grammar = { path="./query-grammar" }
bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]} bitpacking = {version="0.8", default-features = false, features=["bitpacker4x"]}
census = "0.2" census = "0.2"
fnv = "1.0.6" fnv = "1.0.6"
@@ -50,10 +50,10 @@ owned-read = "0.4"
failure = "0.1" failure = "0.1"
htmlescape = "0.3.1" htmlescape = "0.3.1"
fail = "0.3" fail = "0.3"
scoped-pool = "1.0"
murmurhash32 = "0.2" murmurhash32 = "0.2"
chrono = "0.4" chrono = "0.4"
smallvec = "1.0" smallvec = "0.6"
rayon = "1"
[target.'cfg(windows)'.dependencies] [target.'cfg(windows)'.dependencies]
winapi = "0.3" winapi = "0.3"
@@ -64,10 +64,6 @@ maplit = "1"
matches = "0.1.8" matches = "0.1.8"
time = "0.1.42" time = "0.1.42"
[dev-dependencies.fail]
version = "0.3"
features = ["failpoints"]
[profile.release] [profile.release]
opt-level = 3 opt-level = 3
debug = false debug = false
@@ -85,12 +81,13 @@ failpoints = ["fail/failpoints"]
unstable = [] # useful for benches. unstable = [] # useful for benches.
wasm-bindgen = ["uuid/wasm-bindgen"] wasm-bindgen = ["uuid/wasm-bindgen"]
[workspace]
members = ["query-grammar"]
[badges] [badges]
travis-ci = { repository = "tantivy-search/tantivy" } travis-ci = { repository = "tantivy-search/tantivy" }
[dev-dependencies.fail]
features = ["failpoints"]
# Following the "fail" crate best practises, we isolate # Following the "fail" crate best practises, we isolate
# tests that define specific behavior in fail check points # tests that define specific behavior in fail check points
# in a different binary. # in a different binary.
@@ -101,4 +98,4 @@ travis-ci = { repository = "tantivy-search/tantivy" }
[[test]] [[test]]
name = "failpoints" name = "failpoints"
path = "tests/failpoints/mod.rs" 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

57
README.md
View File

@@ -21,9 +21,9 @@
[![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton) [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
**Tantivy** is a **full text search engine library** written in Rust. **Tantivy** is a **full text search engine library** written in rust.
It is closer to [Apache Lucene](https://lucene.apache.org/) than to [Elasticsearch](https://www.elastic.co/products/elasticsearch) 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 an off-the-shelf search engine server, but rather a crate that can be used
to build such a search engine. to build such a search engine.
@@ -31,7 +31,7 @@ Tantivy is, in fact, strongly inspired by Lucene's design.
# Benchmark # Benchmark
Tantivy is typically faster than Lucene, but the results depend on Tantivy is typically faster than Lucene, but the results will depend on
the nature of the queries in your workload. the nature of the queries in your workload.
The following [benchmark](https://tantivy-search.github.io/bench/) break downs The following [benchmark](https://tantivy-search.github.io/bench/) break downs
@@ -40,19 +40,19 @@ performance for different type of queries / collection.
# Features # Features
- Full-text search - Full-text search
- Configurable tokenizer (stemming available for 17 Latin languages with third party support for Chinese ([tantivy-jieba](https://crates.io/crates/tantivy-jieba) and [cang-jie](https://crates.io/crates/cang-jie)) and [Japanese](https://crates.io/crates/tantivy-tokenizer-tiny-segmenter)) - 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:) - Fast (check out the :racehorse: :sparkles: [benchmark](https://tantivy-search.github.io/bench/) :sparkles: :racehorse:)
- Tiny startup time (<10ms), perfect for command line tools - Tiny startup time (<10ms), perfect for command line tools
- BM25 scoring (the same as Lucene) - BM25 scoring (the same as lucene)
- Natural query language (e.g. `(michael AND jackson) OR "king of pop"`) - Natural query language `(michael AND jackson) OR "king of pop"`
- Phrase queries search (e.g. `"michael jackson"`) - Phrase queries search (`"michael jackson"`)
- Incremental indexing - Incremental indexing
- Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop) - Multithreaded indexing (indexing English Wikipedia takes < 3 minutes on my desktop)
- Mmap directory - Mmap directory
- SIMD integer compression when the platform/CPU includes the SSE2 instruction set - SIMD integer compression when the platform/CPU includes the SSE2 instruction set.
- Single valued and multivalued u64, i64, and f64 fast fields (equivalent of doc values in Lucene) - Single valued and multivalued u64, i64 and f64 fast fields (equivalent of doc values in Lucene)
- `&[u8]` fast fields - `&[u8]` fast fields
- Text, i64, u64, f64, dates, and hierarchical facet fields - Text, i64, u64, f64, dates and hierarchical facet fields
- LZ4 compressed document store - LZ4 compressed document store
- Range queries - Range queries
- Faceted search - Faceted search
@@ -61,42 +61,43 @@ performance for different type of queries / collection.
# Non-features # Non-features
- Distributed search is out of the scope of Tantivy. That being said, Tantivy is 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, library upon which one could build a distributed search. Serializable/mergeable collector state for instance,
are within the scope of Tantivy. are within the scope of tantivy.
# Supported OS and compiler # Supported OS and compiler
Tantivy works on stable Rust (>= 1.27) and supports Linux, MacOS, and Windows. Tantivy works on stable rust (>= 1.27) and supports Linux, MacOS and Windows.
# Getting started # Getting started
- [Tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html) - [tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html)
- [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli) - `tantivy-cli` is an actual command line interface that makes it easy for you to create a search engine, - [tantivy-cli and its tutorial](https://github.com/tantivy-search/tantivy-cli).
index documents, and search via the CLI or a small server with a REST API. `tantivy-cli` is an actual command line interface that makes it easy for you to create a search engine,
It walks you through getting a wikipedia search engine up and running in a few minutes. index documents and search via the CLI or a small server with a REST API.
- [Reference doc for the last released version](https://docs.rs/tantivy/) 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? # How can I support this project?
There are many ways to support this project. There are many ways to support this project.
- Use Tantivy and tell us about your experience on [Gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com) - Use tantivy and tell us about your experience on [gitter](https://gitter.im/tantivy-search/tantivy) or by email (paul.masurel@gmail.com)
- Report bugs - Report bugs
- Write a blog post - Write a blog post
- Help with documentation by asking questions or submitting PRs - Help with documentation by asking questions or submitting PRs
- Contribute code (you can join [our Gitter](https://gitter.im/tantivy-search/tantivy)) - Contribute code (you can join [our gitter](https://gitter.im/tantivy-search/tantivy) )
- Talk about Tantivy around you - Talk about tantivy around you
- Drop a word on on [![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton) or even [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton) - Drop a word on on [![Say Thanks!](https://img.shields.io/badge/Say%20Thanks-!-1EAEDB.svg)](https://saythanks.io/to/fulmicoton) or even [![Become a patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/fulmicoton)
# Contributing code # Contributing code
We use the GitHub Pull Request workflow: reference a GitHub ticket and/or include a comprehensive commit message when opening a PR. We use the GitHub Pull Request workflow - reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
## Clone and build locally ## Clone and build locally
Tantivy compiles on stable Rust but requires `Rust >= 1.27`. Tantivy compiles on stable rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run: To check out and run tests, you can simply run :
```bash ```bash
git clone https://github.com/tantivy-search/tantivy.git git clone https://github.com/tantivy-search/tantivy.git
@@ -107,7 +108,7 @@ To check out and run tests, you can simply run:
## Run tests ## Run tests
Some tests will not run with just `cargo test` because of `fail-rs`. Some tests will not run with just `cargo test` because of `fail-rs`.
To run the tests exhaustively, run `./run-tests.sh`. To run the tests exhaustively, run `./run-tests.sh`
## Debug ## Debug
@@ -115,13 +116,13 @@ You might find it useful to step through the programme with a debugger.
### A failing test ### A failing test
Make sure you haven't run `cargo clean` after the most recent `cargo test` or `cargo build` to guarantee that 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 ```bash
find target/debug/ -maxdepth 1 -executable -type f -name "tantivy*" -printf '%TY-%Tm-%Td %TT %p\n' | sort -r | cut -d " " -f 3 | xargs -I RECENT_DBG_TANTIVY rust-gdb RECENT_DBG_TANTIVY find target/debug/ -maxdepth 1 -executable -type f -name "tantivy*" -printf '%TY-%Tm-%Td %TT %p\n' | sort -r | cut -d " " -f 3 | xargs -I RECENT_DBG_TANTIVY rust-gdb RECENT_DBG_TANTIVY
``` ```
Now that you are in `rust-gdb`, you can set breakpoints on lines and methods that match your source code and run the debug executable with flags that you normally pass to `cargo test` 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 ```bash
$gdb run --test-threads 1 --test $NAME_OF_TEST $gdb run --test-threads 1 --test $NAME_OF_TEST
@@ -129,7 +130,7 @@ $gdb run --test-threads 1 --test $NAME_OF_TEST
### An example ### An example
By default, `rustc` compiles everything in the `examples/` directory in debug mode. This makes it easy for you to make examples to reproduce bugs: By default, rustc compiles everything in the `examples/` dir in debug mode. This makes it easy for you to make examples to reproduce bugs.
```bash ```bash
rust-gdb target/debug/examples/$EXAMPLE_NAME rust-gdb target/debug/examples/$EXAMPLE_NAME

5
ci/script.sh
View File

@@ -7,7 +7,7 @@ set -ex
main() { main() {
if [ ! -z $CODECOV ]; then if [ ! -z $CODECOV ]; then
echo "Codecov" 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 else
echo "Build" echo "Build"
cross build --target $TARGET cross build --target $TARGET
@@ -15,8 +15,7 @@ main() {
return return
fi fi
echo "Test" echo "Test"
cross test --target $TARGET --no-default-features --features mmap cross test --target $TARGET --no-default-features --features mmap -- --test-threads 1
cross test --target $TARGET --no-default-features --features mmap query-grammar
fi fi
for example in $(ls examples/*.rs) for example in $(ls examples/*.rs)
do do

40
examples/basic_search.rs
View File

@@ -5,23 +5,26 @@
// //
// We will : // We will :
// - define our schema // - define our schema
// - create an index in a directory // = create an index in a directory
// - index a few documents into our index // - index few documents in our index
// - search for the best document matching a basic query // - search for the best document matchings "sea whale"
// - retrieve the best document's original content. // - retrieve the best document original content.
// --- // ---
// Importing tantivy... // Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::TopDocs; use tantivy::collector::TopDocs;
use tantivy::query::QueryParser; use tantivy::query::QueryParser;
use tantivy::schema::*; use tantivy::schema::*;
use tantivy::{doc, Index, ReloadPolicy}; use tantivy::Index;
use tempfile::TempDir; use tantivy::ReloadPolicy;
use tempdir::TempDir;
fn main() -> tantivy::Result<()> { fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the // Let's create a temporary directory for the
// sake of this example // sake of this example
let index_path = TempDir::new()?; let index_path = TempDir::new("tantivy_example_dir")?;
// # Defining the schema // # Defining the schema
// //
@@ -30,7 +33,7 @@ fn main() -> tantivy::Result<()> {
// and for each field, its type and "the way it should // and for each field, its type and "the way it should
// be indexed". // be indexed".
// First we need to define a schema ... // first we need to define a schema ...
let mut schema_builder = Schema::builder(); let mut schema_builder = Schema::builder();
// Our first field is title. // Our first field is title.
@@ -45,7 +48,7 @@ fn main() -> tantivy::Result<()> {
// //
// `STORED` means that the field will also be saved // `STORED` means that the field will also be saved
// in a compressed, row-oriented key-value store. // 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. // documents that were selected during the search phase.
schema_builder.add_text_field("title", TEXT | STORED); 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 // need to be able to be able to retrieve it
// for our application. // 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); schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build(); let schema = schema_builder.build();
@@ -67,7 +71,7 @@ fn main() -> tantivy::Result<()> {
// with our schema in the directory. // with our schema in the directory.
let index = Index::create_in_dir(&index_path, schema.clone())?; 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. // There must be only one writer at a time.
// This single `IndexWriter` is already // This single `IndexWriter` is already
// multithreaded. // multithreaded.
@@ -145,8 +149,8 @@ fn main() -> tantivy::Result<()> {
// At this point our documents are not searchable. // At this point our documents are not searchable.
// //
// //
// We need to call `.commit()` explicitly to force the // We need to call .commit() explicitly to force the
// `index_writer` to finish processing the documents in the queue, // index_writer to finish processing the documents in the queue,
// flush the current index to the disk, and advertise // flush the current index to the disk, and advertise
// the existence of new documents. // the existence of new documents.
// //
@@ -158,14 +162,14 @@ fn main() -> tantivy::Result<()> {
// persistently indexed. // persistently indexed.
// //
// In the scenario of a crash or a power failure, // 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. // commit.
// # Searching // # Searching
// //
// ### Searcher // ### 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, // It acts as a `Searcher` pool that reloads itself,
// depending on a `ReloadPolicy`. // depending on a `ReloadPolicy`.
// //
@@ -181,7 +185,7 @@ fn main() -> tantivy::Result<()> {
// We now need to acquire a searcher. // 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 // Some search experience might require more than
// one query. Using the same searcher ensures that all of these queries will run on the // one query. Using the same searcher ensures that all of these queries will run on the
@@ -201,7 +205,7 @@ fn main() -> tantivy::Result<()> {
// in both title and body. // in both title and body.
let query_parser = QueryParser::for_index(&index, vec![title, 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. // format. For user facing applications, this can be a problem.
// A ticket has been opened regarding this problem. // A ticket has been opened regarding this problem.
let query = query_parser.parse_query("sea whale")?; let query = query_parser.parse_query("sea whale")?;
@@ -217,7 +221,7 @@ fn main() -> tantivy::Result<()> {
// //
// We are not interested in all of the documents but // We are not interested in all of the documents but
// only in the top 10. Keeping track of our top 10 best documents // 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. // We can now perform our query.
let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?; let top_docs = searcher.search(&query, &TopDocs::with_limit(10))?;

5
examples/custom_collector.rs
View File

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

5
examples/custom_tokenizer.rs
View File

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

5
examples/deleting_updating_documents.rs
View File

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

9
examples/faceted_search.rs
View File

@@ -12,16 +12,17 @@
// --- // ---
// Importing tantivy... // Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::collector::FacetCollector; use tantivy::collector::FacetCollector;
use tantivy::query::AllQuery; use tantivy::query::AllQuery;
use tantivy::schema::*; use tantivy::schema::*;
use tantivy::{doc, Index}; use tantivy::Index;
use tempfile::TempDir;
fn main() -> tantivy::Result<()> { fn main() -> tantivy::Result<()> {
// Let's create a temporary directory for the // Let's create a temporary directory for the
// sake of this example // sake of this example
let index_path = TempDir::new()?; let index_path = TempDir::new("tantivy_facet_example_dir")?;
let mut schema_builder = Schema::builder(); let mut schema_builder = Schema::builder();
schema_builder.add_text_field("name", TEXT | STORED); schema_builder.add_text_field("name", TEXT | STORED);
@@ -73,3 +74,5 @@ fn main() -> tantivy::Result<()> {
Ok(()) Ok(())
} }
use tempdir::TempDir;

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 // 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. // 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::collector::Count;
use tantivy::query::RangeQuery; use tantivy::query::RangeQuery;
use tantivy::schema::{Schema, INDEXED}; use tantivy::schema::{Schema, INDEXED};
use tantivy::{doc, Index, Result}; use tantivy::Index;
use tantivy::Result;
fn run() -> Result<()> { fn run() -> Result<()> {
// For the sake of simplicity, this schema will only have 1 field // For the sake of simplicity, this schema will only have 1 field

5
examples/iterating_docs_and_positions.rs
View File

@@ -9,8 +9,11 @@
// --- // ---
// Importing tantivy... // Importing tantivy...
#[macro_use]
extern crate tantivy;
use tantivy::schema::*; use tantivy::schema::*;
use tantivy::{doc, DocId, DocSet, Index, Postings}; use tantivy::Index;
use tantivy::{DocId, DocSet, Postings};
fn main() -> tantivy::Result<()> { fn main() -> tantivy::Result<()> {
// We first create a schema for the sake of the // We first create a schema for the sake of the

15
examples/multiple_producer.rs
View File

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

140
examples/pre_tokenized_text.rs
View File

@@ -1,140 +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::tokenizer::{PreTokenizedString, SimpleTokenizer, Token, TokenStream, Tokenizer};
use tantivy::collector::{Count, TopDocs};
use tantivy::query::TermQuery;
use tantivy::schema::*;
use tantivy::{doc, Index, ReloadPolicy};
use tempfile::TempDir;
fn pre_tokenize_text(text: &str) -> Vec<Token> {
let mut token_stream = SimpleTokenizer.token_stream(text);
let mut tokens = vec![];
while token_stream.advance() {
tokens.push(token_stream.token().clone());
}
tokens
}
fn main() -> tantivy::Result<()> {
let index_path = TempDir::new()?;
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("title", TEXT | STORED);
schema_builder.add_text_field("body", TEXT);
let schema = schema_builder.build();
let index = Index::create_in_dir(&index_path, schema.clone())?;
let mut index_writer = index.writer(50_000_000)?;
// We can create a document manually, by setting the fields
// one by one in a Document object.
let title = schema.get_field("title").unwrap();
let body = schema.get_field("body").unwrap();
let title_text = "The Old Man and the Sea";
let body_text = "He was an old man who fished alone in a skiff in the Gulf Stream";
// Content of our first document
// We create `PreTokenizedString` which contains original text and vector of tokens
let title_tok = PreTokenizedString {
text: String::from(title_text),
tokens: pre_tokenize_text(title_text),
};
println!(
"Original text: \"{}\" and tokens: {:?}",
title_tok.text, title_tok.tokens
);
let body_tok = PreTokenizedString {
text: String::from(body_text),
tokens: pre_tokenize_text(body_text),
};
// Now lets create a document and add our `PreTokenizedString` using
// `add_pre_tokenized_text` method of `Document`
let mut old_man_doc = Document::default();
old_man_doc.add_pre_tokenized_text(title, &title_tok);
old_man_doc.add_pre_tokenized_text(body, &body_tok);
// ... now let's just add it to the IndexWriter
index_writer.add_document(old_man_doc);
// Pretokenized text can also be fed as JSON
let short_man_json = r#"{
"title":[{
"text":"The Old Man",
"tokens":[
{"offset_from":0,"offset_to":3,"position":0,"text":"The","position_length":1},
{"offset_from":4,"offset_to":7,"position":1,"text":"Old","position_length":1},
{"offset_from":8,"offset_to":11,"position":2,"text":"Man","position_length":1}
]
}]
}"#;
let short_man_doc = schema.parse_document(&short_man_json)?;
index_writer.add_document(short_man_doc);
// Let's commit changes
index_writer.commit()?;
// ... and now is the time to query our index
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::OnCommit)
.try_into()?;
let searcher = reader.searcher();
// We want to get documents with token "Man", we will use TermQuery to do it
// Using PreTokenizedString means the tokens are stored as is avoiding stemming
// and lowercasing, which preserves full words in their original form
let query = TermQuery::new(
Term::from_field_text(title, "Man"),
IndexRecordOption::Basic,
);
let (top_docs, count) = searcher
.search(&query, &(TopDocs::with_limit(2), Count))
.unwrap();
assert_eq!(count, 2);
for (_score, doc_address) in top_docs {
let retrieved_doc = searcher.doc(doc_address)?;
println!("Document: {}", schema.to_json(&retrieved_doc));
}
// In contrary to the previous query, when we search for the "man" term we
// should get no results, as it's not one of the indexed tokens. SimpleTokenizer
// only splits text on whitespace / punctuation.
let query = TermQuery::new(
Term::from_field_text(title, "man"),
IndexRecordOption::Basic,
);
let (_top_docs, count) = searcher
.search(&query, &(TopDocs::with_limit(2), Count))
.unwrap();
assert_eq!(count, 0);
Ok(())
}

9
examples/snippet.rs
View File

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

4
examples/stop_words.rs
View File

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

16
query-grammar/Cargo.toml
View File

@@ -1,16 +0,0 @@
[package]
name = "tantivy-query-grammar"
version = "0.11.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
description = """Search engine library"""
documentation = "https://tantivy-search.github.io/tantivy/tantivy/index.html"
homepage = "https://github.com/tantivy-search/tantivy"
repository = "https://github.com/tantivy-search/tantivy"
readme = "README.md"
keywords = ["search", "information", "retrieval"]
edition = "2018"
[dependencies]
combine = ">=3.6.0,<4.0.0"

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

@@ -1,17 +0,0 @@
#![recursion_limit = "100"]
mod occur;
mod query_grammar;
mod user_input_ast;
use combine::parser::Parser;
pub use crate::occur::Occur;
use crate::query_grammar::parse_to_ast;
pub use crate::user_input_ast::{UserInputAST, UserInputBound, UserInputLeaf, UserInputLiteral};
pub struct Error;
pub fn parse_query(query: &str) -> Result<UserInputAST, Error> {
let (user_input_ast, _remaining) = parse_to_ast().parse(query).map_err(|_| Error)?;
Ok(user_input_ast)
}

380
query-grammar/src/query_grammar.rs
View File

@@ -1,380 +0,0 @@
use super::user_input_ast::*;
use crate::Occur;
use combine::char::*;
use combine::error::StreamError;
use combine::stream::StreamErrorFor;
use combine::*;
parser! {
fn field[I]()(I) -> String
where [I: Stream<Item = char>] {
(
letter(),
many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
).skip(char(':')).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
}
parser! {
fn word[I]()(I) -> String
where [I: Stream<Item = char>] {
(
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" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
"AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
"NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
_ => Ok(s)
})
}
}
parser! {
fn literal[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>]
{
let term_val = || {
let phrase = char('"').with(many1(satisfy(|c| c != '"'))).skip(char('"'));
phrase.or(word())
};
let term_val_with_field = negative_number().or(term_val());
let term_query =
(field(), term_val_with_field)
.map(|(field_name, phrase)| UserInputLiteral {
field_name: Some(field_name),
phrase,
});
let term_default_field = term_val().map(|phrase| UserInputLiteral {
field_name: None,
phrase,
});
attempt(term_query)
.or(term_default_field)
.map(UserInputLeaf::from)
}
}
parser! {
fn negative_number[I]()(I) -> String
where [I: Stream<Item = char>]
{
(char('-'), many1(satisfy(char::is_numeric)),
optional((char('.'), many1(satisfy(char::is_numeric)))))
.map(|(s1, s2, s3): (char, String, Option<(char, String)>)| {
if let Some(('.', s3)) = s3 {
format!("{}{}.{}", s1, s2, s3)
} else {
format!("{}{}", s1, s2)
}
})
}
}
parser! {
fn spaces1[I]()(I) -> ()
where [I: Stream<Item = char>] {
skip_many1(space())
}
}
parser! {
/// Function that parses a range out of a Stream
/// Supports ranges like:
/// [5 TO 10], {5 TO 10}, [* TO 10], [10 TO *], {10 TO *], >5, <=10
/// [a TO *], [a TO c], [abc TO bcd}
fn range[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>] {
let range_term_val = || {
word().or(negative_number()).or(char('*').with(value("*".to_string())))
};
// check for unbounded range in the form of <5, <=10, >5, >=5
let elastic_unbounded_range = (choice([attempt(string(">=")),
attempt(string("<=")),
attempt(string("<")),
attempt(string(">"))])
.skip(spaces()),
range_term_val()).
map(|(comparison_sign, bound): (&str, String)|
match comparison_sign {
">=" => (UserInputBound::Inclusive(bound), UserInputBound::Unbounded),
"<=" => (UserInputBound::Unbounded, UserInputBound::Inclusive(bound)),
"<" => (UserInputBound::Unbounded, UserInputBound::Exclusive(bound)),
">" => (UserInputBound::Exclusive(bound), UserInputBound::Unbounded),
// default case
_ => (UserInputBound::Unbounded, UserInputBound::Unbounded)
});
let lower_bound = (one_of("{[".chars()), range_term_val())
.map(|(boundary_char, lower_bound): (char, String)|
if 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 must(expr: UserInputAST) -> UserInputAST {
expr.unary(Occur::Must)
}
parser! {
fn leaf[I]()(I) -> UserInputAST
where [I: Stream<Item = char>] {
char('-').with(leaf()).map(negate)
.or(char('+').with(leaf()).map(must))
.or(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))
}
}
#[derive(Clone, Copy)]
enum BinaryOperand {
Or,
And,
}
parser! {
fn binary_operand[I]()(I) -> BinaryOperand
where [I: Stream<Item = char>]
{
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)
}
}
parser! {
pub fn ast[I]()(I) -> UserInputAST
where [I: Stream<Item = char>]
{
let operand_leaf = (binary_operand().skip(spaces()), leaf().skip(spaces()));
let boolean_expr = (leaf().skip(spaces().silent()), many1(operand_leaf)).map(
|(left, right)| aggregate_binary_expressions(left,right));
let whitespace_separated_leaves = many1(leaf().skip(spaces().silent()))
.map(|subqueries: Vec<UserInputAST>|
if subqueries.len() == 1 {
subqueries.into_iter().next().unwrap()
} else {
UserInputAST::Clause(subqueries.into_iter().collect())
});
let expr = attempt(boolean_expr).or(whitespace_separated_leaves);
spaces().with(expr).skip(spaces())
}
}
parser! {
pub fn parse_to_ast[I]()(I) -> UserInputAST
where [I: Stream<Item = char>]
{
spaces().with(optional(ast()).skip(eof())).map(|opt_ast| opt_ast.unwrap_or_else(UserInputAST::empty_query))
}
}
#[cfg(test)]
mod test {
use super::*;
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_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_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_to_ast() {
test_parse_query_to_ast_helper("abc", "\"abc\"");
test_parse_query_to_ast_helper("a b", "(\"a\" \"b\")");
test_parse_query_to_ast_helper("+(a b)", "+((\"a\" \"b\"))");
test_parse_query_to_ast_helper("+d", "+(\"d\")");
test_parse_query_to_ast_helper("+(a b) +d", "(+((\"a\" \"b\")) +(\"d\"))");
test_parse_query_to_ast_helper("(+a +b) d", "((+(\"a\") +(\"b\")) \"d\")");
test_parse_query_to_ast_helper("(+a)", "+(\"a\")");
test_parse_query_to_ast_helper("(+a +b)", "(+(\"a\") +(\"b\"))");
test_parse_query_to_ast_helper("abc:toto", "abc:\"toto\"");
test_parse_query_to_ast_helper("abc:1.1", "abc:\"1.1\"");
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_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 + ");
}
}

7
src/collector/count_collector.rs
View File

@@ -10,10 +10,12 @@ use crate::SegmentReader;
/// documents match the query. /// documents match the query.
/// ///
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::Count; /// use tantivy::collector::Count;
/// use tantivy::query::QueryParser; /// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result};
/// ///
/// # fn main() { example().unwrap(); } /// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> { /// fn example() -> Result<()> {
@@ -123,4 +125,5 @@ mod tests {
assert_eq!(count_collector.harvest(), 2); assert_eq!(count_collector.harvest(), 2);
} }
} }
} }

27
src/collector/facet_collector.rs
View File

@@ -81,10 +81,12 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// ///
/// ///
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::FacetCollector; /// use tantivy::collector::FacetCollector;
/// use tantivy::query::AllQuery; /// use tantivy::query::AllQuery;
/// use tantivy::schema::{Facet, Schema, TEXT};
/// use tantivy::{doc, Index, Result};
/// ///
/// # fn main() { example().unwrap(); } /// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> { /// fn example() -> Result<()> {
@@ -515,7 +517,7 @@ mod tests {
#[should_panic(expected = "Tried to add a facet which is a descendant of \ #[should_panic(expected = "Tried to add a facet which is a descendant of \
an already added facet.")] an already added facet.")]
fn test_misused_facet_collector() { fn test_misused_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::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"));
facet_collector.add_facet(Facet::from("/country/europe")); facet_collector.add_facet(Facet::from("/country/europe"));
} }
@@ -546,7 +548,7 @@ mod tests {
#[test] #[test]
fn test_non_used_facet_collector() { fn test_non_used_facet_collector() {
let mut facet_collector = FacetCollector::for_field(Field::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"));
facet_collector.add_facet(Facet::from("/countryeurope")); facet_collector.add_facet(Facet::from("/countryeurope"));
} }
@@ -599,18 +601,19 @@ mod tests {
); );
} }
} }
} }
#[cfg(all(test, feature = "unstable"))] #[cfg(all(test, feature = "unstable"))]
mod bench { mod bench {
use crate::collector::FacetCollector; use collector::FacetCollector;
use crate::query::AllQuery; use query::AllQuery;
use crate::schema::{Facet, Schema}; use rand::{thread_rng, Rng};
use crate::Index; use schema::Facet;
use rand::seq::SliceRandom; use schema::Schema;
use rand::thread_rng;
use test::Bencher; use test::Bencher;
use Index;
#[bench] #[bench]
fn bench_facet_collector(b: &mut Bencher) { fn bench_facet_collector(b: &mut Bencher) {
@@ -627,7 +630,7 @@ mod bench {
} }
} }
// 40425 docs // 40425 docs
docs[..].shuffle(&mut thread_rng()); thread_rng().shuffle(&mut docs[..]);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap(); let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
for doc in docs { for doc in docs {
@@ -636,7 +639,7 @@ mod bench {
index_writer.commit().unwrap(); index_writer.commit().unwrap();
let reader = index.reader().unwrap(); let reader = index.reader().unwrap();
b.iter(|| { b.iter(|| {
let searcher = reader.searcher(); let searcher = index.searcher();
let facet_collector = FacetCollector::for_field(facet_field); let facet_collector = FacetCollector::for_field(facet_field);
searcher.search(&AllQuery, &facet_collector).unwrap(); searcher.search(&AllQuery, &facet_collector).unwrap();
}); });

1
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. in their respective position.
```rust ```rust
# extern crate tantivy;
# use tantivy::schema::*; # use tantivy::schema::*;
# use tantivy::*; # use tantivy::*;
# use tantivy::query::*; # use tantivy::query::*;

6
src/collector/multi_collector.rs
View File

@@ -105,10 +105,12 @@ impl<TFruit: Fruit> FruitHandle<TFruit> {
/// [Combining several collectors section of the collector documentation](./index.html#combining-several-collectors). /// [Combining several collectors section of the collector documentation](./index.html#combining-several-collectors).
/// ///
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::{Count, TopDocs, MultiCollector}; /// use tantivy::collector::{Count, TopDocs, MultiCollector};
/// use tantivy::query::QueryParser; /// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result};
/// ///
/// # fn main() { example().unwrap(); } /// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> { /// fn example() -> Result<()> {

113
src/collector/top_collector.rs
View File

@@ -12,9 +12,6 @@ use std::collections::BinaryHeap;
/// It has a custom implementation of `PartialOrd` that reverses the order. This is because the /// It has a custom implementation of `PartialOrd` that reverses the order. This is because the
/// default Rust heap is a max heap, whereas a min heap is needed. /// default Rust heap is a max heap, whereas a min heap is needed.
/// ///
/// Additionally, it guarantees stable sorting: in case of a tie on the feature, the document
/// address is used.
///
/// WARNING: equality is not what you would expect here. /// WARNING: equality is not what you would expect here.
/// Two elements are equal if their feature is equal, and regardless of whether `doc` /// Two elements are equal if their feature is equal, and regardless of whether `doc`
/// is equal. This should be perfectly fine for this usage, but let's make sure this /// is equal. This should be perfectly fine for this usage, but let's make sure this
@@ -24,37 +21,29 @@ struct ComparableDoc<T, D> {
doc: D, 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> { fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other)) Some(self.cmp(other))
} }
} }
impl<T: PartialOrd, D: PartialOrd> Ord for ComparableDoc<T, D> { impl<T: PartialOrd, D> Ord for ComparableDoc<T, D> {
#[inline] #[inline]
fn cmp(&self, other: &Self) -> Ordering { fn cmp(&self, other: &Self) -> Ordering {
// Reversed to make BinaryHeap work as a min-heap other
let by_feature = other
.feature .feature
.partial_cmp(&self.feature) .partial_cmp(&self.feature)
.unwrap_or(Ordering::Equal); .unwrap_or_else(|| Ordering::Equal)
let lazy_by_doc_address = || self.doc.partial_cmp(&other.doc).unwrap_or(Ordering::Equal);
// In case of a tie on the feature, we sort by ascending
// `DocAddress` in order to ensure a stable sorting of the
// documents.
by_feature.then_with(lazy_by_doc_address)
} }
} }
impl<T: PartialOrd, D: PartialOrd> PartialEq for ComparableDoc<T, D> { impl<T: PartialOrd, D> PartialEq for ComparableDoc<T, D> {
fn eq(&self, other: &Self) -> bool { fn eq(&self, other: &Self) -> bool {
self.cmp(other) == Ordering::Equal self.cmp(other) == Ordering::Equal
} }
} }
impl<T: PartialOrd, D: PartialOrd> Eq for ComparableDoc<T, D> {} impl<T: PartialOrd, D> Eq for ComparableDoc<T, D> {}
pub(crate) struct TopCollector<T> { pub(crate) struct TopCollector<T> {
limit: usize, limit: usize,
@@ -225,94 +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(),
);
}
}
#[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()
});
}
} }

57
src/collector/top_score_collector.rs
View File

@@ -15,21 +15,21 @@ use crate::SegmentLocalId;
use crate::SegmentReader; use crate::SegmentReader;
use std::fmt; use std::fmt;
/// The `TopDocs` collector keeps track of the top `K` documents /// The Top Score Collector keeps track of the K documents
/// sorted by their score. /// sorted by their score.
/// ///
/// The implementation is based on a `BinaryHeap`. /// The implementation is based on a `BinaryHeap`.
/// The theorical complexity for collecting the top `K` out of `n` documents /// The theorical complexity for collecting the top `K` out of `n` documents
/// is `O(n log K)`. /// is `O(n log K)`.
/// ///
/// This collector guarantees a stable sorting in case of a tie on the
/// document score. As such, it is suitable to implement pagination.
///
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::DocAddress;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result};
/// use tantivy::collector::TopDocs; /// use tantivy::collector::TopDocs;
/// use tantivy::query::QueryParser; /// use tantivy::query::QueryParser;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, DocAddress, Index, Result};
/// ///
/// # fn main() { example().unwrap(); } /// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> { /// fn example() -> Result<()> {
@@ -87,8 +87,10 @@ impl TopDocs {
/// Set top-K to rank documents by a given fast field. /// Set top-K to rank documents by a given fast field.
/// ///
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// # use tantivy::schema::{Schema, FAST, TEXT}; /// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, Result, DocAddress}; /// # use tantivy::{Index, Result, DocAddress};
/// # use tantivy::query::{Query, QueryParser}; /// # use tantivy::query::{Query, QueryParser};
/// use tantivy::Searcher; /// use tantivy::Searcher;
/// use tantivy::collector::TopDocs; /// use tantivy::collector::TopDocs;
@@ -126,7 +128,7 @@ impl TopDocs {
/// /// /// ///
/// /// `field` is required to be a FAST field. /// /// `field` is required to be a FAST field.
/// fn docs_sorted_by_rating(searcher: &Searcher, /// fn docs_sorted_by_rating(searcher: &Searcher,
/// query: &dyn Query, /// query: &Query,
/// sort_by_field: Field) /// sort_by_field: Field)
/// -> Result<Vec<(u64, DocAddress)>> { /// -> Result<Vec<(u64, DocAddress)>> {
/// ///
@@ -195,8 +197,10 @@ impl TopDocs {
/// learning-to-rank model over various features /// learning-to-rank model over various features
/// ///
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// # use tantivy::schema::{Schema, FAST, TEXT}; /// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, DocAddress, DocId, Score}; /// # use tantivy::{Index, DocAddress, DocId, Score};
/// # use tantivy::query::QueryParser; /// # use tantivy::query::QueryParser;
/// use tantivy::SegmentReader; /// use tantivy::SegmentReader;
/// use tantivy::collector::TopDocs; /// use tantivy::collector::TopDocs;
@@ -298,8 +302,10 @@ impl TopDocs {
/// # Example /// # Example
/// ///
/// ```rust /// ```rust
/// # #[macro_use]
/// # extern crate tantivy;
/// # use tantivy::schema::{Schema, FAST, TEXT}; /// # use tantivy::schema::{Schema, FAST, TEXT};
/// # use tantivy::{doc, Index, DocAddress, DocId}; /// # use tantivy::{Index, DocAddress, DocId};
/// # use tantivy::query::QueryParser; /// # use tantivy::query::QueryParser;
/// use tantivy::SegmentReader; /// use tantivy::SegmentReader;
/// use tantivy::collector::TopDocs; /// use tantivy::collector::TopDocs;
@@ -431,13 +437,12 @@ impl SegmentCollector for TopScoreSegmentCollector {
mod tests { mod tests {
use super::TopDocs; use super::TopDocs;
use crate::collector::Collector; use crate::collector::Collector;
use crate::query::{AllQuery, Query, QueryParser}; use crate::query::{Query, QueryParser};
use crate::schema::{Field, Schema, FAST, STORED, TEXT}; use crate::schema::{Field, Schema, FAST, STORED, TEXT};
use crate::DocAddress; use crate::DocAddress;
use crate::Index; use crate::Index;
use crate::IndexWriter; use crate::IndexWriter;
use crate::Score; use crate::Score;
use itertools::Itertools;
fn make_index() -> Index { fn make_index() -> Index {
let mut schema_builder = Schema::builder(); let mut schema_builder = Schema::builder();
@@ -498,29 +503,6 @@ mod tests {
); );
} }
#[test]
fn test_top_collector_stable_sorting() {
let index = make_index();
// using AllQuery to get a constant score
let searcher = index.reader().unwrap().searcher();
let page_1 = searcher.search(&AllQuery, &TopDocs::with_limit(2)).unwrap();
let page_2 = searcher.search(&AllQuery, &TopDocs::with_limit(3)).unwrap();
// precondition for the test to be meaningful: we did get documents
// with the same score
assert!(page_1.iter().map(|result| result.0).all_equal());
assert!(page_2.iter().map(|result| result.0).all_equal());
// sanity check since we're relying on make_index()
assert_eq!(page_1.len(), 2);
assert_eq!(page_2.len(), 3);
assert_eq!(page_1, &page_2[..page_1.len()]);
}
#[test] #[test]
#[should_panic] #[should_panic]
fn test_top_0() { fn test_top_0() {
@@ -578,7 +560,7 @@ mod tests {
)); ));
}); });
let searcher = index.reader().unwrap().searcher(); let searcher = index.reader().unwrap().searcher();
let top_collector = TopDocs::with_limit(4).order_by_u64_field(Field::from_field_id(2)); let top_collector = TopDocs::with_limit(4).order_by_u64_field(Field(2));
let segment_reader = searcher.segment_reader(0u32); let segment_reader = searcher.segment_reader(0u32);
top_collector top_collector
.for_segment(0, segment_reader) .for_segment(0, segment_reader)
@@ -609,7 +591,7 @@ mod tests {
query_field: Field, query_field: Field,
schema: Schema, schema: Schema,
mut doc_adder: impl FnMut(&mut IndexWriter) -> (), mut doc_adder: impl FnMut(&mut IndexWriter) -> (),
) -> (Index, Box<dyn Query>) { ) -> (Index, Box<Query>) {
let index = Index::create_in_ram(schema); let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap(); let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
@@ -619,4 +601,5 @@ mod tests {
let query = query_parser.parse_query(query).unwrap(); let query = query_parser.parse_query(query).unwrap();
(index, query) (index, query)
} }
} }

20
src/common/composite_file.rs
View File

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

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;
use std::io::Write; 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)] #[cfg(test)]
mod test { mod test {

19
src/common/mod.rs
View File

@@ -124,24 +124,26 @@ pub fn f64_to_u64(val: f64) -> u64 {
/// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html). /// Reverse the mapping given by [`i64_to_u64`](./fn.i64_to_u64.html).
#[inline(always)] #[inline(always)]
pub fn u64_to_f64(val: u64) -> f64 { pub fn u64_to_f64(val: u64) -> f64 {
f64::from_bits(if val & HIGHEST_BIT != 0 { f64::from_bits(
val ^ HIGHEST_BIT if val & HIGHEST_BIT != 0 {
} else { val ^ HIGHEST_BIT
!val } else {
}) !val
}
)
} }
#[cfg(test)] #[cfg(test)]
pub(crate) mod test { pub(crate) mod test {
pub use super::serialize::test::fixed_size_test; 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; use std::f64;
fn test_i64_converter_helper(val: i64) { fn test_i64_converter_helper(val: i64) {
assert_eq!(u64_to_i64(i64_to_u64(val)), val); assert_eq!(u64_to_i64(i64_to_u64(val)), val);
} }
fn test_f64_converter_helper(val: f64) { fn test_f64_converter_helper(val: f64) {
assert_eq!(u64_to_f64(f64_to_u64(val)), val); assert_eq!(u64_to_f64(f64_to_u64(val)), val);
} }
@@ -170,8 +172,7 @@ pub(crate) mod test {
#[test] #[test]
fn test_f64_order() { fn test_f64_order() {
assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY)) assert!(!(f64_to_u64(f64::NEG_INFINITY)..f64_to_u64(f64::INFINITY)).contains(&f64_to_u64(f64::NAN))); //nan is not a number
.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(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(1.0)); //same mantissa, different exponent
assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa assert!(f64_to_u64(2.0) > f64_to_u64(1.5)); //different exponent and mantissa

5
src/common/serialize.rs
View File

@@ -199,7 +199,10 @@ pub mod test {
fn test_serialize_string() { fn test_serialize_string() {
assert_eq!(serialize_test(String::from("")), 1); 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("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] #[test]

20
src/core/executor.rs
View File

@@ -1,6 +1,6 @@
use crate::Result; use crate::Result;
use crossbeam::channel; use crossbeam::channel;
use rayon::{ThreadPool, ThreadPoolBuilder}; use scoped_pool::{Pool, ThreadConfig};
/// Search executor whether search request are single thread or multithread. /// Search executor whether search request are single thread or multithread.
/// ///
@@ -11,7 +11,7 @@ use rayon::{ThreadPool, ThreadPoolBuilder};
/// used by the client. Second, we may stop using rayon in the future. /// used by the client. Second, we may stop using rayon in the future.
pub enum Executor { pub enum Executor {
SingleThread, SingleThread,
ThreadPool(ThreadPool), ThreadPool(Pool),
} }
impl Executor { impl Executor {
@@ -21,12 +21,10 @@ impl Executor {
} }
// Creates an Executor that dispatches the tasks in a thread pool. // Creates an Executor that dispatches the tasks in a thread pool.
pub fn multi_thread(num_threads: usize, prefix: &'static str) -> Result<Executor> { pub fn multi_thread(num_threads: usize, prefix: &'static str) -> Executor {
let pool = ThreadPoolBuilder::new() let thread_config = ThreadConfig::new().prefix(prefix);
.num_threads(num_threads) let pool = Pool::with_thread_config(num_threads, thread_config);
.thread_name(move |num| format!("{}{}", prefix, num)) Executor::ThreadPool(pool)
.build()?;
Ok(Executor::ThreadPool(pool))
} }
// Perform a map in the thread pool. // Perform a map in the thread pool.
@@ -50,9 +48,9 @@ impl Executor {
let num_fruits = args_with_indices.len(); let num_fruits = args_with_indices.len();
let fruit_receiver = { let fruit_receiver = {
let (fruit_sender, fruit_receiver) = channel::unbounded(); let (fruit_sender, fruit_receiver) = channel::unbounded();
pool.scope(|scope| { pool.scoped(|scope| {
for arg_with_idx in args_with_indices { for arg_with_idx in args_with_indices {
scope.spawn(|_| { scope.execute(|| {
let (idx, arg) = arg_with_idx; let (idx, arg) = arg_with_idx;
let fruit = f(arg); let fruit = f(arg);
if let Err(err) = fruit_sender.send((idx, fruit)) { if let Err(err) = fruit_sender.send((idx, fruit)) {
@@ -105,7 +103,6 @@ mod tests {
#[should_panic] //< unfortunately the panic message is not propagated #[should_panic] //< unfortunately the panic message is not propagated
fn test_panic_propagates_multi_thread() { fn test_panic_propagates_multi_thread() {
let _result: Vec<usize> = Executor::multi_thread(1, "search-test") let _result: Vec<usize> = Executor::multi_thread(1, "search-test")
.unwrap()
.map( .map(
|_| { |_| {
panic!("panic should propagate"); panic!("panic should propagate");
@@ -129,7 +126,6 @@ mod tests {
#[test] #[test]
fn test_map_multithread() { fn test_map_multithread() {
let result: Vec<usize> = Executor::multi_thread(3, "search-test") let result: Vec<usize> = Executor::multi_thread(3, "search-test")
.unwrap()
.map(|i| Ok(i * 2), 0..10) .map(|i| Ok(i * 2), 0..10)
.unwrap(); .unwrap();
assert_eq!(result.len(), 10); assert_eq!(result.len(), 10);

46
src/core/index.rs
View File

@@ -26,10 +26,9 @@ use crate::IndexWriter;
use crate::Result; use crate::Result;
use num_cpus; use num_cpus;
use std::borrow::BorrowMut; use std::borrow::BorrowMut;
use std::collections::HashSet;
use std::fmt; use std::fmt;
#[cfg(feature = "mmap")] #[cfg(feature = "mmap")]
use std::path::{Path, PathBuf}; use std::path::Path;
use std::sync::Arc; use std::sync::Arc;
fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> { fn load_metas(directory: &dyn Directory, inventory: &SegmentMetaInventory) -> Result<IndexMeta> {
@@ -73,16 +72,15 @@ impl Index {
/// Replace the default single thread search executor pool /// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads. /// by a thread pool with a given number of threads.
pub fn set_multithread_executor(&mut self, num_threads: usize) -> Result<()> { pub fn set_multithread_executor(&mut self, num_threads: usize) {
self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-")?); self.executor = Arc::new(Executor::multi_thread(num_threads, "thrd-tantivy-search-"));
Ok(())
} }
/// Replace the default single thread search executor pool /// Replace the default single thread search executor pool
/// by a thread pool with a given number of threads. /// by a thread pool with a given number of threads.
pub fn set_default_multithread_executor(&mut self) -> Result<()> { pub fn set_default_multithread_executor(&mut self) {
let default_num_threads = num_cpus::get(); let default_num_threads = num_cpus::get();
self.set_multithread_executor(default_num_threads) self.set_multithread_executor(default_num_threads);
} }
/// Creates a new index using the `RAMDirectory`. /// Creates a new index using the `RAMDirectory`.
@@ -175,11 +173,11 @@ impl Index {
} }
/// Helper to access the tokenizer associated to a specific field. /// Helper to access the tokenizer associated to a specific field.
pub fn tokenizer_for_field(&self, field: Field) -> Result<BoxedTokenizer> { pub fn tokenizer_for_field(&self, field: Field) -> Result<Box<dyn BoxedTokenizer>> {
let field_entry = self.schema.get_field_entry(field); let field_entry = self.schema.get_field_entry(field);
let field_type = field_entry.field_type(); let field_type = field_entry.field_type();
let tokenizer_manager: &TokenizerManager = self.tokenizers(); let tokenizer_manager: &TokenizerManager = self.tokenizers();
let tokenizer_name_opt: Option<BoxedTokenizer> = match field_type { let tokenizer_name_opt: Option<Box<dyn BoxedTokenizer>> = match field_type {
FieldType::Str(text_options) => text_options FieldType::Str(text_options) => text_options
.get_indexing_options() .get_indexing_options()
.map(|text_indexing_options| text_indexing_options.tokenizer().to_string()) .map(|text_indexing_options| text_indexing_options.tokenizer().to_string())
@@ -218,22 +216,8 @@ impl Index {
Index::open(mmap_directory) Index::open(mmap_directory)
} }
/// Returns the list of the segment metas tracked by the index. pub(crate) fn inventory(&self) -> &SegmentMetaInventory {
/// &self.inventory
/// Such segments can of course be part of the index,
/// but also they could be segments being currently built or in the middle of a merge
/// operation.
pub fn list_all_segment_metas(&self) -> Vec<SegmentMeta> {
self.inventory.all()
}
/// Creates a new segment_meta (Advanced user only).
///
/// As long as the `SegmentMeta` lives, the files associated with the
/// `SegmentMeta` are guaranteed to not be garbage collected, regardless of
/// whether the segment is recorded as part of the index or not.
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
self.inventory.new_segment_meta(segment_id, max_doc)
} }
/// Open the index using the provided directory /// Open the index using the provided directory
@@ -370,11 +354,6 @@ impl Index {
.map(SegmentMeta::id) .map(SegmentMeta::id)
.collect()) .collect())
} }
/// Returns the set of corrupted files
pub fn validate_checksum(&self) -> Result<HashSet<PathBuf>> {
self.directory.list_damaged().map_err(Into::into)
}
} }
impl fmt::Debug for Index { impl fmt::Debug for Index {
@@ -480,13 +459,13 @@ mod tests {
use super::*; use super::*;
use std::path::PathBuf; use std::path::PathBuf;
use tempfile::TempDir; use tempdir::TempDir;
#[test] #[test]
fn test_index_on_commit_reload_policy_mmap() { fn test_index_on_commit_reload_policy_mmap() {
let schema = throw_away_schema(); let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap(); 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 tempdir_path = PathBuf::from(tempdir.path());
let index = Index::create_in_dir(&tempdir_path, schema).unwrap(); let index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap(); let mut writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
@@ -525,7 +504,7 @@ mod tests {
fn test_index_on_commit_reload_policy_different_directories() { fn test_index_on_commit_reload_policy_different_directories() {
let schema = throw_away_schema(); let schema = throw_away_schema();
let field = schema.get_field("num_likes").unwrap(); 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 tempdir_path = PathBuf::from(tempdir.path());
let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap(); let write_index = Index::create_in_dir(&tempdir_path, schema).unwrap();
let read_index = Index::open_in_dir(&tempdir_path).unwrap(); let read_index = Index::open_in_dir(&tempdir_path).unwrap();
@@ -602,4 +581,5 @@ mod tests {
assert_eq!(searcher.num_docs(), 8_000); assert_eq!(searcher.num_docs(), 8_000);
assert!(mem_right_after_merge_finished < mem_right_after_commit); assert!(mem_right_after_merge_finished < mem_right_after_commit);
} }
} }

16
src/core/index_meta.rs
View File

@@ -30,6 +30,7 @@ impl SegmentMetaInventory {
.collect::<Vec<_>>() .collect::<Vec<_>>()
} }
#[doc(hidden)]
pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta { pub fn new_segment_meta(&self, segment_id: SegmentId, max_doc: u32) -> SegmentMeta {
let inner = InnerSegmentMeta { let inner = InnerSegmentMeta {
segment_id, segment_id,
@@ -150,21 +151,6 @@ impl SegmentMeta {
self.num_deleted_docs() > 0 self.num_deleted_docs() > 0
} }
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> SegmentMeta {
assert_eq!(self.tracked.max_doc, 0);
assert!(self.tracked.deletes.is_none());
let tracked = self.tracked.map(move |inner_meta| InnerSegmentMeta {
segment_id: inner_meta.segment_id,
max_doc,
deletes: None,
});
SegmentMeta { tracked }
}
#[doc(hidden)] #[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta { pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> SegmentMeta {
let delete_meta = DeleteMeta { let delete_meta = DeleteMeta {

11
src/core/segment.rs
View File

@@ -50,17 +50,6 @@ impl Segment {
&self.meta &self.meta
} }
/// Updates the max_doc value from the `SegmentMeta`.
///
/// This method is only used when updating `max_doc` from 0
/// as we finalize a fresh new segment.
pub(crate) fn with_max_doc(self, max_doc: u32) -> Segment {
Segment {
index: self.index,
meta: self.meta.with_max_doc(max_doc),
}
}
#[doc(hidden)] #[doc(hidden)]
pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment { pub fn with_delete_meta(self, num_deleted_docs: u32, opstamp: Opstamp) -> Segment {
Segment { Segment {

55
src/core/segment_id.rs
View File

@@ -4,8 +4,6 @@ use uuid::Uuid;
#[cfg(test)] #[cfg(test)]
use once_cell::sync::Lazy; use once_cell::sync::Lazy;
use std::error::Error;
use std::str::FromStr;
#[cfg(test)] #[cfg(test)]
use std::sync::atomic; use std::sync::atomic;
@@ -54,51 +52,15 @@ impl SegmentId {
/// and the rest is random. /// and the rest is random.
/// ///
/// Picking the first 8 chars is ok to identify /// 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 { pub fn short_uuid_string(&self) -> String {
(&self.0.to_simple_ref().to_string()[..8]).to_string() (&self.0.to_simple_ref().to_string()[..8]).to_string()
} }
/// Returns a segment uuid string. /// Returns a segment uuid string.
///
/// It consists in 32 lowercase hexadecimal chars
/// (e.g. a5c4dfcbdfe645089129e308e26d5523)
pub fn uuid_string(&self) -> String { pub fn uuid_string(&self) -> String {
self.0.to_simple_ref().to_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 { impl fmt::Debug for SegmentId {
@@ -118,18 +80,3 @@ impl Ord for SegmentId {
self.0.as_bytes().cmp(other.0.as_bytes()) 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());
}
}

8
src/directory/directory.rs
View File

@@ -48,14 +48,14 @@ impl RetryPolicy {
/// ///
/// It is transparently associated to a lock file, that gets deleted /// It is transparently associated to a lock file, that gets deleted
/// on `Drop.` The lock is released automatically on `Drop`. /// 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 { struct DirectoryLockGuard {
directory: Box<dyn Directory>, directory: Box<dyn Directory>,
path: PathBuf, 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 { fn from(underlying: Box<T>) -> Self {
DirectoryLock(underlying) DirectoryLock(underlying)
} }
@@ -118,8 +118,6 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// ///
/// Specifically, subsequent writes or flushes should /// Specifically, subsequent writes or flushes should
/// have no effect on the returned `ReadOnlySource` object. /// have no effect on the returned `ReadOnlySource` object.
///
/// You should only use this to read files create with [`open_write`]
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>; fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError>;
/// Removes a file /// Removes a file
@@ -159,8 +157,6 @@ pub trait Directory: DirectoryClone + fmt::Debug + Send + Sync + 'static {
/// atomic_write. /// atomic_write.
/// ///
/// This should only be used for small files. /// This should only be used for small files.
///
/// You should only use this to read files create with [`atomic_write`]
fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>; fn atomic_read(&self, path: &Path) -> Result<Vec<u8>, OpenReadError>;
/// Atomically replace the content of a file with data. /// Atomically replace the content of a file with data.

213
src/directory/footer.rs
View File

@@ -1,213 +0,0 @@
use crate::directory::read_only_source::ReadOnlySource;
use crate::directory::{AntiCallToken, TerminatingWrite};
use byteorder::{ByteOrder, LittleEndian};
use crc32fast::Hasher;
use std::io;
use std::io::Write;
const COMMON_FOOTER_SIZE: usize = 4 * 5;
#[derive(Debug, Clone, PartialEq)]
pub struct Footer {
pub tantivy_version: (u32, u32, u32),
pub meta: String,
pub versioned_footer: VersionedFooter,
}
impl Footer {
pub fn new(versioned_footer: VersionedFooter) -> Self {
let tantivy_version = (
env!("CARGO_PKG_VERSION_MAJOR").parse().unwrap(),
env!("CARGO_PKG_VERSION_MINOR").parse().unwrap(),
env!("CARGO_PKG_VERSION_PATCH").parse().unwrap(),
);
Footer {
tantivy_version,
meta: format!(
"tantivy {}.{}.{}, index v{}",
tantivy_version.0,
tantivy_version.1,
tantivy_version.2,
versioned_footer.version()
),
versioned_footer,
}
}
pub fn to_bytes(&self) -> Vec<u8> {
let mut res = self.versioned_footer.to_bytes();
res.extend_from_slice(self.meta.as_bytes());
let len = res.len();
res.resize(len + COMMON_FOOTER_SIZE, 0);
let mut common_footer = &mut res[len..];
LittleEndian::write_u32(&mut common_footer, self.meta.len() as u32);
LittleEndian::write_u32(&mut common_footer[4..], self.tantivy_version.0);
LittleEndian::write_u32(&mut common_footer[8..], self.tantivy_version.1);
LittleEndian::write_u32(&mut common_footer[12..], self.tantivy_version.2);
LittleEndian::write_u32(&mut common_footer[16..], (len + COMMON_FOOTER_SIZE) as u32);
res
}
pub fn from_bytes(data: &[u8]) -> Result<Self, io::Error> {
let len = data.len();
if len < COMMON_FOOTER_SIZE + 4 {
// 4 bytes for index version, stored in versioned footer
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!("File corrupted. The footer len must be over 24, while the entire file len is {}", len)
)
);
}
let size = LittleEndian::read_u32(&data[len - 4..]) as usize;
if len < size as usize {
return Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The footer len is {}, while the entire file len is {}",
size, len
),
));
}
let footer = &data[len - size as usize..];
let meta_len = LittleEndian::read_u32(&footer[size - 20..]) as usize;
let tantivy_major = LittleEndian::read_u32(&footer[size - 16..]);
let tantivy_minor = LittleEndian::read_u32(&footer[size - 12..]);
let tantivy_patch = LittleEndian::read_u32(&footer[size - 8..]);
Ok(Footer {
tantivy_version: (tantivy_major, tantivy_minor, tantivy_patch),
meta: String::from_utf8_lossy(&footer[size - meta_len - 20..size - 20]).into_owned(),
versioned_footer: VersionedFooter::from_bytes(&footer[..size - meta_len - 20])?,
})
}
pub fn extract_footer(source: ReadOnlySource) -> Result<(Footer, ReadOnlySource), io::Error> {
let footer = Footer::from_bytes(source.as_slice())?;
let reader = source.slice_to(source.as_slice().len() - footer.size());
Ok((footer, reader))
}
pub fn size(&self) -> usize {
self.versioned_footer.size() as usize + self.meta.len() + 20
}
}
#[derive(Debug, Clone, PartialEq)]
pub enum VersionedFooter {
UnknownVersion { version: u32, size: u32 },
V0(u32), // crc
}
impl VersionedFooter {
pub fn to_bytes(&self) -> Vec<u8> {
match self {
VersionedFooter::V0(crc) => {
let mut res = vec![0; 8];
LittleEndian::write_u32(&mut res, 0);
LittleEndian::write_u32(&mut res[4..], *crc);
res
}
VersionedFooter::UnknownVersion { .. } => {
panic!("Unsupported index should never get serialized");
}
}
}
pub fn from_bytes(footer: &[u8]) -> Result<Self, io::Error> {
assert!(footer.len() >= 4);
let version = LittleEndian::read_u32(footer);
match version {
0 => {
if footer.len() == 8 {
Ok(VersionedFooter::V0(LittleEndian::read_u32(&footer[4..])))
} else {
Err(io::Error::new(
io::ErrorKind::UnexpectedEof,
format!(
"File corrupted. The versioned footer len is {}, while it should be 8",
footer.len()
),
))
}
}
version => Ok(VersionedFooter::UnknownVersion {
version,
size: footer.len() as u32,
}),
}
}
pub fn size(&self) -> u32 {
match self {
VersionedFooter::V0(_) => 8,
VersionedFooter::UnknownVersion { size, .. } => *size,
}
}
pub fn version(&self) -> u32 {
match self {
VersionedFooter::V0(_) => 0,
VersionedFooter::UnknownVersion { version, .. } => *version,
}
}
pub fn crc(&self) -> Option<u32> {
match self {
VersionedFooter::V0(crc) => Some(*crc),
VersionedFooter::UnknownVersion { .. } => None,
}
}
}
pub(crate) struct FooterProxy<W: TerminatingWrite> {
/// always Some except after terminate call
hasher: Option<Hasher>,
/// always Some except after terminate call
writer: Option<W>,
}
impl<W: TerminatingWrite> FooterProxy<W> {
pub fn new(writer: W) -> Self {
FooterProxy {
hasher: Some(Hasher::new()),
writer: Some(writer),
}
}
}
impl<W: TerminatingWrite> Write for FooterProxy<W> {
fn write(&mut self, buf: &[u8]) -> io::Result<usize> {
let count = self.writer.as_mut().unwrap().write(buf)?;
self.hasher.as_mut().unwrap().update(&buf[..count]);
Ok(count)
}
fn flush(&mut self) -> io::Result<()> {
self.writer.as_mut().unwrap().flush()
}
}
impl<W: TerminatingWrite> TerminatingWrite for FooterProxy<W> {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
let crc = self.hasher.take().unwrap().finalize();
let footer = Footer::new(VersionedFooter::V0(crc)).to_bytes();
let mut writer = self.writer.take().unwrap();
writer.write_all(&footer)?;
writer.terminate()
}
}
#[cfg(test)]
mod tests {
use crate::directory::footer::{Footer, VersionedFooter};
#[test]
fn test_serialize_deserialize_footer() {
let crc = 123456;
let footer = Footer::new(VersionedFooter::V0(crc));
let footer_bytes = footer.to_bytes();
assert_eq!(Footer::from_bytes(&footer_bytes).unwrap(), footer);
}
}

104
src/directory/managed_directory.rs
View File

@@ -1,6 +1,5 @@
use crate::core::MANAGED_FILEPATH; use crate::core::MANAGED_FILEPATH;
use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError}; use crate::directory::error::{DeleteError, IOError, LockError, OpenReadError, OpenWriteError};
use crate::directory::footer::{Footer, FooterProxy};
use crate::directory::DirectoryLock; use crate::directory::DirectoryLock;
use crate::directory::Lock; use crate::directory::Lock;
use crate::directory::META_LOCK; use crate::directory::META_LOCK;
@@ -9,7 +8,6 @@ use crate::directory::{WatchCallback, WatchHandle};
use crate::error::DataCorruption; use crate::error::DataCorruption;
use crate::Directory; use crate::Directory;
use crate::Result; use crate::Result;
use crc32fast::Hasher;
use serde_json; use serde_json;
use std::collections::HashSet; use std::collections::HashSet;
use std::io; use std::io;
@@ -209,59 +207,17 @@ impl ManagedDirectory {
} }
Ok(()) Ok(())
} }
/// Verify checksum of a managed file
pub fn validate_checksum(&self, path: &Path) -> result::Result<bool, OpenReadError> {
let reader = self.directory.open_read(path)?;
let (footer, data) = Footer::extract_footer(reader)
.map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
let mut hasher = Hasher::new();
hasher.update(data.as_slice());
let crc = hasher.finalize();
Ok(footer
.versioned_footer
.crc()
.map(|v| v == crc)
.unwrap_or(false))
}
/// List files for which checksum does not match content
pub fn list_damaged(&self) -> result::Result<HashSet<PathBuf>, OpenReadError> {
let mut hashset = HashSet::new();
let managed_paths = self
.meta_informations
.read()
.expect("Managed directory rlock poisoned in list damaged.")
.managed_paths
.clone();
for path in managed_paths.into_iter() {
if !self.validate_checksum(&path)? {
hashset.insert(path);
}
}
Ok(hashset)
}
} }
impl Directory for ManagedDirectory { impl Directory for ManagedDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> { fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
let read_only_source = self.directory.open_read(path)?; self.directory.open_read(path)
let (_footer, reader) = Footer::extract_footer(read_only_source)
.map_err(|err| IOError::with_path(path.to_path_buf(), err))?;
Ok(reader)
} }
fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> { fn open_write(&mut self, path: &Path) -> result::Result<WritePtr, OpenWriteError> {
self.register_file_as_managed(path) self.register_file_as_managed(path)
.map_err(|e| IOError::with_path(path.to_owned(), e))?; .map_err(|e| IOError::with_path(path.to_owned(), e))?;
Ok(io::BufWriter::new(Box::new(FooterProxy::new( self.directory.open_write(path)
self.directory
.open_write(path)?
.into_inner()
.map_err(|_| ())
.expect("buffer should be empty"),
))))
} }
fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> { fn atomic_write(&mut self, path: &Path, data: &[u8]) -> io::Result<()> {
@@ -303,16 +259,15 @@ impl Clone for ManagedDirectory {
#[cfg(test)] #[cfg(test)]
mod tests_mmap_specific { mod tests_mmap_specific {
use crate::directory::{Directory, ManagedDirectory, MmapDirectory, TerminatingWrite}; use crate::directory::{Directory, ManagedDirectory, MmapDirectory};
use std::collections::HashSet; use std::collections::HashSet;
use std::fs::OpenOptions;
use std::io::Write; use std::io::Write;
use std::path::{Path, PathBuf}; use std::path::{Path, PathBuf};
use tempfile::TempDir; use tempdir::TempDir;
#[test] #[test]
fn test_managed_directory() { fn test_managed_directory() {
let tempdir = TempDir::new().unwrap(); let tempdir = TempDir::new("tantivy-test").unwrap();
let tempdir_path = PathBuf::from(tempdir.path()); let tempdir_path = PathBuf::from(tempdir.path());
let test_path1: &'static Path = Path::new("some_path_for_test"); let test_path1: &'static Path = Path::new("some_path_for_test");
@@ -320,14 +275,15 @@ mod tests_mmap_specific {
{ {
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap(); let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap(); let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let write_file = managed_directory.open_write(test_path1).unwrap(); let mut write_file = managed_directory.open_write(test_path1).unwrap();
write_file.terminate().unwrap(); write_file.flush().unwrap();
managed_directory managed_directory
.atomic_write(test_path2, &[0u8, 1u8]) .atomic_write(test_path2, &[0u8, 1u8])
.unwrap(); .unwrap();
assert!(managed_directory.exists(test_path1)); assert!(managed_directory.exists(test_path1));
assert!(managed_directory.exists(test_path2)); assert!(managed_directory.exists(test_path2));
let living_files: HashSet<PathBuf> = [test_path1.to_owned()].iter().cloned().collect(); let living_files: HashSet<PathBuf> =
[test_path1.to_owned()].into_iter().cloned().collect();
managed_directory.garbage_collect(|| living_files); managed_directory.garbage_collect(|| living_files);
assert!(managed_directory.exists(test_path1)); assert!(managed_directory.exists(test_path1));
assert!(!managed_directory.exists(test_path2)); assert!(!managed_directory.exists(test_path2));
@@ -348,15 +304,15 @@ mod tests_mmap_specific {
fn test_managed_directory_gc_while_mmapped() { fn test_managed_directory_gc_while_mmapped() {
let test_path1: &'static Path = Path::new("some_path_for_test"); 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 tempdir_path = PathBuf::from(tempdir.path());
let living_files = HashSet::new(); let living_files = HashSet::new();
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap(); let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap(); let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let mut write = managed_directory.open_write(test_path1).unwrap(); managed_directory
write.write_all(&[0u8, 1u8]).unwrap(); .atomic_write(test_path1, &vec![0u8, 1u8])
write.terminate().unwrap(); .unwrap();
assert!(managed_directory.exists(test_path1)); assert!(managed_directory.exists(test_path1));
let _mmap_read = managed_directory.open_read(test_path1).unwrap(); let _mmap_read = managed_directory.open_read(test_path1).unwrap();
@@ -375,38 +331,4 @@ mod tests_mmap_specific {
} }
} }
#[test]
fn test_checksum() {
let test_path1: &'static Path = Path::new("some_path_for_test");
let test_path2: &'static Path = Path::new("other_test_path");
let tempdir = TempDir::new().unwrap();
let tempdir_path = PathBuf::from(tempdir.path());
let mmap_directory = MmapDirectory::open(&tempdir_path).unwrap();
let mut managed_directory = ManagedDirectory::wrap(mmap_directory).unwrap();
let mut write = managed_directory.open_write(test_path1).unwrap();
write.write_all(&[0u8, 1u8]).unwrap();
write.terminate().unwrap();
let mut write = managed_directory.open_write(test_path2).unwrap();
write.write_all(&[3u8, 4u8, 5u8]).unwrap();
write.terminate().unwrap();
assert!(managed_directory.list_damaged().unwrap().is_empty());
let mut corrupted_path = tempdir_path.clone();
corrupted_path.push(test_path2);
let mut file = OpenOptions::new()
.write(true)
.open(&corrupted_path)
.unwrap();
file.write_all(&[255u8]).unwrap();
file.flush().unwrap();
drop(file);
let damaged = managed_directory.list_damaged().unwrap();
assert_eq!(damaged.len(), 1);
assert!(damaged.contains(test_path2));
}
} }

77
src/directory/mmap_directory.rs
View File

@@ -11,7 +11,6 @@ use crate::directory::error::{
DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError, DeleteError, IOError, OpenDirectoryError, OpenReadError, OpenWriteError,
}; };
use crate::directory::read_only_source::BoxedData; use crate::directory::read_only_source::BoxedData;
use crate::directory::AntiCallToken;
use crate::directory::Directory; use crate::directory::Directory;
use crate::directory::DirectoryLock; use crate::directory::DirectoryLock;
use crate::directory::Lock; use crate::directory::Lock;
@@ -19,7 +18,7 @@ use crate::directory::ReadOnlySource;
use crate::directory::WatchCallback; use crate::directory::WatchCallback;
use crate::directory::WatchCallbackList; use crate::directory::WatchCallbackList;
use crate::directory::WatchHandle; use crate::directory::WatchHandle;
use crate::directory::{TerminatingWrite, WritePtr}; use crate::directory::WritePtr;
use atomicwrites; use atomicwrites;
use memmap::Mmap; use memmap::Mmap;
use std::collections::HashMap; use std::collections::HashMap;
@@ -37,7 +36,7 @@ use std::sync::Mutex;
use std::sync::RwLock; use std::sync::RwLock;
use std::sync::Weak; use std::sync::Weak;
use std::thread; use std::thread;
use tempfile::TempDir; use tempdir::TempDir;
/// Create a default io error given a string. /// Create a default io error given a string.
pub(crate) fn make_io_err(msg: String) -> io::Error { pub(crate) fn make_io_err(msg: String) -> io::Error {
@@ -142,28 +141,42 @@ impl MmapCache {
} }
} }
struct WatcherWrapper { struct InnerWatcherWrapper {
_watcher: Mutex<notify::RecommendedWatcher>, _watcher: Mutex<notify::RecommendedWatcher>,
watcher_router: Arc<WatchCallbackList>, 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 { impl WatcherWrapper {
pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> { pub fn new(path: &Path) -> Result<Self, OpenDirectoryError> {
let (tx, watcher_recv): (Sender<RawEvent>, Receiver<RawEvent>) = channel(); let (inner, watcher_recv) = InnerWatcherWrapper::new(path).map_err(|err| match err {
// We need to initialize the notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()),
let watcher = notify::raw_watcher(tx) _ => {
.and_then(|mut watcher| { panic!("Unknown error while starting watching directory {:?}", path);
watcher.watch(path, RecursiveMode::Recursive)?; }
Ok(watcher) })?;
}) let watcher_wrapper = WatcherWrapper {
.map_err(|err| match err { inner: Arc::new(inner),
notify::Error::PathNotFound => OpenDirectoryError::DoesNotExist(path.to_owned()), };
_ => { let watcher_wrapper_clone = watcher_wrapper.clone();
panic!("Unknown error while starting watching directory {:?}", path);
}
})?;
let watcher_router: Arc<WatchCallbackList> = Default::default();
let watcher_router_clone = watcher_router.clone();
thread::Builder::new() thread::Builder::new()
.name("meta-file-watch-thread".to_string()) .name("meta-file-watch-thread".to_string())
.spawn(move || { .spawn(move || {
@@ -174,7 +187,7 @@ impl WatcherWrapper {
// We might want to be more accurate than this at one point. // We might want to be more accurate than this at one point.
if let Some(filename) = changed_path.file_name() { if let Some(filename) = changed_path.file_name() {
if filename == *META_FILEPATH { if filename == *META_FILEPATH {
watcher_router_clone.broadcast(); watcher_wrapper_clone.inner.watcher_router.broadcast();
} }
} }
} }
@@ -187,15 +200,13 @@ impl WatcherWrapper {
} }
} }
} }
})?; })
Ok(WatcherWrapper { .expect("Failed to spawn thread to watch meta.json");
_watcher: Mutex::new(watcher), Ok(watcher_wrapper)
watcher_router,
})
} }
pub fn watch(&mut self, watch_callback: WatchCallback) -> WatchHandle { pub fn watch(&mut self, watch_callback: WatchCallback) -> WatchHandle {
self.watcher_router.subscribe(watch_callback) self.inner.watcher_router.subscribe(watch_callback)
} }
} }
@@ -254,7 +265,7 @@ impl MmapDirectoryInner {
} }
} }
if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() { if let Some(watch_wrapper) = self.watcher.write().unwrap().as_mut() {
Ok(watch_wrapper.watch(watch_callback)) return Ok(watch_wrapper.watch(watch_callback));
} else { } else {
unreachable!("At this point, watch wrapper is supposed to be initialized"); unreachable!("At this point, watch wrapper is supposed to be initialized");
} }
@@ -283,7 +294,7 @@ impl MmapDirectory {
/// This is mostly useful to test the MmapDirectory itself. /// This is mostly useful to test the MmapDirectory itself.
/// For your unit tests, prefer the RAMDirectory. /// For your unit tests, prefer the RAMDirectory.
pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> { pub fn create_from_tempdir() -> Result<MmapDirectory, OpenDirectoryError> {
let tempdir = TempDir::new().map_err(OpenDirectoryError::IoError)?; let tempdir = TempDir::new("index").map_err(OpenDirectoryError::IoError)?;
let tempdir_path = PathBuf::from(tempdir.path()); let tempdir_path = PathBuf::from(tempdir.path());
MmapDirectory::new(tempdir_path, Some(tempdir)) MmapDirectory::new(tempdir_path, Some(tempdir))
} }
@@ -401,12 +412,6 @@ impl Seek for SafeFileWriter {
} }
} }
impl TerminatingWrite for SafeFileWriter {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
impl Directory for MmapDirectory { impl Directory for MmapDirectory {
fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> { fn open_read(&self, path: &Path) -> result::Result<ReadOnlySource, OpenReadError> {
debug!("Open Read {:?}", path); debug!("Open Read {:?}", path);
@@ -637,7 +642,7 @@ mod tests {
fn test_watch_wrapper() { fn test_watch_wrapper() {
let counter: Arc<AtomicUsize> = Default::default(); let counter: Arc<AtomicUsize> = Default::default();
let counter_clone = counter.clone(); let counter_clone = counter.clone();
let tmp_dir = tempfile::TempDir::new().unwrap(); let tmp_dir: TempDir = tempdir::TempDir::new("test_watch_wrapper").unwrap();
let tmp_dirpath = tmp_dir.path().to_owned(); let tmp_dirpath = tmp_dir.path().to_owned();
let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath).unwrap(); let mut watch_wrapper = WatcherWrapper::new(&tmp_dirpath).unwrap();
let tmp_file = tmp_dirpath.join("coucou"); let tmp_file = tmp_dirpath.join("coucou");

36
src/directory/mod.rs
View File

@@ -9,7 +9,6 @@ mod mmap_directory;
mod directory; mod directory;
mod directory_lock; mod directory_lock;
mod footer;
mod managed_directory; mod managed_directory;
mod ram_directory; mod ram_directory;
mod read_only_source; mod read_only_source;
@@ -25,49 +24,18 @@ pub use self::ram_directory::RAMDirectory;
pub use self::read_only_source::ReadOnlySource; pub use self::read_only_source::ReadOnlySource;
pub(crate) use self::watch_event_router::WatchCallbackList; pub(crate) use self::watch_event_router::WatchCallbackList;
pub use self::watch_event_router::{WatchCallback, WatchHandle}; pub use self::watch_event_router::{WatchCallback, WatchHandle};
use std::io::{self, BufWriter, Write}; use std::io::{BufWriter, Write};
#[cfg(feature = "mmap")] #[cfg(feature = "mmap")]
pub use self::mmap_directory::MmapDirectory; pub use self::mmap_directory::MmapDirectory;
pub use self::managed_directory::ManagedDirectory; pub use self::managed_directory::ManagedDirectory;
/// Struct used to prevent from calling [`terminate_ref`](trait.TerminatingWrite#method.terminate_ref) directly
pub struct AntiCallToken(());
/// Trait used to indicate when no more write need to be done on a writer
pub trait TerminatingWrite: Write {
/// Indicate that the writer will no longer be used. Internally call terminate_ref.
fn terminate(mut self) -> io::Result<()>
where
Self: Sized,
{
self.terminate_ref(AntiCallToken(()))
}
/// You should implement this function to define custom behavior.
/// This function should flush any buffer it may hold.
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()>;
}
impl<W: TerminatingWrite + ?Sized> TerminatingWrite for Box<W> {
fn terminate_ref(&mut self, token: AntiCallToken) -> io::Result<()> {
self.as_mut().terminate_ref(token)
}
}
impl<W: TerminatingWrite> TerminatingWrite for BufWriter<W> {
fn terminate_ref(&mut self, a: AntiCallToken) -> io::Result<()> {
self.flush()?;
self.get_mut().terminate_ref(a)
}
}
/// Write object for Directory. /// Write object for Directory.
/// ///
/// `WritePtr` are required to implement both Write /// `WritePtr` are required to implement both Write
/// and Seek. /// and Seek.
pub type WritePtr = BufWriter<Box<dyn TerminatingWrite>>; pub type WritePtr = BufWriter<Box<dyn Write>>;
#[cfg(test)] #[cfg(test)]
mod tests; mod tests;

11
src/directory/ram_directory.rs
View File

@@ -1,9 +1,8 @@
use crate::core::META_FILEPATH; use crate::core::META_FILEPATH;
use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError}; use crate::directory::error::{DeleteError, OpenReadError, OpenWriteError};
use crate::directory::AntiCallToken;
use crate::directory::WatchCallbackList; use crate::directory::WatchCallbackList;
use crate::directory::WritePtr;
use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle}; use crate::directory::{Directory, ReadOnlySource, WatchCallback, WatchHandle};
use crate::directory::{TerminatingWrite, WritePtr};
use fail::fail_point; use fail::fail_point;
use std::collections::HashMap; use std::collections::HashMap;
use std::fmt; use std::fmt;
@@ -72,12 +71,6 @@ impl Write for VecWriter {
} }
} }
impl TerminatingWrite for VecWriter {
fn terminate_ref(&mut self, _: AntiCallToken) -> io::Result<()> {
self.flush()
}
}
#[derive(Default)] #[derive(Default)]
struct InnerDirectory { struct InnerDirectory {
fs: HashMap<PathBuf, ReadOnlySource>, fs: HashMap<PathBuf, ReadOnlySource>,
@@ -184,7 +177,7 @@ impl Directory for RAMDirectory {
fn atomic_write(&mut 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( fail_point!("RAMDirectory::atomic_write", |msg| Err(io::Error::new(
io::ErrorKind::Other, io::ErrorKind::Other,
msg.unwrap_or_else(|| "Undefined".to_string()) msg.unwrap_or("Undefined".to_string())
))); )));
let path_buf = PathBuf::from(path); let path_buf = PathBuf::from(path);

2
src/directory/tests.rs
View File

@@ -127,7 +127,7 @@ fn test_watch(directory: &mut dyn Directory) {
assert!(directory assert!(directory
.atomic_write(Path::new("meta.json"), b"random_test_data_2") .atomic_write(Path::new("meta.json"), b"random_test_data_2")
.is_ok()); .is_ok());
for _ in 0..1_000 { for _ in 0..100 {
if counter.load(Ordering::SeqCst) > i { if counter.load(Ordering::SeqCst) > i {
break; break;
} }

1
src/directory/watch_event_router.rs
View File

@@ -152,4 +152,5 @@ mod tests {
thread::sleep(Duration::from_millis(WAIT_TIME)); thread::sleep(Duration::from_millis(WAIT_TIME));
assert_eq!(2, counter.load(Ordering::SeqCst)); assert_eq!(2, counter.load(Ordering::SeqCst));
} }
} }

6
src/error.rs
View File

@@ -170,9 +170,3 @@ impl From<serde_json::Error> for TantivyError {
TantivyError::IOError(io_err.into()) TantivyError::IOError(io_err.into())
} }
} }
impl From<rayon::ThreadPoolBuildError> for TantivyError {
fn from(error: rayon::ThreadPoolBuildError) -> TantivyError {
TantivyError::SystemError(error.to_string())
}
}

20
src/fastfield/delete.rs
View File

@@ -10,14 +10,11 @@ use std::io::Write;
/// Write a delete `BitSet` /// Write a delete `BitSet`
/// ///
/// where `delete_bitset` is the set of deleted `DocId`. /// where `delete_bitset` is the set of deleted `DocId`.
pub fn write_delete_bitset( pub fn write_delete_bitset(delete_bitset: &BitSet, writer: &mut WritePtr) -> io::Result<()> {
delete_bitset: &BitSet, let max_doc = delete_bitset.capacity();
max_doc: u32,
writer: &mut WritePtr,
) -> io::Result<()> {
let mut byte = 0u8; let mut byte = 0u8;
let mut shift = 0u8; let mut shift = 0u8;
for doc in 0..(max_doc as usize) { for doc in 0..max_doc {
if delete_bitset.contains(doc) { if delete_bitset.contains(doc) {
byte |= 1 << shift; byte |= 1 << shift;
} }
@@ -89,17 +86,18 @@ mod tests {
use bit_set::BitSet; use bit_set::BitSet;
use std::path::PathBuf; use std::path::PathBuf;
fn test_delete_bitset_helper(bitset: &BitSet, max_doc: u32) { fn test_delete_bitset_helper(bitset: &BitSet) {
let test_path = PathBuf::from("test"); let test_path = PathBuf::from("test");
let mut directory = RAMDirectory::create(); let mut directory = RAMDirectory::create();
{ {
let mut writer = directory.open_write(&*test_path).unwrap(); let mut writer = directory.open_write(&*test_path).unwrap();
write_delete_bitset(bitset, max_doc, &mut writer).unwrap(); write_delete_bitset(bitset, &mut writer).unwrap();
} }
{ {
let source = directory.open_read(&test_path).unwrap(); let source = directory.open_read(&test_path).unwrap();
let delete_bitset = DeleteBitSet::open(source); let delete_bitset = DeleteBitSet::open(source);
for doc in 0..max_doc as usize { let n = bitset.capacity();
for doc in 0..n {
assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId)); assert_eq!(bitset.contains(doc), delete_bitset.is_deleted(doc as DocId));
} }
assert_eq!(delete_bitset.len(), bitset.len()); assert_eq!(delete_bitset.len(), bitset.len());
@@ -112,7 +110,7 @@ mod tests {
let mut bitset = BitSet::with_capacity(10); let mut bitset = BitSet::with_capacity(10);
bitset.insert(1); bitset.insert(1);
bitset.insert(9); bitset.insert(9);
test_delete_bitset_helper(&bitset, 10); test_delete_bitset_helper(&bitset);
} }
{ {
let mut bitset = BitSet::with_capacity(8); let mut bitset = BitSet::with_capacity(8);
@@ -121,7 +119,7 @@ mod tests {
bitset.insert(3); bitset.insert(3);
bitset.insert(5); bitset.insert(5);
bitset.insert(7); bitset.insert(7);
test_delete_bitset_helper(&bitset, 8); test_delete_bitset_helper(&bitset);
} }
} }
} }

8
src/fastfield/mod.rs
View File

@@ -429,6 +429,7 @@ mod tests {
} }
} }
} }
} }
#[cfg(all(test, feature = "unstable"))] #[cfg(all(test, feature = "unstable"))]
@@ -436,9 +437,9 @@ mod bench {
use super::tests::FIELD; use super::tests::FIELD;
use super::tests::{generate_permutation, SCHEMA}; use super::tests::{generate_permutation, SCHEMA};
use super::*; use super::*;
use crate::common::CompositeFile; use common::CompositeFile;
use crate::directory::{Directory, RAMDirectory, WritePtr}; use directory::{Directory, RAMDirectory, WritePtr};
use crate::fastfield::FastFieldReader; use fastfield::FastFieldReader;
use std::collections::HashMap; use std::collections::HashMap;
use std::path::Path; use std::path::Path;
use test::{self, Bencher}; use test::{self, Bencher};
@@ -536,4 +537,5 @@ mod bench {
}); });
} }
} }
} }

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

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

3
src/fastfield/readers.rs
View File

@@ -59,7 +59,8 @@ impl FastFieldReaders {
fast_bytes: Default::default(), fast_bytes: Default::default(),
fast_fields_composite: fast_fields_composite.clone(), fast_fields_composite: fast_fields_composite.clone(),
}; };
for (field, 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(); let field_type = field_entry.field_type();
if field_type == &FieldType::Bytes { if field_type == &FieldType::Bytes {
let idx_reader = fast_fields_composite let idx_reader = fast_fields_composite

10
src/fastfield/writer.rs
View File

@@ -6,7 +6,6 @@ use crate::fastfield::{BytesFastFieldWriter, FastFieldSerializer};
use crate::postings::UnorderedTermId; use crate::postings::UnorderedTermId;
use crate::schema::{Cardinality, Document, Field, FieldType, Schema}; use crate::schema::{Cardinality, Document, Field, FieldType, Schema};
use crate::termdict::TermOrdinal; use crate::termdict::TermOrdinal;
use fnv::FnvHashMap;
use std::collections::HashMap; use std::collections::HashMap;
use std::io; use std::io;
@@ -24,16 +23,15 @@ impl FastFieldsWriter {
let mut multi_values_writers = Vec::new(); let mut multi_values_writers = Vec::new();
let mut bytes_value_writers = Vec::new(); let mut bytes_value_writers = Vec::new();
for (field, field_entry) in schema.fields() { 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() { let default_value = match *field_entry.field_type() {
FieldType::I64(_) => common::i64_to_u64(0i64), FieldType::I64(_) => common::i64_to_u64(0i64),
FieldType::F64(_) => common::f64_to_u64(0.0f64), FieldType::F64(_) => common::f64_to_u64(0.0f64),
_ => 0u64, _ => 0u64,
}; };
match *field_entry.field_type() { match *field_entry.field_type() {
FieldType::I64(ref int_options) FieldType::I64(ref int_options) | FieldType::U64(ref int_options) | FieldType::F64(ref int_options) => {
| FieldType::U64(ref int_options)
| FieldType::F64(ref int_options) => {
match int_options.get_fastfield_cardinality() { match int_options.get_fastfield_cardinality() {
Some(Cardinality::SingleValue) => { Some(Cardinality::SingleValue) => {
let mut fast_field_writer = IntFastFieldWriter::new(field); let mut fast_field_writer = IntFastFieldWriter::new(field);
@@ -116,7 +114,7 @@ impl FastFieldsWriter {
pub fn serialize( pub fn serialize(
&self, &self,
serializer: &mut FastFieldSerializer, serializer: &mut FastFieldSerializer,
mapping: &HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>, mapping: &HashMap<Field, HashMap<UnorderedTermId, TermOrdinal>>,
) -> io::Result<()> { ) -> io::Result<()> {
for field_writer in &self.single_value_writers { for field_writer in &self.single_value_writers {
field_writer.serialize(serializer)?; field_writer.serialize(serializer)?;

23
src/fieldnorm/writer.rs
View File

@@ -22,14 +22,11 @@ impl FieldNormsWriter {
pub(crate) fn fields_with_fieldnorm(schema: &Schema) -> Vec<Field> { pub(crate) fn fields_with_fieldnorm(schema: &Schema) -> Vec<Field> {
schema schema
.fields() .fields()
.filter_map(|(field, field_entry)| { .iter()
if field_entry.is_indexed() { .enumerate()
Some(field) .filter(|&(_, field_entry)| field_entry.is_indexed())
} else { .map(|(field, _)| Field(field as u32))
None .collect::<Vec<Field>>()
}
})
.collect::<Vec<_>>()
} }
/// Initialize with state for tracking the field norm fields /// Initialize with state for tracking the field norm fields
@@ -38,7 +35,7 @@ impl FieldNormsWriter {
let fields = FieldNormsWriter::fields_with_fieldnorm(schema); let fields = FieldNormsWriter::fields_with_fieldnorm(schema);
let max_field = fields let max_field = fields
.iter() .iter()
.map(Field::field_id) .map(|field| field.0)
.max() .max()
.map(|max_field_id| max_field_id as usize + 1) .map(|max_field_id| max_field_id as usize + 1)
.unwrap_or(0); .unwrap_or(0);
@@ -53,8 +50,8 @@ impl FieldNormsWriter {
/// ///
/// Will extend with 0-bytes for documents that have not been seen. /// Will extend with 0-bytes for documents that have not been seen.
pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) { pub fn fill_up_to_max_doc(&mut self, max_doc: DocId) {
for field in self.fields.iter() { for &field in self.fields.iter() {
self.fieldnorms_buffer[field.field_id() as usize].resize(max_doc as usize, 0u8); self.fieldnorms_buffer[field.0 as usize].resize(max_doc as usize, 0u8);
} }
} }
@@ -67,7 +64,7 @@ impl FieldNormsWriter {
/// * field - the field being set /// * field - the field being set
/// * fieldnorm - the number of terms present in document `doc` in field `field` /// * fieldnorm - the number of terms present in document `doc` in field `field`
pub fn record(&mut self, doc: DocId, field: Field, fieldnorm: u32) { pub fn record(&mut self, doc: DocId, field: Field, fieldnorm: u32) {
let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.field_id() as usize]; let fieldnorm_buffer: &mut Vec<u8> = &mut self.fieldnorms_buffer[field.0 as usize];
assert!( assert!(
fieldnorm_buffer.len() <= doc as usize, fieldnorm_buffer.len() <= doc as usize,
"Cannot register a given fieldnorm twice" "Cannot register a given fieldnorm twice"
@@ -80,7 +77,7 @@ impl FieldNormsWriter {
/// Serialize the seen fieldnorm values to the serializer for all fields. /// Serialize the seen fieldnorm values to the serializer for all fields.
pub fn serialize(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> io::Result<()> { pub fn serialize(&self, fieldnorms_serializer: &mut FieldNormsSerializer) -> io::Result<()> {
for &field in self.fields.iter() { for &field in self.fields.iter() {
let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.field_id() as usize][..]; let fieldnorm_values: &[u8] = &self.fieldnorms_buffer[field.0 as usize][..];
fieldnorms_serializer.serialize_field(field, fieldnorm_values)?; fieldnorms_serializer.serialize_field(field, fieldnorm_values)?;
} }
Ok(()) Ok(())

2
src/indexer/delete_queue.rs
View File

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

50
src/indexer/index_writer.rs
View File

@@ -8,7 +8,6 @@ use crate::core::SegmentId;
use crate::core::SegmentMeta; use crate::core::SegmentMeta;
use crate::core::SegmentReader; use crate::core::SegmentReader;
use crate::directory::DirectoryLock; use crate::directory::DirectoryLock;
use crate::directory::TerminatingWrite;
use crate::docset::DocSet; use crate::docset::DocSet;
use crate::error::TantivyError; use crate::error::TantivyError;
use crate::fastfield::write_delete_bitset; use crate::fastfield::write_delete_bitset;
@@ -148,6 +147,7 @@ pub(crate) fn advance_deletes(
}; };
let delete_cursor = segment_entry.delete_cursor(); let delete_cursor = segment_entry.delete_cursor();
compute_deleted_bitset( compute_deleted_bitset(
&mut delete_bitset, &mut delete_bitset,
&segment_reader, &segment_reader,
@@ -167,8 +167,7 @@ pub(crate) fn advance_deletes(
if num_deleted_docs > 0 { if num_deleted_docs > 0 {
segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp); segment = segment.with_delete_meta(num_deleted_docs as u32, target_opstamp);
let mut delete_file = segment.open_write(SegmentComponent::DELETE)?; let mut delete_file = segment.open_write(SegmentComponent::DELETE)?;
write_delete_bitset(&delete_bitset, max_doc, &mut delete_file)?; write_delete_bitset(&delete_bitset, &mut delete_file)?;
delete_file.terminate()?;
} }
} }
segment_entry.set_meta(segment.meta().clone()); segment_entry.set_meta(segment.meta().clone());
@@ -177,13 +176,13 @@ pub(crate) fn advance_deletes(
fn index_documents( fn index_documents(
memory_budget: usize, memory_budget: usize,
segment: Segment, segment: &Segment,
grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>, grouped_document_iterator: &mut dyn Iterator<Item = OperationGroup>,
segment_updater: &mut SegmentUpdater, segment_updater: &mut SegmentUpdater,
mut delete_cursor: DeleteCursor, mut delete_cursor: DeleteCursor,
) -> Result<bool> { ) -> Result<bool> {
let schema = segment.schema(); let schema = segment.schema();
let segment_id = segment.id();
let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?; let mut segment_writer = SegmentWriter::for_segment(memory_budget, segment.clone(), &schema)?;
for document_group in grouped_document_iterator { for document_group in grouped_document_iterator {
for doc in document_group { for doc in document_group {
@@ -203,32 +202,25 @@ fn index_documents(
return Ok(false); 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 // this is ensured by the call to peek before starting
// the worker thread. // the worker thread.
assert!(max_doc > 0); assert!(num_docs > 0);
let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?; let doc_opstamps: Vec<Opstamp> = segment_writer.finalize()?;
let segment_meta = segment
let segment_with_max_doc = segment.with_max_doc(max_doc); .index()
.inventory()
.new_segment_meta(segment_id, num_docs);
let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap()); let last_docstamp: Opstamp = *(doc_opstamps.last().unwrap());
let delete_bitset_opt = apply_deletes( let delete_bitset_opt =
&segment_with_max_doc, apply_deletes(&segment, &mut delete_cursor, &doc_opstamps, last_docstamp)?;
&mut delete_cursor,
&doc_opstamps,
last_docstamp,
)?;
let segment_entry = SegmentEntry::new( let segment_entry = SegmentEntry::new(segment_meta, delete_cursor, delete_bitset_opt);
segment_with_max_doc.meta().clone(), Ok(segment_updater.add_segment(segment_entry))
delete_cursor,
delete_bitset_opt,
);
segment_updater.add_segment(segment_entry);
Ok(true)
} }
fn apply_deletes( fn apply_deletes(
@@ -244,9 +236,7 @@ fn apply_deletes(
} }
let segment_reader = SegmentReader::open(segment)?; let segment_reader = SegmentReader::open(segment)?;
let doc_to_opstamps = DocToOpstampMapping::from(doc_opstamps); let doc_to_opstamps = DocToOpstampMapping::from(doc_opstamps);
let mut deleted_bitset = BitSet::with_capacity(segment_reader.max_doc() as usize);
let max_doc = segment.meta().max_doc();
let mut deleted_bitset = BitSet::with_capacity(max_doc as usize);
let may_have_deletes = compute_deleted_bitset( let may_have_deletes = compute_deleted_bitset(
&mut deleted_bitset, &mut deleted_bitset,
&segment_reader, &segment_reader,
@@ -418,7 +408,7 @@ impl IndexWriter {
let segment = index.new_segment(); let segment = index.new_segment();
index_documents( index_documents(
mem_budget, mem_budget,
segment, &segment,
&mut document_iterator, &mut document_iterator,
&mut segment_updater, &mut segment_updater,
delete_cursor.clone(), delete_cursor.clone(),
@@ -460,10 +450,12 @@ impl IndexWriter {
/// by clearing and resubmitting necessary documents /// by clearing and resubmitting necessary documents
/// ///
/// ```rust /// ```rust
/// use tantivy::collector::TopDocs; /// #[macro_use]
/// extern crate tantivy;
/// use tantivy::query::QueryParser; /// use tantivy::query::QueryParser;
/// use tantivy::collector::TopDocs;
/// use tantivy::schema::*; /// use tantivy::schema::*;
/// use tantivy::{doc, Index}; /// use tantivy::Index;
/// ///
/// fn main() -> tantivy::Result<()> { /// fn main() -> tantivy::Result<()> {
/// let mut schema_builder = Schema::builder(); /// let mut schema_builder = Schema::builder();
@@ -769,6 +761,7 @@ mod tests {
use crate::Index; use crate::Index;
use crate::ReloadPolicy; use crate::ReloadPolicy;
use crate::Term; use crate::Term;
use fail;
#[test] #[test]
fn test_operations_group() { fn test_operations_group() {
@@ -1190,4 +1183,5 @@ mod tests {
assert!(clear_again.is_ok()); assert!(clear_again.is_ok());
assert!(commit_again.is_ok()); assert!(commit_again.is_ok());
} }
} }

16
src/indexer/merger.rs
View File

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

22
src/indexer/mod.rs
View File

@@ -28,25 +28,3 @@ pub use self::segment_writer::SegmentWriter;
/// Alias for the default merge policy, which is the `LogMergePolicy`. /// Alias for the default merge policy, which is the `LogMergePolicy`.
pub type DefaultMergePolicy = LogMergePolicy; pub type DefaultMergePolicy = LogMergePolicy;
#[cfg(test)]
mod tests {
use crate::schema::{self, Schema};
use crate::{Index, Term};
#[test]
fn test_advance_delete_bug() {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_from_tempdir(schema_builder.build()).unwrap();
let mut index_writer = index.writer_with_num_threads(1, 3_000_000).unwrap();
// there must be one deleted document in the segment
index_writer.add_document(doc!(text_field=>"b"));
index_writer.delete_term(Term::from_field_text(text_field, "b"));
// we need enough data to trigger the bug (at least 32 documents)
for _ in 0..32 {
index_writer.add_document(doc!(text_field=>"c"));
}
index_writer.commit().unwrap();
index_writer.commit().unwrap();
}
}

1
src/indexer/segment_register.rs
View File

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

10
src/indexer/segment_updater.rs
View File

@@ -126,7 +126,9 @@ fn perform_merge(
let num_docs = merger.write(segment_serializer)?; let num_docs = merger.write(segment_serializer)?;
let segment_meta = index.new_segment_meta(merged_segment.id(), num_docs); let segment_meta = index
.inventory()
.new_segment_meta(merged_segment.id(), num_docs);
let after_merge_segment_entry = SegmentEntry::new(segment_meta.clone(), delete_cursor, None); let after_merge_segment_entry = SegmentEntry::new(segment_meta.clone(), delete_cursor, None);
Ok(after_merge_segment_entry) Ok(after_merge_segment_entry)
@@ -199,12 +201,14 @@ impl SegmentUpdater {
self.0.pool.spawn_fn(move || Ok(f(me_clone))) self.0.pool.spawn_fn(move || Ok(f(me_clone)))
} }
pub fn add_segment(&self, segment_entry: SegmentEntry) { pub fn add_segment(&self, segment_entry: SegmentEntry) -> bool {
self.run_async(|segment_updater| { self.run_async(|segment_updater| {
segment_updater.0.segment_manager.add_segment(segment_entry); segment_updater.0.segment_manager.add_segment(segment_entry);
segment_updater.consider_merge_options(); segment_updater.consider_merge_options();
true
}) })
.forget(); .forget();
true
} }
/// Orders `SegmentManager` to remove all segments /// Orders `SegmentManager` to remove all segments
@@ -278,7 +282,7 @@ impl SegmentUpdater {
fn list_files(&self) -> HashSet<PathBuf> { fn list_files(&self) -> HashSet<PathBuf> {
let mut files = HashSet::new(); let mut files = HashSet::new();
files.insert(META_FILEPATH.to_path_buf()); files.insert(META_FILEPATH.to_path_buf());
for segment_meta in self.0.index.list_all_segment_metas() { for segment_meta in self.0.index.inventory().all() {
files.extend(segment_meta.list_files()); files.extend(segment_meta.list_files());
} }
files files

75
src/indexer/segment_writer.rs
View File

@@ -6,15 +6,14 @@ use crate::fieldnorm::FieldNormsWriter;
use crate::indexer::segment_serializer::SegmentSerializer; use crate::indexer::segment_serializer::SegmentSerializer;
use crate::postings::compute_table_size; use crate::postings::compute_table_size;
use crate::postings::MultiFieldPostingsWriter; use crate::postings::MultiFieldPostingsWriter;
use crate::schema::FieldEntry;
use crate::schema::FieldType; use crate::schema::FieldType;
use crate::schema::Schema; use crate::schema::Schema;
use crate::schema::Term; use crate::schema::Term;
use crate::schema::Value; use crate::schema::Value;
use crate::schema::{Field, FieldEntry};
use crate::tokenizer::BoxedTokenizer; use crate::tokenizer::BoxedTokenizer;
use crate::tokenizer::FacetTokenizer; use crate::tokenizer::FacetTokenizer;
use crate::tokenizer::PreTokenizedStream; use crate::tokenizer::{TokenStream, Tokenizer};
use crate::tokenizer::{TokenStream, TokenStreamChain, Tokenizer};
use crate::DocId; use crate::DocId;
use crate::Opstamp; use crate::Opstamp;
use crate::Result; use crate::Result;
@@ -50,7 +49,7 @@ pub struct SegmentWriter {
fast_field_writers: FastFieldsWriter, fast_field_writers: FastFieldsWriter,
fieldnorms_writer: FieldNormsWriter, fieldnorms_writer: FieldNormsWriter,
doc_opstamps: Vec<Opstamp>, doc_opstamps: Vec<Opstamp>,
tokenizers: Vec<Option<BoxedTokenizer>>, tokenizers: Vec<Option<Box<dyn BoxedTokenizer>>>,
} }
impl SegmentWriter { impl SegmentWriter {
@@ -71,10 +70,12 @@ impl SegmentWriter {
let table_num_bits = initial_table_size(memory_budget)?; let table_num_bits = initial_table_size(memory_budget)?;
let segment_serializer = SegmentSerializer::for_segment(&mut segment)?; let segment_serializer = SegmentSerializer::for_segment(&mut segment)?;
let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits); let multifield_postings = MultiFieldPostingsWriter::new(schema, table_num_bits);
let tokenizers = schema let tokenizers =
.fields() schema
.map( .fields()
|(_, field_entry): (Field, &FieldEntry)| match field_entry.field_type() { .iter()
.map(FieldEntry::field_type)
.map(|field_type| match *field_type {
FieldType::Str(ref text_options) => text_options FieldType::Str(ref text_options) => text_options
.get_indexing_options() .get_indexing_options()
.and_then(|text_index_option| { .and_then(|text_index_option| {
@@ -82,9 +83,8 @@ impl SegmentWriter {
segment.index().tokenizers().get(tokenizer_name) segment.index().tokenizers().get(tokenizer_name)
}), }),
_ => None, _ => None,
}, })
) .collect();
.collect();
Ok(SegmentWriter { Ok(SegmentWriter {
max_doc: 0, max_doc: 0,
multifield_postings, multifield_postings,
@@ -159,44 +159,26 @@ impl SegmentWriter {
} }
} }
FieldType::Str(_) => { FieldType::Str(_) => {
let mut token_streams: Vec<Box<dyn TokenStream>> = vec![]; let num_tokens = if let Some(ref mut tokenizer) =
let mut offsets = vec![]; self.tokenizers[field.0 as usize]
let mut total_offset = 0; {
let texts: Vec<&str> = field_values
for field_value in field_values { .iter()
match field_value.value() { .flat_map(|field_value| match *field_value.value() {
Value::PreTokStr(tok_str) => { Value::Str(ref text) => Some(text.as_str()),
offsets.push(total_offset); _ => None,
if let Some(last_token) = tok_str.tokens.last() { })
total_offset += last_token.offset_to; .collect();
} if texts.is_empty() {
0
token_streams } else {
.push(Box::new(PreTokenizedStream::from(tok_str.clone()))); let mut token_stream = tokenizer.token_stream_texts(&texts[..]);
} self.multifield_postings
Value::Str(ref text) => { .index_text(doc_id, field, &mut token_stream)
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 token_streams.is_empty() {
0
} else { } else {
let mut token_stream: Box<dyn TokenStream> = 0
Box::new(TokenStreamChain::new(offsets, token_streams));
self.multifield_postings
.index_text(doc_id, field, &mut token_stream)
}; };
self.fieldnorms_writer.record(doc_id, field, num_tokens); self.fieldnorms_writer.record(doc_id, field, num_tokens);
} }
FieldType::U64(ref int_option) => { FieldType::U64(ref int_option) => {
@@ -314,4 +296,5 @@ mod tests {
assert_eq!(initial_table_size(10_000_000).unwrap(), 17); assert_eq!(initial_table_size(10_000_000).unwrap(), 17);
assert_eq!(initial_table_size(1_000_000_000).unwrap(), 19); assert_eq!(initial_table_size(1_000_000_000).unwrap(), 19);
} }
} }

32
src/lib.rs
View File

@@ -3,6 +3,7 @@
#![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))] #![cfg_attr(feature = "cargo-clippy", allow(clippy::module_inception))]
#![doc(test(attr(allow(unused_variables), deny(warnings))))] #![doc(test(attr(allow(unused_variables), deny(warnings))))]
#![warn(missing_docs)] #![warn(missing_docs)]
#![recursion_limit = "80"]
//! # `tantivy` //! # `tantivy`
//! //!
@@ -10,17 +11,26 @@
//! Think `Lucene`, but in Rust. //! Think `Lucene`, but in Rust.
//! //!
//! ```rust //! ```rust
//! # extern crate tempdir;
//! #
//! #[macro_use]
//! extern crate tantivy;
//!
//! // ...
//!
//! # use std::path::Path; //! # use std::path::Path;
//! # use tempfile::TempDir; //! # use tempdir::TempDir;
//! # use tantivy::Index;
//! # use tantivy::schema::*;
//! # use tantivy::{Score, DocAddress};
//! # use tantivy::collector::TopDocs; //! # use tantivy::collector::TopDocs;
//! # use tantivy::query::QueryParser; //! # use tantivy::query::QueryParser;
//! # use tantivy::schema::*;
//! # use tantivy::{doc, DocAddress, Index, Score};
//! # //! #
//! # fn main() { //! # fn main() {
//! # // Let's create a temporary directory for the //! # // Let's create a temporary directory for the
//! # // sake of this example //! # // sake of this example
//! # if let Ok(dir) = TempDir::new() { //! # if let Ok(dir) = TempDir::new("tantivy_example_dir") {
//! # run_example(dir.path()).unwrap(); //! # run_example(dir.path()).unwrap();
//! # dir.close().unwrap(); //! # dir.close().unwrap();
//! # } //! # }
@@ -212,13 +222,15 @@ pub type Score = f32;
pub type SegmentLocalId = u32; pub type SegmentLocalId = u32;
impl DocAddress { impl DocAddress {
/// Return the segment ordinal id that identifies the segment /// Return the segment ordinal.
/// hosting the document in the `Searcher` it is called from. /// The segment ordinal is an id identifying the segment
/// hosting the document. It is only meaningful, in the context
/// of a searcher.
pub fn segment_ord(self) -> SegmentLocalId { pub fn segment_ord(self) -> SegmentLocalId {
self.0 self.0
} }
/// Return the segment-local `DocId` /// Return the segment local `DocId`
pub fn doc(self) -> DocId { pub fn doc(self) -> DocId {
self.1 self.1
} }
@@ -227,11 +239,11 @@ impl DocAddress {
/// `DocAddress` contains all the necessary information /// `DocAddress` contains all the necessary information
/// to identify a document given a `Searcher` object. /// to identify a document given a `Searcher` object.
/// ///
/// It consists of an id identifying its segment, and /// It consists in an id identifying its segment, and
/// a segment-local `DocId`. /// its segment-local `DocId`.
/// ///
/// The id used for the segment is actually an ordinal /// The id used for the segment is actually an ordinal
/// in the list of `Segment`s held by a `Searcher`. /// in the list of segment hold by a `Searcher`.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)] #[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
pub struct DocAddress(pub SegmentLocalId, pub DocId); pub struct DocAddress(pub SegmentLocalId, pub DocId);

6
src/macros.rs
View File

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

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

@@ -274,15 +274,13 @@ pub mod tests {
mod bench { mod bench {
use super::*; use super::*;
use rand::rngs::StdRng;
use rand::Rng;
use rand::SeedableRng; use rand::SeedableRng;
use rand::{Rng, XorShiftRng};
use test::Bencher; use test::Bencher;
fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> { fn generate_array_with_seed(n: usize, ratio: f64, seed_val: u8) -> Vec<u32> {
let mut seed: [u8; 32] = [0; 32]; let seed: &[u8; 16] = &[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, seed_val];
seed[31] = seed_val; let mut rng: XorShiftRng = XorShiftRng::from_seed(*seed);
let mut rng = StdRng::from_seed(seed);
(0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect() (0u32..).filter(|_| rng.gen_bool(ratio)).take(n).collect()
} }

37
src/postings/mod.rs
View File

@@ -356,9 +356,9 @@ pub mod tests {
#[test] #[test]
fn test_skip_next() { fn test_skip_next() {
let term_0 = Term::from_field_u64(Field::from_field_id(0), 0); let term_0 = Term::from_field_u64(Field(0), 0);
let term_1 = Term::from_field_u64(Field::from_field_id(0), 1); let term_1 = Term::from_field_u64(Field(0), 1);
let term_2 = Term::from_field_u64(Field::from_field_id(0), 2); let term_2 = Term::from_field_u64(Field(0), 2);
let num_docs = 300u32; let num_docs = 300u32;
@@ -511,19 +511,19 @@ pub mod tests {
} }
pub static TERM_A: Lazy<Term> = Lazy::new(|| { pub static TERM_A: Lazy<Term> = Lazy::new(|| {
let field = Field::from_field_id(0); let field = Field(0);
Term::from_field_text(field, "a") Term::from_field_text(field, "a")
}); });
pub static TERM_B: Lazy<Term> = Lazy::new(|| { pub static TERM_B: Lazy<Term> = Lazy::new(|| {
let field = Field::from_field_id(0); let field = Field(0);
Term::from_field_text(field, "b") Term::from_field_text(field, "b")
}); });
pub static TERM_C: Lazy<Term> = Lazy::new(|| { pub static TERM_C: Lazy<Term> = Lazy::new(|| {
let field = Field::from_field_id(0); let field = Field(0);
Term::from_field_text(field, "c") Term::from_field_text(field, "c")
}); });
pub static TERM_D: Lazy<Term> = Lazy::new(|| { pub static TERM_D: Lazy<Term> = Lazy::new(|| {
let field = Field::from_field_id(0); let field = Field(0);
Term::from_field_text(field, "d") Term::from_field_text(field, "d")
}); });
@@ -622,23 +622,23 @@ pub mod tests {
assert!(!postings_unopt.advance()); assert!(!postings_unopt.advance());
} }
} }
} }
#[cfg(all(test, feature = "unstable"))] #[cfg(all(test, feature = "unstable"))]
mod bench { mod bench {
use super::tests::*; use super::tests::*;
use crate::docset::SkipResult; use docset::SkipResult;
use crate::query::Intersection; use query::Intersection;
use crate::schema::IndexRecordOption; use schema::IndexRecordOption;
use crate::tests;
use crate::DocSet;
use test::{self, Bencher}; use test::{self, Bencher};
use tests;
use DocSet;
#[bench] #[bench]
fn bench_segment_postings(b: &mut Bencher) { fn bench_segment_postings(b: &mut Bencher) {
let reader = INDEX.reader().unwrap(); let searcher = INDEX.searcher();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0); let segment_reader = searcher.segment_reader(0);
b.iter(|| { b.iter(|| {
@@ -652,8 +652,7 @@ mod bench {
#[bench] #[bench]
fn bench_segment_intersection(b: &mut Bencher) { fn bench_segment_intersection(b: &mut Bencher) {
let reader = INDEX.reader().unwrap(); let searcher = INDEX.searcher();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0); let segment_reader = searcher.segment_reader(0);
b.iter(|| { b.iter(|| {
let segment_postings_a = segment_reader let segment_postings_a = segment_reader
@@ -683,8 +682,7 @@ mod bench {
} }
fn bench_skip_next(p: f64, b: &mut Bencher) { fn bench_skip_next(p: f64, b: &mut Bencher) {
let reader = INDEX.reader().unwrap(); let searcher = INDEX.searcher();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0); let segment_reader = searcher.segment_reader(0);
let docs = tests::sample(segment_reader.num_docs(), p); let docs = tests::sample(segment_reader.num_docs(), p);
@@ -739,8 +737,7 @@ mod bench {
#[bench] #[bench]
fn bench_iterate_segment_postings(b: &mut Bencher) { fn bench_iterate_segment_postings(b: &mut Bencher) {
let reader = INDEX.reader().unwrap(); let searcher = INDEX.searcher();
let searcher = reader.searcher();
let segment_reader = searcher.segment_reader(0); let segment_reader = searcher.segment_reader(0);
b.iter(|| { b.iter(|| {
let n: u32 = test::black_box(17); let n: u32 = test::black_box(17);

24
src/postings/postings_writer.rs
View File

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

5
src/postings/serializer.rs
View File

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

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

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

1
src/query/all_query.rs
View File

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

18
src/query/automaton_weight.rs
View File

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

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

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

1
src/query/bm25.rs
View File

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

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

@@ -9,8 +9,7 @@ use crate::Result;
use crate::Searcher; use crate::Searcher;
use std::collections::BTreeSet; use std::collections::BTreeSet;
/// The boolean query returns a set of documents /// The boolean query combines a set of queries
/// that matches the Boolean combination of constituent subqueries.
/// ///
/// The documents matched by the boolean query are /// The documents matched by the boolean query are
/// those which /// those which
@@ -20,113 +19,6 @@ use std::collections::BTreeSet;
/// `MustNot` occurence. /// `MustNot` occurence.
/// * match at least one of the subqueries that is not /// * match at least one of the subqueries that is not
/// a `MustNot` occurence. /// a `MustNot` occurence.
///
///
/// You can combine other query types and their `Occur`ances into one `BooleanQuery`
///
/// ```rust
///use tantivy::collector::Count;
///use tantivy::doc;
///use tantivy::query::{BooleanQuery, Occur, PhraseQuery, Query, TermQuery};
///use tantivy::schema::{IndexRecordOption, Schema, TEXT};
///use tantivy::Term;
///use tantivy::{Index, Result};
///
///fn main() -> Result<()> {
/// let mut schema_builder = Schema::builder();
/// let title = schema_builder.add_text_field("title", TEXT);
/// let body = schema_builder.add_text_field("body", TEXT);
/// let schema = schema_builder.build();
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer(3_000_000)?;
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of Muadib",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// body => "hidden",
/// ));
/// index_writer.add_document(doc!(
/// title => "A Dairy Cow",
/// body => "found",
/// ));
/// index_writer.add_document(doc!(
/// title => "The Diary of a Young Girl",
/// ));
/// index_writer.commit().unwrap();
/// }
///
/// let reader = index.reader()?;
/// let searcher = reader.searcher();
///
/// // Make TermQuery's for "girl" and "diary" in the title
/// let girl_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(title, "girl"),
/// IndexRecordOption::Basic,
/// ));
/// let diary_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(title, "diary"),
/// IndexRecordOption::Basic,
/// ));
/// // A TermQuery with "found" in the body
/// let body_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(body, "found"),
/// IndexRecordOption::Basic,
/// ));
/// // TermQuery "diary" must and "girl" must not be present
/// let queries_with_occurs1 = vec![
/// (Occur::Must, diary_term_query.box_clone()),
/// (Occur::MustNot, girl_term_query),
/// ];
/// // Make a BooleanQuery equivalent to
/// // title:+diary title:-girl
/// let diary_must_and_girl_mustnot = BooleanQuery::from(queries_with_occurs1);
/// let count1 = searcher.search(&diary_must_and_girl_mustnot, &Count)?;
/// assert_eq!(count1, 1);
///
/// // TermQuery for "cow" in the title
/// let cow_term_query: Box<dyn Query> = Box::new(TermQuery::new(
/// Term::from_field_text(title, "cow"),
/// IndexRecordOption::Basic,
/// ));
/// // "title:diary OR title:cow"
/// let title_diary_or_cow = BooleanQuery::from(vec![
/// (Occur::Should, diary_term_query.box_clone()),
/// (Occur::Should, cow_term_query),
/// ]);
/// let count2 = searcher.search(&title_diary_or_cow, &Count)?;
/// assert_eq!(count2, 4);
///
/// // Make a `PhraseQuery` from a vector of `Term`s
/// let phrase_query: Box<dyn Query> = Box::new(PhraseQuery::new(vec![
/// Term::from_field_text(title, "dairy"),
/// Term::from_field_text(title, "cow"),
/// ]));
/// // You can combine subqueries of different types into 1 BooleanQuery:
/// // `TermQuery` and `PhraseQuery`
/// // "title:diary OR "dairy cow"
/// let term_of_phrase_query = BooleanQuery::from(vec![
/// (Occur::Should, diary_term_query.box_clone()),
/// (Occur::Should, phrase_query.box_clone()),
/// ]);
/// let count3 = searcher.search(&term_of_phrase_query, &Count)?;
/// assert_eq!(count3, 4);
///
/// // You can nest one BooleanQuery inside another
/// // body:found AND ("title:diary OR "dairy cow")
/// let nested_query = BooleanQuery::from(vec![
/// (Occur::Must, body_term_query),
/// (Occur::Must, Box::new(term_of_phrase_query))
/// ]);
/// let count4 = searcher.search(&nested_query, &Count)?;
/// assert_eq!(count4, 1);
/// Ok(())
///}
/// ```
#[derive(Debug)] #[derive(Debug)]
pub struct BooleanQuery { pub struct BooleanQuery {
subqueries: Vec<(Occur, Box<dyn Query>)>, subqueries: Vec<(Occur, Box<dyn Query>)>,

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

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

1
src/query/exclude.rs
View File

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

30
src/query/fuzzy_query.rs
View File

@@ -1,4 +1,3 @@
use crate::error::TantivyError::InvalidArgument;
use crate::query::{AutomatonWeight, Query, Weight}; use crate::query::{AutomatonWeight, Query, Weight};
use crate::schema::Term; use crate::schema::Term;
use crate::Result; use crate::Result;
@@ -6,16 +5,11 @@ use crate::Searcher;
use levenshtein_automata::{LevenshteinAutomatonBuilder, DFA}; use levenshtein_automata::{LevenshteinAutomatonBuilder, DFA};
use once_cell::sync::Lazy; use once_cell::sync::Lazy;
use std::collections::HashMap; use std::collections::HashMap;
use std::ops::Range;
/// A range of Levenshtein distances that we will build DFAs for our terms
/// The computation is exponential, so best keep it to low single digits
const VALID_LEVENSHTEIN_DISTANCE_RANGE: Range<u8> = (0..3);
static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Lazy::new(|| { static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Lazy::new(|| {
let mut lev_builder_cache = HashMap::new(); let mut lev_builder_cache = HashMap::new();
// TODO make population lazy on a `(distance, val)` basis // TODO make population lazy on a `(distance, val)` basis
for distance in VALID_LEVENSHTEIN_DISTANCE_RANGE { for distance in 0..3 {
for &transposition in &[false, true] { for &transposition in &[false, true] {
let lev_automaton_builder = LevenshteinAutomatonBuilder::new(distance, transposition); let lev_automaton_builder = LevenshteinAutomatonBuilder::new(distance, transposition);
lev_builder_cache.insert((distance, transposition), lev_automaton_builder); lev_builder_cache.insert((distance, transposition), lev_automaton_builder);
@@ -28,10 +22,12 @@ static LEV_BUILDER: Lazy<HashMap<(u8, bool), LevenshteinAutomatonBuilder>> = Laz
/// containing a specific term that is within /// containing a specific term that is within
/// Levenshtein distance /// Levenshtein distance
/// ```rust /// ```rust
/// #[macro_use]
/// extern crate tantivy;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{Index, Result, Term};
/// use tantivy::collector::{Count, TopDocs}; /// use tantivy::collector::{Count, TopDocs};
/// use tantivy::query::FuzzyTermQuery; /// use tantivy::query::FuzzyTermQuery;
/// use tantivy::schema::{Schema, TEXT};
/// use tantivy::{doc, Index, Result, Term};
/// ///
/// # fn main() { example().unwrap(); } /// # fn main() { example().unwrap(); }
/// fn example() -> Result<()> { /// fn example() -> Result<()> {
@@ -104,18 +100,10 @@ impl FuzzyTermQuery {
} }
fn specialized_weight(&self) -> Result<AutomatonWeight<DFA>> { fn specialized_weight(&self) -> Result<AutomatonWeight<DFA>> {
// LEV_BUILDER is a HashMap, whose `get` method returns an Option let automaton = LEV_BUILDER.get(&(self.distance, false))
match LEV_BUILDER.get(&(self.distance, false)) { .unwrap() // TODO return an error
// Unwrap the option and build the Ok(AutomatonWeight) .build_dfa(self.term.text());
Some(automaton_builder) => { Ok(AutomatonWeight::new(self.term.field(), automaton))
let automaton = automaton_builder.build_dfa(self.term.text());
Ok(AutomatonWeight::new(self.term.field(), automaton))
}
None => Err(InvalidArgument(format!(
"Levenshtein distance of {} is not allowed. Choose a value in the {:?} range",
self.distance, VALID_LEVENSHTEIN_DISTANCE_RANGE
))),
}
} }
} }

2
src/query/intersection.rs
View File

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

2
src/query/intersection_two.rs
View File

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

3
src/query/mod.rs
View File

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

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

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

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

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

1
src/query/query_parser/logical_ast.rs
View File

@@ -18,6 +18,7 @@ pub enum LogicalLiteral {
All, All,
} }
#[derive(Clone)]
pub enum LogicalAST { pub enum LogicalAST {
Clause(Vec<(Occur, LogicalAST)>), Clause(Vec<(Occur, LogicalAST)>),
Leaf(Box<LogicalLiteral>), Leaf(Box<LogicalLiteral>),

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

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

284
src/query/query_parser/query_grammar.rs Normal file
View File

@@ -0,0 +1,284 @@
use super::query_grammar;
use super::user_input_ast::*;
use crate::query::occur::Occur;
use crate::query::query_parser::user_input_ast::UserInputBound;
use combine::char::*;
use combine::error::StreamError;
use combine::stream::StreamErrorFor;
use combine::*;
parser! {
fn field[I]()(I) -> String
where [I: Stream<Item = char>] {
(
letter(),
many(satisfy(|c: char| c.is_alphanumeric() || c == '_')),
).map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
}
parser! {
fn word[I]()(I) -> String
where [I: Stream<Item = char>] {
many1(satisfy(|c: char| c.is_alphanumeric() || c=='.'))
.and_then(|s: String| {
match s.as_str() {
"OR" => Err(StreamErrorFor::<I>::unexpected_static_message("OR")),
"AND" => Err(StreamErrorFor::<I>::unexpected_static_message("AND")),
"NOT" => Err(StreamErrorFor::<I>::unexpected_static_message("NOT")),
_ => Ok(s)
}
})
}
}
parser! {
fn literal[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>]
{
let term_val = || {
let phrase = (char('"'), many1(satisfy(|c| c != '"')), char('"')).map(|(_, s, _)| s);
phrase.or(word())
};
let term_val_with_field = negative_number().or(term_val());
let term_query =
(field(), char(':'), term_val_with_field).map(|(field_name, _, phrase)| UserInputLiteral {
field_name: Some(field_name),
phrase,
});
let term_default_field = term_val().map(|phrase| UserInputLiteral {
field_name: None,
phrase,
});
attempt(term_query)
.or(term_default_field)
.map(UserInputLeaf::from)
}
}
parser! {
fn negative_number[I]()(I) -> String
where [I: Stream<Item = char>]
{
(char('-'), many1(satisfy(char::is_numeric)))
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
}
parser! {
fn spaces1[I]()(I) -> ()
where [I: Stream<Item = char>] {
skip_many1(space())
}
}
parser! {
fn range[I]()(I) -> UserInputLeaf
where [I: Stream<Item = char>] {
let term_val = || {
word().or(negative_number()).or(char('*').map(|_| "*".to_string()))
};
let lower_bound = {
let excl = (char('{'), term_val()).map(|(_, w)| UserInputBound::Exclusive(w));
let incl = (char('['), term_val()).map(|(_, w)| UserInputBound::Inclusive(w));
attempt(excl).or(incl)
};
let upper_bound = {
let excl = (term_val(), char('}')).map(|(w, _)| UserInputBound::Exclusive(w));
let incl = (term_val(), char(']')).map(|(w, _)| UserInputBound::Inclusive(w));
attempt(excl).or(incl)
};
(
optional((field(), char(':')).map(|x| x.0)),
lower_bound,
spaces(),
string("TO"),
spaces(),
upper_bound,
).map(|(field, lower, _, _, _, upper)| UserInputLeaf::Range {
field,
lower,
upper
})
}
}
parser! {
fn leaf[I]()(I) -> UserInputAST
where [I: Stream<Item = char>] {
(char('-'), leaf()).map(|(_, expr)| expr.unary(Occur::MustNot) )
.or((char('+'), leaf()).map(|(_, expr)| expr.unary(Occur::Must) ))
.or((char('('), parse_to_ast(), char(')')).map(|(_, expr, _)| expr))
.or(char('*').map(|_| UserInputAST::from(UserInputLeaf::All) ))
.or(attempt(
(string("NOT"), spaces1(), leaf()).map(|(_, _, expr)| expr.unary(Occur::MustNot))
)
)
.or(attempt(
range().map(UserInputAST::from)
)
)
.or(literal().map(|leaf| UserInputAST::Leaf(Box::new(leaf))))
}
}
enum BinaryOperand {
Or,
And,
}
parser! {
fn binary_operand[I]()(I) -> BinaryOperand
where [I: Stream<Item = char>] {
(spaces1(),
(
string("AND").map(|_| BinaryOperand::And)
.or(string("OR").map(|_| BinaryOperand::Or))
),
spaces1()).map(|(_, op,_)| op)
}
}
enum Element {
SingleEl(UserInputAST),
NormalDisjunctive(Vec<Vec<UserInputAST>>),
}
impl Element {
pub fn into_dnf(self) -> Vec<Vec<UserInputAST>> {
match self {
Element::NormalDisjunctive(conjunctions) => conjunctions,
Element::SingleEl(el) => vec![vec![el]],
}
}
}
parser! {
pub fn parse_to_ast[I]()(I) -> UserInputAST
where [I: Stream<Item = char>]
{
(
attempt(
chainl1(
leaf().map(Element::SingleEl),
binary_operand().map(|op: BinaryOperand|
move |left: Element, right: Element| {
let mut dnf = left.into_dnf();
if let Element::SingleEl(el) = right {
match op {
BinaryOperand::And => {
if let Some(last) = dnf.last_mut() {
last.push(el);
}
}
BinaryOperand::Or => {
dnf.push(vec!(el));
}
}
} else {
unreachable!("Please report.")
}
Element::NormalDisjunctive(dnf)
}
)
)
.map(query_grammar::Element::into_dnf)
.map(|fnd| {
if fnd.len() == 1 {
UserInputAST::and(fnd.into_iter().next().unwrap()) //< safe
} else {
let conjunctions = fnd
.into_iter()
.map(UserInputAST::and)
.collect();
UserInputAST::or(conjunctions)
}
})
)
.or(
sep_by(leaf(), spaces())
.map(|subqueries: Vec<UserInputAST>| {
if subqueries.len() == 1 {
subqueries.into_iter().next().unwrap()
} else {
UserInputAST::Clause(subqueries.into_iter().collect())
}
})
)
)
}
}
#[cfg(test)]
mod test {
use super::*;
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_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_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_query_to_ast() {
test_parse_query_to_ast_helper("+(a b) +d", "(+((\"a\" \"b\")) +(\"d\"))");
test_parse_query_to_ast_helper("(+a +b) d", "((+(\"a\") +(\"b\")) \"d\")");
test_parse_query_to_ast_helper("(+a)", "+(\"a\")");
test_parse_query_to_ast_helper("(+a +b)", "(+(\"a\") +(\"b\"))");
test_parse_query_to_ast_helper("abc:toto", "abc:\"toto\"");
test_parse_query_to_ast_helper("abc:1.1", "abc:\"1.1\"");
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_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 + ");
}
}

119
src/query/query_parser/query_parser.rs
View File

@@ -1,5 +1,9 @@
use super::logical_ast::*; use super::logical_ast::*;
use super::query_grammar::parse_to_ast;
use super::user_input_ast::*;
use crate::core::Index; use crate::core::Index;
use crate::query::occur::compose_occur;
use crate::query::query_parser::logical_ast::LogicalAST;
use crate::query::AllQuery; use crate::query::AllQuery;
use crate::query::BooleanQuery; use crate::query::BooleanQuery;
use crate::query::EmptyQuery; use crate::query::EmptyQuery;
@@ -12,11 +16,11 @@ use crate::schema::IndexRecordOption;
use crate::schema::{Field, Schema}; use crate::schema::{Field, Schema};
use crate::schema::{FieldType, Term}; use crate::schema::{FieldType, Term};
use crate::tokenizer::TokenizerManager; use crate::tokenizer::TokenizerManager;
use combine::Parser;
use std::borrow::Cow; use std::borrow::Cow;
use std::num::{ParseFloatError, ParseIntError}; use std::num::{ParseFloatError, ParseIntError};
use std::ops::Bound; use std::ops::Bound;
use std::str::FromStr; use std::str::FromStr;
use tantivy_query_grammar::{UserInputAST, UserInputBound, UserInputLeaf};
/// Possible error that may happen when parsing a query. /// Possible error that may happen when parsing a query.
#[derive(Debug, PartialEq, Eq, Fail)] #[derive(Debug, PartialEq, Eq, Fail)]
@@ -218,8 +222,9 @@ impl QueryParser {
/// Parse the user query into an AST. /// Parse the user query into an AST.
fn parse_query_to_logical_ast(&self, query: &str) -> Result<LogicalAST, QueryParserError> { fn parse_query_to_logical_ast(&self, query: &str) -> Result<LogicalAST, QueryParserError> {
let user_input_ast = let (user_input_ast, _remaining) = parse_to_ast()
tantivy_query_grammar::parse_query(query).map_err(|_| QueryParserError::SyntaxError)?; .parse(query)
.map_err(|_| QueryParserError::SyntaxError)?;
self.compute_logical_ast(user_input_ast) self.compute_logical_ast(user_input_ast)
} }
@@ -364,7 +369,6 @@ impl QueryParser {
match *bound { match *bound {
UserInputBound::Inclusive(_) => Ok(Bound::Included(term)), UserInputBound::Inclusive(_) => Ok(Bound::Included(term)),
UserInputBound::Exclusive(_) => Ok(Bound::Excluded(term)), UserInputBound::Exclusive(_) => Ok(Bound::Excluded(term)),
UserInputBound::Unbounded => Ok(Bound::Unbounded),
} }
} }
@@ -394,7 +398,7 @@ impl QueryParser {
let mut logical_sub_queries: Vec<(Occur, LogicalAST)> = Vec::new(); let mut logical_sub_queries: Vec<(Occur, LogicalAST)> = Vec::new();
for sub_query in sub_queries { for sub_query in sub_queries {
let (occur, sub_ast) = self.compute_logical_ast_with_occur(sub_query)?; let (occur, sub_ast) = self.compute_logical_ast_with_occur(sub_query)?;
let new_occur = Occur::compose(default_occur, occur); let new_occur = compose_occur(default_occur, occur);
logical_sub_queries.push((new_occur, sub_ast)); logical_sub_queries.push((new_occur, sub_ast));
} }
Ok((Occur::Should, LogicalAST::Clause(logical_sub_queries))) Ok((Occur::Should, LogicalAST::Clause(logical_sub_queries)))
@@ -402,7 +406,7 @@ impl QueryParser {
UserInputAST::Unary(left_occur, subquery) => { UserInputAST::Unary(left_occur, subquery) => {
let (right_occur, logical_sub_queries) = let (right_occur, logical_sub_queries) =
self.compute_logical_ast_with_occur(*subquery)?; self.compute_logical_ast_with_occur(*subquery)?;
Ok((Occur::compose(left_occur, right_occur), logical_sub_queries)) Ok((compose_occur(left_occur, right_occur), logical_sub_queries))
} }
UserInputAST::Leaf(leaf) => { UserInputAST::Leaf(leaf) => {
let result_ast = self.compute_logical_ast_from_leaf(*leaf)?; let result_ast = self.compute_logical_ast_from_leaf(*leaf)?;
@@ -624,7 +628,7 @@ mod test {
pub fn test_parse_query_untokenized() { pub fn test_parse_query_untokenized() {
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"nottokenized:\"wordone wordtwo\"", "nottokenized:\"wordone wordtwo\"",
"Term(field=7,bytes=[119, 111, 114, 100, 111, 110, \ "Term([0, 0, 0, 7, 119, 111, 114, 100, 111, 110, \
101, 32, 119, 111, 114, 100, 116, 119, 111])", 101, 32, 119, 111, 114, 100, 116, 119, 111])",
false, false,
); );
@@ -668,46 +672,40 @@ mod test {
.is_ok()); .is_ok());
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"unsigned:2324", "unsigned:2324",
"Term(field=3,bytes=[0, 0, 0, 0, 0, 0, 9, 20])", "Term([0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 9, 20])",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"signed:-2324", "signed:-2324",
&format!( &format!("{:?}", Term::from_field_i64(Field(2u32), -2324)),
"{:?}",
Term::from_field_i64(Field::from_field_id(2u32), -2324)
),
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"float:2.5", "float:2.5",
&format!( &format!("{:?}", Term::from_field_f64(Field(10u32), 2.5)),
"{:?}",
Term::from_field_f64(Field::from_field_id(10u32), 2.5)
),
false, false,
); );
} }
#[test] #[test]
pub fn test_parse_query_to_ast_single_term() { pub fn test_parse_query_to_ast_disjunction() {
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:toto", "title:toto",
"Term(field=0,bytes=[116, 111, 116, 111])", "Term([0, 0, 0, 0, 116, 111, 116, 111])",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"+title:toto", "+title:toto",
"Term(field=0,bytes=[116, 111, 116, 111])", "Term([0, 0, 0, 0, 116, 111, 116, 111])",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"+title:toto -titi", "+title:toto -titi",
"(+Term(field=0,bytes=[116, 111, 116, 111]) \ "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-(Term(field=0,bytes=[116, 105, 116, 105]) \ -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
Term(field=1,bytes=[116, 105, 116, 105])))", Term([0, 0, 0, 1, 116, 105, 116, 105])))",
false, false,
); );
assert_eq!( assert_eq!(
@@ -716,67 +714,49 @@ mod test {
.unwrap(), .unwrap(),
QueryParserError::AllButQueryForbidden QueryParserError::AllButQueryForbidden
); );
}
#[test]
pub fn test_parse_query_to_ast_two_terms() {
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:a b", "title:a b",
"(Term(field=0,bytes=[97]) (Term(field=0,bytes=[98]) Term(field=1,bytes=[98])))", "(Term([0, 0, 0, 0, 97]) (Term([0, 0, 0, 0, 98]) \
Term([0, 0, 0, 1, 98])))",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:\"a b\"", "title:\"a b\"",
"\"[(0, Term(field=0,bytes=[97])), \ "\"[(0, Term([0, 0, 0, 0, 97])), \
(1, Term(field=0,bytes=[98]))]\"", (1, Term([0, 0, 0, 0, 98]))]\"",
false, false,
); );
}
#[test]
pub fn test_parse_query_to_ast_ranges() {
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:[a TO b]", "title:[a TO b]",
"(Included(Term(field=0,bytes=[97])) TO Included(Term(field=0,bytes=[98])))", "(Included(Term([0, 0, 0, 0, 97])) TO \
Included(Term([0, 0, 0, 0, 98])))",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"[a TO b]", "[a TO b]",
"((Included(Term(field=0,bytes=[97])) TO \ "((Included(Term([0, 0, 0, 0, 97])) TO \
Included(Term(field=0,bytes=[98]))) \ Included(Term([0, 0, 0, 0, 98]))) \
(Included(Term(field=1,bytes=[97])) TO \ (Included(Term([0, 0, 0, 1, 97])) TO \
Included(Term(field=1,bytes=[98]))))", Included(Term([0, 0, 0, 1, 98]))))",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:{titi TO toto}", "title:{titi TO toto}",
"(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO \ "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO \
Excluded(Term(field=0,bytes=[116, 111, 116, 111])))", Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:{* TO toto}", "title:{* TO toto}",
"(Unbounded TO Excluded(Term(field=0,bytes=[116, 111, 116, 111])))", "(Unbounded TO \
Excluded(Term([0, 0, 0, 0, 116, 111, 116, 111])))",
false, false,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:{titi TO *}", "title:{titi TO *}",
"(Excluded(Term(field=0,bytes=[116, 105, 116, 105])) TO Unbounded)", "(Excluded(Term([0, 0, 0, 0, 116, 105, 116, 105])) TO Unbounded)",
false, false,
); );
test_parse_query_to_logical_ast_helper(
"signed:{-5 TO 3}",
"(Excluded(Term(field=2,bytes=[127, 255, 255, 255, 255, 255, 255, 251])) TO \
Excluded(Term(field=2,bytes=[128, 0, 0, 0, 0, 0, 0, 3])))",
false,
);
test_parse_query_to_logical_ast_helper(
"float:{-1.5 TO 1.5}",
"(Excluded(Term(field=10,bytes=[64, 7, 255, 255, 255, 255, 255, 255])) TO \
Excluded(Term(field=10,bytes=[191, 248, 0, 0, 0, 0, 0, 0])))",
false,
);
test_parse_query_to_logical_ast_helper("*", "*", false); test_parse_query_to_logical_ast_helper("*", "*", false);
} }
@@ -878,19 +858,19 @@ mod test {
pub fn test_parse_query_to_ast_conjunction() { pub fn test_parse_query_to_ast_conjunction() {
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:toto", "title:toto",
"Term(field=0,bytes=[116, 111, 116, 111])", "Term([0, 0, 0, 0, 116, 111, 116, 111])",
true, true,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"+title:toto", "+title:toto",
"Term(field=0,bytes=[116, 111, 116, 111])", "Term([0, 0, 0, 0, 116, 111, 116, 111])",
true, true,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"+title:toto -titi", "+title:toto -titi",
"(+Term(field=0,bytes=[116, 111, 116, 111]) \ "(+Term([0, 0, 0, 0, 116, 111, 116, 111]) \
-(Term(field=0,bytes=[116, 105, 116, 105]) \ -(Term([0, 0, 0, 0, 116, 105, 116, 105]) \
Term(field=1,bytes=[116, 105, 116, 105])))", Term([0, 0, 0, 1, 116, 105, 116, 105])))",
true, true,
); );
assert_eq!( assert_eq!(
@@ -901,25 +881,16 @@ mod test {
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:a b", "title:a b",
"(+Term(field=0,bytes=[97]) \ "(+Term([0, 0, 0, 0, 97]) \
+(Term(field=0,bytes=[98]) \ +(Term([0, 0, 0, 0, 98]) \
Term(field=1,bytes=[98])))", Term([0, 0, 0, 1, 98])))",
true, true,
); );
test_parse_query_to_logical_ast_helper( test_parse_query_to_logical_ast_helper(
"title:\"a b\"", "title:\"a b\"",
"\"[(0, Term(field=0,bytes=[97])), \ "\"[(0, Term([0, 0, 0, 0, 97])), \
(1, Term(field=0,bytes=[98]))]\"", (1, Term([0, 0, 0, 0, 98]))]\"",
true, true,
); );
} }
#[test]
pub fn test_query_parser_hyphen() {
test_parse_query_to_logical_ast_helper(
"title:www-form-encoded",
"\"[(0, Term(field=0,bytes=[119, 119, 119])), (1, Term(field=0,bytes=[102, 111, 114, 109])), (2, Term(field=0,bytes=[101, 110, 99, 111, 100, 101, 100]))]\"",
false
);
}
} }

44
src/query/query_parser/stemmer.rs Normal file
View File

@@ -0,0 +1,44 @@
use std::sync::Arc;
use stemmer;
pub struct StemmerTokenStream<TailTokenStream>
where TailTokenStream: TokenStream {
tail: TailTokenStream,
stemmer: Arc<stemmer::Stemmer>,
}
impl<TailTokenStream> TokenStream for StemmerTokenStream<TailTokenStream>
where TailTokenStream: TokenStream {
fn token(&self) -> &Token {
self.tail.token()
}
fn token_mut(&mut self) -> &mut Token {
self.tail.token_mut()
}
fn advance(&mut self) -> bool {
if self.tail.advance() {
// self.tail.token_mut().term.make_ascii_lowercase();
let new_str = self.stemmer.stem_str(&self.token().term);
true
}
else {
false
}
}
}
impl<TailTokenStream> StemmerTokenStream<TailTokenStream>
where TailTokenStream: TokenStream {
fn wrap(stemmer: Arc<stemmer::Stemmer>, tail: TailTokenStream) -> StemmerTokenStream<TailTokenStream> {
StemmerTokenStream {
tail,
stemmer,
}
}
}

56
query-grammar/src/user_input_ast.rs → src/query/query_parser/user_input_ast.rs
View File

@@ -1,9 +1,8 @@
use std::fmt; use std::fmt;
use std::fmt::{Debug, Formatter}; use std::fmt::{Debug, Formatter};
use crate::Occur; use crate::query::Occur;
#[derive(PartialEq)]
pub enum UserInputLeaf { pub enum UserInputLeaf {
Literal(UserInputLiteral), Literal(UserInputLiteral),
All, All,
@@ -36,7 +35,6 @@ impl Debug for UserInputLeaf {
} }
} }
#[derive(PartialEq)]
pub struct UserInputLiteral { pub struct UserInputLiteral {
pub field_name: Option<String>, pub field_name: Option<String>,
pub phrase: String, pub phrase: String,
@@ -51,11 +49,9 @@ impl fmt::Debug for UserInputLiteral {
} }
} }
#[derive(PartialEq)]
pub enum UserInputBound { pub enum UserInputBound {
Inclusive(String), Inclusive(String),
Exclusive(String), Exclusive(String),
Unbounded,
} }
impl UserInputBound { impl UserInputBound {
@@ -63,7 +59,6 @@ impl UserInputBound {
match *self { match *self {
UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word), UserInputBound::Inclusive(ref word) => write!(formatter, "[\"{}\"", word),
UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word), UserInputBound::Exclusive(ref word) => write!(formatter, "{{\"{}\"", word),
UserInputBound::Unbounded => write!(formatter, "{{\"*\""),
} }
} }
@@ -71,7 +66,6 @@ impl UserInputBound {
match *self { match *self {
UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word), UserInputBound::Inclusive(ref word) => write!(formatter, "\"{}\"]", word),
UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word), UserInputBound::Exclusive(ref word) => write!(formatter, "\"{}\"}}", word),
UserInputBound::Unbounded => write!(formatter, "\"*\"}}"),
} }
} }
@@ -79,7 +73,6 @@ impl UserInputBound {
match *self { match *self {
UserInputBound::Inclusive(ref contents) => contents, UserInputBound::Inclusive(ref contents) => contents,
UserInputBound::Exclusive(ref contents) => contents, UserInputBound::Exclusive(ref contents) => contents,
UserInputBound::Unbounded => &"*",
} }
} }
} }
@@ -87,6 +80,9 @@ impl UserInputBound {
pub enum UserInputAST { pub enum UserInputAST {
Clause(Vec<UserInputAST>), Clause(Vec<UserInputAST>),
Unary(Occur, Box<UserInputAST>), Unary(Occur, Box<UserInputAST>),
// Not(Box<UserInputAST>),
// Should(Box<UserInputAST>),
// Must(Box<UserInputAST>),
Leaf(Box<UserInputLeaf>), Leaf(Box<UserInputLeaf>),
} }
@@ -96,7 +92,7 @@ impl UserInputAST {
} }
fn compose(occur: Occur, asts: Vec<UserInputAST>) -> UserInputAST { fn compose(occur: Occur, asts: Vec<UserInputAST>) -> UserInputAST {
assert_ne!(occur, Occur::MustNot); assert!(occur != Occur::MustNot);
assert!(!asts.is_empty()); assert!(!asts.is_empty());
if asts.len() == 1 { if asts.len() == 1 {
asts.into_iter().next().unwrap() //< safe asts.into_iter().next().unwrap() //< safe
@@ -109,10 +105,6 @@ impl UserInputAST {
} }
} }
pub fn empty_query() -> UserInputAST {
UserInputAST::Clause(Vec::default())
}
pub fn and(asts: Vec<UserInputAST>) -> UserInputAST { pub fn and(asts: Vec<UserInputAST>) -> UserInputAST {
UserInputAST::compose(Occur::Must, asts) UserInputAST::compose(Occur::Must, asts)
} }
@@ -122,6 +114,42 @@ impl UserInputAST {
} }
} }
/*
impl UserInputAST {
fn compose_occur(self, occur: Occur) -> UserInputAST {
match self {
UserInputAST::Not(other) => {
let new_occur = compose_occur(Occur::MustNot, occur);
other.simplify()
}
_ => {
self
}
}
}
pub fn simplify(self) -> UserInputAST {
match self {
UserInputAST::Clause(els) => {
if els.len() == 1 {
return els.into_iter().next().unwrap();
} else {
return self;
}
}
UserInputAST::Not(els) => {
if els.len() == 1 {
return els.into_iter().next().unwrap();
} else {
return self;
}
}
}
}
}
*/
impl From<UserInputLiteral> for UserInputLeaf { impl From<UserInputLiteral> for UserInputLeaf {
fn from(literal: UserInputLiteral) -> UserInputLeaf { fn from(literal: UserInputLiteral) -> UserInputLeaf {
UserInputLeaf::Literal(literal) UserInputLeaf::Literal(literal)
@@ -151,7 +179,7 @@ impl fmt::Debug for UserInputAST {
Ok(()) Ok(())
} }
UserInputAST::Unary(ref occur, ref subquery) => { UserInputAST::Unary(ref occur, ref subquery) => {
write!(formatter, "{}({:?})", occur, subquery) write!(formatter, "{}({:?})", occur.to_char(), subquery)
} }
UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery), UserInputAST::Leaf(ref subquery) => write!(formatter, "{:?}", subquery),
} }

58
src/query/range_query.rs
View File

@@ -38,10 +38,14 @@ fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
/// # Example /// # Example
/// ///
/// ```rust /// ```rust
/// # use tantivy::collector::Count; ///
/// # use tantivy::query::RangeQuery; /// # #[macro_use]
/// # extern crate tantivy;
/// # use tantivy::Index;
/// # use tantivy::schema::{Schema, INDEXED}; /// # use tantivy::schema::{Schema, INDEXED};
/// # use tantivy::{doc, Index, Result}; /// # use tantivy::collector::Count;
/// # use tantivy::Result;
/// # use tantivy::query::RangeQuery;
/// # /// #
/// # fn run() -> Result<()> { /// # fn run() -> Result<()> {
/// # let mut schema_builder = Schema::builder(); /// # let mut schema_builder = Schema::builder();
@@ -334,33 +338,39 @@ mod tests {
use crate::collector::Count; use crate::collector::Count;
use crate::schema::{Document, Field, Schema, INDEXED}; use crate::schema::{Document, Field, Schema, INDEXED};
use crate::Index; use crate::Index;
use crate::Result;
use std::collections::Bound; use std::collections::Bound;
#[test] #[test]
fn test_range_query_simple() { fn test_range_query_simple() {
let mut schema_builder = Schema::builder(); fn run() -> Result<()> {
let year_field = schema_builder.add_u64_field("year", INDEXED); let mut schema_builder = Schema::builder();
let schema = schema_builder.build(); let year_field = schema_builder.add_u64_field("year", INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema); let index = Index::create_in_ram(schema);
{ {
let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap(); let mut index_writer = index.writer_with_num_threads(1, 6_000_000).unwrap();
for year in 1950u64..2017u64 { for year in 1950u64..2017u64 {
let num_docs_within_year = 10 + (year - 1950) * (year - 1950); let num_docs_within_year = 10 + (year - 1950) * (year - 1950);
for _ in 0..num_docs_within_year { for _ in 0..num_docs_within_year {
index_writer.add_document(doc!(year_field => year)); index_writer.add_document(doc!(year_field => year));
}
} }
index_writer.commit().unwrap();
} }
index_writer.commit().unwrap(); let reader = index.reader().unwrap();
let searcher = reader.searcher();
let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64);
// ... or `1960..=1969` if inclusive range is enabled.
let count = searcher.search(&docs_in_the_sixties, &Count)?;
assert_eq!(count, 2285);
Ok(())
} }
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let docs_in_the_sixties = RangeQuery::new_u64(year_field, 1960u64..1970u64); run().unwrap();
// ... or `1960..=1969` if inclusive range is enabled.
let count = searcher.search(&docs_in_the_sixties, &Count).unwrap();
assert_eq!(count, 2285);
} }
#[test] #[test]
@@ -450,10 +460,7 @@ mod tests {
let count_multiples = let count_multiples =
|range_query: RangeQuery| searcher.search(&range_query, &Count).unwrap(); |range_query: RangeQuery| searcher.search(&range_query, &Count).unwrap();
assert_eq!( assert_eq!(count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)), 9);
count_multiples(RangeQuery::new_f64(float_field, 10.0..11.0)),
9
);
assert_eq!( assert_eq!(
count_multiples(RangeQuery::new_f64_bounds( count_multiples(RangeQuery::new_f64_bounds(
float_field, float_field,
@@ -479,4 +486,5 @@ mod tests {
91 91
); );
} }
} }

102
src/query/regex_query.rs
View File

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

1
src/query/reqopt_scorer.rs
View File

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

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

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

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

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

15
src/query/union.rs
View File

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

1
src/query/vec_docset.rs
View File

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

16
src/schema/document.rs
View File

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

4
src/schema/facet.rs
View File

@@ -120,7 +120,9 @@ impl Facet {
/// Extract path from the `Facet`. /// Extract path from the `Facet`.
pub fn to_path(&self) -> Vec<&str> { pub fn to_path(&self) -> Vec<&str> {
self.encoded_str().split(|c| c == FACET_SEP_CHAR).collect() self.encoded_str()
.split(|c| c == FACET_SEP_CHAR)
.collect()
} }
} }

23
src/schema/field.rs
View File

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

4
src/schema/field_entry.rs
View File

@@ -108,9 +108,7 @@ impl FieldEntry {
/// Returns true iff the field is a int (signed or unsigned) fast field /// Returns true iff the field is a int (signed or unsigned) fast field
pub fn is_int_fast(&self) -> bool { pub fn is_int_fast(&self) -> bool {
match self.field_type { match self.field_type {
FieldType::U64(ref options) FieldType::U64(ref options) | FieldType::I64(ref options) | FieldType::F64(ref options) => options.is_fast(),
| FieldType::I64(ref options)
| FieldType::F64(ref options) => options.is_fast(),
_ => false, _ => false,
} }
} }

114
src/schema/field_type.rs
View File

@@ -1,16 +1,16 @@
use base64::decode; use base64::decode;
use crate::schema::{IntOptions, TextOptions};
use crate::schema::Facet; use crate::schema::Facet;
use crate::schema::IndexRecordOption; use crate::schema::IndexRecordOption;
use crate::schema::TextFieldIndexing; use crate::schema::TextFieldIndexing;
use crate::schema::Value; use crate::schema::Value;
use crate::schema::{IntOptions, TextOptions};
use crate::tokenizer::PreTokenizedString;
use serde_json::Value as JsonValue; use serde_json::Value as JsonValue;
/// Possible error that may occur while parsing a field value /// Possible error that may occur while parsing a field value
/// At this point the JSON is known to be valid. /// At this point the JSON is known to be valid.
#[derive(Debug, PartialEq)] #[derive(Debug)]
pub enum ValueParsingError { pub enum ValueParsingError {
/// Encountered a numerical value that overflows or underflow its integer type. /// Encountered a numerical value that overflows or underflow its integer type.
OverflowError(String), OverflowError(String),
@@ -83,9 +83,9 @@ impl FieldType {
pub fn is_indexed(&self) -> bool { pub fn is_indexed(&self) -> bool {
match *self { match *self {
FieldType::Str(ref text_options) => text_options.get_indexing_options().is_some(), FieldType::Str(ref text_options) => text_options.get_indexing_options().is_some(),
FieldType::U64(ref int_options) FieldType::U64(ref int_options) | FieldType::I64(ref int_options) | FieldType::F64(ref int_options) => {
| FieldType::I64(ref int_options) int_options.is_indexed()
| FieldType::F64(ref int_options) => int_options.is_indexed(), }
FieldType::Date(ref date_options) => date_options.is_indexed(), FieldType::Date(ref date_options) => date_options.is_indexed(),
FieldType::HierarchicalFacet => true, FieldType::HierarchicalFacet => true,
FieldType::Bytes => false, FieldType::Bytes => false,
@@ -125,12 +125,9 @@ impl FieldType {
match *json { match *json {
JsonValue::String(ref field_text) => match *self { JsonValue::String(ref field_text) => match *self {
FieldType::Str(_) => Ok(Value::Str(field_text.clone())), FieldType::Str(_) => Ok(Value::Str(field_text.clone())),
FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => { FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) | FieldType::Date(_) => Err(
Err(ValueParsingError::TypeError(format!( ValueParsingError::TypeError(format!("Expected an integer, got {:?}", json)),
"Expected an integer, got {:?}", ),
json
)))
}
FieldType::HierarchicalFacet => Ok(Value::Facet(Facet::from(field_text))), FieldType::HierarchicalFacet => Ok(Value::Facet(Facet::from(field_text))),
FieldType::Bytes => decode(field_text).map(Value::Bytes).map_err(|_| { FieldType::Bytes => decode(field_text).map(Value::Bytes).map_err(|_| {
ValueParsingError::InvalidBase64(format!( ValueParsingError::InvalidBase64(format!(
@@ -155,7 +152,7 @@ impl FieldType {
let msg = format!("Expected a u64 int, got {:?}", json); let msg = format!("Expected a u64 int, got {:?}", json);
Err(ValueParsingError::OverflowError(msg)) Err(ValueParsingError::OverflowError(msg))
} }
} },
FieldType::F64(_) => { FieldType::F64(_) => {
if let Some(field_val_f64) = field_val_num.as_f64() { if let Some(field_val_f64) = field_val_num.as_f64() {
Ok(Value::F64(field_val_f64)) Ok(Value::F64(field_val_f64))
@@ -169,28 +166,6 @@ impl FieldType {
Err(ValueParsingError::TypeError(msg)) Err(ValueParsingError::TypeError(msg))
} }
}, },
JsonValue::Object(_) => match *self {
FieldType::Str(_) => {
if let Ok(tok_str_val) =
serde_json::from_value::<PreTokenizedString>(json.clone())
{
Ok(Value::PreTokStr(tok_str_val))
} else {
let msg = format!(
"Json value {:?} cannot be translated to PreTokenizedString.",
json
);
Err(ValueParsingError::TypeError(msg))
}
}
_ => {
let msg = format!(
"Json value not supported error {:?}. Expected {:?}",
json, self
);
Err(ValueParsingError::TypeError(msg))
}
},
_ => { _ => {
let msg = format!( let msg = format!(
"Json value not supported error {:?}. Expected {:?}", "Json value not supported error {:?}. Expected {:?}",
@@ -206,9 +181,7 @@ impl FieldType {
mod tests { mod tests {
use super::FieldType; use super::FieldType;
use crate::schema::field_type::ValueParsingError; use crate::schema::field_type::ValueParsingError;
use crate::schema::TextOptions;
use crate::schema::Value; use crate::schema::Value;
use crate::tokenizer::{PreTokenizedString, Token};
#[test] #[test]
fn test_bytes_value_from_json() { fn test_bytes_value_from_json() {
@@ -229,71 +202,4 @@ mod tests {
_ => panic!("Expected parse failure for invalid base64"), _ => panic!("Expected parse failure for invalid base64"),
} }
} }
#[test]
fn test_pre_tok_str_value_from_json() {
let pre_tokenized_string_json = r#"{
"text": "The Old Man",
"tokens": [
{
"offset_from": 0,
"offset_to": 3,
"position": 0,
"text": "The",
"position_length": 1
},
{
"offset_from": 4,
"offset_to": 7,
"position": 1,
"text": "Old",
"position_length": 1
},
{
"offset_from": 8,
"offset_to": 11,
"position": 2,
"text": "Man",
"position_length": 1
}
]
}"#;
let expected_value = Value::PreTokStr(PreTokenizedString {
text: String::from("The Old Man"),
tokens: vec![
Token {
offset_from: 0,
offset_to: 3,
position: 0,
text: String::from("The"),
position_length: 1,
},
Token {
offset_from: 4,
offset_to: 7,
position: 1,
text: String::from("Old"),
position_length: 1,
},
Token {
offset_from: 8,
offset_to: 11,
position: 2,
text: String::from("Man"),
position_length: 1,
},
],
});
let deserialized_value = FieldType::Str(TextOptions::default())
.value_from_json(&serde_json::from_str(pre_tokenized_string_json).unwrap())
.unwrap();
assert_eq!(deserialized_value, expected_value);
let serialized_value_json = serde_json::to_string_pretty(&expected_value).unwrap();
assert_eq!(serialized_value_json, pre_tokenized_string_json);
}
} }

16
src/schema/index_record_option.rs
View File

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

1
src/schema/mod.rs
View File

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

177
src/schema/schema.rs
View File

@@ -167,7 +167,7 @@ impl SchemaBuilder {
/// Adds a field entry to the schema in build. /// Adds a field entry to the schema in build.
fn add_field(&mut self, field_entry: FieldEntry) -> Field { fn add_field(&mut self, field_entry: FieldEntry) -> Field {
let field = Field::from_field_id(self.fields.len() as u32); let field = Field(self.fields.len() as u32);
let field_name = field_entry.name().to_string(); let field_name = field_entry.name().to_string();
self.fields.push(field_entry); self.fields.push(field_entry);
self.fields_map.insert(field_name, field); self.fields_map.insert(field_name, field);
@@ -223,7 +223,7 @@ pub struct Schema(Arc<InnerSchema>);
impl Schema { impl Schema {
/// Return the `FieldEntry` associated to a `Field`. /// Return the `FieldEntry` associated to a `Field`.
pub fn get_field_entry(&self, field: Field) -> &FieldEntry { pub fn get_field_entry(&self, field: Field) -> &FieldEntry {
&self.0.fields[field.field_id() as usize] &self.0.fields[field.0 as usize]
} }
/// Return the field name for a given `Field`. /// Return the field name for a given `Field`.
@@ -232,12 +232,8 @@ impl Schema {
} }
/// Return the list of all the `Field`s. /// Return the list of all the `Field`s.
pub fn fields(&self) -> impl Iterator<Item = (Field, &FieldEntry)> { pub fn fields(&self) -> &[FieldEntry] {
self.0 &self.0.fields
.fields
.iter()
.enumerate()
.map(|(field_id, field_entry)| (Field::from_field_id(field_id as u32), field_entry))
} }
/// Creates a new builder. /// Creates a new builder.
@@ -250,25 +246,6 @@ impl Schema {
self.0.fields_map.get(field_name).cloned() self.0.fields_map.get(field_name).cloned()
} }
/// Create a named document off the doc.
pub fn convert_named_doc(
&self,
named_doc: NamedFieldDocument,
) -> Result<Document, DocParsingError> {
let mut document = Document::new();
for (field_name, values) in named_doc.0 {
if let Some(field) = self.get_field(&field_name) {
for value in values {
let field_value = FieldValue::new(field, value);
document.add(field_value);
}
} else {
return Err(DocParsingError::NoSuchFieldInSchema(field_name));
}
}
Ok(document)
}
/// Create a named document off the doc. /// Create a named document off the doc.
pub fn to_named_doc(&self, doc: &Document) -> NamedFieldDocument { pub fn to_named_doc(&self, doc: &Document) -> NamedFieldDocument {
let mut field_map = BTreeMap::new(); let mut field_map = BTreeMap::new();
@@ -284,6 +261,24 @@ impl Schema {
NamedFieldDocument(field_map) NamedFieldDocument(field_map)
} }
/// Converts a named doc into a document.
pub fn from_named_doc(
&self,
named_doc: NamedFieldDocument,
) -> Result<Document, DocParsingError> {
let mut doc = Document::default();
for (field_name, field_values) in named_doc.0 {
if let Some(field) = self.get_field(&field_name) {
for field_value in field_values {
doc.add(FieldValue::new(field, field_value));
}
} else {
return Err(DocParsingError::NoSuchFieldInSchema(field_name.clone()));
}
}
Ok(doc)
}
/// Encode the schema in JSON. /// Encode the schema in JSON.
/// ///
/// Encoding a document cannot fail. /// Encoding a document cannot fail.
@@ -302,29 +297,30 @@ impl Schema {
}; };
DocParsingError::NotJSON(doc_json_sample) DocParsingError::NotJSON(doc_json_sample)
})?; })?;
let mut doc = Document::default(); let mut doc = Document::default();
for (field_name, json_value) in json_obj.iter() { for (field_name, json_value) in json_obj.iter() {
let field = self match self.get_field(field_name) {
.get_field(field_name) Some(field) => {
.ok_or_else(|| DocParsingError::NoSuchFieldInSchema(field_name.clone()))?; let field_entry = self.get_field_entry(field);
let field_entry = self.get_field_entry(field); let field_type = field_entry.field_type();
let field_type = field_entry.field_type(); match *json_value {
match *json_value { JsonValue::Array(ref json_items) => {
JsonValue::Array(ref json_items) => { for json_item in json_items {
for json_item in json_items { let value = field_type.value_from_json(json_item).map_err(|e| {
let value = field_type DocParsingError::ValueError(field_name.clone(), e)
.value_from_json(json_item) })?;
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?; doc.add(FieldValue::new(field, value));
doc.add(FieldValue::new(field, value)); }
}
_ => {
let value = field_type
.value_from_json(json_value)
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
doc.add(FieldValue::new(field, value));
}
} }
} }
_ => { None => return Err(DocParsingError::NoSuchFieldInSchema(field_name.clone())),
let value = field_type
.value_from_json(json_value)
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
doc.add(FieldValue::new(field, value));
}
} }
} }
Ok(doc) Ok(doc)
@@ -381,7 +377,7 @@ impl<'de> Deserialize<'de> for Schema {
/// Error that may happen when deserializing /// Error that may happen when deserializing
/// a document from JSON. /// a document from JSON.
#[derive(Debug, Fail, PartialEq)] #[derive(Debug, Fail)]
pub enum DocParsingError { pub enum DocParsingError {
/// The payload given is not valid JSON. /// The payload given is not valid JSON.
#[fail(display = "The provided string is not valid JSON")] #[fail(display = "The provided string is not valid JSON")]
@@ -390,10 +386,7 @@ pub enum DocParsingError {
#[fail(display = "The field '{:?}' could not be parsed: {:?}", _0, _1)] #[fail(display = "The field '{:?}' could not be parsed: {:?}", _0, _1)]
ValueError(String, ValueParsingError), ValueError(String, ValueParsingError),
/// The json-document contains a field that is not declared in the schema. /// The json-document contains a field that is not declared in the schema.
#[fail( #[fail(display = "The json-document contains an unknown field: {:?}", _0)]
display = "The document contains a field that is not declared in the schema: {:?}",
_0
)]
NoSuchFieldInSchema(String), NoSuchFieldInSchema(String),
} }
@@ -405,7 +398,6 @@ mod tests {
use crate::schema::*; use crate::schema::*;
use matches::{assert_matches, matches}; use matches::{assert_matches, matches};
use serde_json; use serde_json;
use std::collections::BTreeMap;
#[test] #[test]
pub fn is_indexed_test() { pub fn is_indexed_test() {
@@ -489,32 +481,13 @@ mod tests {
let schema: Schema = serde_json::from_str(expected).unwrap(); let schema: Schema = serde_json::from_str(expected).unwrap();
let mut fields = schema.fields(); let mut fields = schema.fields().iter();
{
let (field, field_entry) = fields.next().unwrap(); assert_eq!("title", fields.next().unwrap().name());
assert_eq!("title", field_entry.name()); assert_eq!("author", fields.next().unwrap().name());
assert_eq!(0, field.field_id()); assert_eq!("count", fields.next().unwrap().name());
} assert_eq!("popularity", fields.next().unwrap().name());
{ assert_eq!("score", fields.next().unwrap().name());
let (field, field_entry) = fields.next().unwrap();
assert_eq!("author", field_entry.name());
assert_eq!(1, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("count", field_entry.name());
assert_eq!(2, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("popularity", field_entry.name());
assert_eq!(3, field.field_id());
}
{
let (field, field_entry) = fields.next().unwrap();
assert_eq!("score", field_entry.name());
assert_eq!(4, field.field_id());
}
assert!(fields.next().is_none()); assert!(fields.next().is_none());
} }
@@ -539,54 +512,6 @@ mod tests {
assert_eq!(doc, doc_serdeser); assert_eq!(doc, doc_serdeser);
} }
#[test]
pub fn test_document_from_nameddoc() {
let mut schema_builder = Schema::builder();
let title = schema_builder.add_text_field("title", TEXT);
let val = schema_builder.add_i64_field("val", INDEXED);
let schema = schema_builder.build();
let mut named_doc_map = BTreeMap::default();
named_doc_map.insert(
"title".to_string(),
vec![Value::from("title1"), Value::from("title2")],
);
named_doc_map.insert(
"val".to_string(),
vec![Value::from(14u64), Value::from(-1i64)],
);
let doc = schema
.convert_named_doc(NamedFieldDocument(named_doc_map))
.unwrap();
assert_eq!(
doc.get_all(title),
vec![
&Value::from("title1".to_string()),
&Value::from("title2".to_string())
]
);
assert_eq!(
doc.get_all(val),
vec![&Value::from(14u64), &Value::from(-1i64)]
);
}
#[test]
pub fn test_document_from_nameddoc_error() {
let schema = Schema::builder().build();
let mut named_doc_map = BTreeMap::default();
named_doc_map.insert(
"title".to_string(),
vec![Value::from("title1"), Value::from("title2")],
);
let err = schema
.convert_named_doc(NamedFieldDocument(named_doc_map))
.unwrap_err();
assert_eq!(
err,
DocParsingError::NoSuchFieldInSchema("title".to_string())
);
}
#[test] #[test]
pub fn test_parse_document() { pub fn test_parse_document() {
let mut schema_builder = Schema::builder(); let mut schema_builder = Schema::builder();

31
src/schema/term.rs
View File

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

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