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

Compare commits

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

2 Commits
0.19.1 ... column-rea

Author SHA1 Message Date
Paul Masurel
c69661f0f0 Removing iterators. 2022-09-21 23:26:01 +09:00
Paul Masurel
85ebb3c420 Introducing ColumnReader. 
Introducing a ColumnReader trait and .reader() to Column,
hence removing the dreaded Mutex in the `MultiValueStartIndex`
thingy.
 2022-09-21 12:47:44 +09:00
187 changed files with 2253 additions and 9757 deletions
Expand all files Collapse all files

1
.gitattributes vendored Normal file
View File

@@ -0,0 +1 @@
cpp/* linguist-vendored

2
.github/workflows/test.yml vendored
View File

@@ -48,7 +48,7 @@ jobs:
strategy:
matrix:
features: [
{ label: "all", flags: "mmap,stopwords,brotli-compression,lz4-compression,snappy-compression,zstd-compression,failpoints" },
{ label: "all", flags: "mmap,brotli-compression,lz4-compression,snappy-compression,zstd-compression,failpoints" },
{ label: "quickwit", flags: "mmap,quickwit,failpoints" }
]

1
.gitignore vendored
View File

@@ -9,6 +9,7 @@ target/release
Cargo.lock
benchmark
.DS_Store
cpp/simdcomp/bitpackingbenchmark
*.bk
.idea
trace.dat

36
CHANGELOG.md
View File

@@ -1,38 +1,10 @@
Tantivy 0.19
================================
#### Bugfixes
- Fix missing fieldnorms for u64, i64, f64, bool, bytes and date [#1620](https://github.com/quickwit-oss/tantivy/pull/1620) (@PSeitz)
- Fix interpolation overflow in linear interpolation fastfield codec [#1480](https://github.com/quickwit-oss/tantivy/pull/1480 (@PSeitz @fulmicoton)
#### Features/Improvements
- Add support for `IN` in queryparser , e.g. `field: IN [val1 val2 val3]` [#1683](https://github.com/quickwit-oss/tantivy/pull/1683) (@trinity-1686a)
- Skip score calculation, when no scoring is required [#1646](https://github.com/quickwit-oss/tantivy/pull/1646) (@PSeitz)
- Limit fast fields to u32 (`get_val(u32)`) [#1644](https://github.com/quickwit-oss/tantivy/pull/1644) (@PSeitz)
- Updated [Date Field Type](https://github.com/quickwit-oss/tantivy/pull/1396)
The `DateTime` type has been updated to hold timestamps with microseconds precision.
`DateOptions` and `DatePrecision` have been added to configure Date fields. The precision is used to hint on fast values compression. Otherwise, seconds precision is used everywhere else (i.e terms, indexing). (@evanxg852000)
- Add IP address field type [#1553](https://github.com/quickwit-oss/tantivy/pull/1553) (@PSeitz)
- Add boolean field type [#1382](https://github.com/quickwit-oss/tantivy/pull/1382) (@boraarslan)
- Remove Searcher pool and make `Searcher` cloneable. (@PSeitz)
- Validate settings on create [#1570](https://github.com/quickwit-oss/tantivy/pull/1570 (@PSeitz)
- Detect and apply gcd on fastfield codecs [#1418](https://github.com/quickwit-oss/tantivy/pull/1418) (@PSeitz)
- Doc store
- use separate thread to compress block store [#1389](https://github.com/quickwit-oss/tantivy/pull/1389) [#1510](https://github.com/quickwit-oss/tantivy/pull/1510 (@PSeitz @fulmicoton)
- Expose doc store cache size [#1403](https://github.com/quickwit-oss/tantivy/pull/1403) (@PSeitz)
- Enable compression levels for doc store [#1378](https://github.com/quickwit-oss/tantivy/pull/1378) (@PSeitz)
- Make block size configurable [#1374](https://github.com/quickwit-oss/tantivy/pull/1374) (@kryesh)
- Make `tantivy::TantivyError` cloneable [#1402](https://github.com/quickwit-oss/tantivy/pull/1402) (@PSeitz)
- Add support for phrase slop in query language [#1393](https://github.com/quickwit-oss/tantivy/pull/1393) (@saroh)
- Aggregation
- Add aggregation support for date type [#1693](https://github.com/quickwit-oss/tantivy/pull/1693)(@PSeitz)
- Add support for keyed parameter in range and histgram aggregations [#1424](https://github.com/quickwit-oss/tantivy/pull/1424) (@k-yomo)
- Add aggregation bucket limit [#1363](https://github.com/quickwit-oss/tantivy/pull/1363) (@PSeitz)
- Faster indexing
- [#1610](https://github.com/quickwit-oss/tantivy/pull/1610) (@PSeitz)
- [#1594](https://github.com/quickwit-oss/tantivy/pull/1594) (@PSeitz)
- [#1582](https://github.com/quickwit-oss/tantivy/pull/1582) (@PSeitz)
- [#1611](https://github.com/quickwit-oss/tantivy/pull/1611) (@PSeitz)
- Added a pre-configured stop word filter for various language [#1666](https://github.com/quickwit-oss/tantivy/pull/1666) (@adamreichold)
`DateOptions` and `DatePrecision` have been added to configure Date fields. The precision is used to hint on fast values compression. Otherwise, seconds precision is used everywhere else (i.e terms, indexing).
- Remove Searcher pool and make `Searcher` cloneable.
Tantivy 0.18
================================
@@ -50,10 +22,6 @@ Tantivy 0.18
- Add terms aggregation (@PSeitz)
- Add support for zstd compression (@kryesh)
Tantivy 0.18.1
================================
- Hotfix: positions computation. #1629 (@fmassot, @fulmicoton, @PSeitz)
Tantivy 0.17
================================

36
Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy"
version = "0.19.1"
version = "0.18.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
@@ -11,21 +11,19 @@ repository = "https://github.com/quickwit-oss/tantivy"
readme = "README.md"
keywords = ["search", "information", "retrieval"]
edition = "2021"
rust-version = "1.62"
[dependencies]
oneshot = "0.1.5"
oneshot = "0.1.3"
base64 = "0.13.0"
byteorder = "1.4.3"
crc32fast = "1.3.2"
once_cell = "1.10.0"
regex = { version = "1.5.5", default-features = false, features = ["std", "unicode"] }
aho-corasick = "0.7"
tantivy-fst = "0.4.0"
tantivy-fst = "0.3.0"
memmap2 = { version = "0.5.3", optional = true }
lz4_flex = { version = "0.9.2", default-features = false, features = ["checked-decode"], optional = true }
brotli = { version = "3.3.4", optional = true }
zstd = { version = "0.12", optional = true, default-features = false }
zstd = { version = "0.11", optional = true }
snap = { version = "1.0.5", optional = true }
tempfile = { version = "3.3.0", optional = true }
log = "0.4.16"
@@ -36,12 +34,17 @@ fs2 = { version = "0.4.3", optional = true }
levenshtein_automata = "0.2.1"
uuid = { version = "1.0.0", features = ["v4", "serde"] }
crossbeam-channel = "0.5.4"
tantivy-query-grammar = { version="0.18.0", path="./query-grammar" }
tantivy-bitpacker = { version="0.2", path="./bitpacker" }
common = { version = "0.3", path = "./common/", package = "tantivy-common" }
fastfield_codecs = { version="0.2", path="./fastfield_codecs", default-features = false }
ownedbytes = { version="0.3", path="./ownedbytes" }
stable_deref_trait = "1.2.0"
rust-stemmers = "1.2.0"
downcast-rs = "1.2.0"
bitpacking = { version = "0.8.4", default-features = false, features = ["bitpacker4x"] }
census = "0.4.0"
rustc-hash = "1.1.0"
fnv = "1.0.7"
thiserror = "1.0.30"
htmlescape = "0.3.1"
fail = "0.5.0"
@@ -53,16 +56,10 @@ lru = "0.7.5"
fastdivide = "0.4.0"
itertools = "0.10.3"
measure_time = "0.8.2"
ciborium = { version = "0.2", optional = true}
serde_cbor = { version = "0.11.2", optional = true }
async-trait = "0.1.53"
arc-swap = "1.5.0"
tantivy-query-grammar = { version= "0.19.0", path="./query-grammar" }
tantivy-bitpacker = { version= "0.3", path="./bitpacker" }
common = { version= "0.4", path = "./common/", package = "tantivy-common" }
fastfield_codecs = { version= "0.3.1", path="./fastfield_codecs", default-features = false }
ownedbytes = { version= "0.4", path="./ownedbytes" }
[target.'cfg(windows)'.dependencies]
winapi = "0.3.9"
@@ -72,10 +69,10 @@ maplit = "1.0.2"
matches = "0.1.9"
pretty_assertions = "1.2.1"
proptest = "1.0.0"
criterion = "0.4"
criterion = "0.3.5"
test-log = "0.2.10"
env_logger = "0.10.0"
pprof = { version = "0.11.0", features = ["flamegraph", "criterion"] }
env_logger = "0.9.0"
pprof = { version = "0.10.0", features = ["flamegraph", "criterion"] }
futures = "0.3.21"
[dev-dependencies.fail]
@@ -92,9 +89,8 @@ debug-assertions = true
overflow-checks = true
[features]
default = ["mmap", "stopwords", "lz4-compression"]
default = ["mmap", "lz4-compression" ]
mmap = ["fs2", "tempfile", "memmap2"]
stopwords = []
brotli-compression = ["brotli"]
lz4-compression = ["lz4_flex"]
@@ -104,7 +100,7 @@ zstd-compression = ["zstd"]
failpoints = ["fail/failpoints"]
unstable = [] # useful for benches.
quickwit = ["ciborium"]
quickwit = ["serde_cbor"]
[workspace]
members = ["query-grammar", "bitpacker", "common", "fastfield_codecs", "ownedbytes"]

8
README.md
View File

@@ -58,7 +58,7 @@ Distributed search is out of the scope of Tantivy, but if you are looking for th
# Getting started
Tantivy works on stable Rust and supports Linux, macOS, and Windows.
Tantivy works on stable Rust (>= 1.27) and supports Linux, macOS, and Windows.
- [Tantivy's simple search example](https://tantivy-search.github.io/examples/basic_search.html)
- [tantivy-cli and its tutorial](https://github.com/quickwit-oss/tantivy-cli) - `tantivy-cli` is an actual command-line interface that makes it easy for you to create a search engine,
@@ -81,13 +81,9 @@ There are many ways to support this project.
We use the GitHub Pull Request workflow: reference a GitHub ticket and/or include a comprehensive commit message when opening a PR.
## Minimum supported Rust version
Tantivy currently requires at least Rust 1.62 or later to compile.
## Clone and build locally
Tantivy compiles on stable Rust.
Tantivy compiles on stable Rust but requires `Rust >= 1.27`.
To check out and run tests, you can simply run:
```bash

4
bitpacker/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-bitpacker"
version = "0.3.0"
version = "0.2.0"
edition = "2021"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
@@ -8,8 +8,6 @@ categories = []
description = """Tantivy-sub crate: bitpacking"""
repository = "https://github.com/quickwit-oss/tantivy"
keywords = []
documentation = "https://docs.rs/tantivy-bitpacker/latest/tantivy_bitpacker"
homepage = "https://github.com/quickwit-oss/tantivy"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

8
bitpacker/src/bitpacker.rs
View File

@@ -87,15 +87,15 @@ impl BitUnpacker {
}
#[inline]
pub fn get(&self, idx: u32, data: &[u8]) -> u64 {
pub fn get(&self, idx: u64, data: &[u8]) -> u64 {
if self.num_bits == 0 {
return 0u64;
}
let addr_in_bits = idx * self.num_bits as u32;
let addr_in_bits = idx * self.num_bits;
let addr = addr_in_bits >> 3;
let bit_shift = addr_in_bits & 7;
debug_assert!(
addr + 8 <= data.len() as u32,
addr + 8 <= data.len() as u64,
"The fast field field should have been padded with 7 bytes."
);
let bytes: [u8; 8] = (&data[(addr as usize)..(addr as usize) + 8])
@@ -130,7 +130,7 @@ mod test {
fn test_bitpacker_util(len: usize, num_bits: u8) {
let (bitunpacker, vals, data) = create_fastfield_bitpacker(len, num_bits);
for (i, val) in vals.iter().enumerate() {
assert_eq!(bitunpacker.get(i as u32, &data), *val);
assert_eq!(bitunpacker.get(i as u64, &data), *val);
}
}

2
bitpacker/src/blocked_bitpacker.rs
View File

@@ -130,7 +130,7 @@ impl BlockedBitpacker {
let pos_in_block = idx % BLOCK_SIZE as usize;
if let Some(metadata) = self.offset_and_bits.get(metadata_pos) {
let unpacked = BitUnpacker::new(metadata.num_bits()).get(
pos_in_block as u32,
pos_in_block as u64,
&self.compressed_blocks[metadata.offset() as usize..],
);
unpacked + metadata.base_value()

8
common/Cargo.toml
View File

@@ -1,20 +1,16 @@
[package]
name = "tantivy-common"
version = "0.4.0"
version = "0.3.0"
authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
license = "MIT"
edition = "2021"
description = "common traits and utility functions used by multiple tantivy subcrates"
documentation = "https://docs.rs/tantivy_common/"
homepage = "https://github.com/quickwit-oss/tantivy"
repository = "https://github.com/quickwit-oss/tantivy"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
byteorder = "1.4.3"
ownedbytes = { version= "0.4", path="../ownedbytes" }
ownedbytes = { version="0.3", path="../ownedbytes" }
[dev-dependencies]
proptest = "1.0.0"

14
common/src/bitset.rs
View File

@@ -259,7 +259,11 @@ impl BitSet {
// we do not check saturated els.
let higher = el / 64u32;
let lower = el % 64u32;
self.len += u64::from(self.tinysets[higher as usize].insert_mut(lower));
self.len += if self.tinysets[higher as usize].insert_mut(lower) {
1
} else {
0
};
}
/// Inserts an element in the `BitSet`
@@ -268,7 +272,11 @@ impl BitSet {
// we do not check saturated els.
let higher = el / 64u32;
let lower = el % 64u32;
self.len -= u64::from(self.tinysets[higher as usize].remove_mut(lower));
self.len -= if self.tinysets[higher as usize].remove_mut(lower) {
1
} else {
0
};
}
/// Returns true iff the elements is in the `BitSet`.
@@ -277,7 +285,7 @@ impl BitSet {
self.tinyset(el / 64u32).contains(el % 64)
}
/// Returns the first non-empty `TinySet` associated with a bucket lower
/// Returns the first non-empty `TinySet` associated to a bucket lower
/// or greater than bucket.
///
/// Reminder: the tiny set with the bucket `bucket`, represents the

30
common/src/serialize.rs
View File

@@ -94,20 +94,6 @@ impl FixedSize for u32 {
const SIZE_IN_BYTES: usize = 4;
}
impl BinarySerializable for u16 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_u16::<Endianness>(*self)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<u16> {
reader.read_u16::<Endianness>()
}
}
impl FixedSize for u16 {
const SIZE_IN_BYTES: usize = 2;
}
impl BinarySerializable for u64 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_u64::<Endianness>(*self)
@@ -121,19 +107,6 @@ impl FixedSize for u64 {
const SIZE_IN_BYTES: usize = 8;
}
impl BinarySerializable for u128 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_u128::<Endianness>(*self)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
reader.read_u128::<Endianness>()
}
}
impl FixedSize for u128 {
const SIZE_IN_BYTES: usize = 16;
}
impl BinarySerializable for f32 {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_f32::<Endianness>(*self)
@@ -188,7 +161,8 @@ impl FixedSize for u8 {
impl BinarySerializable for bool {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
writer.write_u8(u8::from(*self))
let val = if *self { 1 } else { 0 };
writer.write_u8(val)
}
fn deserialize<R: Read>(reader: &mut R) -> io::Result<bool> {
let val = reader.read_u8()?;

2
common/src/vint.rs
View File

@@ -157,7 +157,7 @@ fn vint_len(data: &[u8]) -> usize {
/// If the buffer does not start by a valid
/// vint payload
pub fn read_u32_vint(data: &mut &[u8]) -> u32 {
let (result, vlen) = read_u32_vint_no_advance(data);
let (result, vlen) = read_u32_vint_no_advance(*data);
*data = &data[vlen..];
result
}

2
doc/src/basis.md
View File

@@ -50,7 +50,7 @@ to get tantivy to fit your use case:
*Example 1* You could for instance use hadoop to build a very large search index in a timely manner, copy all of the resulting segment files in the same directory and edit the `meta.json` to get a functional index.[^2]
*Example 2* You could also disable your merge policy and enforce daily segments. Removing data after one week can then be done very efficiently by just editing the `meta.json` and deleting the files associated with segment `D-7`.
*Example 2* You could also disable your merge policy and enforce daily segments. Removing data after one week can then be done very efficiently by just editing the `meta.json` and deleting the files associated to segment `D-7`.
## Merging

2
examples/aggregation.rs
View File

@@ -118,7 +118,7 @@ fn main() -> tantivy::Result<()> {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults = searcher.search(&term_query, &collector).unwrap();

2
examples/custom_collector.rs
View File

@@ -105,7 +105,7 @@ impl SegmentCollector for StatsSegmentCollector {
type Fruit = Option<Stats>;
fn collect(&mut self, doc: u32, _score: Score) {
let value = self.fast_field_reader.get_val(doc) as f64;
let value = self.fast_field_reader.get_val(doc as u64) as f64;
self.stats.count += 1;
self.stats.sum += value;
self.stats.squared_sum += value * value;

2
examples/deleting_updating_documents.rs
View File

@@ -113,7 +113,7 @@ fn main() -> tantivy::Result<()> {
// on its id.
//
// Note that `tantivy` does nothing to enforce the idea that
// there is only one document associated with this id.
// there is only one document associated to this id.
//
// Also you might have noticed that we apply the delete before
// having committed. This does not matter really...

4
examples/iterating_docs_and_positions.rs
View File

@@ -44,7 +44,7 @@ fn main() -> tantivy::Result<()> {
// A segment contains different data structure.
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated with each terms and their positions
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title)?;
// A `Term` is a text token associated with a field.
@@ -105,7 +105,7 @@ fn main() -> tantivy::Result<()> {
// A segment contains different data structure.
// Inverted index stands for the combination of
// - the term dictionary
// - the inverted lists associated with each terms and their positions
// - the inverted lists associated to each terms and their positions
let inverted_index = segment_reader.inverted_index(title)?;
// This segment posting object is like a cursor over the documents matching the term.

2
examples/warmer.rs
View File

@@ -51,7 +51,7 @@ impl Warmer for DynamicPriceColumn {
let product_id_reader = segment.fast_fields().u64(self.field)?;
let product_ids: Vec<ProductId> = segment
.doc_ids_alive()
.map(|doc| product_id_reader.get_val(doc))
.map(|doc| product_id_reader.get_val(doc as u64))
.collect();
let mut prices_it = self.price_fetcher.fetch_prices(&product_ids).into_iter();
let mut price_vals: Vec<Price> = Vec::new();

11
fastfield_codecs/Cargo.toml
View File

@@ -1,20 +1,17 @@
[package]
name = "fastfield_codecs"
version = "0.3.1"
version = "0.2.0"
authors = ["Pascal Seitz <pascal@quickwit.io>"]
license = "MIT"
edition = "2021"
description = "Fast field codecs used by tantivy"
documentation = "https://docs.rs/fastfield_codecs/"
homepage = "https://github.com/quickwit-oss/tantivy"
repository = "https://github.com/quickwit-oss/tantivy"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
common = { version = "0.4", path = "../common/", package = "tantivy-common" }
tantivy-bitpacker = { version= "0.3", path = "../bitpacker/" }
ownedbytes = { version = "0.4.0", path = "../ownedbytes" }
common = { version = "0.3", path = "../common/", package = "tantivy-common" }
tantivy-bitpacker = { version="0.2", path = "../bitpacker/" }
ownedbytes = { version = "0.3.0", path = "../ownedbytes" }
prettytable-rs = {version="0.9.0", optional= true}
rand = {version="0.8.3", optional= true}
fastdivide = "0.4"

47
fastfield_codecs/benches/bench.rs
View File

@@ -65,7 +65,7 @@ mod tests {
b.iter(|| {
let mut a = 0u64;
for _ in 0..n {
a = column.get_val(a as u32);
a = column.get_val(a as u64);
}
a
});
@@ -100,10 +100,9 @@ mod tests {
fn get_u128_column_from_data(data: &[u128]) -> Arc<dyn Column<u128>> {
let mut out = vec![];
let iter_gen = || data.iter().cloned();
serialize_u128(iter_gen, data.len() as u32, &mut out).unwrap();
serialize_u128(VecColumn::from(&data), &mut out).unwrap();
let out = OwnedBytes::new(out);
open_u128::<u128>(out).unwrap()
open_u128(out).unwrap()
}
#[bench]
@@ -111,15 +110,7 @@ mod tests {
let (major_item, _minor_item, data) = get_data_50percent_item();
let column = get_u128_column_from_data(&data);
b.iter(|| {
let mut positions = Vec::new();
column.get_docids_for_value_range(
major_item..=major_item,
0..data.len() as u32,
&mut positions,
);
positions
});
b.iter(|| column.get_between_vals(major_item..=major_item));
}
#[bench]
@@ -127,15 +118,7 @@ mod tests {
let (_major_item, minor_item, data) = get_data_50percent_item();
let column = get_u128_column_from_data(&data);
b.iter(|| {
let mut positions = Vec::new();
column.get_docids_for_value_range(
minor_item..=minor_item,
0..data.len() as u32,
&mut positions,
);
positions
});
b.iter(|| column.get_between_vals(minor_item..=minor_item));
}
#[bench]
@@ -143,11 +126,7 @@ mod tests {
let (_major_item, _minor_item, data) = get_data_50percent_item();
let column = get_u128_column_from_data(&data);
b.iter(|| {
let mut positions = Vec::new();
column.get_docids_for_value_range(0..=u128::MAX, 0..data.len() as u32, &mut positions);
positions
});
b.iter(|| column.get_between_vals(0..=u128::MAX));
}
#[bench]
@@ -157,7 +136,7 @@ mod tests {
b.iter(|| {
let mut a = 0u128;
for i in 0u64..column.num_vals() as u64 {
a += column.get_val(i as u32);
a += column.get_val(i);
}
a
});
@@ -171,7 +150,7 @@ mod tests {
let n = column.num_vals();
let mut a = 0u128;
for i in (0..n / 5).map(|val| val * 5) {
a += column.get_val(i);
a += column.get_val(i as u64);
}
a
});
@@ -196,9 +175,9 @@ mod tests {
let n = permutation.len();
let column: Arc<dyn Column<u64>> = serialize_and_load(&permutation);
b.iter(|| {
let mut a = 0;
let mut a = 0u64;
for i in (0..n / 7).map(|val| val * 7) {
a += column.get_val(i as u32);
a += column.get_val(i as u64);
}
a
});
@@ -211,7 +190,7 @@ mod tests {
let column: Arc<dyn Column<u64>> = serialize_and_load(&permutation);
b.iter(|| {
let mut a = 0u64;
for i in 0u32..n as u32 {
for i in 0u64..n as u64 {
a += column.get_val(i);
}
a
@@ -225,8 +204,8 @@ mod tests {
let column: Arc<dyn Column<u64>> = serialize_and_load(&permutation);
b.iter(|| {
let mut a = 0u64;
for i in 0..n {
a += column.get_val(i as u32);
for i in 0..n as u64 {
a += column.get_val(i);
}
a
});

10
fastfield_codecs/src/bitpacked.rs
View File

@@ -17,7 +17,7 @@ pub struct BitpackedReader {
impl Column for BitpackedReader {
#[inline]
fn get_val(&self, doc: u32) -> u64 {
fn get_val(&self, doc: u64) -> u64 {
self.bit_unpacker.get(doc, &self.data)
}
#[inline]
@@ -30,7 +30,7 @@ impl Column for BitpackedReader {
self.normalized_header.max_value
}
#[inline]
fn num_vals(&self) -> u32 {
fn num_vals(&self) -> u64 {
self.normalized_header.num_vals
}
}
@@ -68,14 +68,16 @@ impl FastFieldCodec for BitpackedCodec {
assert_eq!(column.min_value(), 0u64);
let num_bits = compute_num_bits(column.max_value());
let mut bit_packer = BitPacker::new();
for val in column.iter() {
let mut reader = column.reader();
while reader.advance() {
let val = reader.get();
bit_packer.write(val, num_bits, write)?;
}
bit_packer.close(write)?;
Ok(())
}
fn estimate(column: &dyn Column) -> Option<f32> {
fn estimate(column: &impl Column) -> Option<f32> {
let num_bits = compute_num_bits(column.max_value());
let num_bits_uncompressed = 64;
Some(num_bits as f32 / num_bits_uncompressed as f32)

28
fastfield_codecs/src/blockwise_linear.rs
View File

@@ -36,7 +36,7 @@ impl BinarySerializable for Block {
}
}
fn compute_num_blocks(num_vals: u32) -> usize {
fn compute_num_blocks(num_vals: u64) -> usize {
(num_vals as usize + CHUNK_SIZE - 1) / CHUNK_SIZE
}
@@ -71,14 +71,16 @@ impl FastFieldCodec for BlockwiseLinearCodec {
}
// Estimate first_chunk and extrapolate
fn estimate(column: &dyn crate::Column) -> Option<f32> {
if column.num_vals() < 10 * CHUNK_SIZE as u32 {
fn estimate(column: &impl crate::Column) -> Option<f32> {
if column.num_vals() < 10 * CHUNK_SIZE as u64 {
return None;
}
let mut first_chunk: Vec<u64> = column.iter().take(CHUNK_SIZE as usize).collect();
let mut first_chunk: Vec<u64> = crate::iter_from_reader(column.reader())
.take(CHUNK_SIZE as usize)
.collect();
let line = Line::train(&VecColumn::from(&first_chunk));
for (i, buffer_val) in first_chunk.iter_mut().enumerate() {
let interpolated_val = line.eval(i as u32);
let interpolated_val = line.eval(i as u64);
*buffer_val = buffer_val.wrapping_sub(interpolated_val);
}
let estimated_bit_width = first_chunk
@@ -95,12 +97,12 @@ impl FastFieldCodec for BlockwiseLinearCodec {
};
let num_bits = estimated_bit_width as u64 * column.num_vals() as u64
// function metadata per block
+ metadata_per_block as u64 * (column.num_vals() as u64 / CHUNK_SIZE as u64);
+ metadata_per_block as u64 * (column.num_vals() / CHUNK_SIZE as u64);
let num_bits_uncompressed = 64 * column.num_vals();
Some(num_bits as f32 / num_bits_uncompressed as f32)
}
fn serialize(column: &dyn Column, wrt: &mut impl io::Write) -> io::Result<()> {
fn serialize(column: &dyn crate::Column, wrt: &mut impl io::Write) -> io::Result<()> {
// The BitpackedReader assumes a normalized vector.
assert_eq!(column.min_value(), 0);
let mut buffer = Vec::with_capacity(CHUNK_SIZE);
@@ -109,7 +111,7 @@ impl FastFieldCodec for BlockwiseLinearCodec {
let num_blocks = compute_num_blocks(num_vals);
let mut blocks = Vec::with_capacity(num_blocks);
let mut vals = column.iter();
let mut vals = crate::iter_from_reader(column.reader());
let mut bit_packer = BitPacker::new();
@@ -121,7 +123,7 @@ impl FastFieldCodec for BlockwiseLinearCodec {
assert!(!buffer.is_empty());
for (i, buffer_val) in buffer.iter_mut().enumerate() {
let interpolated_val = line.eval(i as u32);
let interpolated_val = line.eval(i as u64);
*buffer_val = buffer_val.wrapping_sub(interpolated_val);
}
let bit_width = buffer.iter().copied().map(compute_num_bits).max().unwrap();
@@ -161,9 +163,9 @@ pub struct BlockwiseLinearReader {
impl Column for BlockwiseLinearReader {
#[inline(always)]
fn get_val(&self, idx: u32) -> u64 {
let block_id = (idx / CHUNK_SIZE as u32) as usize;
let idx_within_block = idx % (CHUNK_SIZE as u32);
fn get_val(&self, idx: u64) -> u64 {
let block_id = (idx / CHUNK_SIZE as u64) as usize;
let idx_within_block = idx % (CHUNK_SIZE as u64);
let block = &self.blocks[block_id];
let interpoled_val: u64 = block.line.eval(idx_within_block);
let block_bytes = &self.data[block.data_start_offset..];
@@ -180,7 +182,7 @@ impl Column for BlockwiseLinearReader {
self.normalized_header.max_value
}
fn num_vals(&self) -> u32 {
fn num_vals(&self) -> u64 {
self.normalized_header.num_vals
}
}

300
fastfield_codecs/src/column.rs
View File

@@ -1,21 +1,25 @@
use std::fmt::{self, Debug};
use std::marker::PhantomData;
use std::ops::{Range, RangeInclusive};
use std::ops::RangeInclusive;
use tantivy_bitpacker::minmax;
use crate::monotonic_mapping::StrictlyMonotonicFn;
pub trait Column<T: PartialOrd + Copy + 'static = u64>: Send + Sync {
/// Return a `ColumnReader`.
fn reader(&self) -> Box<dyn ColumnReader<T> + '_> {
// Box::new(ColumnReaderAdapter { column: self, idx: 0, })
Box::new(ColumnReaderAdapter::from(self))
}
/// `Column` provides columnar access on a field.
pub trait Column<T: PartialOrd + Debug = u64>: Send + Sync {
/// Return the value associated with the given idx.
/// Return the value associated to the given idx.
///
/// This accessor should return as fast as possible.
///
/// # Panics
///
/// May panic if `idx` is greater than the column length.
fn get_val(&self, idx: u32) -> T;
///
/// TODO remove to force people to use `.reader()`.
fn get_val(&self, idx: u64) -> T;
/// Fills an output buffer with the fast field values
/// associated with the `DocId` going from
@@ -28,28 +32,21 @@ pub trait Column<T: PartialOrd + Debug = u64>: Send + Sync {
#[inline]
fn get_range(&self, start: u64, output: &mut [T]) {
for (out, idx) in output.iter_mut().zip(start..) {
*out = self.get_val(idx as u32);
*out = self.get_val(idx);
}
}
/// Get the positions of values which are in the provided value range.
///
/// Note that position == docid for single value fast fields
/// Return the positions of values which are in the provided range.
#[inline]
fn get_docids_for_value_range(
&self,
value_range: RangeInclusive<T>,
doc_id_range: Range<u32>,
positions: &mut Vec<u32>,
) {
let doc_id_range = doc_id_range.start..doc_id_range.end.min(self.num_vals());
for idx in doc_id_range.start..doc_id_range.end {
fn get_between_vals(&self, range: RangeInclusive<T>) -> Vec<u64> {
let mut vals = Vec::new();
for idx in 0..self.num_vals() {
let val = self.get_val(idx);
if value_range.contains(&val) {
positions.push(idx);
if range.contains(&val) {
vals.push(idx);
}
}
vals
}
/// Returns the minimum value for this fast field.
@@ -68,24 +65,84 @@ pub trait Column<T: PartialOrd + Debug = u64>: Send + Sync {
/// `.max_value()`.
fn max_value(&self) -> T;
/// The number of values in the column.
fn num_vals(&self) -> u32;
fn num_vals(&self) -> u64;
}
/// Returns a iterator over the data
fn iter<'a>(&'a self) -> Box<dyn Iterator<Item = T> + 'a> {
Box::new((0..self.num_vals()).map(|idx| self.get_val(idx)))
/// `ColumnReader` makes it possible to read forward through a column.
pub trait ColumnReader<T = u64> {
/// Advance the reader to the target_idx.
///
/// After a successful call to seek,
/// `.get()` should returns `column.get_val(target_idx)`.
fn seek(&mut self, target_idx: u64) -> T;
fn advance(&mut self) -> bool;
/// Get the current value without advancing the reader
fn get(&self) -> T;
}
pub fn iter_from_reader<'a, T: 'static>(
mut column_reader: Box<dyn ColumnReader<T> + 'a>,
) -> impl Iterator<Item = T> + 'a {
std::iter::from_fn(move || {
if !column_reader.advance() {
return None;
}
Some(column_reader.get())
})
}
pub(crate) struct ColumnReaderAdapter<'a, C: ?Sized, T> {
column: &'a C,
idx: u64,
len: u64,
_phantom: PhantomData<T>,
}
impl<'a, C: Column<T> + ?Sized, T: Copy + PartialOrd + 'static> From<&'a C>
for ColumnReaderAdapter<'a, C, T>
{
fn from(column: &'a C) -> Self {
ColumnReaderAdapter {
column,
idx: u64::MAX,
len: column.num_vals(),
_phantom: PhantomData,
}
}
}
impl<'a, T, C: ?Sized> ColumnReader<T> for ColumnReaderAdapter<'a, C, T>
where
C: Column<T>,
T: PartialOrd<T> + Copy + 'static,
{
fn seek(&mut self, idx: u64) -> T {
self.idx = idx;
self.get()
}
fn advance(&mut self) -> bool {
self.idx = self.idx.wrapping_add(1);
self.idx < self.len
}
fn get(&self) -> T {
self.column.get_val(self.idx)
}
}
/// VecColumn provides `Column` over a slice.
pub struct VecColumn<'a, T = u64> {
values: &'a [T],
min_value: T,
max_value: T,
}
impl<'a, C: Column<T>, T: Copy + PartialOrd + fmt::Debug> Column<T> for &'a C {
fn get_val(&self, idx: u32) -> T {
impl<'a, C: Column<T>, T> Column<T> for &'a C
where T: Copy + PartialOrd + 'static
{
fn get_val(&self, idx: u64) -> T {
(*self).get_val(idx)
}
@@ -97,12 +154,12 @@ impl<'a, C: Column<T>, T: Copy + PartialOrd + fmt::Debug> Column<T> for &'a C {
(*self).max_value()
}
fn num_vals(&self) -> u32 {
fn num_vals(&self) -> u64 {
(*self).num_vals()
}
fn iter<'b>(&'b self) -> Box<dyn Iterator<Item = T> + 'b> {
(*self).iter()
fn reader(&self) -> Box<dyn ColumnReader<T> + '_> {
(*self).reader()
}
fn get_range(&self, start: u64, output: &mut [T]) {
@@ -110,15 +167,11 @@ impl<'a, C: Column<T>, T: Copy + PartialOrd + fmt::Debug> Column<T> for &'a C {
}
}
impl<'a, T: Copy + PartialOrd + Send + Sync + Debug> Column<T> for VecColumn<'a, T> {
fn get_val(&self, position: u32) -> T {
impl<'a, T: Copy + PartialOrd + Send + Sync + 'static> Column<T> for VecColumn<'a, T> {
fn get_val(&self, position: u64) -> T {
self.values[position as usize]
}
fn iter(&self) -> Box<dyn Iterator<Item = T> + '_> {
Box::new(self.values.iter().copied())
}
fn min_value(&self) -> T {
self.min_value
}
@@ -127,8 +180,8 @@ impl<'a, T: Copy + PartialOrd + Send + Sync + Debug> Column<T> for VecColumn<'a,
self.max_value
}
fn num_vals(&self) -> u32 {
self.values.len() as u32
fn num_vals(&self) -> u64 {
self.values.len() as u64
}
fn get_range(&self, start: u64, output: &mut [T]) {
@@ -156,30 +209,16 @@ struct MonotonicMappingColumn<C, T, Input> {
_phantom: PhantomData<Input>,
}
/// Creates a view of a column transformed by a strictly monotonic mapping. See
/// [`StrictlyMonotonicFn`].
///
/// E.g. apply a gcd monotonic_mapping([100, 200, 300]) == [1, 2, 3]
/// monotonic_mapping.mapping() is expected to be injective, and we should always have
/// monotonic_mapping.inverse(monotonic_mapping.mapping(el)) == el
///
/// The inverse of the mapping is required for:
/// `fn get_positions_for_value_range(&self, range: RangeInclusive<T>) -> Vec<u64> `
/// The user provides the original value range and we need to monotonic map them in the same way the
/// serialization does before calling the underlying column.
///
/// Note that when opening a codec, the monotonic_mapping should be the inverse of the mapping
/// during serialization. And therefore the monotonic_mapping_inv when opening is the same as
/// monotonic_mapping during serialization.
pub fn monotonic_map_column<C, T, Input, Output>(
/// Creates a view of a column transformed by a monotonic mapping.
pub fn monotonic_map_column<C, T, Input: PartialOrd + Copy, Output: PartialOrd + Copy>(
from_column: C,
monotonic_mapping: T,
) -> impl Column<Output>
where
C: Column<Input>,
T: StrictlyMonotonicFn<Input, Output> + Send + Sync,
Input: PartialOrd + Send + Sync + Copy + Debug,
Output: PartialOrd + Send + Sync + Copy + Debug,
T: Fn(Input) -> Output + Send + Sync,
Input: Send + Sync + 'static,
Output: Send + Sync + 'static,
{
MonotonicMappingColumn {
from_column,
@@ -188,63 +227,72 @@ where
}
}
impl<C, T, Input, Output> Column<Output> for MonotonicMappingColumn<C, T, Input>
impl<C, T, Input: PartialOrd + Copy, Output: PartialOrd + Copy> Column<Output>
for MonotonicMappingColumn<C, T, Input>
where
C: Column<Input>,
T: StrictlyMonotonicFn<Input, Output> + Send + Sync,
Input: PartialOrd + Send + Sync + Copy + Debug,
Output: PartialOrd + Send + Sync + Copy + Debug,
T: Fn(Input) -> Output + Send + Sync,
Input: Send + Sync + 'static,
Output: Send + Sync + 'static,
{
#[inline]
fn get_val(&self, idx: u32) -> Output {
fn get_val(&self, idx: u64) -> Output {
let from_val = self.from_column.get_val(idx);
self.monotonic_mapping.mapping(from_val)
(self.monotonic_mapping)(from_val)
}
fn min_value(&self) -> Output {
let from_min_value = self.from_column.min_value();
self.monotonic_mapping.mapping(from_min_value)
(self.monotonic_mapping)(from_min_value)
}
fn max_value(&self) -> Output {
let from_max_value = self.from_column.max_value();
self.monotonic_mapping.mapping(from_max_value)
(self.monotonic_mapping)(from_max_value)
}
fn num_vals(&self) -> u32 {
fn num_vals(&self) -> u64 {
self.from_column.num_vals()
}
fn iter(&self) -> Box<dyn Iterator<Item = Output> + '_> {
Box::new(
self.from_column
.iter()
.map(|el| self.monotonic_mapping.mapping(el)),
)
}
fn get_docids_for_value_range(
&self,
range: RangeInclusive<Output>,
doc_id_range: Range<u32>,
positions: &mut Vec<u32>,
) {
if range.start() > &self.max_value() || range.end() < &self.min_value() {
return;
}
let range = self.monotonic_mapping.inverse_coerce(range);
if range.start() > range.end() {
return;
}
self.from_column
.get_docids_for_value_range(range, doc_id_range, positions)
fn reader(&self) -> Box<dyn ColumnReader<Output> + '_> {
Box::new(MonotonicMappingColumnReader {
col_reader: self.from_column.reader(),
monotonic_mapping: &self.monotonic_mapping,
intermdiary_type: PhantomData,
})
}
// We voluntarily do not implement get_range as it yields a regression,
// and we do not have any specialized implementation anyway.
}
/// Wraps an iterator into a `Column`.
struct MonotonicMappingColumnReader<'a, Transform, U> {
col_reader: Box<dyn ColumnReader<U> + 'a>,
monotonic_mapping: &'a Transform,
intermdiary_type: PhantomData<U>,
}
impl<'a, U, V, Transform> ColumnReader<V> for MonotonicMappingColumnReader<'a, Transform, U>
where
U: Copy,
V: Copy,
Transform: Fn(U) -> V,
{
fn seek(&mut self, idx: u64) -> V {
let intermediary_value = self.col_reader.seek(idx);
(*self.monotonic_mapping)(intermediary_value)
}
fn advance(&mut self) -> bool {
self.col_reader.advance()
}
fn get(&self) -> V {
(*self.monotonic_mapping)(self.col_reader.get())
}
}
pub struct IterColumn<T>(T);
impl<T> From<T> for IterColumn<T>
@@ -258,9 +306,9 @@ where T: Iterator + Clone + ExactSizeIterator
impl<T> Column<T::Item> for IterColumn<T>
where
T: Iterator + Clone + ExactSizeIterator + Send + Sync,
T::Item: PartialOrd + fmt::Debug,
T::Item: PartialOrd + Copy + 'static,
{
fn get_val(&self, idx: u32) -> T::Item {
fn get_val(&self, idx: u64) -> T::Item {
self.0.clone().nth(idx as usize).unwrap()
}
@@ -272,34 +320,27 @@ where
self.0.clone().last().unwrap()
}
fn num_vals(&self) -> u32 {
self.0.len() as u32
}
fn iter(&self) -> Box<dyn Iterator<Item = T::Item> + '_> {
Box::new(self.0.clone())
fn num_vals(&self) -> u64 {
self.0.len() as u64
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::monotonic_mapping::{
StrictlyMonotonicMappingInverter, StrictlyMonotonicMappingToInternalBaseval,
StrictlyMonotonicMappingToInternalGCDBaseval,
};
use crate::MonotonicallyMappableToU64;
#[test]
fn test_monotonic_mapping() {
let vals = &[3u64, 5u64][..];
let vals = &[1u64, 3u64][..];
let col = VecColumn::from(vals);
let mapped = monotonic_map_column(col, StrictlyMonotonicMappingToInternalBaseval::new(2));
assert_eq!(mapped.min_value(), 1u64);
assert_eq!(mapped.max_value(), 3u64);
let mapped = monotonic_map_column(col, |el| el + 4);
assert_eq!(mapped.min_value(), 5u64);
assert_eq!(mapped.max_value(), 7u64);
assert_eq!(mapped.num_vals(), 2);
assert_eq!(mapped.num_vals(), 2);
assert_eq!(mapped.get_val(0), 1);
assert_eq!(mapped.get_val(1), 3);
assert_eq!(mapped.get_val(0), 5);
assert_eq!(mapped.get_val(1), 7);
}
#[test]
@@ -311,15 +352,10 @@ mod tests {
#[test]
fn test_monotonic_mapping_iter() {
let vals: Vec<u64> = (10..110u64).map(|el| el * 10).collect();
let vals: Vec<u64> = (-1..99).map(i64::to_u64).collect();
let col = VecColumn::from(&vals);
let mapped = monotonic_map_column(
col,
StrictlyMonotonicMappingInverter::from(
StrictlyMonotonicMappingToInternalGCDBaseval::new(10, 100),
),
);
let val_i64s: Vec<u64> = mapped.iter().collect();
let mapped = monotonic_map_column(col, |el| i64::from_u64(el) * 10i64);
let val_i64s: Vec<i64> = crate::iter_from_reader(mapped.reader()).collect();
for i in 0..100 {
assert_eq!(val_i64s[i as usize], mapped.get_val(i));
}
@@ -327,26 +363,20 @@ mod tests {
#[test]
fn test_monotonic_mapping_get_range() {
let vals: Vec<u64> = (0..100u64).map(|el| el * 10).collect();
let vals: Vec<u64> = (-1..99).map(i64::to_u64).collect();
let col = VecColumn::from(&vals);
let mapped = monotonic_map_column(
col,
StrictlyMonotonicMappingInverter::from(
StrictlyMonotonicMappingToInternalGCDBaseval::new(10, 0),
),
);
assert_eq!(mapped.min_value(), 0u64);
assert_eq!(mapped.max_value(), 9900u64);
let mapped = monotonic_map_column(col, |el| i64::from_u64(el) * 10i64);
assert_eq!(mapped.min_value(), -10i64);
assert_eq!(mapped.max_value(), 980i64);
assert_eq!(mapped.num_vals(), 100);
let val_u64s: Vec<u64> = mapped.iter().collect();
assert_eq!(val_u64s.len(), 100);
let val_i64s: Vec<i64> = crate::iter_from_reader(mapped.reader()).collect();
assert_eq!(val_i64s.len(), 100);
for i in 0..100 {
assert_eq!(val_u64s[i as usize], mapped.get_val(i));
assert_eq!(val_u64s[i as usize], vals[i as usize] * 10);
assert_eq!(val_i64s[i as usize], mapped.get_val(i));
assert_eq!(val_i64s[i as usize], i64::from_u64(vals[i as usize]) * 10);
}
let mut buf = [0u64; 20];
let mut buf = [0i64; 20];
mapped.get_range(7, &mut buf[..]);
assert_eq!(&val_u64s[7..][..20], &buf);
assert_eq!(&val_i64s[7..][..20], &buf);
}
}

2
fastfield_codecs/src/compact_space/build_compact_space.rs
View File

@@ -57,7 +57,7 @@ fn num_bits(val: u128) -> u8 {
/// metadata.
pub fn get_compact_space(
values_deduped_sorted: &BTreeSet<u128>,
total_num_values: u32,
total_num_values: u64,
cost_per_blank: usize,
) -> CompactSpace {
let mut compact_space_builder = CompactSpaceBuilder::new();

346
fastfield_codecs/src/compact_space/mod.rs
View File

@@ -14,7 +14,7 @@ use std::{
cmp::Ordering,
collections::BTreeSet,
io::{self, Write},
ops::{Range, RangeInclusive},
ops::RangeInclusive,
};
use common::{BinarySerializable, CountingWriter, VInt, VIntU128};
@@ -22,7 +22,7 @@ use ownedbytes::OwnedBytes;
use tantivy_bitpacker::{self, BitPacker, BitUnpacker};
use crate::compact_space::build_compact_space::get_compact_space;
use crate::Column;
use crate::{iter_from_reader, Column, ColumnReader};
mod blank_range;
mod build_compact_space;
@@ -165,19 +165,22 @@ pub struct IPCodecParams {
bit_unpacker: BitUnpacker,
min_value: u128,
max_value: u128,
num_vals: u32,
num_vals: u64,
num_bits: u8,
}
impl CompactSpaceCompressor {
/// Taking the vals as Vec may cost a lot of memory. It is used to sort the vals.
pub fn train_from(iter: impl Iterator<Item = u128>, num_vals: u32) -> Self {
pub fn train_from(column: &impl Column<u128>) -> Self {
let mut values_sorted = BTreeSet::new();
values_sorted.extend(iter);
let total_num_values = num_vals;
let total_num_values = column.num_vals();
values_sorted.extend(iter_from_reader(column.reader()));
let compact_space =
get_compact_space(&values_sorted, total_num_values, COST_PER_BLANK_IN_BITS);
let amplitude_compact_space = compact_space.amplitude_compact_space();
assert!(
@@ -200,7 +203,7 @@ impl CompactSpaceCompressor {
bit_unpacker: BitUnpacker::new(num_bits),
min_value,
max_value,
num_vals: total_num_values,
num_vals: total_num_values as u64,
num_bits,
},
}
@@ -218,11 +221,12 @@ impl CompactSpaceCompressor {
pub fn compress_into(
self,
vals: impl Iterator<Item = u128>,
mut vals: Box<dyn ColumnReader<u128> + '_>,
write: &mut impl Write,
) -> io::Result<()> {
let mut bitpacker = BitPacker::default();
for val in vals {
while vals.advance() {
let val = vals.get();
let compact = self
.params
.compact_space
@@ -267,7 +271,7 @@ impl BinarySerializable for IPCodecParams {
let _header_flags = u64::deserialize(reader)?;
let min_value = VIntU128::deserialize(reader)?.0;
let max_value = VIntU128::deserialize(reader)?.0;
let num_vals = VIntU128::deserialize(reader)?.0 as u32;
let num_vals = VIntU128::deserialize(reader)?.0 as u64;
let num_bits = u8::deserialize(reader)?;
let compact_space = CompactSpace::deserialize(reader)?;
@@ -284,7 +288,7 @@ impl BinarySerializable for IPCodecParams {
impl Column<u128> for CompactSpaceDecompressor {
#[inline]
fn get_val(&self, doc: u32) -> u128 {
fn get_val(&self, doc: u64) -> u128 {
self.get(doc)
}
@@ -296,23 +300,16 @@ impl Column<u128> for CompactSpaceDecompressor {
self.max_value()
}
fn num_vals(&self) -> u32 {
fn num_vals(&self) -> u64 {
self.params.num_vals
}
#[inline]
fn iter(&self) -> Box<dyn Iterator<Item = u128> + '_> {
Box::new(self.iter())
fn get_between_vals(&self, range: RangeInclusive<u128>) -> Vec<u64> {
self.get_between_vals(range)
}
#[inline]
fn get_docids_for_value_range(
&self,
value_range: RangeInclusive<u128>,
positions_range: Range<u32>,
positions: &mut Vec<u32>,
) {
self.get_positions_for_value_range(value_range, positions_range, positions)
fn reader(&self) -> Box<dyn ColumnReader<u128> + '_> {
Box::new(self.specialized_reader())
}
}
@@ -347,19 +344,12 @@ impl CompactSpaceDecompressor {
/// Comparing on compact space: Real dataset 1.08 GElements/s
///
/// Comparing on original space: Real dataset .06 GElements/s (not completely optimized)
#[inline]
pub fn get_positions_for_value_range(
&self,
value_range: RangeInclusive<u128>,
position_range: Range<u32>,
positions: &mut Vec<u32>,
) {
if value_range.start() > value_range.end() {
return;
pub fn get_between_vals(&self, range: RangeInclusive<u128>) -> Vec<u64> {
if range.start() > range.end() {
return Vec::new();
}
let position_range = position_range.start..position_range.end.min(self.num_vals());
let from_value = *value_range.start();
let to_value = *value_range.end();
let from_value = *range.start();
let to_value = *range.end();
assert!(to_value >= from_value);
let compact_from = self.u128_to_compact(from_value);
let compact_to = self.u128_to_compact(to_value);
@@ -367,7 +357,7 @@ impl CompactSpaceDecompressor {
// Quick return, if both ranges fall into the same non-mapped space, the range can't cover
// any values, so we can early exit
match (compact_to, compact_from) {
(Err(pos1), Err(pos2)) if pos1 == pos2 => return,
(Err(pos1), Err(pos2)) if pos1 == pos2 => return Vec::new(),
_ => {}
}
@@ -389,28 +379,27 @@ impl CompactSpaceDecompressor {
});
let range = compact_from..=compact_to;
let scan_num_docs = position_range.end - position_range.start;
let mut positions = Vec::new();
let step_size = 4;
let cutoff = position_range.start + scan_num_docs - scan_num_docs % step_size;
let cutoff = self.params.num_vals - self.params.num_vals % step_size;
let mut push_if_in_range = |idx, val| {
if range.contains(&val) {
positions.push(idx);
}
};
let get_val = |idx| self.params.bit_unpacker.get(idx, &self.data);
let get_val = |idx| self.params.bit_unpacker.get(idx as u64, &self.data);
// unrolled loop
for idx in (position_range.start..cutoff).step_by(step_size as usize) {
for idx in (0..cutoff).step_by(step_size as usize) {
let idx1 = idx;
let idx2 = idx + 1;
let idx3 = idx + 2;
let idx4 = idx + 3;
let val1 = get_val(idx1 as u32);
let val2 = get_val(idx2 as u32);
let val3 = get_val(idx3 as u32);
let val4 = get_val(idx4 as u32);
let val1 = get_val(idx1);
let val2 = get_val(idx2);
let val3 = get_val(idx3);
let val4 = get_val(idx4);
push_if_in_range(idx1, val1);
push_if_in_range(idx2, val2);
push_if_in_range(idx3, val3);
@@ -418,27 +407,24 @@ impl CompactSpaceDecompressor {
}
// handle rest
for idx in cutoff..position_range.end {
push_if_in_range(idx, get_val(idx as u32));
for idx in cutoff..self.params.num_vals {
push_if_in_range(idx, get_val(idx));
}
positions
}
fn specialized_reader(&self) -> CompactSpaceReader<'_> {
CompactSpaceReader {
data: self.data.as_slice(),
params: &self.params,
idx: 0u64,
len: self.params.num_vals,
}
}
#[inline]
fn iter_compact(&self) -> impl Iterator<Item = u64> + '_ {
(0..self.params.num_vals)
.map(move |idx| self.params.bit_unpacker.get(idx, &self.data) as u64)
}
#[inline]
fn iter(&self) -> impl Iterator<Item = u128> + '_ {
// TODO: Performance. It would be better to iterate on the ranges and check existence via
// the bit_unpacker.
self.iter_compact()
.map(|compact| self.compact_to_u128(compact))
}
#[inline]
pub fn get(&self, idx: u32) -> u128 {
pub fn get(&self, idx: u64) -> u128 {
let compact = self.params.bit_unpacker.get(idx, &self.data);
self.compact_to_u128(compact)
}
@@ -452,16 +438,35 @@ impl CompactSpaceDecompressor {
}
}
pub struct CompactSpaceReader<'a> {
data: &'a [u8],
params: &'a IPCodecParams,
idx: u64,
len: u64,
}
impl<'a> ColumnReader<u128> for CompactSpaceReader<'a> {
fn seek(&mut self, target_idx: u64) -> u128 {
self.idx = target_idx;
self.get()
}
fn advance(&mut self) -> bool {
self.idx = self.idx.wrapping_add(1);
self.idx < self.len
}
fn get(&self) -> u128 {
let compact_code = self.params.bit_unpacker.get(self.idx, self.data);
self.params.compact_space.compact_to_u128(compact_code)
}
}
#[cfg(test)]
mod tests {
use std::fmt;
use super::*;
use crate::format_version::read_format_version;
use crate::null_index_footer::read_null_index_footer;
use crate::serialize::U128Header;
use crate::{open_u128, serialize_u128};
use crate::{open_u128, serialize_u128, VecColumn};
#[test]
fn compact_space_test() {
@@ -470,7 +475,7 @@ mod tests {
]
.into_iter()
.collect();
let compact_space = get_compact_space(ips, ips.len() as u32, 11);
let compact_space = get_compact_space(ips, ips.len() as u64, 11);
let amplitude = compact_space.amplitude_compact_space();
assert_eq!(amplitude, 17);
assert_eq!(1, compact_space.u128_to_compact(2).unwrap());
@@ -501,30 +506,24 @@ mod tests {
#[test]
fn compact_space_amplitude_test() {
let ips = &[100000u128, 1000000].into_iter().collect();
let compact_space = get_compact_space(ips, ips.len() as u32, 1);
let compact_space = get_compact_space(ips, ips.len() as u64, 1);
let amplitude = compact_space.amplitude_compact_space();
assert_eq!(amplitude, 2);
}
fn test_all(mut data: OwnedBytes, expected: &[u128]) {
let _header = U128Header::deserialize(&mut data);
fn test_all(data: OwnedBytes, expected: &[u128]) {
let decompressor = CompactSpaceDecompressor::open(data).unwrap();
for (idx, expected_val) in expected.iter().cloned().enumerate() {
let val = decompressor.get(idx as u32);
let val = decompressor.get(idx as u64);
assert_eq!(val, expected_val);
let test_range = |range: RangeInclusive<u128>| {
let expected_positions = expected
.iter()
.positions(|val| range.contains(val))
.map(|pos| pos as u32)
.map(|pos| pos as u64)
.collect::<Vec<_>>();
let mut positions = Vec::new();
decompressor.get_positions_for_value_range(
range,
0..decompressor.num_vals(),
&mut positions,
);
let positions = decompressor.get_between_vals(range);
assert_eq!(positions, expected_positions);
};
@@ -537,18 +536,10 @@ mod tests {
fn test_aux_vals(u128_vals: &[u128]) -> OwnedBytes {
let mut out = Vec::new();
serialize_u128(
|| u128_vals.iter().cloned(),
u128_vals.len() as u32,
&mut out,
)
.unwrap();
serialize_u128(VecColumn::from(u128_vals), &mut out).unwrap();
let data = OwnedBytes::new(out);
let (data, _format_version) = read_format_version(data).unwrap();
let (data, _null_index_footer) = read_null_index_footer(data).unwrap();
test_all(data.clone(), u128_vals);
data
}
@@ -565,111 +556,26 @@ mod tests {
4_000_211_222u128,
333u128,
];
let mut data = test_aux_vals(vals);
let _header = U128Header::deserialize(&mut data);
let data = test_aux_vals(vals);
let decomp = CompactSpaceDecompressor::open(data).unwrap();
let complete_range = 0..vals.len() as u32;
for (pos, val) in vals.iter().enumerate() {
let val = *val as u128;
let pos = pos as u32;
let mut positions = Vec::new();
decomp.get_positions_for_value_range(val..=val, pos..pos + 1, &mut positions);
assert_eq!(positions, vec![pos]);
}
// handle docid range out of bounds
let positions = get_positions_for_value_range_helper(&decomp, 0..=1, 1..u32::MAX);
assert_eq!(positions, vec![]);
let positions =
get_positions_for_value_range_helper(&decomp, 0..=1, complete_range.clone());
let positions = decomp.get_between_vals(0..=1);
assert_eq!(positions, vec![0]);
let positions =
get_positions_for_value_range_helper(&decomp, 0..=2, complete_range.clone());
let positions = decomp.get_between_vals(0..=2);
assert_eq!(positions, vec![0]);
let positions =
get_positions_for_value_range_helper(&decomp, 0..=3, complete_range.clone());
let positions = decomp.get_between_vals(0..=3);
assert_eq!(positions, vec![0, 2]);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
99999u128..=99999u128,
complete_range.clone()
),
vec![3]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
99999u128..=100000u128,
complete_range.clone()
),
vec![3, 4]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
99998u128..=100000u128,
complete_range.clone()
),
vec![3, 4]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
99998u128..=99999u128,
complete_range.clone()
),
vec![3]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
99998u128..=99998u128,
complete_range.clone()
),
vec![]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
333u128..=333u128,
complete_range.clone()
),
vec![8]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
332u128..=333u128,
complete_range.clone()
),
vec![8]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
332u128..=334u128,
complete_range.clone()
),
vec![8]
);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
333u128..=334u128,
complete_range.clone()
),
vec![8]
);
assert_eq!(decomp.get_between_vals(99999u128..=99999u128), vec![3]);
assert_eq!(decomp.get_between_vals(99999u128..=100000u128), vec![3, 4]);
assert_eq!(decomp.get_between_vals(99998u128..=100000u128), vec![3, 4]);
assert_eq!(decomp.get_between_vals(99998u128..=99999u128), vec![3]);
assert_eq!(decomp.get_between_vals(99998u128..=99998u128), vec![]);
assert_eq!(decomp.get_between_vals(333u128..=333u128), vec![8]);
assert_eq!(decomp.get_between_vals(332u128..=333u128), vec![8]);
assert_eq!(decomp.get_between_vals(332u128..=334u128), vec![8]);
assert_eq!(decomp.get_between_vals(333u128..=334u128), vec![8]);
assert_eq!(
get_positions_for_value_range_helper(
&decomp,
4_000_211_221u128..=5_000_000_000u128,
complete_range.clone()
),
decomp.get_between_vals(4_000_211_221u128..=5_000_000_000u128),
vec![6, 7]
);
}
@@ -692,32 +598,14 @@ mod tests {
4_000_211_222u128,
333u128,
];
let mut data = test_aux_vals(vals);
let _header = U128Header::deserialize(&mut data);
let data = test_aux_vals(vals);
let decomp = CompactSpaceDecompressor::open(data).unwrap();
let complete_range = 0..vals.len() as u32;
assert_eq!(
get_positions_for_value_range_helper(&decomp, 0..=5, complete_range.clone()),
vec![]
);
assert_eq!(
get_positions_for_value_range_helper(&decomp, 0..=100, complete_range.clone()),
vec![0]
);
assert_eq!(
get_positions_for_value_range_helper(&decomp, 0..=105, complete_range.clone()),
vec![0]
);
}
fn get_positions_for_value_range_helper<C: Column<T> + ?Sized, T: PartialOrd + fmt::Debug>(
column: &C,
value_range: RangeInclusive<T>,
doc_id_range: Range<u32>,
) -> Vec<u32> {
let mut positions = Vec::new();
column.get_docids_for_value_range(value_range, doc_id_range, &mut positions);
positions
let positions = decomp.get_between_vals(0..=5);
assert_eq!(positions, vec![]);
let positions = decomp.get_between_vals(0..=100);
assert_eq!(positions, vec![0]);
let positions = decomp.get_between_vals(0..=105);
assert_eq!(positions, vec![0]);
}
#[test]
@@ -738,33 +626,13 @@ mod tests {
5_000_000_000,
];
let mut out = Vec::new();
serialize_u128(|| vals.iter().cloned(), vals.len() as u32, &mut out).unwrap();
let decomp = open_u128::<u128>(OwnedBytes::new(out)).unwrap();
let complete_range = 0..vals.len() as u32;
serialize_u128(VecColumn::from(vals), &mut out).unwrap();
let decomp = open_u128(OwnedBytes::new(out)).unwrap();
assert_eq!(
get_positions_for_value_range_helper(&*decomp, 199..=200, complete_range.clone()),
vec![0]
);
assert_eq!(
get_positions_for_value_range_helper(&*decomp, 199..=201, complete_range.clone()),
vec![0, 1]
);
assert_eq!(
get_positions_for_value_range_helper(&*decomp, 200..=200, complete_range.clone()),
vec![0]
);
assert_eq!(
get_positions_for_value_range_helper(
&*decomp,
1_000_000..=1_000_000,
complete_range.clone()
),
vec![11]
);
assert_eq!(decomp.get_between_vals(199..=200), vec![0]);
assert_eq!(decomp.get_between_vals(199..=201), vec![0, 1]);
assert_eq!(decomp.get_between_vals(200..=200), vec![0]);
assert_eq!(decomp.get_between_vals(1_000_000..=1_000_000), vec![11]);
}
#[test]

39
fastfield_codecs/src/format_version.rs
View File

@@ -1,39 +0,0 @@
use std::io;
use common::BinarySerializable;
use ownedbytes::OwnedBytes;
const MAGIC_NUMBER: u16 = 4335u16;
const FASTFIELD_FORMAT_VERSION: u8 = 1;
pub(crate) fn append_format_version(output: &mut impl io::Write) -> io::Result<()> {
FASTFIELD_FORMAT_VERSION.serialize(output)?;
MAGIC_NUMBER.serialize(output)?;
Ok(())
}
pub(crate) fn read_format_version(data: OwnedBytes) -> io::Result<(OwnedBytes, u8)> {
let (data, magic_number_bytes) = data.rsplit(2);
let magic_number = u16::deserialize(&mut magic_number_bytes.as_slice())?;
if magic_number != MAGIC_NUMBER {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
format!("magic number mismatch {} != {}", magic_number, MAGIC_NUMBER),
));
}
let (data, format_version_bytes) = data.rsplit(1);
let format_version = u8::deserialize(&mut format_version_bytes.as_slice())?;
if format_version > FASTFIELD_FORMAT_VERSION {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
format!(
"Unsupported fastfield format version: {}. Max supported version: {}",
format_version, FASTFIELD_FORMAT_VERSION
),
));
}
Ok((data, format_version))
}

145
fastfield_codecs/src/lib.rs
View File

@@ -1,12 +1,5 @@
#![warn(missing_docs)]
#![cfg_attr(all(feature = "unstable", test), feature(test))]
//! # `fastfield_codecs`
//!
//! - Columnar storage of data for tantivy [`Column`].
//! - Encode data in different codecs.
//! - Monotonically map values to u64/u128
#[cfg(test)]
#[macro_use]
extern crate more_asserts;
@@ -14,30 +7,21 @@ extern crate more_asserts;
#[cfg(all(test, feature = "unstable"))]
extern crate test;
use std::io;
use std::io::Write;
use std::sync::Arc;
use std::{fmt, io};
use common::BinarySerializable;
use compact_space::CompactSpaceDecompressor;
use format_version::read_format_version;
use monotonic_mapping::{
StrictlyMonotonicMappingInverter, StrictlyMonotonicMappingToInternal,
StrictlyMonotonicMappingToInternalBaseval, StrictlyMonotonicMappingToInternalGCDBaseval,
};
use null_index_footer::read_null_index_footer;
use ownedbytes::OwnedBytes;
use serialize::{Header, U128Header};
use serialize::Header;
mod bitpacked;
mod blockwise_linear;
mod compact_space;
mod format_version;
mod line;
mod linear;
mod monotonic_mapping;
mod monotonic_mapping_u128;
mod null_index_footer;
mod column;
mod gcd;
@@ -45,26 +29,18 @@ mod serialize;
use self::bitpacked::BitpackedCodec;
use self::blockwise_linear::BlockwiseLinearCodec;
pub use self::column::{monotonic_map_column, Column, IterColumn, VecColumn};
pub use self::column::{iter_from_reader, monotonic_map_column, Column, ColumnReader, VecColumn};
use self::linear::LinearCodec;
pub use self::monotonic_mapping::{MonotonicallyMappableToU64, StrictlyMonotonicFn};
pub use self::monotonic_mapping_u128::MonotonicallyMappableToU128;
pub use self::monotonic_mapping::MonotonicallyMappableToU64;
pub use self::serialize::{
estimate, serialize, serialize_and_load, serialize_u128, NormalizedHeader,
};
#[derive(PartialEq, Eq, PartialOrd, Ord, Debug, Clone, Copy)]
#[repr(u8)]
/// Available codecs to use to encode the u64 (via [`MonotonicallyMappableToU64`]) converted data.
pub enum FastFieldCodecType {
/// Bitpack all values in the value range. The number of bits is defined by the amplitude
/// `column.max_value() - column.min_value()`
Bitpacked = 1,
/// Linear interpolation puts a line between the first and last value and then bitpacks the
/// values by the offset from the line. The number of bits is defined by the max deviation from
/// the line.
Linear = 2,
/// Same as [`FastFieldCodecType::Linear`], but encodes in blocks of 512 elements.
BlockwiseLinear = 3,
}
@@ -82,11 +58,11 @@ impl BinarySerializable for FastFieldCodecType {
}
impl FastFieldCodecType {
pub(crate) fn to_code(self) -> u8 {
pub fn to_code(self) -> u8 {
self as u8
}
pub(crate) fn from_code(code: u8) -> Option<Self> {
pub fn from_code(code: u8) -> Option<Self> {
match code {
1 => Some(Self::Bitpacked),
2 => Some(Self::Linear),
@@ -96,61 +72,15 @@ impl FastFieldCodecType {
}
}
#[derive(PartialEq, Eq, PartialOrd, Ord, Debug, Clone, Copy)]
#[repr(u8)]
/// Available codecs to use to encode the u128 (via [`MonotonicallyMappableToU128`]) converted data.
pub enum U128FastFieldCodecType {
/// This codec takes a large number space (u128) and reduces it to a compact number space, by
/// removing the holes.
CompactSpace = 1,
}
impl BinarySerializable for U128FastFieldCodecType {
fn serialize<W: Write>(&self, wrt: &mut W) -> io::Result<()> {
self.to_code().serialize(wrt)
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let code = u8::deserialize(reader)?;
let codec_type: Self = Self::from_code(code)
.ok_or_else(|| io::Error::new(io::ErrorKind::InvalidData, "Unknown code `{code}.`"))?;
Ok(codec_type)
}
}
impl U128FastFieldCodecType {
pub(crate) fn to_code(self) -> u8 {
self as u8
}
pub(crate) fn from_code(code: u8) -> Option<Self> {
match code {
1 => Some(Self::CompactSpace),
_ => None,
}
}
/// Returns the correct codec reader wrapped in the `Arc` for the data.
pub fn open_u128(bytes: OwnedBytes) -> io::Result<Arc<dyn Column<u128>>> {
Ok(Arc::new(CompactSpaceDecompressor::open(bytes)?))
}
/// Returns the correct codec reader wrapped in the `Arc` for the data.
pub fn open_u128<Item: MonotonicallyMappableToU128 + fmt::Debug>(
bytes: OwnedBytes,
) -> io::Result<Arc<dyn Column<Item>>> {
let (bytes, _format_version) = read_format_version(bytes)?;
let (mut bytes, _null_index_footer) = read_null_index_footer(bytes)?;
let header = U128Header::deserialize(&mut bytes)?;
assert_eq!(header.codec_type, U128FastFieldCodecType::CompactSpace);
let reader = CompactSpaceDecompressor::open(bytes)?;
let inverted: StrictlyMonotonicMappingInverter<StrictlyMonotonicMappingToInternal<Item>> =
StrictlyMonotonicMappingToInternal::<Item>::new().into();
Ok(Arc::new(monotonic_map_column(reader, inverted)))
}
/// Returns the correct codec reader wrapped in the `Arc` for the data.
pub fn open<T: MonotonicallyMappableToU64 + fmt::Debug>(
bytes: OwnedBytes,
pub fn open<T: MonotonicallyMappableToU64>(
mut bytes: OwnedBytes,
) -> io::Result<Arc<dyn Column<T>>> {
let (bytes, _format_version) = read_format_version(bytes)?;
let (mut bytes, _null_index_footer) = read_null_index_footer(bytes)?;
let header = Header::deserialize(&mut bytes)?;
match header.codec_type {
FastFieldCodecType::Bitpacked => open_specific_codec::<BitpackedCodec, _>(bytes, &header),
@@ -161,7 +91,7 @@ pub fn open<T: MonotonicallyMappableToU64 + fmt::Debug>(
}
}
fn open_specific_codec<C: FastFieldCodec, Item: MonotonicallyMappableToU64 + fmt::Debug>(
fn open_specific_codec<C: FastFieldCodec, Item: MonotonicallyMappableToU64>(
bytes: OwnedBytes,
header: &Header,
) -> io::Result<Arc<dyn Column<Item>>> {
@@ -169,15 +99,11 @@ fn open_specific_codec<C: FastFieldCodec, Item: MonotonicallyMappableToU64 + fmt
let reader = C::open_from_bytes(bytes, normalized_header)?;
let min_value = header.min_value;
if let Some(gcd) = header.gcd {
let mapping = StrictlyMonotonicMappingInverter::from(
StrictlyMonotonicMappingToInternalGCDBaseval::new(gcd.get(), min_value),
);
Ok(Arc::new(monotonic_map_column(reader, mapping)))
let monotonic_mapping = move |val: u64| Item::from_u64(min_value + val * gcd.get());
Ok(Arc::new(monotonic_map_column(reader, monotonic_mapping)))
} else {
let mapping = StrictlyMonotonicMappingInverter::from(
StrictlyMonotonicMappingToInternalBaseval::new(min_value),
);
Ok(Arc::new(monotonic_map_column(reader, mapping)))
let monotonic_mapping = move |val: u64| Item::from_u64(min_value + val);
Ok(Arc::new(monotonic_map_column(reader, monotonic_mapping)))
}
}
@@ -197,7 +123,7 @@ trait FastFieldCodec: 'static {
///
/// The column iterator should be preferred over using column `get_val` method for
/// performance reasons.
fn serialize(column: &dyn Column, write: &mut impl Write) -> io::Result<()>;
fn serialize(column: &dyn Column<u64>, write: &mut impl Write) -> io::Result<()>;
/// Returns an estimate of the compression ratio.
/// If the codec is not applicable, returns `None`.
@@ -206,10 +132,9 @@ trait FastFieldCodec: 'static {
///
/// It could make sense to also return a value representing
/// computational complexity.
fn estimate(column: &dyn Column) -> Option<f32>;
fn estimate(column: &impl Column) -> Option<f32>;
}
/// The list of all available codecs for u64 convertible data.
pub const ALL_CODEC_TYPES: [FastFieldCodecType; 3] = [
FastFieldCodecType::Bitpacked,
FastFieldCodecType::BlockwiseLinear,
@@ -218,7 +143,6 @@ pub const ALL_CODEC_TYPES: [FastFieldCodecType; 3] = [
#[cfg(test)]
mod tests {
use proptest::prelude::*;
use proptest::strategy::Strategy;
use proptest::{prop_oneof, proptest};
@@ -244,32 +168,15 @@ mod tests {
let actual_compression = out.len() as f32 / (data.len() as f32 * 8.0);
let reader = crate::open::<u64>(OwnedBytes::new(out)).unwrap();
assert_eq!(reader.num_vals(), data.len() as u32);
assert_eq!(reader.num_vals(), data.len() as u64);
for (doc, orig_val) in data.iter().copied().enumerate() {
let val = reader.get_val(doc as u32);
let val = reader.get_val(doc as u64);
assert_eq!(
val, orig_val,
"val `{val}` does not match orig_val {orig_val:?}, in data set {name}, data \
`{data:?}`",
);
}
if !data.is_empty() {
let test_rand_idx = rand::thread_rng().gen_range(0..=data.len() - 1);
let expected_positions: Vec<u32> = data
.iter()
.enumerate()
.filter(|(_, el)| **el == data[test_rand_idx])
.map(|(pos, _)| pos as u32)
.collect();
let mut positions = Vec::new();
reader.get_docids_for_value_range(
data[test_rand_idx]..=data[test_rand_idx],
0..data.len() as u32,
&mut positions,
);
assert_eq!(expected_positions, positions);
}
Some((estimation, actual_compression))
}
@@ -322,9 +229,6 @@ mod tests {
pub fn get_codec_test_datasets() -> Vec<(Vec<u64>, &'static str)> {
let mut data_and_names = vec![];
let data = vec![10];
data_and_names.push((data, "minimal test"));
let data = (10..=10_000_u64).collect::<Vec<_>>();
data_and_names.push((data, "simple monotonically increasing"));
@@ -332,9 +236,6 @@ mod tests {
vec![5, 6, 7, 8, 9, 10, 99, 100],
"offset in linear interpol",
));
data_and_names.push((vec![3, 18446744073709551613, 5], "docid range regression"));
data_and_names.push((vec![5, 50, 3, 13, 1, 1000, 35], "rand small"));
data_and_names.push((vec![10], "single value"));
@@ -411,7 +312,7 @@ mod tests {
#[test]
fn estimation_test_bad_interpolation_case_monotonically_increasing() {
let mut data: Vec<u64> = (201..=20000_u64).collect();
let mut data: Vec<u64> = (200..=20000_u64).collect();
data.push(1_000_000);
let data: VecColumn = data.as_slice().into();
@@ -485,7 +386,7 @@ mod bench {
b.iter(|| {
let mut sum = 0u64;
for pos in value_iter() {
let val = col.get_val(pos as u32);
let val = col.get_val(pos as u64);
sum = sum.wrapping_add(val);
}
sum
@@ -497,7 +398,7 @@ mod bench {
b.iter(|| {
let mut sum = 0u64;
for pos in value_iter() {
let val = col.get_val(pos as u32);
let val = col.get_val(pos as u64);
sum = sum.wrapping_add(val);
}
sum

60
fastfield_codecs/src/line.rs
View File

@@ -1,5 +1,5 @@
use std::io;
use std::num::NonZeroU32;
use std::num::NonZeroU64;
use common::{BinarySerializable, VInt};
@@ -29,7 +29,7 @@ pub struct Line {
/// compute_slope(y0, y1)
/// = compute_slope(y0 + X % 2^64, y1 + X % 2^64)
/// `
fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU32) -> u64 {
fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU64) -> u64 {
let dy = y1.wrapping_sub(y0);
let sign = dy <= (1 << 63);
let abs_dy = if sign {
@@ -43,7 +43,7 @@ fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU32) -> u64 {
return 0u64;
}
let abs_slope = (abs_dy << 32) / num_vals.get() as u64;
let abs_slope = (abs_dy << 32) / num_vals.get();
if sign {
abs_slope
} else {
@@ -62,43 +62,30 @@ fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU32) -> u64 {
impl Line {
#[inline(always)]
pub fn eval(&self, x: u32) -> u64 {
let linear_part = ((x as u64).wrapping_mul(self.slope) >> 32) as i32 as u64;
pub fn eval(&self, x: u64) -> u64 {
let linear_part = (x.wrapping_mul(self.slope) >> 32) as i32 as u64;
self.intercept.wrapping_add(linear_part)
}
// Same as train, but the intercept is only estimated from provided sample positions
pub fn estimate(sample_positions_and_values: &[(u64, u64)]) -> Self {
let first_val = sample_positions_and_values[0].1;
let last_val = sample_positions_and_values[sample_positions_and_values.len() - 1].1;
let num_vals = sample_positions_and_values[sample_positions_and_values.len() - 1].0 + 1;
Self::train_from(
first_val,
last_val,
num_vals as u32,
sample_positions_and_values.iter().cloned(),
)
pub fn estimate(ys: &dyn Column, sample_positions: &[u64]) -> Self {
Self::train_from(ys, sample_positions.iter().cloned())
}
// Intercept is only computed from provided positions
fn train_from(
first_val: u64,
last_val: u64,
num_vals: u32,
positions_and_values: impl Iterator<Item = (u64, u64)>,
) -> Self {
// TODO replace with let else
let idx_last_val = if let Some(idx_last_val) = NonZeroU32::new(num_vals - 1) {
idx_last_val
fn train_from(ys: &dyn Column, positions: impl Iterator<Item = u64>) -> Self {
let last_idx = if let Some(last_idx) = NonZeroU64::new(ys.num_vals() - 1) {
last_idx
} else {
return Line::default();
};
let y0 = first_val;
let y1 = last_val;
let mut ys_reader = ys.reader();
let y0 = ys_reader.seek(0);
let y1 = ys_reader.seek(last_idx.get());
// We first independently pick our slope.
let slope = compute_slope(y0, y1, idx_last_val);
let slope = compute_slope(y0, y1, last_idx);
// We picked our slope. Note that it does not have to be perfect.
// Now we need to compute the best intercept.
@@ -128,8 +115,12 @@ impl Line {
intercept: 0,
};
let heuristic_shift = y0.wrapping_sub(MID_POINT);
line.intercept = positions_and_values
.map(|(pos, y)| y.wrapping_sub(line.eval(pos as u32)))
let mut ys_reader = ys.reader();
line.intercept = positions
.map(|pos| {
let y = ys_reader.seek(pos);
y.wrapping_sub(line.eval(pos))
})
.min_by_key(|&val| val.wrapping_sub(heuristic_shift))
.unwrap_or(0u64); //< Never happens.
line
@@ -146,14 +137,7 @@ impl Line {
/// This function is only invariable by translation if all of the
/// `ys` are packaged into half of the space. (See heuristic below)
pub fn train(ys: &dyn Column) -> Self {
let first_val = ys.iter().next().unwrap();
let last_val = ys.iter().nth(ys.num_vals() as usize - 1).unwrap();
Self::train_from(
first_val,
last_val,
ys.num_vals(),
ys.iter().enumerate().map(|(pos, val)| (pos as u64, val)),
)
Self::train_from(ys, 0..ys.num_vals())
}
}
@@ -199,7 +183,7 @@ mod tests {
let line = Line::train(&VecColumn::from(&ys));
ys.iter()
.enumerate()
.map(|(x, y)| y.wrapping_sub(line.eval(x as u32)))
.map(|(x, y)| y.wrapping_sub(line.eval(x as u64)))
.max()
}

44
fastfield_codecs/src/linear.rs
View File

@@ -19,7 +19,7 @@ pub struct LinearReader {
impl Column for LinearReader {
#[inline]
fn get_val(&self, doc: u32) -> u64 {
fn get_val(&self, doc: u64) -> u64 {
let interpoled_val: u64 = self.linear_params.line.eval(doc);
let bitpacked_diff = self.linear_params.bit_unpacker.get(doc, &self.data);
interpoled_val.wrapping_add(bitpacked_diff)
@@ -37,7 +37,7 @@ impl Column for LinearReader {
}
#[inline]
fn num_vals(&self) -> u32 {
fn num_vals(&self) -> u64 {
self.header.num_vals
}
}
@@ -89,11 +89,10 @@ impl FastFieldCodec for LinearCodec {
assert_eq!(column.min_value(), 0);
let line = Line::train(column);
let max_offset_from_line = column
.iter()
let max_offset_from_line = crate::iter_from_reader(column.reader())
.enumerate()
.map(|(pos, actual_value)| {
let calculated_value = line.eval(pos as u32);
let calculated_value = line.eval(pos as u64);
actual_value.wrapping_sub(calculated_value)
})
.max()
@@ -107,8 +106,13 @@ impl FastFieldCodec for LinearCodec {
linear_params.serialize(write)?;
let mut bit_packer = BitPacker::new();
for (pos, actual_value) in column.iter().enumerate() {
let calculated_value = line.eval(pos as u32);
let mut col_reader = column.reader();
for pos in 0.. {
if !col_reader.advance() {
break;
}
let actual_value = col_reader.get();
let calculated_value = line.eval(pos as u64);
let offset = actual_value.wrapping_sub(calculated_value);
bit_packer.write(offset, num_bits, write)?;
}
@@ -121,26 +125,25 @@ impl FastFieldCodec for LinearCodec {
/// where the local maxima for the deviation of the calculated value are and
/// the offset to shift all values to >=0 is also unknown.
#[allow(clippy::question_mark)]
fn estimate(column: &dyn Column) -> Option<f32> {
fn estimate(column: &impl Column) -> Option<f32> {
if column.num_vals() < 3 {
return None; // disable compressor for this case
}
let limit_num_vals = column.num_vals().min(100_000);
// let's sample at 0%, 5%, 10% .. 95%, 100%
let num_vals = column.num_vals() as f32 / 100.0;
let sample_positions = (0..20)
.map(|pos| (num_vals * pos as f32 * 5.0) as u64)
.collect::<Vec<_>>();
let num_samples = 100;
let step_size = (limit_num_vals / num_samples).max(1); // 20 samples
let mut sample_positions_and_values: Vec<_> = Vec::new();
for (pos, val) in column.iter().enumerate().step_by(step_size as usize) {
sample_positions_and_values.push((pos as u64, val));
}
let line = Line::estimate(column, &sample_positions);
let line = Line::estimate(&sample_positions_and_values);
let estimated_bit_width = sample_positions_and_values
let mut column_reader = column.reader();
let estimated_bit_width = sample_positions
.into_iter()
.map(|(pos, actual_value)| {
let interpolated_val = line.eval(pos as u32);
.map(|pos| {
let actual_value = column_reader.seek(pos);
let interpolated_val = line.eval(pos as u64);
actual_value.wrapping_sub(interpolated_val)
})
.map(|diff| ((diff as f32 * 1.5) * 2.0) as u64)
@@ -148,7 +151,6 @@ impl FastFieldCodec for LinearCodec {
.max()
.unwrap_or(0);
// Extrapolate to whole column
let num_bits = (estimated_bit_width as u64 * column.num_vals() as u64) + 64;
let num_bits_uncompressed = 64 * column.num_vals();
Some(num_bits as f32 / num_bits_uncompressed as f32)

17
fastfield_codecs/src/main.rs
View File

@@ -90,7 +90,7 @@ fn bench_ip() {
{
let mut data = vec![];
for dataset in dataset.chunks(500_000) {
serialize_u128(|| dataset.iter().cloned(), dataset.len() as u32, &mut data).unwrap();
serialize_u128(VecColumn::from(dataset), &mut data).unwrap();
}
let compression = data.len() as f64 / (dataset.len() * 16) as f64;
println!("Compression 50_000 chunks {:.4}", compression);
@@ -101,10 +101,7 @@ fn bench_ip() {
}
let mut data = vec![];
{
print_time!("creation");
serialize_u128(|| dataset.iter().cloned(), dataset.len() as u32, &mut data).unwrap();
}
serialize_u128(VecColumn::from(&dataset), &mut data).unwrap();
let compression = data.len() as f64 / (dataset.len() * 16) as f64;
println!("Compression {:.2}", compression);
@@ -113,17 +110,11 @@ fn bench_ip() {
(data.len() * 8) as f32 / dataset.len() as f32
);
let decompressor = open_u128::<u128>(OwnedBytes::new(data)).unwrap();
let decompressor = open_u128(OwnedBytes::new(data)).unwrap();
// Sample some ranges
let mut doc_values = Vec::new();
for value in dataset.iter().take(1110).skip(1100).cloned() {
doc_values.clear();
print_time!("get range");
decompressor.get_docids_for_value_range(
value..=value,
0..decompressor.num_vals(),
&mut doc_values,
);
let doc_values = decompressor.get_between_vals(value..=value);
println!("{:?}", doc_values.len());
}
}

255
fastfield_codecs/src/monotonic_mapping.rs
View File

@@ -1,16 +1,4 @@
use std::fmt;
use std::marker::PhantomData;
use std::ops::RangeInclusive;
use fastdivide::DividerU64;
use crate::MonotonicallyMappableToU128;
/// Monotonic maps a value to u64 value space.
/// Monotonic mapping enables `PartialOrd` on u64 space without conversion to original space.
pub trait MonotonicallyMappableToU64:
'static + PartialOrd + Copy + Send + Sync + fmt::Debug
{
pub trait MonotonicallyMappableToU64: 'static + PartialOrd + Copy + Send + Sync {
/// Converts a value to u64.
///
/// Internally all fast field values are encoded as u64.
@@ -23,211 +11,6 @@ pub trait MonotonicallyMappableToU64:
fn from_u64(val: u64) -> Self;
}
/// Values need to be strictly monotonic mapped to a `Internal` value (u64 or u128) that can be
/// used in fast field codecs.
///
/// The monotonic mapping is required so that `PartialOrd` can be used on `Internal` without
/// converting to `External`.
///
/// All strictly monotonic functions are invertible because they are guaranteed to have a one-to-one
/// mapping from their range to their domain. The `inverse` method is required when opening a codec,
/// so a value can be converted back to its original domain (e.g. ip address or f64) from its
/// internal representation.
pub trait StrictlyMonotonicFn<External: Copy, Internal: Copy> {
/// Strictly monotonically maps the value from External to Internal.
fn mapping(&self, inp: External) -> Internal;
/// Inverse of `mapping`. Maps the value from Internal to External.
fn inverse(&self, out: Internal) -> External;
/// Maps a user provded value from External to Internal.
/// It may be necessary to coerce the value if it is outside the value space.
/// In that case it tries to find the next greater value in the value space.
///
/// Returns a bool to mark if a value was outside the value space and had to be coerced _up_.
/// With that information we can detect if two values in a range both map outside the same value
/// space.
///
/// coerce_up means the next valid upper value in the value space will be chosen if the value
/// has to be coerced.
fn mapping_coerce(&self, inp: RangeInclusive<External>) -> RangeInclusive<Internal> {
self.mapping(*inp.start())..=self.mapping(*inp.end())
}
/// Inverse of `mapping_coerce`.
fn inverse_coerce(&self, out: RangeInclusive<Internal>) -> RangeInclusive<External> {
self.inverse(*out.start())..=self.inverse(*out.end())
}
}
/// Inverts a strictly monotonic mapping from `StrictlyMonotonicFn<A, B>` to
/// `StrictlyMonotonicFn<B, A>`.
///
/// # Warning
///
/// This type comes with a footgun. A type being strictly monotonic does not impose that the inverse
/// mapping is strictly monotonic over the entire space External. e.g. a -> a * 2. Use at your own
/// risks.
pub(crate) struct StrictlyMonotonicMappingInverter<T> {
orig_mapping: T,
}
impl<T> From<T> for StrictlyMonotonicMappingInverter<T> {
fn from(orig_mapping: T) -> Self {
Self { orig_mapping }
}
}
impl<From, To, T> StrictlyMonotonicFn<To, From> for StrictlyMonotonicMappingInverter<T>
where
T: StrictlyMonotonicFn<From, To>,
From: Copy,
To: Copy,
{
fn mapping(&self, val: To) -> From {
self.orig_mapping.inverse(val)
}
fn inverse(&self, val: From) -> To {
self.orig_mapping.mapping(val)
}
#[inline]
fn mapping_coerce(&self, inp: RangeInclusive<To>) -> RangeInclusive<From> {
self.orig_mapping.inverse_coerce(inp)
}
#[inline]
fn inverse_coerce(&self, out: RangeInclusive<From>) -> RangeInclusive<To> {
self.orig_mapping.mapping_coerce(out)
}
}
/// Applies the strictly monotonic mapping from `T` without any additional changes.
pub(crate) struct StrictlyMonotonicMappingToInternal<T> {
_phantom: PhantomData<T>,
}
impl<T> StrictlyMonotonicMappingToInternal<T> {
pub(crate) fn new() -> StrictlyMonotonicMappingToInternal<T> {
Self {
_phantom: PhantomData,
}
}
}
impl<External: MonotonicallyMappableToU128, T: MonotonicallyMappableToU128>
StrictlyMonotonicFn<External, u128> for StrictlyMonotonicMappingToInternal<T>
where T: MonotonicallyMappableToU128
{
fn mapping(&self, inp: External) -> u128 {
External::to_u128(inp)
}
fn inverse(&self, out: u128) -> External {
External::from_u128(out)
}
}
impl<External: MonotonicallyMappableToU64, T: MonotonicallyMappableToU64>
StrictlyMonotonicFn<External, u64> for StrictlyMonotonicMappingToInternal<T>
where T: MonotonicallyMappableToU64
{
fn mapping(&self, inp: External) -> u64 {
External::to_u64(inp)
}
fn inverse(&self, out: u64) -> External {
External::from_u64(out)
}
}
/// Mapping dividing by gcd and a base value.
///
/// The function is assumed to be only called on values divided by passed
/// gcd value. (It is necessary for the function to be monotonic.)
pub(crate) struct StrictlyMonotonicMappingToInternalGCDBaseval {
gcd_divider: DividerU64,
gcd: u64,
min_value: u64,
}
impl StrictlyMonotonicMappingToInternalGCDBaseval {
pub(crate) fn new(gcd: u64, min_value: u64) -> Self {
let gcd_divider = DividerU64::divide_by(gcd);
Self {
gcd_divider,
gcd,
min_value,
}
}
}
impl<External: MonotonicallyMappableToU64> StrictlyMonotonicFn<External, u64>
for StrictlyMonotonicMappingToInternalGCDBaseval
{
fn mapping(&self, inp: External) -> u64 {
self.gcd_divider
.divide(External::to_u64(inp) - self.min_value)
}
fn inverse(&self, out: u64) -> External {
External::from_u64(self.min_value + out * self.gcd)
}
#[inline]
#[allow(clippy::reversed_empty_ranges)]
fn mapping_coerce(&self, inp: RangeInclusive<External>) -> RangeInclusive<u64> {
let end = External::to_u64(*inp.end());
if end < self.min_value || inp.end() < inp.start() {
return 1..=0;
}
let map_coerce = |mut inp, coerce_up| {
let inp_lower_bound = self.inverse(0);
if inp < inp_lower_bound {
inp = inp_lower_bound;
}
let val = External::to_u64(inp);
let need_coercion = coerce_up && (val - self.min_value) % self.gcd != 0;
let mut mapped_val = self.mapping(inp);
if need_coercion {
mapped_val += 1;
}
mapped_val
};
let start = map_coerce(*inp.start(), true);
let end = map_coerce(*inp.end(), false);
start..=end
}
}
/// Strictly monotonic mapping with a base value.
pub(crate) struct StrictlyMonotonicMappingToInternalBaseval {
min_value: u64,
}
impl StrictlyMonotonicMappingToInternalBaseval {
pub(crate) fn new(min_value: u64) -> Self {
Self { min_value }
}
}
impl<External: MonotonicallyMappableToU64> StrictlyMonotonicFn<External, u64>
for StrictlyMonotonicMappingToInternalBaseval
{
#[inline]
#[allow(clippy::reversed_empty_ranges)]
fn mapping_coerce(&self, inp: RangeInclusive<External>) -> RangeInclusive<u64> {
if External::to_u64(*inp.end()) < self.min_value {
return 1..=0;
}
let start = self.mapping(External::to_u64(*inp.start()).max(self.min_value));
let end = self.mapping(External::to_u64(*inp.end()));
start..=end
}
fn mapping(&self, val: External) -> u64 {
External::to_u64(val) - self.min_value
}
fn inverse(&self, val: u64) -> External {
External::from_u64(self.min_value + val)
}
}
impl MonotonicallyMappableToU64 for u64 {
fn to_u64(self) -> u64 {
self
@@ -253,7 +36,11 @@ impl MonotonicallyMappableToU64 for i64 {
impl MonotonicallyMappableToU64 for bool {
#[inline(always)]
fn to_u64(self) -> u64 {
u64::from(self)
if self {
1
} else {
0
}
}
#[inline(always)]
@@ -271,33 +58,3 @@ impl MonotonicallyMappableToU64 for f64 {
common::u64_to_f64(val)
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn strictly_monotonic_test() {
// identity mapping
test_round_trip(&StrictlyMonotonicMappingToInternal::<u64>::new(), 100u64);
// round trip to i64
test_round_trip(&StrictlyMonotonicMappingToInternal::<i64>::new(), 100u64);
// identity mapping
test_round_trip(&StrictlyMonotonicMappingToInternal::<u128>::new(), 100u128);
// base value to i64 round trip
let mapping = StrictlyMonotonicMappingToInternalBaseval::new(100);
test_round_trip::<_, _, u64>(&mapping, 100i64);
// base value and gcd to u64 round trip
let mapping = StrictlyMonotonicMappingToInternalGCDBaseval::new(10, 100);
test_round_trip::<_, _, u64>(&mapping, 100u64);
}
fn test_round_trip<T: StrictlyMonotonicFn<K, L>, K: std::fmt::Debug + Eq + Copy, L: Copy>(
mapping: &T,
test_val: K,
) {
assert_eq!(mapping.inverse(mapping.mapping(test_val)), test_val);
}
}

43
fastfield_codecs/src/monotonic_mapping_u128.rs
View File

@@ -1,43 +0,0 @@
use std::fmt;
use std::net::Ipv6Addr;
/// Montonic maps a value to u128 value space
/// Monotonic mapping enables `PartialOrd` on u128 space without conversion to original space.
pub trait MonotonicallyMappableToU128:
'static + PartialOrd + Copy + Send + Sync + fmt::Debug
{
/// Converts a value to u128.
///
/// Internally all fast field values are encoded as u64.
fn to_u128(self) -> u128;
/// Converts a value from u128
///
/// Internally all fast field values are encoded as u64.
/// **Note: To be used for converting encoded Term, Posting values.**
fn from_u128(val: u128) -> Self;
}
impl MonotonicallyMappableToU128 for u128 {
fn to_u128(self) -> u128 {
self
}
fn from_u128(val: u128) -> Self {
val
}
}
impl MonotonicallyMappableToU128 for Ipv6Addr {
fn to_u128(self) -> u128 {
ip_to_u128(self)
}
fn from_u128(val: u128) -> Self {
Ipv6Addr::from(val.to_be_bytes())
}
}
fn ip_to_u128(ip_addr: Ipv6Addr) -> u128 {
u128::from_be_bytes(ip_addr.octets())
}

144
fastfield_codecs/src/null_index_footer.rs
View File

@@ -1,144 +0,0 @@
use std::io::{self, Write};
use std::ops::Range;
use common::{BinarySerializable, CountingWriter, VInt};
use ownedbytes::OwnedBytes;
#[derive(Debug, Clone, Copy, Eq, PartialEq)]
pub(crate) enum FastFieldCardinality {
Single = 1,
}
impl BinarySerializable for FastFieldCardinality {
fn serialize<W: Write>(&self, wrt: &mut W) -> io::Result<()> {
self.to_code().serialize(wrt)
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let code = u8::deserialize(reader)?;
let codec_type: Self = Self::from_code(code)
.ok_or_else(|| io::Error::new(io::ErrorKind::InvalidData, "Unknown code `{code}.`"))?;
Ok(codec_type)
}
}
impl FastFieldCardinality {
pub(crate) fn to_code(self) -> u8 {
self as u8
}
pub(crate) fn from_code(code: u8) -> Option<Self> {
match code {
1 => Some(Self::Single),
_ => None,
}
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub(crate) enum NullIndexCodec {
Full = 1,
}
impl BinarySerializable for NullIndexCodec {
fn serialize<W: Write>(&self, wrt: &mut W) -> io::Result<()> {
self.to_code().serialize(wrt)
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let code = u8::deserialize(reader)?;
let codec_type: Self = Self::from_code(code)
.ok_or_else(|| io::Error::new(io::ErrorKind::InvalidData, "Unknown code `{code}.`"))?;
Ok(codec_type)
}
}
impl NullIndexCodec {
pub(crate) fn to_code(self) -> u8 {
self as u8
}
pub(crate) fn from_code(code: u8) -> Option<Self> {
match code {
1 => Some(Self::Full),
_ => None,
}
}
}
#[derive(Debug, Clone, Eq, PartialEq)]
pub(crate) struct NullIndexFooter {
pub(crate) cardinality: FastFieldCardinality,
pub(crate) null_index_codec: NullIndexCodec,
// Unused for NullIndexCodec::Full
pub(crate) null_index_byte_range: Range<u64>,
}
impl BinarySerializable for NullIndexFooter {
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
self.cardinality.serialize(writer)?;
self.null_index_codec.serialize(writer)?;
VInt(self.null_index_byte_range.start).serialize(writer)?;
VInt(self.null_index_byte_range.end - self.null_index_byte_range.start)
.serialize(writer)?;
Ok(())
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let cardinality = FastFieldCardinality::deserialize(reader)?;
let null_index_codec = NullIndexCodec::deserialize(reader)?;
let null_index_byte_range_start = VInt::deserialize(reader)?.0;
let null_index_byte_range_end = VInt::deserialize(reader)?.0 + null_index_byte_range_start;
Ok(Self {
cardinality,
null_index_codec,
null_index_byte_range: null_index_byte_range_start..null_index_byte_range_end,
})
}
}
pub(crate) fn append_null_index_footer(
output: &mut impl io::Write,
null_index_footer: NullIndexFooter,
) -> io::Result<()> {
let mut counting_write = CountingWriter::wrap(output);
null_index_footer.serialize(&mut counting_write)?;
let footer_payload_len = counting_write.written_bytes();
BinarySerializable::serialize(&(footer_payload_len as u16), &mut counting_write)?;
Ok(())
}
pub(crate) fn read_null_index_footer(
data: OwnedBytes,
) -> io::Result<(OwnedBytes, NullIndexFooter)> {
let (data, null_footer_length_bytes) = data.rsplit(2);
let footer_length = u16::deserialize(&mut null_footer_length_bytes.as_slice())?;
let (data, null_index_footer_bytes) = data.rsplit(footer_length as usize);
let null_index_footer = NullIndexFooter::deserialize(&mut null_index_footer_bytes.as_ref())?;
Ok((data, null_index_footer))
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn null_index_footer_deser_test() {
let null_index_footer = NullIndexFooter {
cardinality: FastFieldCardinality::Single,
null_index_codec: NullIndexCodec::Full,
null_index_byte_range: 100..120,
};
let mut out = vec![];
null_index_footer.serialize(&mut out).unwrap();
assert_eq!(
null_index_footer,
NullIndexFooter::deserialize(&mut &out[..]).unwrap()
);
}
}

161
fastfield_codecs/src/serialize.rs
View File

@@ -17,47 +17,38 @@
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
use std::io;
use std::num::NonZeroU64;
use std::sync::Arc;
use std::{fmt, io};
use common::{BinarySerializable, VInt};
use fastdivide::DividerU64;
use log::warn;
use ownedbytes::OwnedBytes;
use crate::bitpacked::BitpackedCodec;
use crate::blockwise_linear::BlockwiseLinearCodec;
use crate::compact_space::CompactSpaceCompressor;
use crate::format_version::append_format_version;
use crate::linear::LinearCodec;
use crate::monotonic_mapping::{
StrictlyMonotonicFn, StrictlyMonotonicMappingToInternal,
StrictlyMonotonicMappingToInternalGCDBaseval,
};
use crate::null_index_footer::{
append_null_index_footer, FastFieldCardinality, NullIndexCodec, NullIndexFooter,
};
use crate::{
monotonic_map_column, Column, FastFieldCodec, FastFieldCodecType, MonotonicallyMappableToU64,
U128FastFieldCodecType, VecColumn, ALL_CODEC_TYPES,
iter_from_reader, monotonic_map_column, Column, FastFieldCodec, FastFieldCodecType,
MonotonicallyMappableToU64, VecColumn, ALL_CODEC_TYPES,
};
/// The normalized header gives some parameters after applying the following
/// normalization of the vector:
/// `val -> (val - min_value) / gcd`
/// val -> (val - min_value) / gcd
///
/// By design, after normalization, `min_value = 0` and `gcd = 1`.
#[derive(Debug, Copy, Clone)]
pub struct NormalizedHeader {
/// The number of values in the underlying column.
pub num_vals: u32,
/// The max value of the underlying column.
pub num_vals: u64,
pub max_value: u64,
}
#[derive(Debug, Copy, Clone)]
pub(crate) struct Header {
pub num_vals: u32,
pub num_vals: u64,
pub min_value: u64,
pub max_value: u64,
pub gcd: Option<NonZeroU64>,
@@ -66,11 +57,8 @@ pub(crate) struct Header {
impl Header {
pub fn normalized(self) -> NormalizedHeader {
let gcd = self.gcd.map(|gcd| gcd.get()).unwrap_or(1);
let gcd_min_val_mapping =
StrictlyMonotonicMappingToInternalGCDBaseval::new(gcd, self.min_value);
let max_value = gcd_min_val_mapping.mapping(self.max_value);
let max_value =
(self.max_value - self.min_value) / self.gcd.map(|gcd| gcd.get()).unwrap_or(1);
NormalizedHeader {
num_vals: self.num_vals,
max_value,
@@ -78,7 +66,10 @@ impl Header {
}
pub fn normalize_column<C: Column>(&self, from_column: C) -> impl Column {
normalize_column(from_column, self.min_value, self.gcd)
let min_value = self.min_value;
let gcd = self.gcd.map(|gcd| gcd.get()).unwrap_or(1);
let divider = DividerU64::divide_by(gcd);
monotonic_map_column(from_column, move |val| divider.divide(val - min_value))
}
pub fn compute_header(
@@ -88,10 +79,12 @@ impl Header {
let num_vals = column.num_vals();
let min_value = column.min_value();
let max_value = column.max_value();
let gcd = crate::gcd::find_gcd(column.iter().map(|val| val - min_value))
.filter(|gcd| gcd.get() > 1u64);
let normalized_column = normalize_column(column, min_value, gcd);
let codec_type = detect_codec(normalized_column, codecs)?;
let gcd =
crate::gcd::find_gcd(iter_from_reader(column.reader()).map(|val| val - min_value))
.filter(|gcd| gcd.get() > 1u64);
let divider = DividerU64::divide_by(gcd.map(|gcd| gcd.get()).unwrap_or(1u64));
let shifted_column = monotonic_map_column(&column, |val| divider.divide(val - min_value));
let codec_type = detect_codec(shifted_column, codecs)?;
Some(Header {
num_vals,
min_value,
@@ -102,42 +95,9 @@ impl Header {
}
}
#[derive(Debug, Copy, Clone, PartialEq, Eq)]
pub(crate) struct U128Header {
pub num_vals: u32,
pub codec_type: U128FastFieldCodecType,
}
impl BinarySerializable for U128Header {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
VInt(self.num_vals as u64).serialize(writer)?;
self.codec_type.serialize(writer)?;
Ok(())
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let num_vals = VInt::deserialize(reader)?.0 as u32;
let codec_type = U128FastFieldCodecType::deserialize(reader)?;
Ok(U128Header {
num_vals,
codec_type,
})
}
}
pub fn normalize_column<C: Column>(
from_column: C,
min_value: u64,
gcd: Option<NonZeroU64>,
) -> impl Column {
let gcd = gcd.map(|gcd| gcd.get()).unwrap_or(1);
let mapping = StrictlyMonotonicMappingToInternalGCDBaseval::new(gcd, min_value);
monotonic_map_column(from_column, mapping)
}
impl BinarySerializable for Header {
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
VInt(self.num_vals as u64).serialize(writer)?;
VInt(self.num_vals).serialize(writer)?;
VInt(self.min_value).serialize(writer)?;
VInt(self.max_value - self.min_value).serialize(writer)?;
if let Some(gcd) = self.gcd {
@@ -150,7 +110,7 @@ impl BinarySerializable for Header {
}
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
let num_vals = VInt::deserialize(reader)?.0 as u32;
let num_vals = VInt::deserialize(reader)?.0;
let min_value = VInt::deserialize(reader)?.0;
let amplitude = VInt::deserialize(reader)?.0;
let max_value = min_value + amplitude;
@@ -166,21 +126,16 @@ impl BinarySerializable for Header {
}
}
/// Return estimated compression for given codec in the value range [0.0..1.0], where 1.0 means no
/// compression.
pub fn estimate<T: MonotonicallyMappableToU64 + fmt::Debug>(
pub fn estimate<T: MonotonicallyMappableToU64>(
typed_column: impl Column<T>,
codec_type: FastFieldCodecType,
) -> Option<f32> {
let column = monotonic_map_column(typed_column, StrictlyMonotonicMappingToInternal::<T>::new());
let column = monotonic_map_column(typed_column, T::to_u64);
let min_value = column.min_value();
let gcd = crate::gcd::find_gcd(column.iter().map(|val| val - min_value))
let gcd = crate::gcd::find_gcd(iter_from_reader(column.reader()).map(|val| val - min_value))
.filter(|gcd| gcd.get() > 1u64);
let mapping = StrictlyMonotonicMappingToInternalGCDBaseval::new(
gcd.map(|gcd| gcd.get()).unwrap_or(1u64),
min_value,
);
let normalized_column = monotonic_map_column(&column, mapping);
let divider = DividerU64::divide_by(gcd.map(|gcd| gcd.get()).unwrap_or(1u64));
let normalized_column = monotonic_map_column(&column, |val| divider.divide(val - min_value));
match codec_type {
FastFieldCodecType::Bitpacked => BitpackedCodec::estimate(&normalized_column),
FastFieldCodecType::Linear => LinearCodec::estimate(&normalized_column),
@@ -188,38 +143,25 @@ pub fn estimate<T: MonotonicallyMappableToU64 + fmt::Debug>(
}
}
/// Serializes u128 values with the compact space codec.
pub fn serialize_u128<F: Fn() -> I, I: Iterator<Item = u128>>(
iter_gen: F,
num_vals: u32,
pub fn serialize_u128(
typed_column: impl Column<u128>,
output: &mut impl io::Write,
) -> io::Result<()> {
let header = U128Header {
num_vals,
codec_type: U128FastFieldCodecType::CompactSpace,
};
header.serialize(output)?;
let compressor = CompactSpaceCompressor::train_from(iter_gen(), num_vals);
compressor.compress_into(iter_gen(), output).unwrap();
let null_index_footer = NullIndexFooter {
cardinality: FastFieldCardinality::Single,
null_index_codec: NullIndexCodec::Full,
null_index_byte_range: 0..0,
};
append_null_index_footer(output, null_index_footer)?;
append_format_version(output)?;
// TODO write header, to later support more codecs
let compressor = CompactSpaceCompressor::train_from(&typed_column);
compressor
.compress_into(typed_column.reader(), output)
.unwrap();
Ok(())
}
/// Serializes the column with the codec with the best estimate on the data.
pub fn serialize<T: MonotonicallyMappableToU64 + fmt::Debug>(
pub fn serialize<T: MonotonicallyMappableToU64>(
typed_column: impl Column<T>,
output: &mut impl io::Write,
codecs: &[FastFieldCodecType],
) -> io::Result<()> {
let column = monotonic_map_column(typed_column, StrictlyMonotonicMappingToInternal::<T>::new());
let column = monotonic_map_column(typed_column, T::to_u64);
let header = Header::compute_header(&column, codecs).ok_or_else(|| {
io::Error::new(
io::ErrorKind::InvalidInput,
@@ -233,15 +175,6 @@ pub fn serialize<T: MonotonicallyMappableToU64 + fmt::Debug>(
let normalized_column = header.normalize_column(column);
assert_eq!(normalized_column.min_value(), 0u64);
serialize_given_codec(normalized_column, header.codec_type, output)?;
let null_index_footer = NullIndexFooter {
cardinality: FastFieldCardinality::Single,
null_index_codec: NullIndexCodec::Full,
null_index_byte_range: 0..0,
};
append_null_index_footer(output, null_index_footer)?;
append_format_version(output)?;
Ok(())
}
@@ -293,8 +226,7 @@ fn serialize_given_codec(
Ok(())
}
/// Helper function to serialize a column (autodetect from all codecs) and then open it
pub fn serialize_and_load<T: MonotonicallyMappableToU64 + Ord + Default + fmt::Debug>(
pub fn serialize_and_load<T: MonotonicallyMappableToU64 + Ord + Default>(
column: &[T],
) -> Arc<dyn Column<T>> {
let mut buffer = Vec::new();
@@ -306,22 +238,11 @@ pub fn serialize_and_load<T: MonotonicallyMappableToU64 + Ord + Default + fmt::D
mod tests {
use super::*;
#[test]
fn test_serialize_deserialize_u128_header() {
let original = U128Header {
num_vals: 11,
codec_type: U128FastFieldCodecType::CompactSpace,
};
let mut out = Vec::new();
original.serialize(&mut out).unwrap();
let restored = U128Header::deserialize(&mut &out[..]).unwrap();
assert_eq!(restored, original);
}
#[test]
fn test_serialize_deserialize() {
let original = [1u64, 5u64, 10u64];
let restored: Vec<u64> = serialize_and_load(&original[..]).iter().collect();
let restored: Vec<u64> =
crate::iter_from_reader(serialize_and_load(&original[..]).reader()).collect();
assert_eq!(&restored, &original[..]);
}
@@ -331,7 +252,7 @@ mod tests {
let col = VecColumn::from(&[false, true][..]);
serialize(col, &mut buffer, &ALL_CODEC_TYPES).unwrap();
// 5 bytes of header, 1 byte of value, 7 bytes of padding.
assert_eq!(buffer.len(), 3 + 5 + 8 + 4 + 2);
assert_eq!(buffer.len(), 5 + 8);
}
#[test]
@@ -340,7 +261,7 @@ mod tests {
let col = VecColumn::from(&[true][..]);
serialize(col, &mut buffer, &ALL_CODEC_TYPES).unwrap();
// 5 bytes of header, 0 bytes of value, 7 bytes of padding.
assert_eq!(buffer.len(), 3 + 5 + 7 + 4 + 2);
assert_eq!(buffer.len(), 5 + 7);
}
#[test]
@@ -350,6 +271,6 @@ mod tests {
let col = VecColumn::from(&vals[..]);
serialize(col, &mut buffer, &[FastFieldCodecType::Bitpacked]).unwrap();
// Values are stored over 3 bits.
assert_eq!(buffer.len(), 3 + 7 + (3 * 80 / 8) + 7 + 4 + 2);
assert_eq!(buffer.len(), 7 + (3 * 80 / 8) + 7);
}
}

6
ownedbytes/Cargo.toml
View File

@@ -1,14 +1,10 @@
[package]
authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
name = "ownedbytes"
version = "0.4.0"
version = "0.3.0"
edition = "2021"
description = "Expose data as static slice"
license = "MIT"
documentation = "https://docs.rs/ownedbytes/"
homepage = "https://github.com/quickwit-oss/tantivy"
repository = "https://github.com/quickwit-oss/tantivy"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]

15
ownedbytes/src/lib.rs
View File

@@ -80,21 +80,6 @@ impl OwnedBytes {
(left, right)
}
/// Splits the OwnedBytes into two OwnedBytes `(left, right)`.
///
/// Right will hold `split_len` bytes.
///
/// This operation is cheap and does not require to copy any memory.
/// On the other hand, both `left` and `right` retain a handle over
/// the entire slice of memory. In other words, the memory will only
/// be released when both left and right are dropped.
#[inline]
#[must_use]
pub fn rsplit(self, split_len: usize) -> (OwnedBytes, OwnedBytes) {
let data_len = self.data.len();
self.split(data_len - split_len)
}
/// Splits the right part of the `OwnedBytes` at the given offset.
///
/// `self` is truncated to `split_len`, left with the remaining bytes.

2
query-grammar/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-query-grammar"
version = "0.19.0"
version = "0.18.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]

67
query-grammar/src/query_grammar.rs
View File

@@ -5,8 +5,7 @@ use combine::parser::range::{take_while, take_while1};
use combine::parser::repeat::escaped;
use combine::parser::Parser;
use combine::{
attempt, between, choice, eof, many, many1, one_of, optional, parser, satisfy, sep_by,
skip_many1, value,
attempt, choice, eof, many, many1, one_of, optional, parser, satisfy, skip_many1, value,
};
use once_cell::sync::Lazy;
use regex::Regex;
@@ -63,20 +62,6 @@ fn word<'a>() -> impl Parser<&'a str, Output = String> {
})
}
// word variant that allows more characters, e.g. for range queries that don't allow field
// specifier
fn relaxed_word<'a>() -> impl Parser<&'a str, Output = String> {
(
satisfy(|c: char| {
!c.is_whitespace() && !['`', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
}),
many(satisfy(|c: char| {
!c.is_whitespace() && !['{', '}', '"', '[', ']', '(', ')'].contains(&c)
})),
)
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
}
/// Parses a date time according to rfc3339
/// 2015-08-02T18:54:42+02
/// 2021-04-13T19:46:26.266051969+00:00
@@ -196,8 +181,8 @@ fn spaces1<'a>() -> impl Parser<&'a str, Output = ()> {
fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let range_term_val = || {
attempt(date_time())
.or(word())
.or(negative_number())
.or(relaxed_word())
.or(char('*').with(value("*".to_string())))
};
@@ -265,17 +250,6 @@ fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
})
}
/// Function that parses a set out of a Stream
/// Supports ranges like: `IN [val1 val2 val3]`
fn set<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
let term_list = between(char('['), char(']'), sep_by(term_val(), spaces()));
let set_content = ((string("IN"), spaces()), term_list).map(|(_, elements)| elements);
(optional(attempt(field_name().skip(spaces()))), set_content)
.map(|(field, elements)| UserInputLeaf::Set { field, elements })
}
fn negate(expr: UserInputAst) -> UserInputAst {
expr.unary(Occur::MustNot)
}
@@ -290,7 +264,6 @@ fn leaf<'a>() -> impl Parser<&'a str, Output = UserInputAst> {
string("NOT").skip(spaces1()).with(leaf()).map(negate),
))
.or(attempt(range().map(UserInputAst::from)))
.or(attempt(set().map(UserInputAst::from)))
.or(literal().map(UserInputAst::from))
.parse_stream(input)
.into_result()
@@ -676,34 +649,6 @@ mod test {
.expect("Cannot parse date range")
.0;
assert_eq!(res6, expected_flexible_dates);
// IP Range Unbounded
let expected_weight = UserInputLeaf::Range {
field: Some("ip".to_string()),
lower: UserInputBound::Inclusive("::1".to_string()),
upper: UserInputBound::Unbounded,
};
let res1 = range()
.parse("ip: >=::1")
.expect("Cannot parse ip v6 format")
.0;
let res2 = range()
.parse("ip:[::1 TO *}")
.expect("Cannot parse ip v6 format")
.0;
assert_eq!(res1, expected_weight);
assert_eq!(res2, expected_weight);
// IP Range Bounded
let expected_weight = UserInputLeaf::Range {
field: Some("ip".to_string()),
lower: UserInputBound::Inclusive("::0.0.0.50".to_string()),
upper: UserInputBound::Exclusive("::0.0.0.52".to_string()),
};
let res1 = range()
.parse("ip:[::0.0.0.50 TO ::0.0.0.52}")
.expect("Cannot parse ip v6 format")
.0;
assert_eq!(res1, expected_weight);
}
#[test]
@@ -760,14 +705,6 @@ mod test {
test_parse_query_to_ast_helper("+(a b) +d", "(+(*\"a\" *\"b\") +\"d\")");
}
#[test]
fn test_parse_test_query_set() {
test_parse_query_to_ast_helper("abc: IN [a b c]", r#""abc": IN ["a" "b" "c"]"#);
test_parse_query_to_ast_helper("abc: IN [1]", r#""abc": IN ["1"]"#);
test_parse_query_to_ast_helper("abc: IN []", r#""abc": IN []"#);
test_parse_query_to_ast_helper("IN [1 2]", r#"IN ["1" "2"]"#);
}
#[test]
fn test_parse_test_query_other() {
test_parse_query_to_ast_helper("(+a +b) d", "(*(+\"a\" +\"b\") *\"d\")");

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

@@ -12,10 +12,6 @@ pub enum UserInputLeaf {
lower: UserInputBound,
upper: UserInputBound,
},
Set {
field: Option<String>,
elements: Vec<String>,
},
}
impl Debug for UserInputLeaf {
@@ -35,19 +31,6 @@ impl Debug for UserInputLeaf {
upper.display_upper(formatter)?;
Ok(())
}
UserInputLeaf::Set { field, elements } => {
if let Some(ref field) = field {
write!(formatter, "\"{}\": ", field)?;
}
write!(formatter, "IN [")?;
for (i, element) in elements.iter().enumerate() {
if i != 0 {
write!(formatter, " ")?;
}
write!(formatter, "\"{}\"", element)?;
}
write!(formatter, "]")
}
UserInputLeaf::All => write!(formatter, "*"),
}
}

10
src/aggregation/agg_req_with_accessor.rs
View File

@@ -11,7 +11,7 @@ use super::bucket::{HistogramAggregation, RangeAggregation, TermsAggregation};
use super::metric::{AverageAggregation, StatsAggregation};
use super::segment_agg_result::BucketCount;
use super::VecWithNames;
use crate::fastfield::{type_and_cardinality, MultiValuedFastFieldReader};
use crate::fastfield::{type_and_cardinality, FastType, MultiValuedFastFieldReader};
use crate::schema::{Cardinality, Type};
use crate::{InvertedIndexReader, SegmentReader, TantivyError};
@@ -194,7 +194,13 @@ fn get_ff_reader_and_validate(
.ok_or_else(|| TantivyError::FieldNotFound(field_name.to_string()))?;
let field_type = reader.schema().get_field_entry(field).field_type();
if let Some((_ff_type, field_cardinality)) = type_and_cardinality(field_type) {
if let Some((ff_type, field_cardinality)) = type_and_cardinality(field_type) {
if ff_type == FastType::Date {
return Err(TantivyError::InvalidArgument(
"Unsupported field type date in aggregation".to_string(),
));
}
if cardinality != field_cardinality {
return Err(TantivyError::InvalidArgument(format!(
"Invalid field cardinality on field {} expected {:?}, but got {:?}",

25
src/aggregation/agg_result.rs
View File

@@ -4,7 +4,9 @@
//! intermediate average results, which is the sum and the number of values. The actual average is
//! calculated on the step from intermediate to final aggregation result tree.
use rustc_hash::FxHashMap;
use std::collections::HashMap;
use fnv::FnvHashMap;
use serde::{Deserialize, Serialize};
use super::agg_req::BucketAggregationInternal;
@@ -12,12 +14,11 @@ use super::bucket::GetDocCount;
use super::intermediate_agg_result::{IntermediateBucketResult, IntermediateMetricResult};
use super::metric::{SingleMetricResult, Stats};
use super::Key;
use crate::schema::Schema;
use crate::TantivyError;
#[derive(Clone, Default, Debug, PartialEq, Serialize, Deserialize)]
/// The final aggegation result.
pub struct AggregationResults(pub FxHashMap<String, AggregationResult>);
pub struct AggregationResults(pub HashMap<String, AggregationResult>);
impl AggregationResults {
pub(crate) fn get_value_from_aggregation(
@@ -130,12 +131,9 @@ pub enum BucketResult {
}
impl BucketResult {
pub(crate) fn empty_from_req(
req: &BucketAggregationInternal,
schema: &Schema,
) -> crate::Result<Self> {
pub(crate) fn empty_from_req(req: &BucketAggregationInternal) -> crate::Result<Self> {
let empty_bucket = IntermediateBucketResult::empty_from_req(&req.bucket_agg);
empty_bucket.into_final_bucket_result(req, schema)
empty_bucket.into_final_bucket_result(req)
}
}
@@ -147,7 +145,7 @@ pub enum BucketEntries<T> {
/// Vector format bucket entries
Vec(Vec<T>),
/// HashMap format bucket entries
HashMap(FxHashMap<String, T>),
HashMap(FnvHashMap<String, T>),
}
/// This is the default entry for a bucket, which contains a key, count, and optionally
@@ -178,9 +176,6 @@ pub enum BucketEntries<T> {
/// ```
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
pub struct BucketEntry {
#[serde(skip_serializing_if = "Option::is_none")]
/// The string representation of the bucket.
pub key_as_string: Option<String>,
/// The identifier of the bucket.
pub key: Key,
/// Number of documents in the bucket.
@@ -245,10 +240,4 @@ pub struct RangeBucketEntry {
/// The to range of the bucket. Equals `f64::MAX` when `None`.
#[serde(skip_serializing_if = "Option::is_none")]
pub to: Option<f64>,
/// The optional string representation for the `from` range.
#[serde(skip_serializing_if = "Option::is_none")]
pub from_as_string: Option<String>,
/// The optional string representation for the `to` range.
#[serde(skip_serializing_if = "Option::is_none")]
pub to_as_string: Option<String>,
}

111
src/aggregation/bucket/histogram/histogram.rs
View File

@@ -10,12 +10,12 @@ use crate::aggregation::agg_req_with_accessor::{
AggregationsWithAccessor, BucketAggregationWithAccessor,
};
use crate::aggregation::agg_result::BucketEntry;
use crate::aggregation::f64_from_fastfield_u64;
use crate::aggregation::intermediate_agg_result::{
IntermediateAggregationResults, IntermediateBucketResult, IntermediateHistogramBucketEntry,
};
use crate::aggregation::segment_agg_result::SegmentAggregationResultsCollector;
use crate::aggregation::{f64_from_fastfield_u64, format_date};
use crate::schema::{Schema, Type};
use crate::schema::Type;
use crate::{DocId, TantivyError};
/// Histogram is a bucket aggregation, where buckets are created dynamically for given `interval`.
@@ -331,10 +331,10 @@ impl SegmentHistogramCollector {
.expect("unexpected fast field cardinatility");
let mut iter = doc.chunks_exact(4);
for docs in iter.by_ref() {
let val0 = self.f64_from_fastfield_u64(accessor.get_val(docs[0]));
let val1 = self.f64_from_fastfield_u64(accessor.get_val(docs[1]));
let val2 = self.f64_from_fastfield_u64(accessor.get_val(docs[2]));
let val3 = self.f64_from_fastfield_u64(accessor.get_val(docs[3]));
let val0 = self.f64_from_fastfield_u64(accessor.get_val(docs[0] as u64));
let val1 = self.f64_from_fastfield_u64(accessor.get_val(docs[1] as u64));
let val2 = self.f64_from_fastfield_u64(accessor.get_val(docs[2] as u64));
let val3 = self.f64_from_fastfield_u64(accessor.get_val(docs[3] as u64));
let bucket_pos0 = get_bucket_num(val0);
let bucket_pos1 = get_bucket_num(val1);
@@ -371,7 +371,7 @@ impl SegmentHistogramCollector {
)?;
}
for &doc in iter.remainder() {
let val = f64_from_fastfield_u64(accessor.get_val(doc), &self.field_type);
let val = f64_from_fastfield_u64(accessor.get_val(doc as u64), &self.field_type);
if !bounds.contains(val) {
continue;
}
@@ -425,7 +425,7 @@ impl SegmentHistogramCollector {
let bucket = &mut self.buckets[bucket_pos];
bucket.doc_count += 1;
if let Some(sub_aggregation) = self.sub_aggregations.as_mut() {
sub_aggregation[bucket_pos].collect(doc, bucket_with_accessor)?;
(&mut sub_aggregation[bucket_pos]).collect(doc, bucket_with_accessor)?;
}
Ok(())
}
@@ -451,9 +451,8 @@ fn intermediate_buckets_to_final_buckets_fill_gaps(
buckets: Vec<IntermediateHistogramBucketEntry>,
histogram_req: &HistogramAggregation,
sub_aggregation: &AggregationsInternal,
schema: &Schema,
) -> crate::Result<Vec<BucketEntry>> {
// Generate the full list of buckets without gaps.
// Generate the the full list of buckets without gaps.
//
// The bounds are the min max from the current buckets, optionally extended by
// extended_bounds from the request
@@ -492,9 +491,7 @@ fn intermediate_buckets_to_final_buckets_fill_gaps(
sub_aggregation: empty_sub_aggregation.clone(),
},
})
.map(|intermediate_bucket| {
intermediate_bucket.into_final_bucket_entry(sub_aggregation, schema)
})
.map(|intermediate_bucket| intermediate_bucket.into_final_bucket_entry(sub_aggregation))
.collect::<crate::Result<Vec<_>>>()
}
@@ -503,43 +500,20 @@ pub(crate) fn intermediate_histogram_buckets_to_final_buckets(
buckets: Vec<IntermediateHistogramBucketEntry>,
histogram_req: &HistogramAggregation,
sub_aggregation: &AggregationsInternal,
schema: &Schema,
) -> crate::Result<Vec<BucketEntry>> {
let mut buckets = if histogram_req.min_doc_count() == 0 {
if histogram_req.min_doc_count() == 0 {
// With min_doc_count != 0, we may need to add buckets, so that there are no
// gaps, since intermediate result does not contain empty buckets (filtered to
// reduce serialization size).
intermediate_buckets_to_final_buckets_fill_gaps(
buckets,
histogram_req,
sub_aggregation,
schema,
)?
intermediate_buckets_to_final_buckets_fill_gaps(buckets, histogram_req, sub_aggregation)
} else {
buckets
.into_iter()
.filter(|histogram_bucket| histogram_bucket.doc_count >= histogram_req.min_doc_count())
.map(|histogram_bucket| {
histogram_bucket.into_final_bucket_entry(sub_aggregation, schema)
})
.collect::<crate::Result<Vec<_>>>()?
};
// If we have a date type on the histogram buckets, we add the `key_as_string` field as rfc339
let field = schema
.get_field(&histogram_req.field)
.ok_or_else(|| TantivyError::FieldNotFound(histogram_req.field.to_string()))?;
if schema.get_field_entry(field).field_type().is_date() {
for bucket in buckets.iter_mut() {
if let crate::aggregation::Key::F64(val) = bucket.key {
let key_as_string = format_date(val as i64)?;
bucket.key_as_string = Some(key_as_string);
}
}
.map(|histogram_bucket| histogram_bucket.into_final_bucket_entry(sub_aggregation))
.collect::<crate::Result<Vec<_>>>()
}
Ok(buckets)
}
/// Applies req extended_bounds/hard_bounds on the min_max value
@@ -1398,63 +1372,6 @@ mod tests {
Ok(())
}
#[test]
fn histogram_date_test_single_segment() -> crate::Result<()> {
histogram_date_test_with_opt(true)
}
#[test]
fn histogram_date_test_multi_segment() -> crate::Result<()> {
histogram_date_test_with_opt(false)
}
fn histogram_date_test_with_opt(merge_segments: bool) -> crate::Result<()> {
let index = get_test_index_2_segments(merge_segments)?;
let agg_req: Aggregations = vec![(
"histogram".to_string(),
Aggregation::Bucket(BucketAggregation {
bucket_agg: BucketAggregationType::Histogram(HistogramAggregation {
field: "date".to_string(),
interval: 86400000000.0, // one day in microseconds
..Default::default()
}),
sub_aggregation: Default::default(),
}),
)]
.into_iter()
.collect();
let agg_res = exec_request(agg_req, &index)?;
let res: Value = serde_json::from_str(&serde_json::to_string(&agg_res)?)?;
assert_eq!(res["histogram"]["buckets"][0]["key"], 1546300800000000.0);
assert_eq!(
res["histogram"]["buckets"][0]["key_as_string"],
"2019-01-01T00:00:00Z"
);
assert_eq!(res["histogram"]["buckets"][0]["doc_count"], 1);
assert_eq!(res["histogram"]["buckets"][1]["key"], 1546387200000000.0);
assert_eq!(
res["histogram"]["buckets"][1]["key_as_string"],
"2019-01-02T00:00:00Z"
);
assert_eq!(res["histogram"]["buckets"][1]["doc_count"], 5);
assert_eq!(res["histogram"]["buckets"][2]["key"], 1546473600000000.0);
assert_eq!(
res["histogram"]["buckets"][2]["key_as_string"],
"2019-01-03T00:00:00Z"
);
assert_eq!(res["histogram"]["buckets"][3], Value::Null);
Ok(())
}
#[test]
fn histogram_invalid_request() -> crate::Result<()> {
let index = get_test_index_2_segments(true)?;

126
src/aggregation/bucket/range.rs
View File

@@ -1,8 +1,7 @@
use std::fmt::Debug;
use std::ops::Range;
use fastfield_codecs::MonotonicallyMappableToU64;
use rustc_hash::FxHashMap;
use fnv::FnvHashMap;
use serde::{Deserialize, Serialize};
use crate::aggregation::agg_req_with_accessor::{
@@ -12,9 +11,7 @@ use crate::aggregation::intermediate_agg_result::{
IntermediateBucketResult, IntermediateRangeBucketEntry, IntermediateRangeBucketResult,
};
use crate::aggregation::segment_agg_result::{BucketCount, SegmentAggregationResultsCollector};
use crate::aggregation::{
f64_from_fastfield_u64, f64_to_fastfield_u64, format_date, Key, SerializedKey,
};
use crate::aggregation::{f64_from_fastfield_u64, f64_to_fastfield_u64, Key, SerializedKey};
use crate::schema::Type;
use crate::{DocId, TantivyError};
@@ -179,12 +176,12 @@ impl SegmentRangeCollector {
) -> crate::Result<IntermediateBucketResult> {
let field_type = self.field_type;
let buckets: FxHashMap<SerializedKey, IntermediateRangeBucketEntry> = self
let buckets: FnvHashMap<SerializedKey, IntermediateRangeBucketEntry> = self
.buckets
.into_iter()
.map(move |range_bucket| {
Ok((
range_to_string(&range_bucket.range, &field_type)?,
range_to_string(&range_bucket.range, &field_type),
range_bucket
.bucket
.into_intermediate_bucket_entry(&agg_with_accessor.sub_aggregation)?,
@@ -212,8 +209,8 @@ impl SegmentRangeCollector {
let key = range
.key
.clone()
.map(|key| Ok(Key::Str(key)))
.unwrap_or_else(|| range_to_key(&range.range, &field_type))?;
.map(Key::Str)
.unwrap_or_else(|| range_to_key(&range.range, &field_type));
let to = if range.range.end == u64::MAX {
None
} else {
@@ -231,7 +228,6 @@ impl SegmentRangeCollector {
sub_aggregation,
)?)
};
Ok(SegmentRangeAndBucketEntry {
range: range.range.clone(),
bucket: SegmentRangeBucketEntry {
@@ -267,10 +263,10 @@ impl SegmentRangeCollector {
.as_single()
.expect("unexpected fast field cardinality");
for docs in iter.by_ref() {
let val1 = accessor.get_val(docs[0]);
let val2 = accessor.get_val(docs[1]);
let val3 = accessor.get_val(docs[2]);
let val4 = accessor.get_val(docs[3]);
let val1 = accessor.get_val(docs[0] as u64);
let val2 = accessor.get_val(docs[1] as u64);
let val3 = accessor.get_val(docs[2] as u64);
let val4 = accessor.get_val(docs[3] as u64);
let bucket_pos1 = self.get_bucket_pos(val1);
let bucket_pos2 = self.get_bucket_pos(val2);
let bucket_pos3 = self.get_bucket_pos(val3);
@@ -282,7 +278,7 @@ impl SegmentRangeCollector {
self.increment_bucket(bucket_pos4, docs[3], &bucket_with_accessor.sub_aggregation)?;
}
for &doc in iter.remainder() {
let val = accessor.get_val(doc);
let val = accessor.get_val(doc as u64);
let bucket_pos = self.get_bucket_pos(val);
self.increment_bucket(bucket_pos, doc, &bucket_with_accessor.sub_aggregation)?;
}
@@ -327,8 +323,8 @@ impl SegmentRangeCollector {
/// Converts the user provided f64 range value to fast field value space.
///
/// Internally fast field values are always stored as u64.
/// If the fast field has u64 `[1, 2, 5]`, these values are stored as is in the fast field.
/// A fast field with f64 `[1.0, 2.0, 5.0]` is converted to u64 space, using a
/// If the fast field has u64 [1,2,5], these values are stored as is in the fast field.
/// A fast field with f64 [1.0, 2.0, 5.0] is converted to u64 space, using a
/// monotonic mapping function, so the order is preserved.
///
/// Consequently, a f64 user range 1.0..3.0 needs to be converted to fast field value space using
@@ -406,45 +402,34 @@ fn extend_validate_ranges(
Ok(converted_buckets)
}
pub(crate) fn range_to_string(range: &Range<u64>, field_type: &Type) -> crate::Result<String> {
pub(crate) fn range_to_string(range: &Range<u64>, field_type: &Type) -> String {
// is_start is there for malformed requests, e.g. ig the user passes the range u64::MIN..0.0,
// it should be rendered as "*-0" and not "*-*"
let to_str = |val: u64, is_start: bool| {
if (is_start && val == u64::MIN) || (!is_start && val == u64::MAX) {
Ok("*".to_string())
} else if *field_type == Type::Date {
let val = i64::from_u64(val);
format_date(val)
"*".to_string()
} else {
Ok(f64_from_fastfield_u64(val, field_type).to_string())
f64_from_fastfield_u64(val, field_type).to_string()
}
};
Ok(format!(
"{}-{}",
to_str(range.start, true)?,
to_str(range.end, false)?
))
format!("{}-{}", to_str(range.start, true), to_str(range.end, false))
}
pub(crate) fn range_to_key(range: &Range<u64>, field_type: &Type) -> crate::Result<Key> {
Ok(Key::Str(range_to_string(range, field_type)?))
pub(crate) fn range_to_key(range: &Range<u64>, field_type: &Type) -> Key {
Key::Str(range_to_string(range, field_type))
}
#[cfg(test)]
mod tests {
use fastfield_codecs::MonotonicallyMappableToU64;
use serde_json::Value;
use super::*;
use crate::aggregation::agg_req::{
Aggregation, Aggregations, BucketAggregation, BucketAggregationType,
};
use crate::aggregation::tests::{
exec_request, exec_request_with_query, get_test_index_2_segments,
get_test_index_with_num_docs,
};
use crate::aggregation::tests::{exec_request_with_query, get_test_index_with_num_docs};
pub fn get_collector_from_ranges(
ranges: Vec<RangeAggregationRange>,
@@ -582,77 +567,6 @@ mod tests {
Ok(())
}
#[test]
fn range_date_test_single_segment() -> crate::Result<()> {
range_date_test_with_opt(true)
}
#[test]
fn range_date_test_multi_segment() -> crate::Result<()> {
range_date_test_with_opt(false)
}
fn range_date_test_with_opt(merge_segments: bool) -> crate::Result<()> {
let index = get_test_index_2_segments(merge_segments)?;
let agg_req: Aggregations = vec![(
"date_ranges".to_string(),
Aggregation::Bucket(BucketAggregation {
bucket_agg: BucketAggregationType::Range(RangeAggregation {
field: "date".to_string(),
ranges: vec![
RangeAggregationRange {
key: None,
from: None,
to: Some(1546300800000000.0f64),
},
RangeAggregationRange {
key: None,
from: Some(1546300800000000.0f64),
to: Some(1546387200000000.0f64),
},
],
keyed: false,
}),
sub_aggregation: Default::default(),
}),
)]
.into_iter()
.collect();
let agg_res = exec_request(agg_req, &index)?;
let res: Value = serde_json::from_str(&serde_json::to_string(&agg_res)?)?;
assert_eq!(
res["date_ranges"]["buckets"][0]["from_as_string"],
Value::Null
);
assert_eq!(
res["date_ranges"]["buckets"][0]["key"],
"*-2019-01-01T00:00:00Z"
);
assert_eq!(
res["date_ranges"]["buckets"][1]["from_as_string"],
"2019-01-01T00:00:00Z"
);
assert_eq!(
res["date_ranges"]["buckets"][1]["to_as_string"],
"2019-01-02T00:00:00Z"
);
assert_eq!(
res["date_ranges"]["buckets"][2]["from_as_string"],
"2019-01-02T00:00:00Z"
);
assert_eq!(
res["date_ranges"]["buckets"][2]["to_as_string"],
Value::Null
);
Ok(())
}
#[test]
fn range_custom_key_keyed_buckets_test() -> crate::Result<()> {
let index = get_test_index_with_num_docs(false, 100)?;

67
src/aggregation/bucket/term_agg.rs
View File

@@ -1,7 +1,7 @@
use std::fmt::Debug;
use fnv::FnvHashMap;
use itertools::Itertools;
use rustc_hash::FxHashMap;
use serde::{Deserialize, Serialize};
use super::{CustomOrder, Order, OrderTarget};
@@ -17,11 +17,7 @@ use crate::fastfield::MultiValuedFastFieldReader;
use crate::schema::Type;
use crate::{DocId, TantivyError};
/// Creates a bucket for every unique term and counts the number of occurences.
/// Note that doc_count in the response buckets equals term count here.
///
/// If the text is untokenized and single value, that means one term per document and therefore it
/// is in fact doc count.
/// Creates a bucket for every unique term
///
/// ### Terminology
/// Shard parameters are supposed to be equivalent to elasticsearch shard parameter.
@@ -68,25 +64,6 @@ use crate::{DocId, TantivyError};
/// }
/// }
/// ```
///
/// /// # Response JSON Format
/// ```json
/// {
/// ...
/// "aggregations": {
/// "genres": {
/// "doc_count_error_upper_bound": 0,
/// "sum_other_doc_count": 0,
/// "buckets": [
/// { "key": "drumnbass", "doc_count": 6 },
/// { "key": "raggae", "doc_count": 4 },
/// { "key": "jazz", "doc_count": 2 }
/// ]
/// }
/// }
/// }
/// ```
#[derive(Clone, Debug, Default, PartialEq, Serialize, Deserialize)]
pub struct TermsAggregation {
/// The field to aggregate on.
@@ -199,7 +176,7 @@ impl TermsAggregationInternal {
#[derive(Clone, Debug, PartialEq)]
/// Container to store term_ids and their buckets.
struct TermBuckets {
pub(crate) entries: FxHashMap<u32, TermBucketEntry>,
pub(crate) entries: FnvHashMap<u32, TermBucketEntry>,
blueprint: Option<SegmentAggregationResultsCollector>,
}
@@ -397,7 +374,7 @@ impl SegmentTermCollector {
.expect("internal error: inverted index not loaded for term aggregation");
let term_dict = inverted_index.terms();
let mut dict: FxHashMap<String, IntermediateTermBucketEntry> = Default::default();
let mut dict: FnvHashMap<String, IntermediateTermBucketEntry> = Default::default();
let mut buffer = vec![];
for (term_id, entry) in entries {
term_dict
@@ -1129,9 +1106,9 @@ mod tests {
assert_eq!(res["my_texts"]["buckets"][0]["key"], "terma");
assert_eq!(res["my_texts"]["buckets"][0]["doc_count"], 4);
assert_eq!(res["my_texts"]["buckets"][1]["key"], "termc");
assert_eq!(res["my_texts"]["buckets"][1]["key"], "termb");
assert_eq!(res["my_texts"]["buckets"][1]["doc_count"], 0);
assert_eq!(res["my_texts"]["buckets"][2]["key"], "termb");
assert_eq!(res["my_texts"]["buckets"][2]["key"], "termc");
assert_eq!(res["my_texts"]["buckets"][2]["doc_count"], 0);
assert_eq!(res["my_texts"]["sum_other_doc_count"], 0);
assert_eq!(res["my_texts"]["doc_count_error_upper_bound"], 0);
@@ -1229,43 +1206,11 @@ mod tests {
.collect();
let res = exec_request_with_query(agg_req, &index, None);
assert!(res.is_err());
Ok(())
}
#[test]
fn terms_aggregation_multi_token_per_doc() -> crate::Result<()> {
let terms = vec!["Hello Hello", "Hallo Hallo"];
let index = get_test_index_from_terms(true, &[terms])?;
let agg_req: Aggregations = vec![(
"my_texts".to_string(),
Aggregation::Bucket(BucketAggregation {
bucket_agg: BucketAggregationType::Terms(TermsAggregation {
field: "text_id".to_string(),
min_doc_count: Some(0),
..Default::default()
}),
sub_aggregation: Default::default(),
}),
)]
.into_iter()
.collect();
let res = exec_request_with_query(agg_req, &index, None).unwrap();
assert_eq!(res["my_texts"]["buckets"][0]["key"], "hello");
assert_eq!(res["my_texts"]["buckets"][0]["doc_count"], 2);
assert_eq!(res["my_texts"]["buckets"][1]["key"], "hallo");
assert_eq!(res["my_texts"]["buckets"][1]["doc_count"], 2);
Ok(())
}
#[test]
fn test_json_format() -> crate::Result<()> {
let agg_req: Aggregations = vec![(

7
src/aggregation/collector.rs
View File

@@ -7,7 +7,6 @@ use super::intermediate_agg_result::IntermediateAggregationResults;
use super::segment_agg_result::SegmentAggregationResultsCollector;
use crate::aggregation::agg_req_with_accessor::get_aggs_with_accessor_and_validate;
use crate::collector::{Collector, SegmentCollector};
use crate::schema::Schema;
use crate::{SegmentReader, TantivyError};
/// The default max bucket count, before the aggregation fails.
@@ -17,7 +16,6 @@ pub const MAX_BUCKET_COUNT: u32 = 65000;
///
/// The collector collects all aggregations by the underlying aggregation request.
pub struct AggregationCollector {
schema: Schema,
agg: Aggregations,
max_bucket_count: u32,
}
@@ -27,9 +25,8 @@ impl AggregationCollector {
///
/// Aggregation fails when the total bucket count is higher than max_bucket_count.
/// max_bucket_count will default to `MAX_BUCKET_COUNT` (65000) when unset
pub fn from_aggs(agg: Aggregations, max_bucket_count: Option<u32>, schema: Schema) -> Self {
pub fn from_aggs(agg: Aggregations, max_bucket_count: Option<u32>) -> Self {
Self {
schema,
agg,
max_bucket_count: max_bucket_count.unwrap_or(MAX_BUCKET_COUNT),
}
@@ -116,7 +113,7 @@ impl Collector for AggregationCollector {
segment_fruits: Vec<<Self::Child as SegmentCollector>::Fruit>,
) -> crate::Result<Self::Fruit> {
let res = merge_fruits(segment_fruits)?;
res.into_final_bucket_result(self.agg.clone(), &self.schema)
res.into_final_bucket_result(self.agg.clone())
}
}

18
src/aggregation/date.rs
View File

@@ -1,18 +0,0 @@
use time::format_description::well_known::Rfc3339;
use time::OffsetDateTime;
use crate::TantivyError;
pub(crate) fn format_date(val: i64) -> crate::Result<String> {
let datetime =
OffsetDateTime::from_unix_timestamp_nanos(1_000 * (val as i128)).map_err(|err| {
TantivyError::InvalidArgument(format!(
"Could not convert {:?} to OffsetDateTime, err {:?}",
val, err
))
})?;
let key_as_string = datetime
.format(&Rfc3339)
.map_err(|_err| TantivyError::InvalidArgument("Could not serialize date".to_string()))?;
Ok(key_as_string)
}

103
src/aggregation/intermediate_agg_result.rs
View File

@@ -3,14 +3,15 @@
//! indices.
use std::cmp::Ordering;
use std::collections::HashMap;
use fnv::FnvHashMap;
use itertools::Itertools;
use rustc_hash::FxHashMap;
use serde::{Deserialize, Serialize};
use super::agg_req::{
Aggregations, AggregationsInternal, BucketAggregationInternal, BucketAggregationType,
MetricAggregation, RangeAggregation,
MetricAggregation,
};
use super::agg_result::{AggregationResult, BucketResult, RangeBucketEntry};
use super::bucket::{
@@ -19,11 +20,9 @@ use super::bucket::{
};
use super::metric::{IntermediateAverage, IntermediateStats};
use super::segment_agg_result::SegmentMetricResultCollector;
use super::{format_date, Key, SerializedKey, VecWithNames};
use super::{Key, SerializedKey, VecWithNames};
use crate::aggregation::agg_result::{AggregationResults, BucketEntries, BucketEntry};
use crate::aggregation::bucket::TermsAggregationInternal;
use crate::schema::Schema;
use crate::TantivyError;
/// Contains the intermediate aggregation result, which is optimized to be merged with other
/// intermediate results.
@@ -37,12 +36,8 @@ pub struct IntermediateAggregationResults {
impl IntermediateAggregationResults {
/// Convert intermediate result and its aggregation request to the final result.
pub fn into_final_bucket_result(
self,
req: Aggregations,
schema: &Schema,
) -> crate::Result<AggregationResults> {
self.into_final_bucket_result_internal(&(req.into()), schema)
pub fn into_final_bucket_result(self, req: Aggregations) -> crate::Result<AggregationResults> {
self.into_final_bucket_result_internal(&(req.into()))
}
/// Convert intermediate result and its aggregation request to the final result.
@@ -52,19 +47,18 @@ impl IntermediateAggregationResults {
pub(crate) fn into_final_bucket_result_internal(
self,
req: &AggregationsInternal,
schema: &Schema,
) -> crate::Result<AggregationResults> {
// Important assumption:
// When the tree contains buckets/metric, we expect it to have all buckets/metrics from the
// request
let mut results: FxHashMap<String, AggregationResult> = FxHashMap::default();
let mut results: HashMap<String, AggregationResult> = HashMap::new();
if let Some(buckets) = self.buckets {
convert_and_add_final_buckets_to_result(&mut results, buckets, &req.buckets, schema)?
convert_and_add_final_buckets_to_result(&mut results, buckets, &req.buckets)?
} else {
// When there are no buckets, we create empty buckets, so that the serialized json
// format is constant
add_empty_final_buckets_to_result(&mut results, &req.buckets, schema)?
add_empty_final_buckets_to_result(&mut results, &req.buckets)?
};
if let Some(metrics) = self.metrics {
@@ -138,7 +132,7 @@ impl IntermediateAggregationResults {
}
fn convert_and_add_final_metrics_to_result(
results: &mut FxHashMap<String, AggregationResult>,
results: &mut HashMap<String, AggregationResult>,
metrics: VecWithNames<IntermediateMetricResult>,
) {
results.extend(
@@ -149,7 +143,7 @@ fn convert_and_add_final_metrics_to_result(
}
fn add_empty_final_metrics_to_result(
results: &mut FxHashMap<String, AggregationResult>,
results: &mut HashMap<String, AggregationResult>,
req_metrics: &VecWithNames<MetricAggregation>,
) -> crate::Result<()> {
results.extend(req_metrics.iter().map(|(key, req)| {
@@ -163,30 +157,27 @@ fn add_empty_final_metrics_to_result(
}
fn add_empty_final_buckets_to_result(
results: &mut FxHashMap<String, AggregationResult>,
results: &mut HashMap<String, AggregationResult>,
req_buckets: &VecWithNames<BucketAggregationInternal>,
schema: &Schema,
) -> crate::Result<()> {
let requested_buckets = req_buckets.iter();
for (key, req) in requested_buckets {
let empty_bucket =
AggregationResult::BucketResult(BucketResult::empty_from_req(req, schema)?);
let empty_bucket = AggregationResult::BucketResult(BucketResult::empty_from_req(req)?);
results.insert(key.to_string(), empty_bucket);
}
Ok(())
}
fn convert_and_add_final_buckets_to_result(
results: &mut FxHashMap<String, AggregationResult>,
results: &mut HashMap<String, AggregationResult>,
buckets: VecWithNames<IntermediateBucketResult>,
req_buckets: &VecWithNames<BucketAggregationInternal>,
schema: &Schema,
) -> crate::Result<()> {
assert_eq!(buckets.len(), req_buckets.len());
let buckets_with_request = buckets.into_iter().zip(req_buckets.values());
for ((key, bucket), req) in buckets_with_request {
let result = AggregationResult::BucketResult(bucket.into_final_bucket_result(req, schema)?);
let result = AggregationResult::BucketResult(bucket.into_final_bucket_result(req)?);
results.insert(key, result);
}
Ok(())
@@ -276,21 +267,13 @@ impl IntermediateBucketResult {
pub(crate) fn into_final_bucket_result(
self,
req: &BucketAggregationInternal,
schema: &Schema,
) -> crate::Result<BucketResult> {
match self {
IntermediateBucketResult::Range(range_res) => {
let mut buckets: Vec<RangeBucketEntry> = range_res
.buckets
.into_iter()
.map(|(_, bucket)| {
bucket.into_final_bucket_entry(
&req.sub_aggregation,
schema,
req.as_range()
.expect("unexpected aggregation, expected histogram aggregation"),
)
})
.map(|(_, bucket)| bucket.into_final_bucket_entry(&req.sub_aggregation))
.collect::<crate::Result<Vec<_>>>()?;
buckets.sort_by(|left, right| {
@@ -305,7 +288,7 @@ impl IntermediateBucketResult {
.keyed;
let buckets = if is_keyed {
let mut bucket_map =
FxHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
FnvHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
for bucket in buckets {
bucket_map.insert(bucket.key.to_string(), bucket);
}
@@ -321,12 +304,11 @@ impl IntermediateBucketResult {
req.as_histogram()
.expect("unexpected aggregation, expected histogram aggregation"),
&req.sub_aggregation,
schema,
)?;
let buckets = if req.as_histogram().unwrap().keyed {
let mut bucket_map =
FxHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
FnvHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
for bucket in buckets {
bucket_map.insert(bucket.key.to_string(), bucket);
}
@@ -340,7 +322,6 @@ impl IntermediateBucketResult {
req.as_term()
.expect("unexpected aggregation, expected term aggregation"),
&req.sub_aggregation,
schema,
),
}
}
@@ -415,13 +396,13 @@ impl IntermediateBucketResult {
#[derive(Default, Clone, Debug, PartialEq, Serialize, Deserialize)]
/// Range aggregation including error counts
pub struct IntermediateRangeBucketResult {
pub(crate) buckets: FxHashMap<SerializedKey, IntermediateRangeBucketEntry>,
pub(crate) buckets: FnvHashMap<SerializedKey, IntermediateRangeBucketEntry>,
}
#[derive(Default, Clone, Debug, PartialEq, Serialize, Deserialize)]
/// Term aggregation including error counts
pub struct IntermediateTermBucketResult {
pub(crate) entries: FxHashMap<String, IntermediateTermBucketEntry>,
pub(crate) entries: FnvHashMap<String, IntermediateTermBucketEntry>,
pub(crate) sum_other_doc_count: u64,
pub(crate) doc_count_error_upper_bound: u64,
}
@@ -431,7 +412,6 @@ impl IntermediateTermBucketResult {
self,
req: &TermsAggregation,
sub_aggregation_req: &AggregationsInternal,
schema: &Schema,
) -> crate::Result<BucketResult> {
let req = TermsAggregationInternal::from_req(req);
let mut buckets: Vec<BucketEntry> = self
@@ -440,12 +420,11 @@ impl IntermediateTermBucketResult {
.filter(|bucket| bucket.1.doc_count >= req.min_doc_count)
.map(|(key, entry)| {
Ok(BucketEntry {
key_as_string: None,
key: Key::Str(key),
doc_count: entry.doc_count,
sub_aggregation: entry
.sub_aggregation
.into_final_bucket_result_internal(sub_aggregation_req, schema)?,
.into_final_bucket_result_internal(sub_aggregation_req)?,
})
})
.collect::<crate::Result<_>>()?;
@@ -520,8 +499,8 @@ trait MergeFruits {
}
fn merge_maps<V: MergeFruits + Clone>(
entries_left: &mut FxHashMap<SerializedKey, V>,
mut entries_right: FxHashMap<SerializedKey, V>,
entries_left: &mut FnvHashMap<SerializedKey, V>,
mut entries_right: FnvHashMap<SerializedKey, V>,
) {
for (name, entry_left) in entries_left.iter_mut() {
if let Some(entry_right) = entries_right.remove(name) {
@@ -550,15 +529,13 @@ impl IntermediateHistogramBucketEntry {
pub(crate) fn into_final_bucket_entry(
self,
req: &AggregationsInternal,
schema: &Schema,
) -> crate::Result<BucketEntry> {
Ok(BucketEntry {
key_as_string: None,
key: Key::F64(self.key),
doc_count: self.doc_count,
sub_aggregation: self
.sub_aggregation
.into_final_bucket_result_internal(req, schema)?,
.into_final_bucket_result_internal(req)?,
})
}
}
@@ -595,38 +572,16 @@ impl IntermediateRangeBucketEntry {
pub(crate) fn into_final_bucket_entry(
self,
req: &AggregationsInternal,
schema: &Schema,
range_req: &RangeAggregation,
) -> crate::Result<RangeBucketEntry> {
let mut range_bucket_entry = RangeBucketEntry {
Ok(RangeBucketEntry {
key: self.key,
doc_count: self.doc_count,
sub_aggregation: self
.sub_aggregation
.into_final_bucket_result_internal(req, schema)?,
.into_final_bucket_result_internal(req)?,
to: self.to,
from: self.from,
to_as_string: None,
from_as_string: None,
};
// If we have a date type on the histogram buckets, we add the `key_as_string` field as
// rfc339
let field = schema
.get_field(&range_req.field)
.ok_or_else(|| TantivyError::FieldNotFound(range_req.field.to_string()))?;
if schema.get_field_entry(field).field_type().is_date() {
if let Some(val) = range_bucket_entry.to {
let key_as_string = format_date(val as i64)?;
range_bucket_entry.to_as_string = Some(key_as_string);
}
if let Some(val) = range_bucket_entry.from {
let key_as_string = format_date(val as i64)?;
range_bucket_entry.from_as_string = Some(key_as_string);
}
}
Ok(range_bucket_entry)
})
}
}
@@ -671,7 +626,7 @@ mod tests {
fn get_sub_test_tree(data: &[(String, u64)]) -> IntermediateAggregationResults {
let mut map = HashMap::new();
let mut buckets = FxHashMap::default();
let mut buckets = FnvHashMap::default();
for (key, doc_count) in data {
buckets.insert(
key.to_string(),
@@ -698,7 +653,7 @@ mod tests {
data: &[(String, u64, String, u64)],
) -> IntermediateAggregationResults {
let mut map = HashMap::new();
let mut buckets: FxHashMap<_, _> = Default::default();
let mut buckets: FnvHashMap<_, _> = Default::default();
for (key, doc_count, sub_aggregation_key, sub_aggregation_count) in data {
buckets.insert(
key.to_string(),

10
src/aggregation/metric/average.rs
View File

@@ -60,10 +60,10 @@ impl SegmentAverageCollector {
pub(crate) fn collect_block(&mut self, doc: &[DocId], field: &dyn Column<u64>) {
let mut iter = doc.chunks_exact(4);
for docs in iter.by_ref() {
let val1 = field.get_val(docs[0]);
let val2 = field.get_val(docs[1]);
let val3 = field.get_val(docs[2]);
let val4 = field.get_val(docs[3]);
let val1 = field.get_val(docs[0] as u64);
let val2 = field.get_val(docs[1] as u64);
let val3 = field.get_val(docs[2] as u64);
let val4 = field.get_val(docs[3] as u64);
let val1 = f64_from_fastfield_u64(val1, &self.field_type);
let val2 = f64_from_fastfield_u64(val2, &self.field_type);
let val3 = f64_from_fastfield_u64(val3, &self.field_type);
@@ -74,7 +74,7 @@ impl SegmentAverageCollector {
self.data.collect(val4);
}
for &doc in iter.remainder() {
let val = field.get_val(doc);
let val = field.get_val(doc as u64);
let val = f64_from_fastfield_u64(val, &self.field_type);
self.data.collect(val);
}

14
src/aggregation/metric/stats.rs
View File

@@ -166,10 +166,10 @@ impl SegmentStatsCollector {
pub(crate) fn collect_block(&mut self, doc: &[DocId], field: &dyn Column<u64>) {
let mut iter = doc.chunks_exact(4);
for docs in iter.by_ref() {
let val1 = field.get_val(docs[0]);
let val2 = field.get_val(docs[1]);
let val3 = field.get_val(docs[2]);
let val4 = field.get_val(docs[3]);
let val1 = field.get_val(docs[0] as u64);
let val2 = field.get_val(docs[1] as u64);
let val3 = field.get_val(docs[2] as u64);
let val4 = field.get_val(docs[3] as u64);
let val1 = f64_from_fastfield_u64(val1, &self.field_type);
let val2 = f64_from_fastfield_u64(val2, &self.field_type);
let val3 = f64_from_fastfield_u64(val3, &self.field_type);
@@ -180,7 +180,7 @@ impl SegmentStatsCollector {
self.stats.collect(val4);
}
for &doc in iter.remainder() {
let val = field.get_val(doc);
let val = field.get_val(doc as u64);
let val = f64_from_fastfield_u64(val, &self.field_type);
self.stats.collect(val);
}
@@ -222,7 +222,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let reader = index.reader()?;
let searcher = reader.searcher();
@@ -300,7 +300,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults = searcher.search(&term_query, &collector).unwrap();

84
src/aggregation/mod.rs
View File

@@ -10,19 +10,21 @@
//!
//! There are two categories: [Metrics](metric) and [Buckets](bucket).
//!
//! ## Prerequisite
//! Currently aggregations work only on [fast fields](`crate::fastfield`). Single value fast fields
//! of type `u64`, `f64`, `i64`, `date` and fast fields on text fields.
//! # Usage
//!
//!
//! ## Usage
//! To use aggregations, build an aggregation request by constructing
//! [`Aggregations`](agg_req::Aggregations).
//! Create an [`AggregationCollector`] from this request. `AggregationCollector` implements the
//! [`Collector`](crate::collector::Collector) trait and can be passed as collector into
//! [`Searcher::search()`](crate::Searcher::search).
//!
//! #### Limitations
//!
//! ## JSON Format
//! Currently aggregations work only on single value fast fields of type `u64`, `f64`, `i64` and
//! fast fields on text fields.
//!
//! # JSON Format
//! Aggregations request and result structures de/serialize into elasticsearch compatible JSON.
//!
//! ```verbatim
@@ -33,7 +35,7 @@
//! let json_response_string: String = &serde_json::to_string(&agg_res)?;
//! ```
//!
//! ## Supported Aggregations
//! # Supported Aggregations
//! - [Bucket](bucket)
//! - [Histogram](bucket::HistogramAggregation)
//! - [Range](bucket::RangeAggregation)
@@ -53,10 +55,9 @@
//! use tantivy::query::AllQuery;
//! use tantivy::aggregation::agg_result::AggregationResults;
//! use tantivy::IndexReader;
//! use tantivy::schema::Schema;
//!
//! # #[allow(dead_code)]
//! fn aggregate_on_index(reader: &IndexReader, schema: Schema) {
//! fn aggregate_on_index(reader: &IndexReader) {
//! let agg_req: Aggregations = vec![
//! (
//! "average".to_string(),
@@ -68,7 +69,7 @@
//! .into_iter()
//! .collect();
//!
//! let collector = AggregationCollector::from_aggs(agg_req, None, schema);
//! let collector = AggregationCollector::from_aggs(agg_req, None);
//!
//! let searcher = reader.searcher();
//! let agg_res: AggregationResults = searcher.search(&AllQuery, &collector).unwrap();
@@ -158,7 +159,6 @@ mod agg_req_with_accessor;
pub mod agg_result;
pub mod bucket;
mod collector;
mod date;
pub mod intermediate_agg_result;
pub mod metric;
mod segment_agg_result;
@@ -169,7 +169,6 @@ pub use collector::{
AggregationCollector, AggregationSegmentCollector, DistributedAggregationCollector,
MAX_BUCKET_COUNT,
};
pub(crate) use date::format_date;
use fastfield_codecs::MonotonicallyMappableToU64;
use itertools::Itertools;
use serde::{Deserialize, Serialize};
@@ -286,11 +285,11 @@ impl Display for Key {
/// Inverse of `to_fastfield_u64`. Used to convert to `f64` for metrics.
///
/// # Panics
/// Only `u64`, `f64`, `date`, and `i64` are supported.
/// Only `u64`, `f64`, and `i64` are supported.
pub(crate) fn f64_from_fastfield_u64(val: u64, field_type: &Type) -> f64 {
match field_type {
Type::U64 => val as f64,
Type::I64 | Type::Date => i64::from_u64(val) as f64,
Type::I64 => i64::from_u64(val) as f64,
Type::F64 => f64::from_u64(val),
_ => {
panic!("unexpected type {:?}. This should not happen", field_type)
@@ -298,9 +297,10 @@ pub(crate) fn f64_from_fastfield_u64(val: u64, field_type: &Type) -> f64 {
}
}
/// Converts the `f64` value to fast field value space, which is always u64.
/// Converts the `f64` value to fast field value space.
///
/// If the fast field has `u64`, values are stored unchanged as `u64` in the fast field.
/// If the fast field has `u64`, values are stored as `u64` in the fast field.
/// A `f64` value of e.g. `2.0` therefore needs to be converted to `1u64`.
///
/// If the fast field has `f64` values are converted and stored to `u64` using a
/// monotonic mapping.
@@ -310,7 +310,7 @@ pub(crate) fn f64_from_fastfield_u64(val: u64, field_type: &Type) -> f64 {
pub(crate) fn f64_to_fastfield_u64(val: f64, field_type: &Type) -> Option<u64> {
match field_type {
Type::U64 => Some(val as u64),
Type::I64 | Type::Date => Some((val as i64).to_u64()),
Type::I64 => Some((val as i64).to_u64()),
Type::F64 => Some(val.to_u64()),
_ => None,
}
@@ -319,7 +319,6 @@ pub(crate) fn f64_to_fastfield_u64(val: f64, field_type: &Type) -> Option<u64> {
#[cfg(test)]
mod tests {
use serde_json::Value;
use time::OffsetDateTime;
use super::agg_req::{Aggregation, Aggregations, BucketAggregation};
use super::bucket::RangeAggregation;
@@ -335,7 +334,7 @@ mod tests {
use crate::aggregation::DistributedAggregationCollector;
use crate::query::{AllQuery, TermQuery};
use crate::schema::{Cardinality, IndexRecordOption, Schema, TextFieldIndexing, FAST, STRING};
use crate::{DateTime, Index, Term};
use crate::{Index, Term};
fn get_avg_req(field_name: &str) -> Aggregation {
Aggregation::Metric(MetricAggregation::Average(
@@ -361,7 +360,7 @@ mod tests {
index: &Index,
query: Option<(&str, &str)>,
) -> crate::Result<Value> {
let collector = AggregationCollector::from_aggs(agg_req, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req, None);
let reader = index.reader()?;
let searcher = reader.searcher();
@@ -555,10 +554,10 @@ mod tests {
let searcher = reader.searcher();
let intermediate_agg_result = searcher.search(&AllQuery, &collector).unwrap();
intermediate_agg_result
.into_final_bucket_result(agg_req, &index.schema())
.into_final_bucket_result(agg_req)
.unwrap()
} else {
let collector = AggregationCollector::from_aggs(agg_req, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req, None);
let searcher = reader.searcher();
searcher.search(&AllQuery, &collector).unwrap()
@@ -651,7 +650,6 @@ mod tests {
.set_fast()
.set_stored();
let text_field = schema_builder.add_text_field("text", text_fieldtype);
let date_field = schema_builder.add_date_field("date", FAST);
schema_builder.add_text_field("dummy_text", STRING);
let score_fieldtype =
crate::schema::NumericOptions::default().set_fast(Cardinality::SingleValue);
@@ -669,7 +667,6 @@ mod tests {
// writing the segment
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800).unwrap()),
score_field => 1u64,
score_field_f64 => 1f64,
score_field_i64 => 1i64,
@@ -678,7 +675,6 @@ mod tests {
))?;
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400).unwrap()),
score_field => 3u64,
score_field_f64 => 3f64,
score_field_i64 => 3i64,
@@ -687,21 +683,18 @@ mod tests {
))?;
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400).unwrap()),
score_field => 5u64,
score_field_f64 => 5f64,
score_field_i64 => 5i64,
))?;
index_writer.add_document(doc!(
text_field => "nohit",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400).unwrap()),
score_field => 6u64,
score_field_f64 => 6f64,
score_field_i64 => 6i64,
))?;
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400).unwrap()),
score_field => 7u64,
score_field_f64 => 7f64,
score_field_i64 => 7i64,
@@ -709,14 +702,12 @@ mod tests {
index_writer.commit()?;
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400).unwrap()),
score_field => 11u64,
score_field_f64 => 11f64,
score_field_i64 => 11i64,
))?;
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400 + 86400).unwrap()),
score_field => 14u64,
score_field_f64 => 14f64,
score_field_i64 => 14i64,
@@ -724,7 +715,6 @@ mod tests {
index_writer.add_document(doc!(
text_field => "cool",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400 + 86400).unwrap()),
score_field => 44u64,
score_field_f64 => 44.5f64,
score_field_i64 => 44i64,
@@ -735,7 +725,6 @@ mod tests {
// no hits segment
index_writer.add_document(doc!(
text_field => "nohit",
date_field => DateTime::from_utc(OffsetDateTime::from_unix_timestamp(1_546_300_800 + 86400 + 86400).unwrap()),
score_field => 44u64,
score_field_f64 => 44.5f64,
score_field_i64 => 44i64,
@@ -808,7 +797,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults = searcher.search(&term_query, &collector).unwrap();
@@ -1008,10 +997,9 @@ mod tests {
// Test de/serialization roundtrip on intermediate_agg_result
let res: IntermediateAggregationResults =
serde_json::from_str(&serde_json::to_string(&res).unwrap()).unwrap();
res.into_final_bucket_result(agg_req.clone(), &index.schema())
.unwrap()
res.into_final_bucket_result(agg_req.clone()).unwrap()
} else {
let collector = AggregationCollector::from_aggs(agg_req.clone(), None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req.clone(), None);
let searcher = reader.searcher();
searcher.search(&term_query, &collector).unwrap()
@@ -1069,7 +1057,7 @@ mod tests {
);
// Test empty result set
let collector = AggregationCollector::from_aggs(agg_req, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req, None);
let searcher = reader.searcher();
searcher.search(&query_with_no_hits, &collector).unwrap();
@@ -1134,7 +1122,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
@@ -1247,7 +1235,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1278,7 +1266,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1309,7 +1297,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1348,7 +1336,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1377,7 +1365,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1406,7 +1394,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1443,7 +1431,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1478,7 +1466,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1517,7 +1505,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1547,7 +1535,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =
@@ -1604,7 +1592,7 @@ mod tests {
.into_iter()
.collect();
let collector = AggregationCollector::from_aggs(agg_req_1, None, index.schema());
let collector = AggregationCollector::from_aggs(agg_req_1, None);
let searcher = reader.searcher();
let agg_res: AggregationResults =

2
src/collector/custom_score_top_collector.rs
View File

@@ -38,7 +38,7 @@ pub trait CustomSegmentScorer<TScore>: 'static {
pub trait CustomScorer<TScore>: Sync {
/// Type of the associated [`CustomSegmentScorer`].
type Child: CustomSegmentScorer<TScore>;
/// Builds a child scorer for a specific segment. The child scorer is associated with
/// Builds a child scorer for a specific segment. The child scorer is associated to
/// a specific segment.
fn segment_scorer(&self, segment_reader: &SegmentReader) -> crate::Result<Self::Child>;
}

10
src/collector/facet_collector.rs
View File

@@ -91,7 +91,7 @@ fn facet_depth(facet_bytes: &[u8]) -> usize {
/// let index = Index::create_in_ram(schema);
/// {
/// let mut index_writer = index.writer(3_000_000)?;
/// // a document can be associated with any number of facets
/// // a document can be associated to any number of facets
/// index_writer.add_document(doc!(
/// title => "The Name of the Wind",
/// facet => Facet::from("/lang/en"),
@@ -338,7 +338,11 @@ impl SegmentCollector for FacetSegmentCollector {
let mut previous_collapsed_ord: usize = usize::MAX;
for &facet_ord in &self.facet_ords_buf {
let collapsed_ord = self.collapse_mapping[facet_ord as usize];
self.counts[collapsed_ord] += u64::from(collapsed_ord != previous_collapsed_ord);
self.counts[collapsed_ord] += if collapsed_ord == previous_collapsed_ord {
0
} else {
1
};
previous_collapsed_ord = collapsed_ord;
}
}
@@ -616,7 +620,7 @@ mod tests {
.map(|mut doc| {
doc.add_facet(
facet_field,
&format!("/facet/{}", thread_rng().sample(uniform)),
&format!("/facet/{}", thread_rng().sample(&uniform)),
);
doc
})

2
src/collector/filter_collector_wrapper.rs
View File

@@ -177,7 +177,7 @@ where
type Fruit = TSegmentCollector::Fruit;
fn collect(&mut self, doc: u32, score: Score) {
let value = self.fast_field_reader.get_val(doc);
let value = self.fast_field_reader.get_val(doc as u64);
if (self.predicate)(value) {
self.segment_collector.collect(doc, score)
}

4
src/collector/histogram_collector.rs
View File

@@ -37,7 +37,7 @@ impl HistogramCollector {
/// The scale/range of the histogram is not dynamic. It is required to
/// define it by supplying following parameter:
/// - `min_value`: the minimum value that can be recorded in the histogram.
/// - `bucket_width`: the length of the interval that is associated with each buckets.
/// - `bucket_width`: the length of the interval that is associated to each buckets.
/// - `num_buckets`: The overall number of buckets.
///
/// Together, this parameters define a partition of `[min_value, min_value + num_buckets *
@@ -94,7 +94,7 @@ impl SegmentCollector for SegmentHistogramCollector {
type Fruit = Vec<u64>;
fn collect(&mut self, doc: DocId, _score: Score) {
let value = self.ff_reader.get_val(doc);
let value = self.ff_reader.get_val(doc as u64);
self.histogram_computer.add_value(value);
}

38
src/collector/mod.rs
View File

@@ -142,7 +142,7 @@ pub trait Collector: Sync + Send {
/// e.g. `usize` for the `Count` collector.
type Fruit: Fruit;
/// Type of the `SegmentCollector` associated with this collector.
/// Type of the `SegmentCollector` associated to this collector.
type Child: SegmentCollector;
/// `set_segment` is called before beginning to enumerate
@@ -156,7 +156,7 @@ pub trait Collector: Sync + Send {
/// Returns true iff the collector requires to compute scores for documents.
fn requires_scoring(&self) -> bool;
/// Combines the fruit associated with the collection of each segments
/// Combines the fruit associated to the collection of each segments
/// into one fruit.
fn merge_fruits(
&self,
@@ -172,33 +172,17 @@ pub trait Collector: Sync + Send {
) -> crate::Result<<Self::Child as SegmentCollector>::Fruit> {
let mut segment_collector = self.for_segment(segment_ord as u32, reader)?;
match (reader.alive_bitset(), self.requires_scoring()) {
(Some(alive_bitset), true) => {
weight.for_each(reader, &mut |doc, score| {
if alive_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
}
})?;
}
(Some(alive_bitset), false) => {
weight.for_each_no_score(reader, &mut |doc| {
if alive_bitset.is_alive(doc) {
segment_collector.collect(doc, 0.0);
}
})?;
}
(None, true) => {
weight.for_each(reader, &mut |doc, score| {
if let Some(alive_bitset) = reader.alive_bitset() {
weight.for_each(reader, &mut |doc, score| {
if alive_bitset.is_alive(doc) {
segment_collector.collect(doc, score);
})?;
}
(None, false) => {
weight.for_each_no_score(reader, &mut |doc| {
segment_collector.collect(doc, 0.0);
})?;
}
}
})?;
} else {
weight.for_each(reader, &mut |doc, score| {
segment_collector.collect(doc, score);
})?;
}
Ok(segment_collector.harvest())
}
}

2
src/collector/tests.rs
View File

@@ -201,7 +201,7 @@ impl SegmentCollector for FastFieldSegmentCollector {
type Fruit = Vec<u64>;
fn collect(&mut self, doc: DocId, _score: Score) {
let val = self.reader.get_val(doc);
let val = self.reader.get_val(doc as u64);
self.vals.push(val);
}

10
src/collector/top_score_collector.rs
View File

@@ -137,7 +137,7 @@ struct ScorerByFastFieldReader {
impl CustomSegmentScorer<u64> for ScorerByFastFieldReader {
fn score(&mut self, doc: DocId) -> u64 {
self.ff_reader.get_val(doc)
self.ff_reader.get_val(doc as u64)
}
}
@@ -458,7 +458,7 @@ impl TopDocs {
///
/// // We can now define our actual scoring function
/// move |doc: DocId, original_score: Score| {
/// let popularity: u64 = popularity_reader.get_val(doc);
/// let popularity: u64 = popularity_reader.get_val(doc as u64);
/// // Well.. For the sake of the example we use a simple logarithm
/// // function.
/// let popularity_boost_score = ((2u64 + popularity) as Score).log2();
@@ -567,8 +567,8 @@ impl TopDocs {
///
/// // We can now define our actual scoring function
/// move |doc: DocId| {
/// let popularity: u64 = popularity_reader.get_val(doc);
/// let boosted: u64 = boosted_reader.get_val(doc);
/// let popularity: u64 = popularity_reader.get_val(doc as u64);
/// let boosted: u64 = boosted_reader.get_val(doc as u64);
/// // Score do not have to be `f64` in tantivy.
/// // Here we return a couple to get lexicographical order
/// // for free.
@@ -693,7 +693,7 @@ impl Collector for TopDocs {
}
}
/// Segment Collector associated with `TopDocs`.
/// Segment Collector associated to `TopDocs`.
pub struct TopScoreSegmentCollector(TopSegmentCollector<Score>);
impl SegmentCollector for TopScoreSegmentCollector {

2
src/collector/tweak_score_top_collector.rs
View File

@@ -40,7 +40,7 @@ pub trait ScoreTweaker<TScore>: Sync {
/// Type of the associated [`ScoreSegmentTweaker`].
type Child: ScoreSegmentTweaker<TScore>;
/// Builds a child tweaker for a specific segment. The child scorer is associated with
/// Builds a child tweaker for a specific segment. The child scorer is associated to
/// a specific segment.
fn segment_tweaker(&self, segment_reader: &SegmentReader) -> Result<Self::Child>;
}

43
src/core/index.rs
View File

@@ -19,7 +19,7 @@ use crate::error::{DataCorruption, TantivyError};
use crate::indexer::index_writer::{MAX_NUM_THREAD, MEMORY_ARENA_NUM_BYTES_MIN};
use crate::indexer::segment_updater::save_metas;
use crate::reader::{IndexReader, IndexReaderBuilder};
use crate::schema::{Cardinality, Field, FieldType, Schema};
use crate::schema::{Field, FieldType, Schema};
use crate::tokenizer::{TextAnalyzer, TokenizerManager};
use crate::IndexWriter;
@@ -149,11 +149,12 @@ impl IndexBuilder {
/// Creates a new index using the [`RamDirectory`].
///
/// The index will be allocated in anonymous memory.
/// This is useful for indexing small set of documents
/// for instances like unit test or temporary in memory index.
/// This should only be used for unit tests.
pub fn create_in_ram(self) -> Result<Index, TantivyError> {
let ram_directory = RamDirectory::create();
self.create(ram_directory)
Ok(self
.create(ram_directory)
.expect("Creating a RamDirectory should never fail"))
}
/// Creates a new index in a given filepath.
@@ -227,44 +228,10 @@ impl IndexBuilder {
))
}
}
fn validate(&self) -> crate::Result<()> {
if let Some(schema) = self.schema.as_ref() {
if let Some(sort_by_field) = self.index_settings.sort_by_field.as_ref() {
let schema_field = schema.get_field(&sort_by_field.field).ok_or_else(|| {
TantivyError::InvalidArgument(format!(
"Field to sort index {} not found in schema",
sort_by_field.field
))
})?;
let entry = schema.get_field_entry(schema_field);
if !entry.is_fast() {
return Err(TantivyError::InvalidArgument(format!(
"Field {} is no fast field. Field needs to be a single value fast field \
to be used to sort an index",
sort_by_field.field
)));
}
if entry.field_type().fastfield_cardinality() != Some(Cardinality::SingleValue) {
return Err(TantivyError::InvalidArgument(format!(
"Only single value fast field Cardinality supported for sorting index {}",
sort_by_field.field
)));
}
}
Ok(())
} else {
Err(TantivyError::InvalidArgument(
"no schema passed".to_string(),
))
}
}
/// Creates a new index given an implementation of the trait `Directory`.
///
/// If a directory previously existed, it will be erased.
fn create<T: Into<Box<dyn Directory>>>(self, dir: T) -> crate::Result<Index> {
self.validate()?;
let dir = dir.into();
let directory = ManagedDirectory::wrap(dir)?;
save_new_metas(

10
src/core/index_meta.rs
View File

@@ -130,10 +130,10 @@ impl SegmentMeta {
/// Returns the relative path of a component of our segment.
///
/// It just joins the segment id with the extension
/// associated with a segment component.
/// associated to a segment component.
pub fn relative_path(&self, component: SegmentComponent) -> PathBuf {
let mut path = self.id().uuid_string();
path.push_str(&match component {
path.push_str(&*match component {
SegmentComponent::Postings => ".idx".to_string(),
SegmentComponent::Positions => ".pos".to_string(),
SegmentComponent::Terms => ".term".to_string(),
@@ -326,13 +326,13 @@ pub struct IndexMeta {
/// `IndexSettings` to configure index options.
#[serde(default)]
pub index_settings: IndexSettings,
/// List of `SegmentMeta` information associated with each finalized segment of the index.
/// List of `SegmentMeta` information associated to each finalized segment of the index.
pub segments: Vec<SegmentMeta>,
/// Index `Schema`
pub schema: Schema,
/// Opstamp associated with the last `commit` operation.
/// Opstamp associated to the last `commit` operation.
pub opstamp: Opstamp,
/// Payload associated with the last commit.
/// Payload associated to the last commit.
///
/// Upon commit, clients can optionally add a small `String` payload to their commit
/// to help identify this commit.

41
src/core/inverted_index_reader.rs
View File

@@ -9,17 +9,18 @@ use crate::schema::{IndexRecordOption, Term};
use crate::termdict::TermDictionary;
/// The inverted index reader is in charge of accessing
/// the inverted index associated with a specific field.
/// the inverted index associated to a specific field.
///
/// # Note
///
/// It is safe to delete the segment associated with
/// It is safe to delete the segment associated to
/// an `InvertedIndexReader`. As long as it is open,
/// the [`FileSlice`] it is relying on should
/// the `FileSlice` it is relying on should
/// stay available.
///
///
/// `InvertedIndexReader` are created by calling
/// [`SegmentReader::inverted_index()`](crate::SegmentReader::inverted_index).
/// the `SegmentReader`'s [`.inverted_index(...)`] method
pub struct InvertedIndexReader {
termdict: TermDictionary,
postings_file_slice: FileSlice,
@@ -29,7 +30,7 @@ pub struct InvertedIndexReader {
}
impl InvertedIndexReader {
#[allow(clippy::needless_pass_by_value)] // for symmetry
#[cfg_attr(feature = "cargo-clippy", allow(clippy::needless_pass_by_value))] // for symmetry
pub(crate) fn new(
termdict: TermDictionary,
postings_file_slice: FileSlice,
@@ -74,7 +75,7 @@ impl InvertedIndexReader {
///
/// This is useful for enumerating through a list of terms,
/// and consuming the associated posting lists while avoiding
/// reallocating a [`BlockSegmentPostings`].
/// reallocating a `BlockSegmentPostings`.
///
/// # Warning
///
@@ -95,7 +96,7 @@ impl InvertedIndexReader {
/// Returns a block postings given a `Term`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
/// Most user should prefer using `read_postings` instead.
pub fn read_block_postings(
&self,
term: &Term,
@@ -109,7 +110,7 @@ impl InvertedIndexReader {
/// Returns a block postings given a `term_info`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
/// Most user should prefer using `read_postings` instead.
pub fn read_block_postings_from_terminfo(
&self,
term_info: &TermInfo,
@@ -129,7 +130,7 @@ impl InvertedIndexReader {
/// Returns a posting object given a `term_info`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
/// Most user should prefer using `read_postings` instead.
pub fn read_postings_from_terminfo(
&self,
term_info: &TermInfo,
@@ -163,12 +164,12 @@ impl InvertedIndexReader {
/// or `None` if the term has never been encountered and indexed.
///
/// If the field was not indexed with the indexing options that cover
/// the requested options, the returned [`SegmentPostings`] the method does not fail
/// the requested options, the returned `SegmentPostings` the method does not fail
/// and returns a `SegmentPostings` with as much information as possible.
///
/// For instance, requesting [`IndexRecordOption::WithFreqs`] for a
/// [`TextOptions`](crate::schema::TextOptions) that does not index position
/// will return a [`SegmentPostings`] with `DocId`s and frequencies.
/// For instance, requesting `IndexRecordOption::Freq` for a
/// `TextIndexingOptions` that does not index position will return a `SegmentPostings`
/// with `DocId`s and frequencies.
pub fn read_postings(
&self,
term: &Term,
@@ -210,7 +211,7 @@ impl InvertedIndexReader {
/// Returns a block postings given a `Term`.
/// This method is for an advanced usage only.
///
/// Most users should prefer using [`Self::read_postings()`] instead.
/// Most user should prefer using `read_postings` instead.
pub async fn warm_postings(
&self,
term: &Term,
@@ -230,18 +231,6 @@ impl InvertedIndexReader {
Ok(())
}
/// Read the block postings for all terms.
/// This method is for an advanced usage only.
///
/// If you know which terms to pre-load, prefer using [`Self::warm_postings`] instead.
pub async fn warm_postings_full(&self, with_positions: bool) -> crate::AsyncIoResult<()> {
self.postings_file_slice.read_bytes_async().await?;
if with_positions {
self.positions_file_slice.read_bytes_async().await?;
}
Ok(())
}
/// Returns the number of documents containing the term asynchronously.
pub async fn doc_freq_async(&self, term: &Term) -> crate::AsyncIoResult<u32> {
Ok(self

17
src/core/searcher.rs
View File

@@ -4,7 +4,7 @@ use std::{fmt, io};
use crate::collector::Collector;
use crate::core::{Executor, SegmentReader};
use crate::query::{EnableScoring, Query};
use crate::query::Query;
use crate::schema::{Document, Schema, Term};
use crate::space_usage::SearcherSpaceUsage;
use crate::store::{CacheStats, StoreReader};
@@ -69,7 +69,7 @@ pub struct Searcher {
}
impl Searcher {
/// Returns the `Index` associated with the `Searcher`
/// Returns the `Index` associated to the `Searcher`
pub fn index(&self) -> &Index {
&self.inner.index
}
@@ -108,7 +108,7 @@ impl Searcher {
store_reader.get_async(doc_address.doc_id).await
}
/// Access the schema associated with the index of this searcher.
/// Access the schema associated to the index of this searcher.
pub fn schema(&self) -> &Schema {
&self.inner.schema
}
@@ -161,11 +161,11 @@ impl Searcher {
///
/// Search works as follows :
///
/// First the weight object associated with the query is created.
/// First the weight object associated to the query is created.
///
/// Then, the query loops over the segments and for each segment :
/// - setup the collector and informs it that the segment being processed has changed.
/// - creates a SegmentCollector for collecting documents associated with the segment
/// - creates a SegmentCollector for collecting documents associated to the segment
/// - creates a `Scorer` object associated for this segment
/// - iterate through the matched documents and push them to the segment collector.
///
@@ -199,12 +199,7 @@ impl Searcher {
executor: &Executor,
) -> crate::Result<C::Fruit> {
let scoring_enabled = collector.requires_scoring();
let enabled_scoring = if scoring_enabled {
EnableScoring::Enabled(self)
} else {
EnableScoring::Disabled(self.schema())
};
let weight = query.weight(enabled_scoring)?;
let weight = query.weight(self, scoring_enabled)?;
let segment_readers = self.segment_readers();
let fruits = executor.map(
|(segment_ord, segment_reader)| {

2
src/core/segment.rs
View File

@@ -70,7 +70,7 @@ impl Segment {
/// Returns the relative path of a component of our segment.
///
/// It just joins the segment id with the extension
/// associated with a segment component.
/// associated to a segment component.
pub fn relative_path(&self, component: SegmentComponent) -> PathBuf {
self.meta.relative_path(component)
}

2
src/core/segment_component.rs
View File

@@ -6,7 +6,7 @@ use std::slice;
/// except the delete component that takes an `segment_uuid`.`delete_opstamp`.`component_extension`
#[derive(Copy, Clone, Eq, PartialEq)]
pub enum SegmentComponent {
/// Postings (or inverted list). Sorted lists of document ids, associated with terms
/// Postings (or inverted list). Sorted lists of document ids, associated to terms
Postings,
/// Positions of terms in each document.
Positions,

2
src/core/segment_id.rs
View File

@@ -57,7 +57,7 @@ impl SegmentId {
/// Picking the first 8 chars is ok to identify
/// segments in a display message (e.g. a5c4dfcb).
pub fn short_uuid_string(&self) -> String {
self.0.as_simple().to_string()[..8].to_string()
(&self.0.as_simple().to_string()[..8]).to_string()
}
/// Returns a segment uuid string.

16
src/core/segment_reader.rs
View File

@@ -89,7 +89,7 @@ impl SegmentReader {
&self.fast_fields_readers
}
/// Accessor to the `FacetReader` associated with a given `Field`.
/// Accessor to the `FacetReader` associated to a given `Field`.
pub fn facet_reader(&self, field: Field) -> crate::Result<FacetReader> {
let field_entry = self.schema.get_field_entry(field);
@@ -208,18 +208,18 @@ impl SegmentReader {
})
}
/// Returns a field reader associated with the field given in argument.
/// Returns a field reader associated to the field given in argument.
/// If the field was not present in the index during indexing time,
/// the InvertedIndexReader is empty.
///
/// The field reader is in charge of iterating through the
/// term dictionary associated with a specific field,
/// and opening the posting list associated with any term.
/// term dictionary associated to a specific field,
/// and opening the posting list associated to any term.
///
/// If the field is not marked as index, a warning is logged and an empty `InvertedIndexReader`
/// If the field is not marked as index, a warn is logged and an empty `InvertedIndexReader`
/// is returned.
/// Similarly, if the field is marked as indexed but no term has been indexed for the given
/// index, an empty `InvertedIndexReader` is returned (but no warning is logged).
/// Similarly if the field is marked as indexed but no term has been indexed for the given
/// index. an empty `InvertedIndexReader` is returned (but no warning is logged).
pub fn inverted_index(&self, field: Field) -> crate::Result<Arc<InvertedIndexReader>> {
if let Some(inv_idx_reader) = self
.inv_idx_reader_cache
@@ -241,7 +241,7 @@ impl SegmentReader {
if postings_file_opt.is_none() || record_option_opt.is_none() {
// no documents in the segment contained this field.
// As a result, no data is associated with the inverted index.
// As a result, no data is associated to the inverted index.
//
// Returns an empty inverted index.
let record_option = record_option_opt.unwrap_or(IndexRecordOption::Basic);

8
src/directory/composite_file.rs
View File

@@ -154,14 +154,14 @@ impl CompositeFile {
}
}
/// Returns the `FileSlice` associated with
/// a given `Field` and stored in a `CompositeFile`.
/// Returns the `FileSlice` associated
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read(&self, field: Field) -> Option<FileSlice> {
self.open_read_with_idx(field, 0)
}
/// Returns the `FileSlice` associated with
/// a given `Field` and stored in a `CompositeFile`.
/// Returns the `FileSlice` associated
/// to a given `Field` and stored in a `CompositeFile`.
pub fn open_read_with_idx(&self, field: Field, idx: usize) -> Option<FileSlice> {
self.offsets_index
.get(&FileAddr { field, idx })

4
src/directory/directory.rs
View File

@@ -39,7 +39,7 @@ impl RetryPolicy {
/// The `DirectoryLock` is an object that represents a file lock.
///
/// It is associated with a lock file, that gets deleted on `Drop.`
/// It is associated to a lock file, that gets deleted on `Drop.`
pub struct DirectoryLock(Box<dyn Send + Sync + 'static>);
struct DirectoryLockGuard {
@@ -55,7 +55,7 @@ impl<T: Send + Sync + 'static> From<Box<T>> for DirectoryLock {
impl Drop for DirectoryLockGuard {
fn drop(&mut self) {
if let Err(e) = self.directory.delete(&self.path) {
if let Err(e) = self.directory.delete(&*self.path) {
error!("Failed to remove the lock file. {:?}", e);
}
}

9
src/directory/file_slice.rs
View File

@@ -1,5 +1,5 @@
use std::ops::{Deref, Range};
use std::sync::Arc;
use std::sync::{Arc, Weak};
use std::{fmt, io};
use async_trait::async_trait;
@@ -8,13 +8,16 @@ use stable_deref_trait::StableDeref;
use crate::directory::OwnedBytes;
pub type ArcBytes = Arc<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
pub type WeakArcBytes = Weak<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
/// Objects that represents files sections in tantivy.
///
/// By contract, whatever happens to the directory file, as long as a FileHandle
/// is alive, the data associated with it cannot be altered or destroyed.
///
/// The underlying behavior is therefore specific to the [`Directory`](crate::Directory) that
/// created it. Despite its name, a [`FileSlice`] may or may not directly map to an actual file
/// The underlying behavior is therefore specific to the `Directory` that created it.
/// Despite its name, a `FileSlice` may or may not directly map to an actual file
/// on the filesystem.
#[async_trait]

2
src/directory/file_watcher.rs
View File

@@ -9,7 +9,7 @@ use crc32fast::Hasher;
use crate::directory::{WatchCallback, WatchCallbackList, WatchHandle};
const POLLING_INTERVAL: Duration = Duration::from_millis(if cfg!(test) { 1 } else { 500 });
pub const POLLING_INTERVAL: Duration = Duration::from_millis(if cfg!(test) { 1 } else { 500 });
// Watches a file and executes registered callbacks when the file is modified.
pub struct FileWatcher {

77
src/directory/mmap_directory.rs
View File

@@ -3,7 +3,7 @@ use std::fs::{self, File, OpenOptions};
use std::io::{self, BufWriter, Read, Seek, Write};
use std::ops::Deref;
use std::path::{Path, PathBuf};
use std::sync::{Arc, RwLock, Weak};
use std::sync::{Arc, RwLock};
use std::{fmt, result};
use fs2::FileExt;
@@ -18,13 +18,10 @@ use crate::directory::error::{
};
use crate::directory::file_watcher::FileWatcher;
use crate::directory::{
AntiCallToken, Directory, DirectoryLock, FileHandle, Lock, OwnedBytes, TerminatingWrite,
WatchCallback, WatchHandle, WritePtr,
AntiCallToken, ArcBytes, Directory, DirectoryLock, FileHandle, Lock, OwnedBytes,
TerminatingWrite, WatchCallback, WatchHandle, WeakArcBytes, WritePtr,
};
pub type ArcBytes = Arc<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
pub type WeakArcBytes = Weak<dyn Deref<Target = [u8]> + Send + Sync + 'static>;
/// Create a default io error given a string.
pub(crate) fn make_io_err(msg: String) -> io::Error {
io::Error::new(io::ErrorKind::Other, msg)
@@ -304,7 +301,7 @@ pub(crate) fn atomic_write(path: &Path, content: &[u8]) -> io::Result<()> {
"Path {:?} does not have parent directory.",
)
})?;
let mut tempfile = tempfile::Builder::new().tempfile_in(parent_path)?;
let mut tempfile = tempfile::Builder::new().tempfile_in(&parent_path)?;
tempfile.write_all(content)?;
tempfile.flush()?;
tempfile.as_file_mut().sync_data()?;
@@ -337,7 +334,7 @@ impl Directory for MmapDirectory {
Ok(Arc::new(owned_bytes))
}
/// Any entry associated with the path in the mmap will be
/// Any entry associated to the path in the mmap will be
/// removed before the file is deleted.
fn delete(&self, path: &Path) -> result::Result<(), DeleteError> {
let full_path = self.resolve_path(path);
@@ -475,8 +472,6 @@ mod tests {
// There are more tests in directory/mod.rs
// The following tests are specific to the MmapDirectory
use std::time::Duration;
use common::HasLen;
use super::*;
@@ -571,21 +566,9 @@ mod tests {
assert_eq!(mmap_directory.get_cache_info().mmapped.len(), 0);
}
fn assert_eventually<P: Fn() -> Option<String>>(predicate: P) {
for _ in 0..30 {
if predicate().is_none() {
break;
}
std::thread::sleep(Duration::from_millis(200));
}
if let Some(error_msg) = predicate() {
panic!("{}", error_msg);
}
}
#[test]
fn test_mmap_released() {
let mmap_directory = MmapDirectory::create_from_tempdir().unwrap();
fn test_mmap_released() -> crate::Result<()> {
let mmap_directory = MmapDirectory::create_from_tempdir()?;
let mut schema_builder: SchemaBuilder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let schema = schema_builder.build();
@@ -594,56 +577,40 @@ mod tests {
let index =
Index::create(mmap_directory.clone(), schema, IndexSettings::default()).unwrap();
let mut index_writer = index.writer_for_tests().unwrap();
let mut index_writer = index.writer_for_tests()?;
let mut log_merge_policy = LogMergePolicy::default();
log_merge_policy.set_min_num_segments(3);
index_writer.set_merge_policy(Box::new(log_merge_policy));
for _num_commits in 0..10 {
for _ in 0..10 {
index_writer.add_document(doc!(text_field=>"abc")).unwrap();
index_writer.add_document(doc!(text_field=>"abc"))?;
}
index_writer.commit().unwrap();
index_writer.commit()?;
}
let reader = index
.reader_builder()
.reload_policy(ReloadPolicy::Manual)
.try_into()
.unwrap();
.try_into()?;
for _ in 0..4 {
index_writer.add_document(doc!(text_field=>"abc")).unwrap();
index_writer.commit().unwrap();
reader.reload().unwrap();
index_writer.add_document(doc!(text_field=>"abc"))?;
index_writer.commit()?;
reader.reload()?;
}
index_writer.wait_merging_threads().unwrap();
index_writer.wait_merging_threads()?;
reader.reload().unwrap();
reader.reload()?;
let num_segments = reader.searcher().segment_readers().len();
assert!(num_segments <= 4);
let num_components_except_deletes_and_tempstore =
crate::core::SegmentComponent::iterator().len() - 2;
let max_num_mmapped = num_components_except_deletes_and_tempstore * num_segments;
assert_eventually(|| {
let num_mmapped = mmap_directory.get_cache_info().mmapped.len();
if num_mmapped > max_num_mmapped {
Some(format!(
"Expected at most {max_num_mmapped} mmapped files, got {num_mmapped}"
))
} else {
None
}
});
assert_eq!(
num_segments * num_components_except_deletes_and_tempstore,
mmap_directory.get_cache_info().mmapped.len()
);
}
// This test failed on CI. The last Mmap is dropped from the merging thread so there might
// be a race condition indeed.
assert_eventually(|| {
let num_mmapped = mmap_directory.get_cache_info().mmapped.len();
if num_mmapped > 0 {
Some(format!("Expected no mmapped files, got {num_mmapped}"))
} else {
None
}
});
assert!(mmap_directory.get_cache_info().mmapped.is_empty());
Ok(())
}
}

1
src/directory/mod.rs
View File

@@ -26,6 +26,7 @@ pub use ownedbytes::OwnedBytes;
pub(crate) use self::composite_file::{CompositeFile, CompositeWrite};
pub use self::directory::{Directory, DirectoryClone, DirectoryLock};
pub use self::directory_lock::{Lock, INDEX_WRITER_LOCK, META_LOCK};
pub(crate) use self::file_slice::{ArcBytes, WeakArcBytes};
pub use self::file_slice::{FileHandle, FileSlice};
pub use self::ram_directory::RamDirectory;
pub use self::watch_event_router::{WatchCallback, WatchCallbackList, WatchHandle};

33
src/directory/ram_directory.rs
View File

@@ -136,20 +136,6 @@ impl RamDirectory {
Self::default()
}
/// Deep clones the directory.
///
/// Ulterior writes on one of the copy
/// will not affect the other copy.
pub fn deep_clone(&self) -> RamDirectory {
let inner_clone = InnerDirectory {
fs: self.fs.read().unwrap().fs.clone(),
watch_router: Default::default(),
};
RamDirectory {
fs: Arc::new(RwLock::new(inner_clone)),
}
}
/// Returns the sum of the size of the different files
/// in the [`RamDirectory`].
pub fn total_mem_usage(&self) -> usize {
@@ -270,23 +256,4 @@ mod tests {
assert_eq!(directory_copy.atomic_read(path_atomic).unwrap(), msg_atomic);
assert_eq!(directory_copy.atomic_read(path_seq).unwrap(), msg_seq);
}
#[test]
fn test_ram_directory_deep_clone() {
let dir = RamDirectory::default();
let test = Path::new("test");
let test2 = Path::new("test2");
dir.atomic_write(test, b"firstwrite").unwrap();
let dir_clone = dir.deep_clone();
assert_eq!(
dir_clone.atomic_read(test).unwrap(),
dir.atomic_read(test).unwrap()
);
dir.atomic_write(test, b"original").unwrap();
dir_clone.atomic_write(test, b"clone").unwrap();
dir_clone.atomic_write(test2, b"clone2").unwrap();
assert_eq!(dir.atomic_read(test).unwrap(), b"original");
assert_eq!(&dir_clone.atomic_read(test).unwrap(), b"clone");
assert_eq!(&dir_clone.atomic_read(test2).unwrap(), b"clone2");
}
}

7
src/fastfield/bytes/mod.rs
View File

@@ -6,7 +6,7 @@ pub use self::writer::BytesFastFieldWriter;
#[cfg(test)]
mod tests {
use crate::query::{EnableScoring, TermQuery};
use crate::query::TermQuery;
use crate::schema::{BytesOptions, IndexRecordOption, Schema, Value, FAST, INDEXED, STORED};
use crate::{DocAddress, DocSet, Index, Searcher, Term};
@@ -82,7 +82,7 @@ mod tests {
let field = searcher.schema().get_field("string_bytes").unwrap();
let term = Term::from_field_bytes(field, b"lucene".as_ref());
let term_query = TermQuery::new(term, IndexRecordOption::Basic);
let term_weight = term_query.specialized_weight(EnableScoring::Enabled(&searcher))?;
let term_weight = term_query.specialized_weight(&searcher, true)?;
let term_scorer = term_weight.specialized_scorer(searcher.segment_reader(0), 1.0)?;
assert_eq!(term_scorer.doc(), 0u32);
Ok(())
@@ -95,8 +95,7 @@ mod tests {
let field = searcher.schema().get_field("string_bytes").unwrap();
let term = Term::from_field_bytes(field, b"lucene".as_ref());
let term_query = TermQuery::new(term, IndexRecordOption::Basic);
let term_weight_err =
term_query.specialized_weight(EnableScoring::Disabled(searcher.schema()));
let term_weight_err = term_query.specialized_weight(&searcher, false);
assert!(matches!(
term_weight_err,
Err(crate::TantivyError::SchemaError(_))

44
src/fastfield/bytes/reader.rs
View File

@@ -3,7 +3,7 @@ use std::sync::Arc;
use fastfield_codecs::Column;
use crate::directory::{FileSlice, OwnedBytes};
use crate::fastfield::MultiValueIndex;
use crate::fastfield::MultiValueLength;
use crate::DocId;
/// Reader for byte array fast fields
@@ -18,7 +18,7 @@ use crate::DocId;
/// and the start index for the next document, and keeping the bytes in between.
#[derive(Clone)]
pub struct BytesFastFieldReader {
idx_reader: MultiValueIndex,
idx_reader: Arc<dyn Column<u64>>,
values: OwnedBytes,
}
@@ -28,31 +28,39 @@ impl BytesFastFieldReader {
values_file: FileSlice,
) -> crate::Result<BytesFastFieldReader> {
let values = values_file.read_bytes()?;
Ok(BytesFastFieldReader {
idx_reader: MultiValueIndex::new(idx_reader),
values,
})
Ok(BytesFastFieldReader { idx_reader, values })
}
/// returns the multivalue index
pub fn get_index_reader(&self) -> &MultiValueIndex {
&self.idx_reader
fn range(&self, doc: DocId) -> (usize, usize) {
let idx = doc as u64;
let start = self.idx_reader.get_val(idx) as usize;
let stop = self.idx_reader.get_val(idx + 1) as usize;
(start, stop)
}
/// Returns the bytes associated with the given `doc`
/// Returns the bytes associated to the given `doc`
pub fn get_bytes(&self, doc: DocId) -> &[u8] {
let range = self.idx_reader.range(doc);
&self.values.as_slice()[range.start as usize..range.end as usize]
let (start, stop) = self.range(doc);
&self.values.as_slice()[start..stop]
}
/// Returns the length of the bytes associated with the given `doc`
pub fn num_bytes(&self, doc: DocId) -> u64 {
let range = self.idx_reader.range(doc);
(range.end - range.start) as u64
/// Returns the length of the bytes associated to the given `doc`
pub fn num_bytes(&self, doc: DocId) -> usize {
let (start, stop) = self.range(doc);
stop - start
}
/// Returns the overall number of bytes in this bytes fast field.
pub fn total_num_bytes(&self) -> u32 {
self.values.len() as u32
pub fn total_num_bytes(&self) -> usize {
self.values.len()
}
}
impl MultiValueLength for BytesFastFieldReader {
fn get_len(&self, doc_id: DocId) -> u64 {
self.num_bytes(doc_id) as u64
}
fn get_total_len(&self) -> u64 {
self.total_num_bytes() as u64
}
}

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

@@ -24,7 +24,7 @@ use crate::DocId;
///
/// Once acquired, writing is done by calling
/// [`.add_document_val(&[u8])`](BytesFastFieldWriter::add_document_val)
/// once per document, even if there are no bytes associated with it.
/// once per document, even if there are no bytes associated to it.
pub struct BytesFastFieldWriter {
field: Field,
vals: Vec<u8>,
@@ -45,7 +45,7 @@ impl BytesFastFieldWriter {
pub fn mem_usage(&self) -> usize {
self.vals.capacity() + self.doc_index.capacity() * std::mem::size_of::<u64>()
}
/// Access the field associated with the `BytesFastFieldWriter`
/// Access the field associated to the `BytesFastFieldWriter`
pub fn field(&self) -> Field {
self.field
}
@@ -57,18 +57,17 @@ impl BytesFastFieldWriter {
/// Shift to the next document and add all of the
/// matching field values present in the document.
pub fn add_document(&mut self, doc: &Document) -> crate::Result<()> {
pub fn add_document(&mut self, doc: &Document) {
self.next_doc();
for field_value in doc.get_all(self.field) {
if let Value::Bytes(ref bytes) = field_value {
self.vals.extend_from_slice(bytes);
return Ok(());
return;
}
}
Ok(())
}
/// Register the bytes associated with a document.
/// Register the bytes associated to a document.
///
/// The method returns the `DocId` of the document that was
/// just written.

6
src/fastfield/facet_reader.rs
View File

@@ -7,7 +7,7 @@ use crate::termdict::{TermDictionary, TermOrdinal};
use crate::DocId;
/// The facet reader makes it possible to access the list of
/// facets associated with a given document in a specific
/// facets associated to a given document in a specific
/// segment.
///
/// Rather than manipulating `Facet` object directly, the API
@@ -58,7 +58,7 @@ impl FacetReader {
&self.term_dict
}
/// Given a term ordinal returns the term associated with it.
/// Given a term ordinal returns the term associated to it.
pub fn facet_from_ord(
&mut self,
facet_ord: TermOrdinal,
@@ -74,7 +74,7 @@ impl FacetReader {
Ok(())
}
/// Return the list of facet ordinals associated with a document.
/// Return the list of facet ordinals associated to a document.
pub fn facet_ords(&self, doc: DocId, output: &mut Vec<u64>) {
self.term_ords.get_vals(doc, output);
}

303
src/fastfield/mod.rs
View File

@@ -7,15 +7,16 @@
//! It is designed for the fast random access of some document
//! fields given a document id.
//!
//! Fast fields are useful when a field is required for all or most of
//! the `DocSet`: for instance for scoring, grouping, aggregation, filtering, or faceting.
//! `FastField` are useful when a field is required for all or most of
//! the `DocSet` : for instance for scoring, grouping, filtering, or faceting.
//!
//!
//! Fields have to be declared as `FAST` in the schema.
//! Currently supported fields are: u64, i64, f64, bytes and text.
//! Fields have to be declared as `FAST` in the schema.
//! Currently supported fields are: u64, i64, f64 and bytes.
//!
//! Fast fields are stored in with [different codecs](fastfield_codecs). The best codec is detected
//! automatically, when serializing.
//! u64, i64 and f64 fields are stored in a bit-packed fashion so that
//! their memory usage is directly linear with the amplitude of the
//! values stored.
//!
//! Read access performance is comparable to that of an array lookup.
@@ -25,18 +26,14 @@ pub use self::alive_bitset::{intersect_alive_bitsets, write_alive_bitset, AliveB
pub use self::bytes::{BytesFastFieldReader, BytesFastFieldWriter};
pub use self::error::{FastFieldNotAvailableError, Result};
pub use self::facet_reader::FacetReader;
pub(crate) use self::multivalued::{get_fastfield_codecs_for_multivalue, MultivalueStartIndex};
pub use self::multivalued::{
MultiValueIndex, MultiValueU128FastFieldWriter, MultiValuedFastFieldReader,
MultiValuedFastFieldWriter, MultiValuedU128FastFieldReader,
};
pub(crate) use self::readers::type_and_cardinality;
pub(crate) use self::multivalued::MultivalueStartIndex;
pub use self::multivalued::{MultiValuedFastFieldReader, MultiValuedFastFieldWriter};
pub use self::readers::FastFieldReaders;
pub(crate) use self::readers::{type_and_cardinality, FastType};
pub use self::serializer::{Column, CompositeFastFieldSerializer};
use self::writer::unexpected_value;
pub use self::writer::{FastFieldsWriter, IntFastFieldWriter};
use crate::schema::{Type, Value};
use crate::DateTime;
use crate::{DateTime, DocId};
mod alive_bitset;
mod bytes;
@@ -44,9 +41,19 @@ mod error;
mod facet_reader;
mod multivalued;
mod readers;
mod remapped_column;
mod serializer;
mod writer;
/// Trait for `BytesFastFieldReader` and `MultiValuedFastFieldReader` to return the length of data
/// for a doc_id
pub trait MultiValueLength {
/// returns the num of values associated to a doc_id
fn get_len(&self, doc_id: DocId) -> u64;
/// returns the sum of num values for all doc_ids
fn get_total_len(&self) -> u64;
}
/// Trait for types that are allowed for fast fields:
/// (u64, i64 and f64, bool, DateTime).
pub trait FastValue:
@@ -109,16 +116,15 @@ impl FastValue for DateTime {
}
}
fn value_to_u64(value: &Value) -> crate::Result<u64> {
let value = match value {
fn value_to_u64(value: &Value) -> u64 {
match value {
Value::U64(val) => val.to_u64(),
Value::I64(val) => val.to_u64(),
Value::F64(val) => val.to_u64(),
Value::Bool(val) => val.to_u64(),
Value::Date(val) => val.to_u64(),
_ => return Err(unexpected_value("u64/i64/f64/bool/date", value)),
};
Ok(value)
_ => panic!("Expected a u64/i64/f64/bool/date field, got {:?} ", value),
}
}
/// The fast field type
@@ -145,7 +151,7 @@ impl FastFieldType {
mod tests {
use std::collections::HashMap;
use std::ops::{Range, RangeInclusive};
use std::ops::Range;
use std::path::Path;
use std::sync::Arc;
@@ -159,9 +165,7 @@ mod tests {
use super::*;
use crate::directory::{CompositeFile, Directory, RamDirectory, WritePtr};
use crate::merge_policy::NoMergePolicy;
use crate::schema::{
Cardinality, Document, Field, Schema, SchemaBuilder, FAST, INDEXED, STRING, TEXT,
};
use crate::schema::{Cardinality, Document, Field, Schema, SchemaBuilder, FAST, STRING, TEXT};
use crate::time::OffsetDateTime;
use crate::{DateOptions, DatePrecision, Index, SegmentId, SegmentReader};
@@ -175,9 +179,9 @@ mod tests {
#[test]
pub fn test_fastfield() {
let test_fastfield = fastfield_codecs::serialize_and_load(&[100u64, 200u64, 300u64][..]);
assert_eq!(test_fastfield.get_val(0), 100);
assert_eq!(test_fastfield.get_val(1), 200);
assert_eq!(test_fastfield.get_val(2), 300);
assert_eq!(test_fastfield.get_val(0u64), 100);
assert_eq!(test_fastfield.get_val(1u64), 200);
assert_eq!(test_fastfield.get_val(2u64), 300);
}
#[test]
@@ -194,22 +198,16 @@ mod tests {
let write: WritePtr = directory.open_write(Path::new("test")).unwrap();
let mut serializer = CompositeFastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
fast_field_writers
.add_document(&doc!(*FIELD=>13u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>14u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>2u64))
.unwrap();
fast_field_writers.add_document(&doc!(*FIELD=>13u64));
fast_field_writers.add_document(&doc!(*FIELD=>14u64));
fast_field_writers.add_document(&doc!(*FIELD=>2u64));
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(path).unwrap();
assert_eq!(file.len(), 34);
assert_eq!(file.len(), 25);
let composite_file = CompositeFile::open(&file)?;
let fast_field_bytes = composite_file.open_read(*FIELD).unwrap().read_bytes()?;
let fast_field_reader = open::<u64>(fast_field_bytes)?;
@@ -227,38 +225,20 @@ mod tests {
let write: WritePtr = directory.open_write(Path::new("test"))?;
let mut serializer = CompositeFastFieldSerializer::from_write(write)?;
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
fast_field_writers
.add_document(&doc!(*FIELD=>4u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>14_082_001u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>3_052u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>9_002u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>15_001u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>777u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>1_002u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>1_501u64))
.unwrap();
fast_field_writers
.add_document(&doc!(*FIELD=>215u64))
.unwrap();
fast_field_writers.add_document(&doc!(*FIELD=>4u64));
fast_field_writers.add_document(&doc!(*FIELD=>14_082_001u64));
fast_field_writers.add_document(&doc!(*FIELD=>3_052u64));
fast_field_writers.add_document(&doc!(*FIELD=>9_002u64));
fast_field_writers.add_document(&doc!(*FIELD=>15_001u64));
fast_field_writers.add_document(&doc!(*FIELD=>777u64));
fast_field_writers.add_document(&doc!(*FIELD=>1_002u64));
fast_field_writers.add_document(&doc!(*FIELD=>1_501u64));
fast_field_writers.add_document(&doc!(*FIELD=>215u64));
fast_field_writers.serialize(&mut serializer, &HashMap::new(), None)?;
serializer.close()?;
}
let file = directory.open_read(path)?;
assert_eq!(file.len(), 62);
assert_eq!(file.len(), 53);
{
let fast_fields_composite = CompositeFile::open(&file)?;
let data = fast_fields_composite
@@ -289,9 +269,7 @@ mod tests {
let mut serializer = CompositeFastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
for _ in 0..10_000 {
fast_field_writers
.add_document(&doc!(*FIELD=>100_000u64))
.unwrap();
fast_field_writers.add_document(&doc!(*FIELD=>100_000u64));
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -299,7 +277,7 @@ mod tests {
serializer.close().unwrap();
}
let file = directory.open_read(path).unwrap();
assert_eq!(file.len(), 35);
assert_eq!(file.len(), 26);
{
let fast_fields_composite = CompositeFile::open(&file).unwrap();
let data = fast_fields_composite
@@ -324,13 +302,9 @@ mod tests {
let mut serializer = CompositeFastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
// forcing the amplitude to be high
fast_field_writers
.add_document(&doc!(*FIELD=>0u64))
.unwrap();
fast_field_writers.add_document(&doc!(*FIELD=>0u64));
for i in 0u64..10_000u64 {
fast_field_writers
.add_document(&doc!(*FIELD=>5_000_000_000_000_000_000u64 + i))
.unwrap();
fast_field_writers.add_document(&doc!(*FIELD=>5_000_000_000_000_000_000u64 + i));
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -338,7 +312,7 @@ mod tests {
serializer.close().unwrap();
}
let file = directory.open_read(path).unwrap();
assert_eq!(file.len(), 80049);
assert_eq!(file.len(), 80040);
{
let fast_fields_composite = CompositeFile::open(&file)?;
let data = fast_fields_composite
@@ -372,7 +346,7 @@ mod tests {
for i in -100i64..10_000i64 {
let mut doc = Document::default();
doc.add_i64(i64_field, i);
fast_field_writers.add_document(&doc).unwrap();
fast_field_writers.add_document(&doc);
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -380,7 +354,7 @@ mod tests {
serializer.close().unwrap();
}
let file = directory.open_read(path).unwrap();
assert_eq!(file.len(), 49_usize);
assert_eq!(file.len(), 40_usize);
{
let fast_fields_composite = CompositeFile::open(&file)?;
@@ -393,7 +367,7 @@ mod tests {
assert_eq!(fast_field_reader.min_value(), -100i64);
assert_eq!(fast_field_reader.max_value(), 9_999i64);
for (doc, i) in (-100i64..10_000i64).enumerate() {
assert_eq!(fast_field_reader.get_val(doc as u32), i);
assert_eq!(fast_field_reader.get_val(doc as u64), i);
}
let mut buffer = vec![0i64; 100];
fast_field_reader.get_range(53, &mut buffer[..]);
@@ -417,7 +391,7 @@ mod tests {
let mut serializer = CompositeFastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&schema);
let doc = Document::default();
fast_field_writers.add_document(&doc).unwrap();
fast_field_writers.add_document(&doc);
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
.unwrap();
@@ -451,7 +425,7 @@ mod tests {
permutation
}
fn test_intfastfield_permutation_with_data(permutation: Vec<u64>) -> crate::Result<()> {
fn test_intfastfield_permutation_with_data(permutation: &[u64]) -> crate::Result<()> {
let path = Path::new("test");
let n = permutation.len();
let directory = RamDirectory::create();
@@ -459,8 +433,8 @@ mod tests {
let write: WritePtr = directory.open_write(Path::new("test"))?;
let mut serializer = CompositeFastFieldSerializer::from_write(write)?;
let mut fast_field_writers = FastFieldsWriter::from_schema(&SCHEMA);
for &x in &permutation {
fast_field_writers.add_document(&doc!(*FIELD=>x)).unwrap();
for &x in permutation {
fast_field_writers.add_document(&doc!(*FIELD=>x));
}
fast_field_writers.serialize(&mut serializer, &HashMap::new(), None)?;
serializer.close()?;
@@ -473,25 +447,31 @@ mod tests {
.unwrap()
.read_bytes()?;
let fast_field_reader = open::<u64>(data)?;
for a in 0..n {
assert_eq!(fast_field_reader.get_val(a as u32), permutation[a as usize]);
assert_eq!(fast_field_reader.get_val(a as u64), permutation[a as usize]);
}
}
Ok(())
}
#[test]
fn test_intfastfield_permutation_gcd() -> crate::Result<()> {
let permutation = generate_permutation_gcd();
test_intfastfield_permutation_with_data(permutation)?;
fn test_intfastfield_simple() -> crate::Result<()> {
let permutation = &[1, 2, 3];
test_intfastfield_permutation_with_data(&permutation[..])?;
Ok(())
}
#[test]
fn test_intfastfield_permutation() -> crate::Result<()> {
let permutation = generate_permutation();
test_intfastfield_permutation_with_data(permutation)?;
test_intfastfield_permutation_with_data(&permutation)?;
Ok(())
}
#[test]
fn test_intfastfield_permutation_gcd() -> crate::Result<()> {
let permutation = generate_permutation_gcd();
test_intfastfield_permutation_with_data(&permutation)?;
Ok(())
}
@@ -810,21 +790,17 @@ mod tests {
let write: WritePtr = directory.open_write(path).unwrap();
let mut serializer = CompositeFastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&schema);
fast_field_writers.add_document(&doc!(field=>true)).unwrap();
fast_field_writers
.add_document(&doc!(field=>false))
.unwrap();
fast_field_writers.add_document(&doc!(field=>true)).unwrap();
fast_field_writers
.add_document(&doc!(field=>false))
.unwrap();
fast_field_writers.add_document(&doc!(field=>true));
fast_field_writers.add_document(&doc!(field=>false));
fast_field_writers.add_document(&doc!(field=>true));
fast_field_writers.add_document(&doc!(field=>false));
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
.unwrap();
serializer.close().unwrap();
}
let file = directory.open_read(path).unwrap();
assert_eq!(file.len(), 33);
assert_eq!(file.len(), 24);
let composite_file = CompositeFile::open(&file)?;
let data = composite_file.open_read(field).unwrap().read_bytes()?;
let fast_field_reader = open::<bool>(data)?;
@@ -851,10 +827,8 @@ mod tests {
let mut serializer = CompositeFastFieldSerializer::from_write(write).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(&schema);
for _ in 0..50 {
fast_field_writers.add_document(&doc!(field=>true)).unwrap();
fast_field_writers
.add_document(&doc!(field=>false))
.unwrap();
fast_field_writers.add_document(&doc!(field=>true));
fast_field_writers.add_document(&doc!(field=>false));
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -862,7 +836,7 @@ mod tests {
serializer.close().unwrap();
}
let file = directory.open_read(path).unwrap();
assert_eq!(file.len(), 45);
assert_eq!(file.len(), 36);
let composite_file = CompositeFile::open(&file)?;
let data = composite_file.open_read(field).unwrap().read_bytes()?;
let fast_field_reader = open::<bool>(data)?;
@@ -888,13 +862,13 @@ mod tests {
let mut serializer = CompositeFastFieldSerializer::from_write(write)?;
let mut fast_field_writers = FastFieldsWriter::from_schema(&schema);
let doc = Document::default();
fast_field_writers.add_document(&doc).unwrap();
fast_field_writers.add_document(&doc);
fast_field_writers.serialize(&mut serializer, &HashMap::new(), None)?;
serializer.close()?;
}
let file = directory.open_read(path).unwrap();
let composite_file = CompositeFile::open(&file)?;
assert_eq!(file.len(), 32);
assert_eq!(file.len(), 23);
let data = composite_file.open_read(field).unwrap().read_bytes()?;
let fast_field_reader = open::<bool>(data)?;
assert_eq!(fast_field_reader.get_val(0), false);
@@ -914,7 +888,7 @@ mod tests {
CompositeFastFieldSerializer::from_write_with_codec(write, codec_types).unwrap();
let mut fast_field_writers = FastFieldsWriter::from_schema(schema);
for doc in docs {
fast_field_writers.add_document(doc).unwrap();
fast_field_writers.add_document(doc);
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -928,10 +902,10 @@ mod tests {
pub fn test_gcd_date() -> crate::Result<()> {
let size_prec_sec =
test_gcd_date_with_codec(FastFieldCodecType::Bitpacked, DatePrecision::Seconds)?;
assert_eq!(size_prec_sec, 5 + 4 + 28 + (1_000 * 13) / 8); // 13 bits per val = ceil(log_2(number of seconds in 2hours);
assert_eq!(size_prec_sec, 28 + (1_000 * 13) / 8); // 13 bits per val = ceil(log_2(number of seconds in 2hours);
let size_prec_micro =
test_gcd_date_with_codec(FastFieldCodecType::Bitpacked, DatePrecision::Microseconds)?;
assert_eq!(size_prec_micro, 5 + 4 + 26 + (1_000 * 33) / 8); // 33 bits per val = ceil(log_2(number of microsecsseconds in 2hours);
assert_eq!(size_prec_micro, 26 + (1_000 * 33) / 8); // 33 bits per val = ceil(log_2(number of microsecsseconds in 2hours);
Ok(())
}
@@ -967,121 +941,8 @@ mod tests {
let test_fastfield = open::<DateTime>(file.read_bytes()?)?;
for (i, time) in times.iter().enumerate() {
assert_eq!(test_fastfield.get_val(i as u32), time.truncate(precision));
assert_eq!(test_fastfield.get_val(i as u64), time.truncate(precision));
}
Ok(len)
}
#[test]
fn test_gcd_bug_regression_1757() {
let mut schema_builder = Schema::builder();
let num_field = schema_builder.add_u64_field("url_norm_hash", FAST | INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
let mut writer = index.writer_for_tests().unwrap();
writer
.add_document(doc! {
num_field => 100u64,
})
.unwrap();
writer
.add_document(doc! {
num_field => 200u64,
})
.unwrap();
writer
.add_document(doc! {
num_field => 300u64,
})
.unwrap();
writer.commit().unwrap();
}
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let segment = &searcher.segment_readers()[0];
let field = segment.fast_fields().u64(num_field).unwrap();
let numbers = vec![100, 200, 300];
let test_range = |range: RangeInclusive<u64>| {
let expexted_count = numbers.iter().filter(|num| range.contains(num)).count();
let mut vec = vec![];
field.get_docids_for_value_range(range, 0..u32::MAX, &mut vec);
assert_eq!(vec.len(), expexted_count);
};
test_range(50..=50);
test_range(150..=150);
test_range(350..=350);
test_range(100..=250);
test_range(101..=200);
test_range(101..=199);
test_range(100..=300);
test_range(100..=299);
}
#[test]
fn test_mapping_bug_docids_for_value_range() {
let mut schema_builder = Schema::builder();
let num_field = schema_builder.add_u64_field("url_norm_hash", FAST | INDEXED);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
{
// Values without gcd, but with min_value
let mut writer = index.writer_for_tests().unwrap();
writer
.add_document(doc! {
num_field => 1000u64,
})
.unwrap();
writer
.add_document(doc! {
num_field => 1001u64,
})
.unwrap();
writer
.add_document(doc! {
num_field => 1003u64,
})
.unwrap();
writer.commit().unwrap();
}
let reader = index.reader().unwrap();
let searcher = reader.searcher();
let segment = &searcher.segment_readers()[0];
let field = segment.fast_fields().u64(num_field).unwrap();
let numbers = vec![1000, 1001, 1003];
let test_range = |range: RangeInclusive<u64>| {
let expexted_count = numbers.iter().filter(|num| range.contains(num)).count();
let mut vec = vec![];
field.get_docids_for_value_range(range, 0..u32::MAX, &mut vec);
assert_eq!(vec.len(), expexted_count);
};
let test_range_variant = |start, stop| {
let start_range = start..=stop;
test_range(start_range);
let start_range = start..=(stop - 1);
test_range(start_range);
let start_range = start..=(stop + 1);
test_range(start_range);
let start_range = (start - 1)..=stop;
test_range(start_range);
let start_range = (start - 1)..=(stop - 1);
test_range(start_range);
let start_range = (start - 1)..=(stop + 1);
test_range(start_range);
let start_range = (start + 1)..=stop;
test_range(start_range);
let start_range = (start + 1)..=(stop - 1);
test_range(start_range);
let start_range = (start + 1)..=(stop + 1);
test_range(start_range);
};
test_range_variant(50, 50);
test_range_variant(1000, 1000);
test_range_variant(1000, 1002);
}
}

148
src/fastfield/multivalued/index.rs
View File

@@ -1,148 +0,0 @@
use std::ops::Range;
use std::sync::Arc;
use fastfield_codecs::Column;
use crate::DocId;
#[derive(Clone)]
/// Index to resolve value range for given doc_id.
/// Starts at 0.
pub struct MultiValueIndex {
idx: Arc<dyn Column<u64>>,
}
impl MultiValueIndex {
pub(crate) fn new(idx: Arc<dyn Column<u64>>) -> Self {
Self { idx }
}
/// Returns `[start, end)`, such that the values associated with
/// the given document are `start..end`.
#[inline]
pub(crate) fn range(&self, doc: DocId) -> Range<u32> {
let start = self.idx.get_val(doc) as u32;
let end = self.idx.get_val(doc + 1) as u32;
start..end
}
/// Given a range of documents, returns the Range of value offsets fo
/// these documents.
///
/// For instance, `given start_doc..end_doc`,
/// if we assume Document #start_doc end #end_doc both
/// have values, this function returns `start..end`
/// such that `value_column.get(start_doc)` is the first value of
/// `start_doc` (well, if there is one), and `value_column.get(end_doc - 1)`
/// is the last value of `end_doc`.
///
/// The passed end range is allowed to be out of bounds, in which case
/// it will be clipped to make it valid.
#[inline]
pub(crate) fn docid_range_to_position_range(&self, range: Range<DocId>) -> Range<u32> {
let end_docid = range.end.min(self.num_docs() - 1) + 1;
let start_docid = range.start.min(end_docid);
let start = self.idx.get_val(start_docid) as u32;
let end = self.idx.get_val(end_docid) as u32;
assert!(start <= end);
start..end
}
/// returns the num of values associated with a doc_id
pub(crate) fn num_vals_for_doc(&self, doc: DocId) -> u32 {
let range = self.range(doc);
range.end - range.start
}
/// Returns the overall number of values in this field.
#[inline]
pub fn total_num_vals(&self) -> u32 {
self.idx.max_value() as u32
}
/// Returns the number of documents in the index.
#[inline]
pub fn num_docs(&self) -> u32 {
self.idx.num_vals() - 1
}
/// Converts a list of positions of values in a 1:n index to the corresponding list of DocIds.
/// Positions are converted inplace to docids.
///
/// Since there is no index for value pos -> docid, but docid -> value pos range, we scan the
/// index.
///
/// Correctness: positions needs to be sorted. idx_reader needs to contain monotonically
/// increasing positions.
///
///
/// TODO: Instead of a linear scan we can employ a exponential search into binary search to
/// match a docid to its value position.
pub(crate) fn positions_to_docids(&self, doc_id_range: Range<u32>, positions: &mut Vec<u32>) {
if positions.is_empty() {
return;
}
let mut cur_doc = doc_id_range.start;
let mut last_doc = None;
assert!(self.idx.get_val(doc_id_range.start) as u32 <= positions[0]);
let mut write_doc_pos = 0;
for i in 0..positions.len() {
let pos = positions[i];
loop {
let end = self.idx.get_val(cur_doc + 1) as u32;
if end > pos {
positions[write_doc_pos] = cur_doc;
write_doc_pos += if last_doc == Some(cur_doc) { 0 } else { 1 };
last_doc = Some(cur_doc);
break;
}
cur_doc += 1;
}
}
positions.truncate(write_doc_pos);
}
}
#[cfg(test)]
mod tests {
use std::ops::Range;
use std::sync::Arc;
use fastfield_codecs::IterColumn;
use crate::fastfield::MultiValueIndex;
fn index_to_pos_helper(
index: &MultiValueIndex,
doc_id_range: Range<u32>,
positions: &[u32],
) -> Vec<u32> {
let mut positions = positions.to_vec();
index.positions_to_docids(doc_id_range, &mut positions);
positions
}
#[test]
fn test_positions_to_docid() {
let offsets = vec![0, 10, 12, 15, 22, 23]; // docid values are [0..10, 10..12, 12..15, etc.]
let column = IterColumn::from(offsets.into_iter());
let index = MultiValueIndex::new(Arc::new(column));
assert_eq!(index.num_docs(), 5);
{
let positions = vec![10u32, 11, 15, 20, 21, 22];
assert_eq!(index_to_pos_helper(&index, 0..5, &positions), vec![1, 3, 4]);
assert_eq!(index_to_pos_helper(&index, 1..5, &positions), vec![1, 3, 4]);
assert_eq!(index_to_pos_helper(&index, 0..5, &[9]), vec![0]);
assert_eq!(index_to_pos_helper(&index, 1..5, &[10]), vec![1]);
assert_eq!(index_to_pos_helper(&index, 1..5, &[11]), vec![1]);
assert_eq!(index_to_pos_helper(&index, 2..5, &[12]), vec![2]);
assert_eq!(index_to_pos_helper(&index, 2..5, &[12, 14]), vec![2]);
assert_eq!(index_to_pos_helper(&index, 2..5, &[12, 14, 15]), vec![2, 3]);
}
}
}

95
src/fastfield/multivalued/mod.rs
View File

@@ -1,23 +1,10 @@
mod index;
mod multivalue_start_index;
mod reader;
mod writer;
use fastfield_codecs::FastFieldCodecType;
pub use index::MultiValueIndex;
pub use self::reader::{MultiValuedFastFieldReader, MultiValuedU128FastFieldReader};
pub(crate) use self::writer::MultivalueStartIndex;
pub use self::writer::{MultiValueU128FastFieldWriter, MultiValuedFastFieldWriter};
/// The valid codecs for multivalue values excludes the linear interpolation codec.
///
/// This limitation is only valid for the values, not the offset index of the multivalue index.
pub(crate) fn get_fastfield_codecs_for_multivalue() -> [FastFieldCodecType; 2] {
[
FastFieldCodecType::Bitpacked,
FastFieldCodecType::BlockwiseLinear,
]
}
pub(crate) use self::multivalue_start_index::MultivalueStartIndex;
pub use self::reader::MultiValuedFastFieldReader;
pub use self::writer::MultiValuedFastFieldWriter;
#[cfg(test)]
mod tests {
@@ -416,74 +403,6 @@ mod bench {
use crate::schema::{Cardinality, NumericOptions, Schema};
use crate::Document;
fn bench_multi_value_ff_merge_opt(
num_docs: usize,
segments_every_n_docs: usize,
merge_policy: impl crate::indexer::MergePolicy + 'static,
) {
let mut builder = crate::schema::SchemaBuilder::new();
let fast_multi =
crate::schema::NumericOptions::default().set_fast(Cardinality::MultiValues);
let multi_field = builder.add_f64_field("f64s", fast_multi);
let index = crate::Index::create_in_ram(builder.build());
let mut writer = index.writer_for_tests().unwrap();
writer.set_merge_policy(Box::new(merge_policy));
for i in 0..num_docs {
let mut doc = crate::Document::new();
doc.add_f64(multi_field, 0.24);
doc.add_f64(multi_field, 0.27);
doc.add_f64(multi_field, 0.37);
if i % 3 == 0 {
doc.add_f64(multi_field, 0.44);
}
writer.add_document(doc).unwrap();
if i % segments_every_n_docs == 0 {
writer.commit().unwrap();
}
}
{
writer.wait_merging_threads().unwrap();
let mut writer = index.writer_for_tests().unwrap();
let segment_ids = index.searchable_segment_ids().unwrap();
writer.merge(&segment_ids).wait().unwrap();
}
// If a merging thread fails, we should end up with more
// than one segment here
assert_eq!(1, index.searchable_segments().unwrap().len());
}
#[bench]
fn bench_multi_value_ff_merge_many_segments(b: &mut Bencher) {
let num_docs = 100_000;
b.iter(|| {
bench_multi_value_ff_merge_opt(num_docs, 1_000, crate::indexer::NoMergePolicy);
});
}
#[bench]
fn bench_multi_value_ff_merge_many_segments_log_merge(b: &mut Bencher) {
let num_docs = 100_000;
b.iter(|| {
let merge_policy = crate::indexer::LogMergePolicy::default();
bench_multi_value_ff_merge_opt(num_docs, 1_000, merge_policy);
});
}
#[bench]
fn bench_multi_value_ff_merge_few_segments(b: &mut Bencher) {
let num_docs = 100_000;
b.iter(|| {
bench_multi_value_ff_merge_opt(num_docs, 33_000, crate::indexer::NoMergePolicy);
});
}
fn multi_values(num_docs: usize, vals_per_doc: usize) -> Vec<Vec<u64>> {
let mut vals = vec![];
for _i in 0..num_docs {
@@ -517,7 +436,7 @@ mod bench {
for val in block {
doc.add_u64(field, *val);
}
fast_field_writers.add_document(&doc).unwrap();
fast_field_writers.add_document(&doc);
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -575,7 +494,7 @@ mod bench {
for val in block {
doc.add_u64(field, *val);
}
fast_field_writers.add_document(&doc).unwrap();
fast_field_writers.add_document(&doc);
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), None)
@@ -608,7 +527,7 @@ mod bench {
for val in block {
doc.add_u64(field, *val);
}
fast_field_writers.add_document(&doc).unwrap();
fast_field_writers.add_document(&doc);
}
fast_field_writers
.serialize(&mut serializer, &HashMap::new(), Some(&doc_id_mapping))

195
src/fastfield/multivalued/multivalue_start_index.rs Normal file
View File

@@ -0,0 +1,195 @@
use fastfield_codecs::{Column, ColumnReader};
use crate::indexer::doc_id_mapping::DocIdMapping;
use crate::DocId;
pub(crate) struct MultivalueStartIndex<'a, C: Column> {
column: &'a C,
doc_id_map: &'a DocIdMapping,
min_value: u64,
max_value: u64,
}
struct MultivalueStartIndexReader<'a, C: Column> {
column: &'a C,
doc_id_map: &'a DocIdMapping,
idx: u64,
val: u64,
len: u64,
}
impl<'a, C: Column> MultivalueStartIndexReader<'a, C> {
fn new(column: &'a C, doc_id_map: &'a DocIdMapping) -> Self {
Self {
column,
doc_id_map,
idx: u64::MAX,
val: 0,
len: doc_id_map.num_new_doc_ids() as u64 + 1,
}
}
fn reset(&mut self) {
self.idx = u64::MAX;
self.val = 0;
}
}
impl<'a, C: Column> ColumnReader for MultivalueStartIndexReader<'a, C> {
fn seek(&mut self, idx: u64) -> u64 {
if self.idx > idx {
self.reset();
self.advance();
}
for _ in self.idx..idx {
self.advance();
}
self.get()
}
fn advance(&mut self) -> bool {
if self.idx == u64::MAX {
self.idx = 0;
self.val = 0;
return true;
}
let new_doc_id: DocId = self.idx as DocId;
self.idx += 1;
if self.idx >= self.len {
self.idx = self.len;
return false;
}
let old_doc: DocId = self.doc_id_map.get_old_doc_id(new_doc_id);
let num_vals_for_doc =
self.column.get_val(old_doc as u64 + 1) - self.column.get_val(old_doc as u64);
self.val += num_vals_for_doc;
true
}
fn get(&self) -> u64 {
self.val
}
}
impl<'a, C: Column> MultivalueStartIndex<'a, C> {
pub fn new(column: &'a C, doc_id_map: &'a DocIdMapping) -> Self {
assert_eq!(column.num_vals(), doc_id_map.num_old_doc_ids() as u64 + 1);
let iter = MultivalueStartIndexIter::new(column, doc_id_map);
let (min_value, max_value) = tantivy_bitpacker::minmax(iter).unwrap_or((0, 0));
MultivalueStartIndex {
column,
doc_id_map,
min_value,
max_value,
}
}
fn specialized_reader(&self) -> MultivalueStartIndexReader<'a, C> {
MultivalueStartIndexReader::new(self.column, self.doc_id_map)
}
}
impl<'a, C: Column> Column for MultivalueStartIndex<'a, C> {
fn reader(&self) -> Box<dyn ColumnReader + '_> {
Box::new(self.specialized_reader())
}
fn get_val(&self, idx: u64) -> u64 {
let mut reader = self.specialized_reader();
reader.seek(idx)
}
fn min_value(&self) -> u64 {
self.min_value
}
fn max_value(&self) -> u64 {
self.max_value
}
fn num_vals(&self) -> u64 {
(self.doc_id_map.num_new_doc_ids() + 1) as u64
}
}
struct MultivalueStartIndexIter<'a, C: Column> {
column: &'a C,
doc_id_map: &'a DocIdMapping,
new_doc_id: usize,
offset: u64,
}
impl<'a, C: Column> MultivalueStartIndexIter<'a, C> {
fn new(column: &'a C, doc_id_map: &'a DocIdMapping) -> Self {
Self {
column,
doc_id_map,
new_doc_id: 0,
offset: 0,
}
}
}
impl<'a, C: Column> Iterator for MultivalueStartIndexIter<'a, C> {
type Item = u64;
fn next(&mut self) -> Option<Self::Item> {
if self.new_doc_id > self.doc_id_map.num_new_doc_ids() {
return None;
}
let new_doc_id = self.new_doc_id;
self.new_doc_id += 1;
let start_offset = self.offset;
if new_doc_id < self.doc_id_map.num_new_doc_ids() {
let old_doc = self.doc_id_map.get_old_doc_id(new_doc_id as u32) as u64;
let num_vals_for_doc = self.column.get_val(old_doc + 1) - self.column.get_val(old_doc);
self.offset += num_vals_for_doc;
}
Some(start_offset)
}
}
#[cfg(test)]
mod tests {
use fastfield_codecs::VecColumn;
use super::*;
#[test]
fn test_multivalue_start_index() {
let doc_id_mapping = DocIdMapping::from_new_id_to_old_id(vec![4, 1, 2]);
assert_eq!(doc_id_mapping.num_old_doc_ids(), 5);
let col = VecColumn::from(&[0u64, 3, 5, 10, 12, 16][..]);
let multivalue_start_index = MultivalueStartIndex::new(
&col, // 3, 2, 5, 2, 4
&doc_id_mapping,
);
assert_eq!(multivalue_start_index.num_vals(), 4);
assert_eq!(
fastfield_codecs::iter_from_reader(multivalue_start_index.reader())
.collect::<Vec<u64>>(),
vec![0, 4, 6, 11]
); // 4, 2, 5
}
#[test]
fn test_multivalue_get_vals() {
let doc_id_mapping =
DocIdMapping::from_new_id_to_old_id(vec![0, 1, 2, 3, 4, 5, 6, 7, 8, 9]);
assert_eq!(doc_id_mapping.num_old_doc_ids(), 10);
let col = VecColumn::from(&[0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55][..]);
let multivalue_start_index = MultivalueStartIndex::new(&col, &doc_id_mapping);
assert_eq!(
fastfield_codecs::iter_from_reader(multivalue_start_index.reader())
.collect::<Vec<u64>>(),
vec![0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55]
);
assert_eq!(multivalue_start_index.num_vals(), 11);
let mut multivalue_start_index_reader = multivalue_start_index.reader();
assert_eq!(multivalue_start_index_reader.seek(3), 2);
assert_eq!(multivalue_start_index_reader.seek(5), 5);
assert_eq!(multivalue_start_index_reader.seek(8), 21);
assert_eq!(multivalue_start_index_reader.seek(4), 3);
assert_eq!(multivalue_start_index_reader.seek(0), 0);
assert_eq!(multivalue_start_index_reader.seek(10), 55);
}
}

162
src/fastfield/multivalued/reader.rs
View File

@@ -1,10 +1,9 @@
use std::ops::{Range, RangeInclusive};
use std::ops::Range;
use std::sync::Arc;
use fastfield_codecs::{Column, MonotonicallyMappableToU128};
use fastfield_codecs::Column;
use super::MultiValueIndex;
use crate::fastfield::FastValue;
use crate::fastfield::{FastValue, MultiValueLength};
use crate::DocId;
/// Reader for a multivalued `u64` fast field.
@@ -14,10 +13,9 @@ use crate::DocId;
/// The `vals_reader` will access the concatenated list of all
/// values for all reader.
/// The `idx_reader` associated, for each document, the index of its first value.
/// Stores the start position for each document.
#[derive(Clone)]
pub struct MultiValuedFastFieldReader<Item: FastValue> {
idx_reader: MultiValueIndex,
idx_reader: Arc<dyn Column<u64>>,
vals_reader: Arc<dyn Column<Item>>,
}
@@ -27,32 +25,36 @@ impl<Item: FastValue> MultiValuedFastFieldReader<Item> {
vals_reader: Arc<dyn Column<Item>>,
) -> MultiValuedFastFieldReader<Item> {
MultiValuedFastFieldReader {
idx_reader: MultiValueIndex::new(idx_reader),
idx_reader,
vals_reader,
}
}
/// Returns the array of values associated with the given `doc`.
/// Returns `[start, end)`, such that the values associated
/// to the given document are `start..end`.
#[inline]
fn get_vals_for_range(&self, range: Range<u32>, vals: &mut Vec<Item>) {
fn range(&self, doc: DocId) -> Range<u64> {
let idx = doc as u64;
let start = self.idx_reader.get_val(idx);
let end = self.idx_reader.get_val(idx + 1);
start..end
}
/// Returns the array of values associated to the given `doc`.
#[inline]
fn get_vals_for_range(&self, range: Range<u64>, vals: &mut Vec<Item>) {
let len = (range.end - range.start) as usize;
vals.resize(len, Item::make_zero());
self.vals_reader
.get_range(range.start as u64, &mut vals[..]);
self.vals_reader.get_range(range.start, &mut vals[..]);
}
/// Returns the array of values associated with the given `doc`.
/// Returns the array of values associated to the given `doc`.
#[inline]
pub fn get_vals(&self, doc: DocId, vals: &mut Vec<Item>) {
let range = self.idx_reader.range(doc);
let range = self.range(doc);
self.get_vals_for_range(range, vals);
}
/// returns the multivalue index
pub fn get_index_reader(&self) -> &MultiValueIndex {
&self.idx_reader
}
/// Returns the minimum value for this fast field.
///
/// The min value does not take in account of possible
@@ -73,129 +75,27 @@ impl<Item: FastValue> MultiValuedFastFieldReader<Item> {
/// Returns the number of values associated with the document `DocId`.
#[inline]
pub fn num_vals(&self, doc: DocId) -> u32 {
self.idx_reader.num_vals_for_doc(doc)
pub fn num_vals(&self, doc: DocId) -> usize {
let range = self.range(doc);
(range.end - range.start) as usize
}
/// Returns the overall number of values in this field.
/// Returns the overall number of values in this field .
#[inline]
pub fn total_num_vals(&self) -> u32 {
self.idx_reader.total_num_vals()
pub fn total_num_vals(&self) -> u64 {
self.idx_reader.max_value()
}
}
/// Reader for a multivalued `u128` fast field.
///
/// The reader is implemented as a `u64` fast field for the index and a `u128` fast field.
///
/// The `vals_reader` will access the concatenated list of all
/// values for all reader.
/// The `idx_reader` associated, for each document, the index of its first value.
#[derive(Clone)]
pub struct MultiValuedU128FastFieldReader<T: MonotonicallyMappableToU128> {
idx_reader: MultiValueIndex,
vals_reader: Arc<dyn Column<T>>,
}
impl<T: MonotonicallyMappableToU128> MultiValuedU128FastFieldReader<T> {
pub(crate) fn open(
idx_reader: Arc<dyn Column<u64>>,
vals_reader: Arc<dyn Column<T>>,
) -> MultiValuedU128FastFieldReader<T> {
Self {
idx_reader: MultiValueIndex::new(idx_reader),
vals_reader,
}
impl<Item: FastValue> MultiValueLength for MultiValuedFastFieldReader<Item> {
fn get_len(&self, doc_id: DocId) -> u64 {
self.num_vals(doc_id) as u64
}
/// Returns the array of values associated to the given `doc`.
#[inline]
pub fn get_first_val(&self, doc: DocId) -> Option<T> {
let range = self.idx_reader.range(doc);
if range.is_empty() {
return None;
}
Some(self.vals_reader.get_val(range.start))
}
/// Returns the array of values associated to the given `doc`.
#[inline]
fn get_vals_for_range(&self, range: Range<u32>, vals: &mut Vec<T>) {
let len = (range.end - range.start) as usize;
vals.resize(len, T::from_u128(0));
self.vals_reader
.get_range(range.start as u64, &mut vals[..]);
}
/// Returns the index reader
pub fn get_index_reader(&self) -> &MultiValueIndex {
&self.idx_reader
}
/// Returns the array of values associated to the given `doc`.
#[inline]
pub fn get_vals(&self, doc: DocId, vals: &mut Vec<T>) {
let range = self.idx_reader.range(doc);
self.get_vals_for_range(range, vals);
}
/// Iterates over all elements in the fast field
pub fn iter(&self) -> impl Iterator<Item = T> + '_ {
self.vals_reader.iter()
}
/// Returns the minimum value for this fast field.
///
/// The min value does not take in account of possible
/// deleted document, and should be considered as a lower bound
/// of the actual mimimum value.
pub fn min_value(&self) -> T {
self.vals_reader.min_value()
}
/// Returns the maximum value for this fast field.
///
/// The max value does not take in account of possible
/// deleted document, and should be considered as an upper bound
/// of the actual maximum value.
pub fn max_value(&self) -> T {
self.vals_reader.max_value()
}
/// Returns the number of values associated with the document `DocId`.
#[inline]
pub fn num_vals(&self, doc: DocId) -> u32 {
self.idx_reader.num_vals_for_doc(doc)
}
/// Returns the overall number of values in this field. It does not include deletes.
#[inline]
pub fn total_num_vals(&self) -> u32 {
assert_eq!(
self.vals_reader.num_vals(),
self.get_index_reader().total_num_vals()
);
self.idx_reader.total_num_vals()
}
/// Returns the docids matching given doc_id_range and value_range.
#[inline]
pub fn get_docids_for_value_range(
&self,
value_range: RangeInclusive<T>,
doc_id_range: Range<u32>,
positions: &mut Vec<u32>,
) {
let position_range = self
.get_index_reader()
.docid_range_to_position_range(doc_id_range.clone());
self.vals_reader
.get_docids_for_value_range(value_range, position_range, positions);
self.idx_reader.positions_to_docids(doc_id_range, positions);
fn get_total_len(&self) -> u64 {
self.total_num_vals() as u64
}
}
#[cfg(test)]
mod tests {

261
src/fastfield/multivalued/writer.rs
View File

@@ -1,13 +1,11 @@
use std::io;
use fastfield_codecs::{
Column, MonotonicallyMappableToU128, MonotonicallyMappableToU64, VecColumn,
};
use rustc_hash::FxHashMap;
use fastfield_codecs::{MonotonicallyMappableToU64, VecColumn};
use fnv::FnvHashMap;
use super::get_fastfield_codecs_for_multivalue;
use crate::fastfield::writer::unexpected_value;
use crate::fastfield::{value_to_u64, CompositeFastFieldSerializer, FastFieldType};
use crate::fastfield::{
value_to_u64, CompositeFastFieldSerializer, FastFieldType, MultivalueStartIndex,
};
use crate::indexer::doc_id_mapping::DocIdMapping;
use crate::postings::UnorderedTermId;
use crate::schema::{Document, Field, Value};
@@ -65,7 +63,7 @@ impl MultiValuedFastFieldWriter {
+ self.doc_index.capacity() * std::mem::size_of::<u64>()
}
/// Access the field associated with the `MultiValuedFastFieldWriter`
/// Access the field associated to the `MultiValuedFastFieldWriter`
pub fn field(&self) -> Field {
self.field
}
@@ -82,11 +80,11 @@ impl MultiValuedFastFieldWriter {
/// Shift to the next document and adds
/// all of the matching field values present in the document.
pub fn add_document(&mut self, doc: &Document) -> crate::Result<()> {
pub fn add_document(&mut self, doc: &Document) {
self.next_doc();
// facets/texts are indexed in the `SegmentWriter` as we encode their unordered id.
if self.fast_field_type.is_storing_term_ids() {
return Ok(());
return;
}
for field_value in doc.field_values() {
if field_value.field == self.field {
@@ -95,12 +93,11 @@ impl MultiValuedFastFieldWriter {
(Some(precision), Value::Date(date_val)) => {
date_val.truncate(precision).to_u64()
}
_ => value_to_u64(value)?,
_ => value_to_u64(value),
};
self.add_val(value_u64);
}
}
Ok(())
}
/// Returns an iterator over values per doc_id in ascending doc_id order.
@@ -144,7 +141,7 @@ impl MultiValuedFastFieldWriter {
pub fn serialize(
mut self,
serializer: &mut CompositeFastFieldSerializer,
term_mapping_opt: Option<&FxHashMap<UnorderedTermId, TermOrdinal>>,
term_mapping_opt: Option<&FnvHashMap<UnorderedTermId, TermOrdinal>>,
doc_id_map: Option<&DocIdMapping>,
) -> io::Result<()> {
{
@@ -199,244 +196,8 @@ impl MultiValuedFastFieldWriter {
}
}
let col = VecColumn::from(&values[..]);
serializer.create_auto_detect_u64_fast_field_with_idx_and_codecs(
self.field,
col,
1,
&get_fastfield_codecs_for_multivalue(),
)?;
serializer.create_auto_detect_u64_fast_field_with_idx(self.field, col, 1)?;
}
Ok(())
}
}
pub(crate) struct MultivalueStartIndex<'a, C: Column> {
column: &'a C,
doc_id_map: &'a DocIdMapping,
min: u64,
max: u64,
}
impl<'a, C: Column> MultivalueStartIndex<'a, C> {
pub fn new(column: &'a C, doc_id_map: &'a DocIdMapping) -> Self {
assert_eq!(column.num_vals(), doc_id_map.num_old_doc_ids() as u32 + 1);
let (min, max) =
tantivy_bitpacker::minmax(iter_remapped_multivalue_index(doc_id_map, column))
.unwrap_or((0u64, 0u64));
MultivalueStartIndex {
column,
doc_id_map,
min,
max,
}
}
}
impl<'a, C: Column> Column for MultivalueStartIndex<'a, C> {
fn get_val(&self, _idx: u32) -> u64 {
unimplemented!()
}
fn min_value(&self) -> u64 {
self.min
}
fn max_value(&self) -> u64 {
self.max
}
fn num_vals(&self) -> u32 {
(self.doc_id_map.num_new_doc_ids() + 1) as u32
}
fn iter(&self) -> Box<dyn Iterator<Item = u64> + '_> {
Box::new(iter_remapped_multivalue_index(
self.doc_id_map,
&self.column,
))
}
}
fn iter_remapped_multivalue_index<'a, C: Column>(
doc_id_map: &'a DocIdMapping,
column: &'a C,
) -> impl Iterator<Item = u64> + 'a {
let mut offset = 0;
std::iter::once(0).chain(doc_id_map.iter_old_doc_ids().map(move |old_doc| {
let num_vals_for_doc = column.get_val(old_doc + 1) - column.get_val(old_doc);
offset += num_vals_for_doc;
offset as u64
}))
}
/// Writer for multi-valued (as in, more than one value per document)
/// int fast field.
///
/// This `Writer` is only useful for advanced users.
/// The normal way to get your multivalued int in your index
/// is to
/// - declare your field with fast set to `Cardinality::MultiValues`
/// in your schema
/// - add your document simply by calling `.add_document(...)`.
///
/// The `MultiValuedFastFieldWriter` can be acquired from the
pub struct MultiValueU128FastFieldWriter {
field: Field,
vals: Vec<u128>,
doc_index: Vec<u64>,
}
impl MultiValueU128FastFieldWriter {
/// Creates a new `U128MultiValueFastFieldWriter`
pub(crate) fn new(field: Field) -> Self {
MultiValueU128FastFieldWriter {
field,
vals: Vec::new(),
doc_index: Vec::new(),
}
}
/// The memory used (inclusive childs)
pub fn mem_usage(&self) -> usize {
self.vals.capacity() * std::mem::size_of::<UnorderedTermId>()
+ self.doc_index.capacity() * std::mem::size_of::<u64>()
}
/// Finalize the current document.
pub(crate) fn next_doc(&mut self) {
self.doc_index.push(self.vals.len() as u64);
}
/// Pushes a new value to the current document.
pub(crate) fn add_val(&mut self, val: u128) {
self.vals.push(val);
}
/// Shift to the next document and adds
/// all of the matching field values present in the document.
pub fn add_document(&mut self, doc: &Document) -> crate::Result<()> {
self.next_doc();
for field_value in doc.field_values() {
if field_value.field == self.field {
let value = field_value.value();
let ip_addr = value
.as_ip_addr()
.ok_or_else(|| unexpected_value("ip", value))?;
let ip_addr_u128 = ip_addr.to_u128();
self.add_val(ip_addr_u128);
}
}
Ok(())
}
/// Returns an iterator over values per doc_id in ascending doc_id order.
///
/// Normally the order is simply iterating self.doc_id_index.
/// With doc_id_map it accounts for the new mapping, returning values in the order of the
/// new doc_ids.
fn get_ordered_values<'a: 'b, 'b>(
&'a self,
doc_id_map: Option<&'b DocIdMapping>,
) -> impl Iterator<Item = &'b [u128]> {
get_ordered_values(&self.vals, &self.doc_index, doc_id_map)
}
/// Serializes fast field values.
pub fn serialize(
mut self,
serializer: &mut CompositeFastFieldSerializer,
doc_id_map: Option<&DocIdMapping>,
) -> io::Result<()> {
{
// writing the offset index
//
self.doc_index.push(self.vals.len() as u64);
let col = VecColumn::from(&self.doc_index[..]);
if let Some(doc_id_map) = doc_id_map {
let multi_value_start_index = MultivalueStartIndex::new(&col, doc_id_map);
serializer.create_auto_detect_u64_fast_field_with_idx(
self.field,
multi_value_start_index,
0,
)?;
} else {
serializer.create_auto_detect_u64_fast_field_with_idx(self.field, col, 0)?;
}
}
{
let iter_gen = || self.get_ordered_values(doc_id_map).flatten().cloned();
serializer.create_u128_fast_field_with_idx(
self.field,
iter_gen,
self.vals.len() as u32,
1,
)?;
}
Ok(())
}
}
/// Returns an iterator over values per doc_id in ascending doc_id order.
///
/// Normally the order is simply iterating self.doc_id_index.
/// With doc_id_map it accounts for the new mapping, returning values in the order of the
/// new doc_ids.
fn get_ordered_values<'a: 'b, 'b, T>(
vals: &'a [T],
doc_index: &'a [u64],
doc_id_map: Option<&'b DocIdMapping>,
) -> impl Iterator<Item = &'b [T]> {
let doc_id_iter: Box<dyn Iterator<Item = u32>> = if let Some(doc_id_map) = doc_id_map {
Box::new(doc_id_map.iter_old_doc_ids())
} else {
let max_doc = doc_index.len() as DocId;
Box::new(0..max_doc)
};
doc_id_iter.map(move |doc_id| get_values_for_doc_id(doc_id, vals, doc_index))
}
/// returns all values for a doc_id
fn get_values_for_doc_id<'a, T>(doc_id: u32, vals: &'a [T], doc_index: &'a [u64]) -> &'a [T] {
let start_pos = doc_index[doc_id as usize] as usize;
let end_pos = doc_index
.get(doc_id as usize + 1)
.cloned()
.unwrap_or(vals.len() as u64) as usize; // special case, last doc_id has no offset information
&vals[start_pos..end_pos]
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_multivalue_start_index() {
let doc_id_mapping = DocIdMapping::from_new_id_to_old_id(vec![4, 1, 2]);
assert_eq!(doc_id_mapping.num_old_doc_ids(), 5);
let col = VecColumn::from(&[0u64, 3, 5, 10, 12, 16][..]);
let multivalue_start_index = MultivalueStartIndex::new(
&col, // 3, 2, 5, 2, 4
&doc_id_mapping,
);
assert_eq!(multivalue_start_index.num_vals(), 4);
assert_eq!(
multivalue_start_index.iter().collect::<Vec<u64>>(),
vec![0, 4, 6, 11]
); // 4, 2, 5
}
#[test]
fn test_multivalue_get_vals() {
let doc_id_mapping =
DocIdMapping::from_new_id_to_old_id(vec![0, 1, 2, 3, 4, 5, 6, 7, 8, 9]);
assert_eq!(doc_id_mapping.num_old_doc_ids(), 10);
let col = VecColumn::from(&[0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55][..]);
let multivalue_start_index = MultivalueStartIndex::new(&col, &doc_id_mapping);
assert_eq!(
multivalue_start_index.iter().collect::<Vec<u64>>(),
vec![0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55]
);
assert_eq!(multivalue_start_index.num_vals(), 11);
}
}

93
src/fastfield/readers.rs
View File

@@ -1,9 +1,7 @@
use std::net::Ipv6Addr;
use std::sync::Arc;
use fastfield_codecs::{open, open_u128, Column};
use fastfield_codecs::{open, Column};
use super::multivalued::MultiValuedU128FastFieldReader;
use crate::directory::{CompositeFile, FileSlice};
use crate::fastfield::{
BytesFastFieldReader, FastFieldNotAvailableError, FastValue, MultiValuedFastFieldReader,
@@ -25,7 +23,6 @@ pub struct FastFieldReaders {
pub(crate) enum FastType {
I64,
U64,
U128,
F64,
Bool,
Date,
@@ -52,9 +49,6 @@ pub(crate) fn type_and_cardinality(field_type: &FieldType) -> Option<(FastType,
FieldType::Str(options) if options.is_fast() => {
Some((FastType::U64, Cardinality::MultiValues))
}
FieldType::IpAddr(options) => options
.get_fastfield_cardinality()
.map(|cardinality| (FastType::U128, cardinality)),
_ => None,
}
}
@@ -141,7 +135,7 @@ impl FastFieldReaders {
Ok(MultiValuedFastFieldReader::open(idx_reader, vals_reader))
}
/// Returns the `u64` fast field reader reader associated with `field`.
/// Returns the `u64` fast field reader reader associated to `field`.
///
/// If `field` is not a u64 fast field, this method returns an Error.
pub fn u64(&self, field: Field) -> crate::Result<Arc<dyn Column<u64>>> {
@@ -149,69 +143,16 @@ impl FastFieldReaders {
self.typed_fast_field_reader(field)
}
/// Returns the `ip` fast field reader reader associated to `field`.
/// Returns the `u64` fast field reader reader associated to `field`, regardless of whether the
/// given field is effectively of type `u64` or not.
///
/// If `field` is not a u128 fast field, this method returns an Error.
pub fn ip_addr(&self, field: Field) -> crate::Result<Arc<dyn Column<Ipv6Addr>>> {
self.check_type(field, FastType::U128, Cardinality::SingleValue)?;
let bytes = self.fast_field_data(field, 0)?.read_bytes()?;
Ok(open_u128::<Ipv6Addr>(bytes)?)
}
/// Returns the `ip` fast field reader reader associated to `field`.
///
/// If `field` is not a u128 fast field, this method returns an Error.
pub fn ip_addrs(
&self,
field: Field,
) -> crate::Result<MultiValuedU128FastFieldReader<Ipv6Addr>> {
self.check_type(field, FastType::U128, Cardinality::MultiValues)?;
let idx_reader: Arc<dyn Column<u64>> = self.typed_fast_field_reader(field)?;
let bytes = self.fast_field_data(field, 1)?.read_bytes()?;
let vals_reader = open_u128::<Ipv6Addr>(bytes)?;
Ok(MultiValuedU128FastFieldReader::open(
idx_reader,
vals_reader,
))
}
/// Returns the `u128` fast field reader reader associated to `field`.
///
/// If `field` is not a u128 fast field, this method returns an Error.
pub(crate) fn u128(&self, field: Field) -> crate::Result<Arc<dyn Column<u128>>> {
self.check_type(field, FastType::U128, Cardinality::SingleValue)?;
let bytes = self.fast_field_data(field, 0)?.read_bytes()?;
Ok(open_u128::<u128>(bytes)?)
}
/// Returns the `u128` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a u128 multi-valued fast field, this method returns an Error.
pub fn u128s(&self, field: Field) -> crate::Result<MultiValuedU128FastFieldReader<u128>> {
self.check_type(field, FastType::U128, Cardinality::MultiValues)?;
let idx_reader: Arc<dyn Column<u64>> = self.typed_fast_field_reader(field)?;
let bytes = self.fast_field_data(field, 1)?.read_bytes()?;
let vals_reader = open_u128::<u128>(bytes)?;
Ok(MultiValuedU128FastFieldReader::open(
idx_reader,
vals_reader,
))
}
/// Returns the `u64` fast field reader reader associated with `field`, regardless of whether
/// the given field is effectively of type `u64` or not.
///
/// If not, the fastfield reader will returns the u64-value associated with the original
/// If not, the fastfield reader will returns the u64-value associated to the original
/// FastValue.
pub fn u64_lenient(&self, field: Field) -> crate::Result<Arc<dyn Column<u64>>> {
self.typed_fast_field_reader(field)
}
/// Returns the `i64` fast field reader reader associated with `field`.
/// Returns the `i64` fast field reader reader associated to `field`.
///
/// If `field` is not a i64 fast field, this method returns an Error.
pub fn i64(&self, field: Field) -> crate::Result<Arc<dyn Column<i64>>> {
@@ -219,7 +160,7 @@ impl FastFieldReaders {
self.typed_fast_field_reader(field)
}
/// Returns the `date` fast field reader reader associated with `field`.
/// Returns the `date` fast field reader reader associated to `field`.
///
/// If `field` is not a date fast field, this method returns an Error.
pub fn date(&self, field: Field) -> crate::Result<Arc<dyn Column<DateTime>>> {
@@ -227,7 +168,7 @@ impl FastFieldReaders {
self.typed_fast_field_reader(field)
}
/// Returns the `f64` fast field reader reader associated with `field`.
/// Returns the `f64` fast field reader reader associated to `field`.
///
/// If `field` is not a f64 fast field, this method returns an Error.
pub fn f64(&self, field: Field) -> crate::Result<Arc<dyn Column<f64>>> {
@@ -235,7 +176,7 @@ impl FastFieldReaders {
self.typed_fast_field_reader(field)
}
/// Returns the `bool` fast field reader reader associated with `field`.
/// Returns the `bool` fast field reader reader associated to `field`.
///
/// If `field` is not a bool fast field, this method returns an Error.
pub fn bool(&self, field: Field) -> crate::Result<Arc<dyn Column<bool>>> {
@@ -243,7 +184,7 @@ impl FastFieldReaders {
self.typed_fast_field_reader(field)
}
/// Returns a `u64s` multi-valued fast field reader reader associated with `field`.
/// Returns a `u64s` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a u64 multi-valued fast field, this method returns an Error.
pub fn u64s(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<u64>> {
@@ -251,15 +192,15 @@ impl FastFieldReaders {
self.typed_fast_field_multi_reader(field)
}
/// Returns a `u64s` multi-valued fast field reader reader associated with `field`, regardless
/// of whether the given field is effectively of type `u64` or not.
/// Returns a `u64s` multi-valued fast field reader reader associated to `field`, regardless of
/// whether the given field is effectively of type `u64` or not.
///
/// If `field` is not a u64 multi-valued fast field, this method returns an Error.
pub fn u64s_lenient(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<u64>> {
self.typed_fast_field_multi_reader(field)
}
/// Returns a `i64s` multi-valued fast field reader reader associated with `field`.
/// Returns a `i64s` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a i64 multi-valued fast field, this method returns an Error.
pub fn i64s(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<i64>> {
@@ -267,7 +208,7 @@ impl FastFieldReaders {
self.typed_fast_field_multi_reader(field)
}
/// Returns a `f64s` multi-valued fast field reader reader associated with `field`.
/// Returns a `f64s` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a f64 multi-valued fast field, this method returns an Error.
pub fn f64s(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<f64>> {
@@ -275,7 +216,7 @@ impl FastFieldReaders {
self.typed_fast_field_multi_reader(field)
}
/// Returns a `bools` multi-valued fast field reader reader associated with `field`.
/// Returns a `bools` multi-valued fast field reader reader associated to `field`.
///
/// If `field` is not a bool multi-valued fast field, this method returns an Error.
pub fn bools(&self, field: Field) -> crate::Result<MultiValuedFastFieldReader<bool>> {
@@ -283,7 +224,7 @@ impl FastFieldReaders {
self.typed_fast_field_multi_reader(field)
}
/// Returns a `time::OffsetDateTime` multi-valued fast field reader reader associated with
/// Returns a `time::OffsetDateTime` multi-valued fast field reader reader associated to
/// `field`.
///
/// If `field` is not a `time::OffsetDateTime` multi-valued fast field, this method returns an
@@ -293,7 +234,7 @@ impl FastFieldReaders {
self.typed_fast_field_multi_reader(field)
}
/// Returns the `bytes` fast field reader associated with `field`.
/// Returns the `bytes` fast field reader associated to `field`.
///
/// If `field` is not a bytes fast field, returns an Error.
pub fn bytes(&self, field: Field) -> crate::Result<BytesFastFieldReader> {

112
src/fastfield/remapped_column.rs Normal file
View File

@@ -0,0 +1,112 @@
use fastfield_codecs::{Column, ColumnReader};
use tantivy_bitpacker::BlockedBitpacker;
use crate::indexer::doc_id_mapping::DocIdMapping;
use crate::DocId;
#[derive(Clone)]
pub(crate) struct WriterFastFieldColumn<'map, 'bitp> {
pub(crate) doc_id_mapping_opt: Option<&'map DocIdMapping>,
pub(crate) vals: &'bitp BlockedBitpacker,
pub(crate) min_value: u64,
pub(crate) max_value: u64,
pub(crate) num_vals: u64,
}
impl<'map, 'bitp> Column for WriterFastFieldColumn<'map, 'bitp> {
/// Return the value associated to the given doc.
///
/// Whenever possible use the Iterator passed to the fastfield creation instead, for performance
/// reasons.
///
/// # Panics
///
/// May panic if `doc` is greater than the index.
fn get_val(&self, doc: u64) -> u64 {
if let Some(doc_id_map) = self.doc_id_mapping_opt {
self.vals
.get(doc_id_map.get_old_doc_id(doc as u32) as usize) // consider extra
// FastFieldReader wrapper for
// non doc_id_map
} else {
self.vals.get(doc as usize)
}
}
fn reader(&self) -> Box<dyn ColumnReader + '_> {
if let Some(doc_id_mapping) = self.doc_id_mapping_opt {
Box::new(RemappedColumnReader {
doc_id_mapping,
vals: self.vals,
idx: u64::MAX,
len: doc_id_mapping.num_new_doc_ids() as u64,
})
} else {
Box::new(BitpackedColumnReader {
vals: self.vals,
idx: u64::MAX,
len: self.num_vals,
})
}
}
fn min_value(&self) -> u64 {
self.min_value
}
fn max_value(&self) -> u64 {
self.max_value
}
fn num_vals(&self) -> u64 {
self.num_vals
}
}
struct RemappedColumnReader<'a> {
doc_id_mapping: &'a DocIdMapping,
vals: &'a BlockedBitpacker,
idx: u64,
len: u64,
}
impl<'a> ColumnReader for RemappedColumnReader<'a> {
fn seek(&mut self, target_idx: u64) -> u64 {
assert!(target_idx < self.len);
self.idx = target_idx;
self.get()
}
fn advance(&mut self) -> bool {
self.idx = self.idx.wrapping_add(1);
self.idx < self.len
}
fn get(&self) -> u64 {
let old_doc_id: DocId = self.doc_id_mapping.get_old_doc_id(self.idx as DocId);
self.vals.get(old_doc_id as usize)
}
}
struct BitpackedColumnReader<'a> {
vals: &'a BlockedBitpacker,
idx: u64,
len: u64,
}
impl<'a> ColumnReader for BitpackedColumnReader<'a> {
fn seek(&mut self, target_idx: u64) -> u64 {
assert!(target_idx < self.len);
self.idx = target_idx;
self.get()
}
fn advance(&mut self) -> bool {
self.idx = self.idx.wrapping_add(1);
self.idx < self.len
}
fn get(&self) -> u64 {
self.vals.get(self.idx as usize)
}
}

38
src/fastfield/serializer/mod.rs
View File

@@ -1,4 +1,3 @@
use std::fmt;
use std::io::{self, Write};
pub use fastfield_codecs::Column;
@@ -50,7 +49,7 @@ impl CompositeFastFieldSerializer {
/// Serialize data into a new u64 fast field. The best compression codec will be chosen
/// automatically.
pub fn create_auto_detect_u64_fast_field<T: MonotonicallyMappableToU64 + fmt::Debug>(
pub fn create_auto_detect_u64_fast_field<T: MonotonicallyMappableToU64>(
&mut self,
field: Field,
fastfield_accessor: impl Column<T>,
@@ -60,9 +59,7 @@ impl CompositeFastFieldSerializer {
/// Serialize data into a new u64 fast field. The best compression codec will be chosen
/// automatically.
pub fn create_auto_detect_u64_fast_field_with_idx<
T: MonotonicallyMappableToU64 + fmt::Debug,
>(
pub fn create_auto_detect_u64_fast_field_with_idx<T: MonotonicallyMappableToU64>(
&mut self,
field: Field,
fastfield_accessor: impl Column<T>,
@@ -73,37 +70,6 @@ impl CompositeFastFieldSerializer {
Ok(())
}
/// Serialize data into a new u64 fast field. The best compression codec of the the provided
/// will be chosen.
pub fn create_auto_detect_u64_fast_field_with_idx_and_codecs<
T: MonotonicallyMappableToU64 + fmt::Debug,
>(
&mut self,
field: Field,
fastfield_accessor: impl Column<T>,
idx: usize,
codec_types: &[FastFieldCodecType],
) -> io::Result<()> {
let field_write = self.composite_write.for_field_with_idx(field, idx);
fastfield_codecs::serialize(fastfield_accessor, field_write, codec_types)?;
Ok(())
}
/// Serialize data into a new u128 fast field. The codec will be compact space compressor,
/// which is optimized for scanning the fast field for a given range.
pub fn create_u128_fast_field_with_idx<F: Fn() -> I, I: Iterator<Item = u128>>(
&mut self,
field: Field,
iter_gen: F,
num_vals: u32,
idx: usize,
) -> io::Result<()> {
let field_write = self.composite_write.for_field_with_idx(field, idx);
fastfield_codecs::serialize_u128(iter_gen, num_vals, field_write)?;
Ok(())
}
/// Start serializing a new [u8] fast field. Use the returned writer to write data into the
/// bytes field. To associate the bytes with documents a seperate index must be created on
/// index 0. See bytes/writer.rs::serialize for an example.

241
src/fastfield/writer.rs
View File

@@ -2,12 +2,13 @@ use std::collections::HashMap;
use std::io;
use common;
use fastfield_codecs::{Column, MonotonicallyMappableToU128, MonotonicallyMappableToU64};
use rustc_hash::FxHashMap;
use fastfield_codecs::MonotonicallyMappableToU64;
use fnv::FnvHashMap;
use tantivy_bitpacker::BlockedBitpacker;
use super::multivalued::{MultiValueU128FastFieldWriter, MultiValuedFastFieldWriter};
use super::multivalued::MultiValuedFastFieldWriter;
use super::FastFieldType;
use crate::fastfield::remapped_column::WriterFastFieldColumn;
use crate::fastfield::{BytesFastFieldWriter, CompositeFastFieldSerializer};
use crate::indexer::doc_id_mapping::DocIdMapping;
use crate::postings::UnorderedTermId;
@@ -19,19 +20,10 @@ use crate::DatePrecision;
pub struct FastFieldsWriter {
term_id_writers: Vec<MultiValuedFastFieldWriter>,
single_value_writers: Vec<IntFastFieldWriter>,
u128_value_writers: Vec<U128FastFieldWriter>,
u128_multi_value_writers: Vec<MultiValueU128FastFieldWriter>,
multi_values_writers: Vec<MultiValuedFastFieldWriter>,
bytes_value_writers: Vec<BytesFastFieldWriter>,
}
pub(crate) fn unexpected_value(expected: &str, actual: &Value) -> crate::TantivyError {
crate::TantivyError::SchemaError(format!(
"Expected a {:?} in fast field, but got {:?}",
expected, actual
))
}
fn fast_field_default_value(field_entry: &FieldEntry) -> u64 {
match *field_entry.field_type() {
FieldType::I64(_) | FieldType::Date(_) => common::i64_to_u64(0i64),
@@ -43,8 +35,6 @@ fn fast_field_default_value(field_entry: &FieldEntry) -> u64 {
impl FastFieldsWriter {
/// Create all `FastFieldWriter` required by the schema.
pub fn from_schema(schema: &Schema) -> FastFieldsWriter {
let mut u128_value_writers = Vec::new();
let mut u128_multi_value_writers = Vec::new();
let mut single_value_writers = Vec::new();
let mut term_id_writers = Vec::new();
let mut multi_values_writers = Vec::new();
@@ -108,27 +98,10 @@ impl FastFieldsWriter {
bytes_value_writers.push(fast_field_writer);
}
}
FieldType::IpAddr(opt) => {
if opt.is_fast() {
match opt.get_fastfield_cardinality() {
Some(Cardinality::SingleValue) => {
let fast_field_writer = U128FastFieldWriter::new(field);
u128_value_writers.push(fast_field_writer);
}
Some(Cardinality::MultiValues) => {
let fast_field_writer = MultiValueU128FastFieldWriter::new(field);
u128_multi_value_writers.push(fast_field_writer);
}
None => {}
}
}
}
FieldType::Str(_) | FieldType::JsonObject(_) => {}
}
}
FastFieldsWriter {
u128_value_writers,
u128_multi_value_writers,
term_id_writers,
single_value_writers,
multi_values_writers,
@@ -157,19 +130,9 @@ impl FastFieldsWriter {
.iter()
.map(|w| w.mem_usage())
.sum::<usize>()
+ self
.u128_value_writers
.iter()
.map(|w| w.mem_usage())
.sum::<usize>()
+ self
.u128_multi_value_writers
.iter()
.map(|w| w.mem_usage())
.sum::<usize>()
}
/// Get the `FastFieldWriter` associated with a field.
/// Get the `FastFieldWriter` associated to a field.
pub fn get_term_id_writer(&self, field: Field) -> Option<&MultiValuedFastFieldWriter> {
// TODO optimize
self.term_id_writers
@@ -177,7 +140,7 @@ impl FastFieldsWriter {
.find(|field_writer| field_writer.field() == field)
}
/// Get the `FastFieldWriter` associated with a field.
/// Get the `FastFieldWriter` associated to a field.
pub fn get_field_writer(&self, field: Field) -> Option<&IntFastFieldWriter> {
// TODO optimize
self.single_value_writers
@@ -185,7 +148,7 @@ impl FastFieldsWriter {
.find(|field_writer| field_writer.field() == field)
}
/// Get the `FastFieldWriter` associated with a field.
/// Get the `FastFieldWriter` associated to a field.
pub fn get_field_writer_mut(&mut self, field: Field) -> Option<&mut IntFastFieldWriter> {
// TODO optimize
self.single_value_writers
@@ -193,7 +156,7 @@ impl FastFieldsWriter {
.find(|field_writer| field_writer.field() == field)
}
/// Get the `FastFieldWriter` associated with a field.
/// Get the `FastFieldWriter` associated to a field.
pub fn get_term_id_writer_mut(
&mut self,
field: Field,
@@ -228,27 +191,21 @@ impl FastFieldsWriter {
.iter_mut()
.find(|field_writer| field_writer.field() == field)
}
/// Indexes all of the fastfields of a new document.
pub fn add_document(&mut self, doc: &Document) -> crate::Result<()> {
pub fn add_document(&mut self, doc: &Document) {
for field_writer in &mut self.term_id_writers {
field_writer.add_document(doc)?;
field_writer.add_document(doc);
}
for field_writer in &mut self.single_value_writers {
field_writer.add_document(doc)?;
field_writer.add_document(doc);
}
for field_writer in &mut self.multi_values_writers {
field_writer.add_document(doc)?;
field_writer.add_document(doc);
}
for field_writer in &mut self.bytes_value_writers {
field_writer.add_document(doc)?;
field_writer.add_document(doc);
}
for field_writer in &mut self.u128_value_writers {
field_writer.add_document(doc)?;
}
for field_writer in &mut self.u128_multi_value_writers {
field_writer.add_document(doc)?;
}
Ok(())
}
/// Serializes all of the `FastFieldWriter`s by pushing them in
@@ -256,7 +213,7 @@ impl FastFieldsWriter {
pub fn serialize(
self,
serializer: &mut CompositeFastFieldSerializer,
mapping: &HashMap<Field, FxHashMap<UnorderedTermId, TermOrdinal>>,
mapping: &HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>,
doc_id_map: Option<&DocIdMapping>,
) -> io::Result<()> {
for field_writer in self.term_id_writers {
@@ -274,108 +231,6 @@ impl FastFieldsWriter {
for field_writer in self.bytes_value_writers {
field_writer.serialize(serializer, doc_id_map)?;
}
for field_writer in self.u128_value_writers {
field_writer.serialize(serializer, doc_id_map)?;
}
for field_writer in self.u128_multi_value_writers {
field_writer.serialize(serializer, doc_id_map)?;
}
Ok(())
}
}
/// Fast field writer for u128 values.
/// The fast field writer just keeps the values in memory.
///
/// Only when the segment writer can be closed and
/// persisted on disk, the fast field writer is
/// sent to a `FastFieldSerializer` via the `.serialize(...)`
/// method.
///
/// We cannot serialize earlier as the values are
/// compressed to a compact number space and the number of
/// bits required for bitpacking can only been known once
/// we have seen all of the values.
pub struct U128FastFieldWriter {
field: Field,
vals: Vec<u128>,
val_count: u32,
}
impl U128FastFieldWriter {
/// Creates a new `IntFastFieldWriter`
pub fn new(field: Field) -> Self {
Self {
field,
vals: vec![],
val_count: 0,
}
}
/// The memory used (inclusive childs)
pub fn mem_usage(&self) -> usize {
self.vals.len() * 16
}
/// Records a new value.
///
/// The n-th value being recorded is implicitely
/// associated to the document with the `DocId` n.
/// (Well, `n-1` actually because of 0-indexing)
pub fn add_val(&mut self, val: u128) {
self.vals.push(val);
}
/// Extract the fast field value from the document
/// (or use the default value) and records it.
///
/// Extract the value associated to the fast field for
/// this document.
pub fn add_document(&mut self, doc: &Document) -> crate::Result<()> {
match doc.get_first(self.field) {
Some(v) => {
let ip_addr = v.as_ip_addr().ok_or_else(|| unexpected_value("ip", v))?;
let value = ip_addr.to_u128();
self.add_val(value);
}
None => {
self.add_val(0); // TODO fix null handling
}
};
self.val_count += 1;
Ok(())
}
/// Push the fast fields value to the `FastFieldWriter`.
pub fn serialize(
&self,
serializer: &mut CompositeFastFieldSerializer,
doc_id_map: Option<&DocIdMapping>,
) -> io::Result<()> {
if let Some(doc_id_map) = doc_id_map {
let iter_gen = || {
doc_id_map
.iter_old_doc_ids()
.map(|idx| self.vals[idx as usize])
};
serializer.create_u128_fast_field_with_idx(
self.field,
iter_gen,
self.val_count as u32,
0,
)?;
} else {
let iter_gen = || self.vals.iter().cloned();
serializer.create_u128_fast_field_with_idx(
self.field,
iter_gen,
self.val_count as u32,
0,
)?;
}
Ok(())
}
}
@@ -384,7 +239,7 @@ impl U128FastFieldWriter {
/// The fast field writer just keeps the values in memory.
///
/// Only when the segment writer can be closed and
/// persisted on disk, the fast field writer is
/// persisted on disc, the fast field writer is
/// sent to a `FastFieldSerializer` via the `.serialize(...)`
/// method.
///
@@ -440,7 +295,7 @@ impl IntFastFieldWriter {
/// Records a new value.
///
/// The n-th value being recorded is implicitly
/// associated with the document with the `DocId` n.
/// associated to the document with the `DocId` n.
/// (Well, `n-1` actually because of 0-indexing)
pub fn add_val(&mut self, val: u64) {
self.vals.add(val);
@@ -459,7 +314,7 @@ impl IntFastFieldWriter {
/// (or use the default value) and records it.
///
///
/// Extract the value associated with the fast field for
/// Extract the value associated to the fast field for
/// this document.
///
/// i64 and f64 are remapped to u64 using the logic
@@ -471,14 +326,14 @@ impl IntFastFieldWriter {
/// only the first one is taken in account.
///
/// Values on text fast fields are skipped.
pub fn add_document(&mut self, doc: &Document) -> crate::Result<()> {
pub fn add_document(&mut self, doc: &Document) {
match doc.get_first(self.field) {
Some(v) => {
let value = match (self.precision_opt, v) {
(Some(precision), Value::Date(date_val)) => {
date_val.truncate(precision).to_u64()
}
_ => super::value_to_u64(v)?,
_ => super::value_to_u64(v),
};
self.add_val(value);
}
@@ -486,7 +341,6 @@ impl IntFastFieldWriter {
self.add_val(self.val_if_missing);
}
};
Ok(())
}
/// get iterator over the data
@@ -498,7 +352,7 @@ impl IntFastFieldWriter {
pub fn serialize(
&self,
serializer: &mut CompositeFastFieldSerializer,
doc_id_map: Option<&DocIdMapping>,
doc_id_mapping_opt: Option<&DocIdMapping>,
) -> io::Result<()> {
let (min, max) = if self.val_min > self.val_max {
(0, 0)
@@ -506,12 +360,12 @@ impl IntFastFieldWriter {
(self.val_min, self.val_max)
};
let fastfield_accessor = WriterFastFieldAccessProvider {
doc_id_map,
let fastfield_accessor = WriterFastFieldColumn {
doc_id_mapping_opt,
vals: &self.vals,
min_value: min,
max_value: max,
num_vals: self.val_count as u32,
num_vals: self.val_count as u64,
};
serializer.create_auto_detect_u64_fast_field(self.field, fastfield_accessor)?;
@@ -519,50 +373,3 @@ impl IntFastFieldWriter {
Ok(())
}
}
#[derive(Clone)]
struct WriterFastFieldAccessProvider<'map, 'bitp> {
doc_id_map: Option<&'map DocIdMapping>,
vals: &'bitp BlockedBitpacker,
min_value: u64,
max_value: u64,
num_vals: u32,
}
impl<'map, 'bitp> Column for WriterFastFieldAccessProvider<'map, 'bitp> {
/// Return the value associated with the given doc.
///
/// Whenever possible use the Iterator passed to the fastfield creation instead, for performance
/// reasons.
///
/// # Panics
///
/// May panic if `doc` is greater than the index.
fn get_val(&self, _doc: u32) -> u64 {
unimplemented!()
}
fn iter(&self) -> Box<dyn Iterator<Item = u64> + '_> {
if let Some(doc_id_map) = self.doc_id_map {
Box::new(
doc_id_map
.iter_old_doc_ids()
.map(|doc_id| self.vals.get(doc_id as usize)),
)
} else {
Box::new(self.vals.iter())
}
}
fn min_value(&self) -> u64 {
self.min_value
}
fn max_value(&self) -> u64 {
self.max_value
}
fn num_vals(&self) -> u32 {
self.num_vals
}
}

8
src/fieldnorm/mod.rs
View File

@@ -1,4 +1,4 @@
//! The fieldnorm represents the length associated with
//! The fieldnorm represents the length associated to
//! a given Field of a given document.
//!
//! This metric is important to compute the score of a
@@ -34,7 +34,7 @@ mod tests {
use crate::directory::{CompositeFile, Directory, RamDirectory, WritePtr};
use crate::fieldnorm::{FieldNormReader, FieldNormsSerializer, FieldNormsWriter};
use crate::query::{EnableScoring, Query, TermQuery};
use crate::query::{Query, TermQuery};
use crate::schema::{
Field, IndexRecordOption, Schema, TextFieldIndexing, TextOptions, STORED, TEXT,
};
@@ -112,7 +112,7 @@ mod tests {
Term::from_field_text(text, "hello"),
IndexRecordOption::WithFreqs,
);
let weight = query.weight(EnableScoring::Enabled(&searcher))?;
let weight = query.weight(&searcher, true)?;
let mut scorer = weight.scorer(searcher.segment_reader(0), 1.0f32)?;
assert_eq!(scorer.doc(), 0);
assert!((scorer.score() - 0.22920431).abs() < 0.001f32);
@@ -141,7 +141,7 @@ mod tests {
Term::from_field_text(text, "hello"),
IndexRecordOption::WithFreqs,
);
let weight = query.weight(EnableScoring::Enabled(&searcher))?;
let weight = query.weight(&searcher, true)?;
let mut scorer = weight.scorer(searcher.segment_reader(0), 1.0f32)?;
assert_eq!(scorer.doc(), 0);
assert!((scorer.score() - 0.22920431).abs() < 0.001f32);

8
src/fieldnorm/reader.rs
View File

@@ -47,9 +47,9 @@ impl FieldNormReaders {
}
}
/// Reads the fieldnorm associated with a document.
/// Reads the fieldnorm associated to a document.
///
/// The [fieldnorm](FieldNormReader::fieldnorm) represents the length associated with
/// The [fieldnorm](FieldNormReader::fieldnorm) represents the length associated to
/// a given Field of a given document.
#[derive(Clone)]
pub struct FieldNormReader(ReaderImplEnum);
@@ -104,7 +104,7 @@ impl FieldNormReader {
}
}
/// Returns the `fieldnorm` associated with a doc id.
/// Returns the `fieldnorm` associated to a doc id.
/// The fieldnorm is a value approximating the number
/// of tokens in a given field of the `doc_id`.
///
@@ -123,7 +123,7 @@ impl FieldNormReader {
}
}
/// Returns the `fieldnorm_id` associated with a document.
/// Returns the `fieldnorm_id` associated to a document.
#[inline]
pub fn fieldnorm_id(&self, doc_id: DocId) -> u8 {
match &self.0 {

2
src/fieldnorm/writer.rs
View File

@@ -9,7 +9,7 @@ use crate::DocId;
/// The `FieldNormsWriter` is in charge of tracking the fieldnorm byte
/// of each document for each field with field norms.
///
/// `FieldNormsWriter` stores a `Vec<u8>` for each tracked field, using a
/// `FieldNormsWriter` stores a Vec<u8> for each tracked field, using a
/// byte per document per field.
pub struct FieldNormsWriter {
fieldnorms_buffers: Vec<Option<Vec<u8>>>,

25
src/indexer/delete_queue.rs
View File

@@ -188,7 +188,7 @@ impl DeleteCursor {
}
}
#[allow(clippy::wrong_self_convention)]
#[cfg_attr(feature = "cargo-clippy", allow(clippy::wrong_self_convention))]
fn is_behind_opstamp(&mut self, target_opstamp: Opstamp) -> bool {
self.get()
.map(|operation| operation.opstamp < target_opstamp)
@@ -246,27 +246,18 @@ impl DeleteCursor {
mod tests {
use super::{DeleteOperation, DeleteQueue};
use crate::query::{Explanation, Scorer, Weight};
use crate::{DocId, Score, SegmentReader};
struct DummyWeight;
impl Weight for DummyWeight {
fn scorer(&self, _reader: &SegmentReader, _boost: Score) -> crate::Result<Box<dyn Scorer>> {
Err(crate::TantivyError::InternalError("dummy impl".to_owned()))
}
fn explain(&self, _reader: &SegmentReader, _doc: DocId) -> crate::Result<Explanation> {
Err(crate::TantivyError::InternalError("dummy impl".to_owned()))
}
}
use crate::schema::{Field, Term};
#[test]
fn test_deletequeue() {
let delete_queue = DeleteQueue::new();
let make_op = |i: usize| DeleteOperation {
opstamp: i as u64,
target: Box::new(DummyWeight),
let make_op = |i: usize| {
let field = Field::from_field_id(1u32);
DeleteOperation {
opstamp: i as u64,
term: Term::from_field_u64(field, i as u64),
}
};
delete_queue.push(make_op(1));

6
src/indexer/doc_id_mapping.rs
View File

@@ -24,7 +24,7 @@ impl SegmentDocIdMapping {
/// Returns an iterator over the old document addresses, ordered by the new document ids.
///
/// In the returned `DocAddress`, the `segment_ord` is the ordinal of targeted segment
/// In the returned `DocAddress`, the `segment_ord` is the ordinal of targetted segment
/// in the list of merged segments.
pub(crate) fn iter_old_doc_addrs(&self) -> impl Iterator<Item = DocAddress> + '_ {
self.new_doc_id_to_old_doc_addr.iter().copied()
@@ -34,6 +34,10 @@ impl SegmentDocIdMapping {
self.new_doc_id_to_old_doc_addr.len()
}
pub(crate) fn get_old_doc_addr(&self, new_doc_id: DocId) -> DocAddress {
self.new_doc_id_to_old_doc_addr[new_doc_id as usize]
}
/// This flags means the segments are simply stacked in the order of their ordinal.
/// e.g. [(0, 1), .. (n, 1), (0, 2)..., (m, 2)]
///

69
src/indexer/flat_map_with_buffer.rs
View File

@@ -1,69 +0,0 @@
pub struct FlatMapWithBuffer<T, F, Iter> {
buffer: Vec<T>,
fill_buffer: F,
underlying_it: Iter,
}
impl<T, F, Iter, I> Iterator for FlatMapWithBuffer<T, F, Iter>
where
Iter: Iterator<Item = I>,
F: Fn(I, &mut Vec<T>),
{
type Item = T;
fn next(&mut self) -> Option<Self::Item> {
while self.buffer.is_empty() {
let next_el = self.underlying_it.next()?;
(self.fill_buffer)(next_el, &mut self.buffer);
// We will pop elements, so we reverse the buffer first.
self.buffer.reverse();
}
self.buffer.pop()
}
}
pub trait FlatMapWithBufferIter: Iterator {
/// Function similar to `flat_map`, but allows reusing a shared `Vec`.
fn flat_map_with_buffer<F, T>(self, fill_buffer: F) -> FlatMapWithBuffer<T, F, Self>
where
F: Fn(Self::Item, &mut Vec<T>),
Self: Sized,
{
FlatMapWithBuffer {
buffer: Vec::with_capacity(10),
fill_buffer,
underlying_it: self,
}
}
}
impl<T: ?Sized> FlatMapWithBufferIter for T where T: Iterator {}
#[cfg(test)]
mod tests {
use crate::indexer::flat_map_with_buffer::FlatMapWithBufferIter;
#[test]
fn test_flat_map_with_buffer_empty() {
let mut empty_iter = std::iter::empty::<usize>()
.flat_map_with_buffer(|_val: usize, _buffer: &mut Vec<usize>| {});
assert!(empty_iter.next().is_none());
}
#[test]
fn test_flat_map_with_buffer_simple() {
let vals: Vec<usize> = (1..5)
.flat_map_with_buffer(|val: usize, buffer: &mut Vec<usize>| buffer.extend(0..val))
.collect();
assert_eq!(&[0, 0, 1, 0, 1, 2, 0, 1, 2, 3], &vals[..]);
}
#[test]
fn test_flat_map_filling_no_elements_does_not_stop_iterator() {
let vals: Vec<usize> = [2, 0, 0, 3]
.into_iter()
.flat_map_with_buffer(|val: usize, buffer: &mut Vec<usize>| buffer.extend(0..val))
.collect();
assert_eq!(&[0, 1, 0, 1, 2], &vals[..]);
}
}

695
src/indexer/index_writer.rs
View File

@@ -11,6 +11,7 @@ use super::segment_updater::SegmentUpdater;
use super::{AddBatch, AddBatchReceiver, AddBatchSender, PreparedCommit};
use crate::core::{Index, Segment, SegmentComponent, SegmentId, SegmentMeta, SegmentReader};
use crate::directory::{DirectoryLock, GarbageCollectionResult, TerminatingWrite};
use crate::docset::{DocSet, TERMINATED};
use crate::error::TantivyError;
use crate::fastfield::write_alive_bitset;
use crate::indexer::delete_queue::{DeleteCursor, DeleteQueue};
@@ -19,7 +20,6 @@ use crate::indexer::index_writer_status::IndexWriterStatus;
use crate::indexer::operation::DeleteOperation;
use crate::indexer::stamper::Stamper;
use crate::indexer::{MergePolicy, SegmentEntry, SegmentWriter};
use crate::query::{EnableScoring, Query, TermQuery};
use crate::schema::{Document, IndexRecordOption, Term};
use crate::{FutureResult, Opstamp};
@@ -92,14 +92,19 @@ fn compute_deleted_bitset(
// A delete operation should only affect
// document that were inserted before it.
delete_op
.target
.for_each_no_score(segment_reader, &mut |doc_matching_delete_query| {
if doc_opstamps.is_deleted(doc_matching_delete_query, delete_op.opstamp) {
alive_bitset.remove(doc_matching_delete_query);
let inverted_index = segment_reader.inverted_index(delete_op.term.field())?;
if let Some(mut docset) =
inverted_index.read_postings(&delete_op.term, IndexRecordOption::Basic)?
{
let mut doc_matching_deleted_term = docset.doc();
while doc_matching_deleted_term != TERMINATED {
if doc_opstamps.is_deleted(doc_matching_deleted_term, delete_op.opstamp) {
alive_bitset.remove(doc_matching_deleted_term);
might_have_changed = true;
}
})?;
doc_matching_deleted_term = docset.advance();
}
}
delete_cursor.advance();
}
Ok(might_have_changed)
@@ -297,6 +302,7 @@ impl IndexWriter {
memory_arena_in_bytes_per_thread,
index: index.clone(),
index_writer_status: IndexWriterStatus::from(document_receiver),
operation_sender: document_sender,
@@ -367,9 +373,9 @@ impl IndexWriter {
/// This method is useful only for users trying to do complex
/// operations, like converting an index format to another.
///
/// It is safe to start writing file associated with the new `Segment`.
/// It is safe to start writing file associated to the new `Segment`.
/// These will not be garbage collected as long as an instance object of
/// `SegmentMeta` object associated with the new `Segment` is "alive".
/// `SegmentMeta` object associated to the new `Segment` is "alive".
pub fn new_segment(&self) -> Segment {
self.index.new_segment()
}
@@ -660,32 +666,10 @@ impl IndexWriter {
/// Like adds, the deletion itself will be visible
/// only after calling `commit()`.
pub fn delete_term(&self, term: Term) -> Opstamp {
let query = TermQuery::new(term, IndexRecordOption::Basic);
// For backward compatibility, if Term is invalid for the index, do nothing but return an
// Opstamp
self.delete_query(Box::new(query))
.unwrap_or_else(|_| self.stamper.stamp())
}
/// Delete all documents matching a given query.
/// Returns an `Err` if the query can't be executed.
///
/// Delete operation only affects documents that
/// were added in previous commits, and documents
/// that were added previously in the same commit.
///
/// Like adds, the deletion itself will be visible
/// only after calling `commit()`.
#[doc(hidden)]
pub fn delete_query(&self, query: Box<dyn Query>) -> crate::Result<Opstamp> {
let weight = query.weight(EnableScoring::Disabled(&self.index.schema()))?;
let opstamp = self.stamper.stamp();
let delete_operation = DeleteOperation {
opstamp,
target: weight,
};
let delete_operation = DeleteOperation { opstamp, term };
self.delete_queue.push(delete_operation);
Ok(opstamp)
opstamp
}
/// Returns the opstamp of the last successful commit.
@@ -754,16 +738,10 @@ impl IndexWriter {
let (batch_opstamp, stamps) = self.get_batch_opstamps(count);
let mut adds = AddBatch::default();
for (user_op, opstamp) in user_operations_it.zip(stamps) {
match user_op {
UserOperation::Delete(term) => {
let query = TermQuery::new(term, IndexRecordOption::Basic);
let weight = query.weight(EnableScoring::Disabled(&self.index.schema()))?;
let delete_operation = DeleteOperation {
opstamp,
target: weight,
};
let delete_operation = DeleteOperation { opstamp, term };
self.delete_queue.push(delete_operation);
}
UserOperation::Add(document) => {
@@ -798,9 +776,7 @@ impl Drop for IndexWriter {
#[cfg(test)]
mod tests {
use std::collections::{HashMap, HashSet};
use std::net::Ipv6Addr;
use fastfield_codecs::MonotonicallyMappableToU128;
use proptest::prelude::*;
use proptest::prop_oneof;
use proptest::strategy::Strategy;
@@ -810,15 +786,13 @@ mod tests {
use crate::directory::error::LockError;
use crate::error::*;
use crate::indexer::NoMergePolicy;
use crate::query::{BooleanQuery, Occur, Query, QueryParser, TermQuery};
use crate::query::{QueryParser, TermQuery};
use crate::schema::{
self, Cardinality, Facet, FacetOptions, IndexRecordOption, IpAddrOptions, NumericOptions,
self, Cardinality, Facet, FacetOptions, IndexRecordOption, NumericOptions,
TextFieldIndexing, TextOptions, FAST, INDEXED, STORED, STRING, TEXT,
};
use crate::store::DOCSTORE_CACHE_CAPACITY;
use crate::{
DateTime, DocAddress, Index, IndexSettings, IndexSortByField, Order, ReloadPolicy, Term,
};
use crate::{DocAddress, Index, IndexSettings, IndexSortByField, Order, ReloadPolicy, Term};
const LOREM: &str = "Doc Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do \
eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad \
@@ -1394,35 +1368,6 @@ mod tests {
assert!(commit_again.is_ok());
}
#[test]
fn test_sort_by_multivalue_field_error() -> crate::Result<()> {
let mut schema_builder = schema::Schema::builder();
let options = NumericOptions::default().set_fast(Cardinality::MultiValues);
schema_builder.add_u64_field("id", options);
let schema = schema_builder.build();
let settings = IndexSettings {
sort_by_field: Some(IndexSortByField {
field: "id".to_string(),
order: Order::Desc,
}),
..Default::default()
};
let err = Index::builder()
.schema(schema)
.settings(settings)
.create_in_ram()
.unwrap_err();
assert_eq!(
err.to_string(),
"An invalid argument was passed: 'Only single value fast field Cardinality supported \
for sorting index id'"
);
Ok(())
}
#[test]
fn test_delete_with_sort_by_field() -> crate::Result<()> {
let mut schema_builder = schema::Schema::builder();
@@ -1467,78 +1412,16 @@ mod tests {
let fast_field_reader = segment_reader.fast_fields().u64(id_field)?;
let in_order_alive_ids: Vec<u64> = segment_reader
.doc_ids_alive()
.map(|doc| fast_field_reader.get_val(doc))
.map(|doc| fast_field_reader.get_val(doc as u64))
.collect();
assert_eq!(&in_order_alive_ids[..], &[9, 8, 7, 6, 5, 4, 1, 0]);
Ok(())
}
#[test]
fn test_delete_query_with_sort_by_field() -> crate::Result<()> {
let mut schema_builder = schema::Schema::builder();
let id_field =
schema_builder.add_u64_field("id", schema::INDEXED | schema::STORED | schema::FAST);
let schema = schema_builder.build();
let settings = IndexSettings {
sort_by_field: Some(IndexSortByField {
field: "id".to_string(),
order: Order::Desc,
}),
..Default::default()
};
let index = Index::builder()
.schema(schema)
.settings(settings)
.create_in_ram()?;
let index_reader = index.reader()?;
let mut index_writer = index.writer_for_tests()?;
// create and delete docs in same commit
for id in 0u64..5u64 {
index_writer.add_document(doc!(id_field => id))?;
}
for id in 1u64..4u64 {
let term = Term::from_field_u64(id_field, id);
let not_term = Term::from_field_u64(id_field, 2);
let term = Box::new(TermQuery::new(term, Default::default()));
let not_term = Box::new(TermQuery::new(not_term, Default::default()));
let query: BooleanQuery = vec![
(Occur::Must, term as Box<dyn Query>),
(Occur::MustNot, not_term as Box<dyn Query>),
]
.into();
index_writer.delete_query(Box::new(query))?;
}
for id in 5u64..10u64 {
index_writer.add_document(doc!(id_field => id))?;
}
index_writer.commit()?;
index_reader.reload()?;
let searcher = index_reader.searcher();
assert_eq!(searcher.segment_readers().len(), 1);
let segment_reader = searcher.segment_reader(0);
assert_eq!(segment_reader.num_docs(), 8);
assert_eq!(segment_reader.max_doc(), 10);
let fast_field_reader = segment_reader.fast_fields().u64(id_field)?;
let in_order_alive_ids: Vec<u64> = segment_reader
.doc_ids_alive()
.map(|doc| fast_field_reader.get_val(doc))
.collect();
assert_eq!(&in_order_alive_ids[..], &[9, 8, 7, 6, 5, 4, 2, 0]);
Ok(())
}
#[derive(Debug, Clone, Copy)]
enum IndexingOp {
AddDoc { id: u64 },
DeleteDoc { id: u64 },
DeleteDocQuery { id: u64 },
Commit,
Merge,
}
@@ -1546,7 +1429,6 @@ mod tests {
fn balanced_operation_strategy() -> impl Strategy<Value = IndexingOp> {
prop_oneof![
(0u64..20u64).prop_map(|id| IndexingOp::DeleteDoc { id }),
(0u64..20u64).prop_map(|id| IndexingOp::DeleteDocQuery { id }),
(0u64..20u64).prop_map(|id| IndexingOp::AddDoc { id }),
(0u64..1u64).prop_map(|_| IndexingOp::Commit),
(0u64..1u64).prop_map(|_| IndexingOp::Merge),
@@ -1555,8 +1437,7 @@ mod tests {
fn adding_operation_strategy() -> impl Strategy<Value = IndexingOp> {
prop_oneof![
5 => (0u64..100u64).prop_map(|id| IndexingOp::DeleteDoc { id }),
5 => (0u64..100u64).prop_map(|id| IndexingOp::DeleteDocQuery { id }),
10 => (0u64..100u64).prop_map(|id| IndexingOp::DeleteDoc { id }),
50 => (0u64..100u64).prop_map(|id| IndexingOp::AddDoc { id }),
2 => (0u64..1u64).prop_map(|_| IndexingOp::Commit),
1 => (0u64..1u64).prop_map(|_| IndexingOp::Merge),
@@ -1576,52 +1457,19 @@ mod tests {
existing_ids.remove(&id);
deleted_ids.insert(id);
}
IndexingOp::DeleteDocQuery { id } => {
existing_ids.remove(&id);
deleted_ids.insert(id);
}
_ => {}
}
}
(existing_ids, deleted_ids)
}
fn get_id_list(ops: &[IndexingOp]) -> Vec<u64> {
let mut id_list = Vec::new();
for &op in ops {
match op {
IndexingOp::AddDoc { id } => {
id_list.push(id);
}
IndexingOp::DeleteDoc { id } => {
id_list.retain(|el| *el != id);
}
IndexingOp::DeleteDocQuery { id } => {
id_list.retain(|el| *el != id);
}
_ => {}
}
}
id_list
}
fn test_operation_strategy(
ops: &[IndexingOp],
sort_index: bool,
force_end_merge: bool,
) -> crate::Result<()> {
let mut schema_builder = schema::Schema::builder();
let ip_field = schema_builder.add_ip_addr_field("ip", FAST | INDEXED | STORED);
let ips_field = schema_builder.add_ip_addr_field(
"ips",
IpAddrOptions::default()
.set_fast(Cardinality::MultiValues)
.set_indexed(),
);
let id_field = schema_builder.add_u64_field("id", FAST | INDEXED | STORED);
let i64_field = schema_builder.add_i64_field("i64", INDEXED);
let f64_field = schema_builder.add_f64_field("f64", INDEXED);
let date_field = schema_builder.add_date_field("date", INDEXED);
let bytes_field = schema_builder.add_bytes_field("bytes", FAST | INDEXED | STORED);
let bool_field = schema_builder.add_bool_field("bool", FAST | INDEXED | STORED);
let text_field = schema_builder.add_text_field(
@@ -1635,7 +1483,6 @@ mod tests {
);
let large_text_field = schema_builder.add_text_field("large_text_field", TEXT | STORED);
let multi_text_fields = schema_builder.add_text_field("multi_text_fields", TEXT | STORED);
let multi_numbers = schema_builder.add_u64_field(
"multi_numbers",
@@ -1673,72 +1520,25 @@ mod tests {
let old_reader = index.reader()?;
let ip_exists = |id| id % 3 != 0; // 0 does not exist
let multi_text_field_text1 = "test1 test2 test3 test1 test2 test3";
// rotate left
let multi_text_field_text2 = "test2 test3 test1 test2 test3 test1";
// rotate right
let multi_text_field_text3 = "test3 test1 test2 test3 test1 test2";
let ip_from_id = |id| Ipv6Addr::from_u128(id as u128);
for &op in ops {
match op {
IndexingOp::AddDoc { id } => {
let facet = Facet::from(&("/cola/".to_string() + &id.to_string()));
let ip = ip_from_id(id);
if !ip_exists(id) {
// every 3rd doc has no ip field
index_writer.add_document(doc!(id_field=>id,
bytes_field => id.to_le_bytes().as_slice(),
multi_numbers=> id,
multi_numbers => id,
bool_field => (id % 2u64) != 0,
i64_field => id as i64,
f64_field => id as f64,
date_field => DateTime::from_timestamp_secs(id as i64),
multi_bools => (id % 2u64) != 0,
multi_bools => (id % 2u64) == 0,
text_field => id.to_string(),
facet_field => facet,
large_text_field => LOREM,
multi_text_fields => multi_text_field_text1,
multi_text_fields => multi_text_field_text2,
multi_text_fields => multi_text_field_text3,
))?;
} else {
index_writer.add_document(doc!(id_field=>id,
bytes_field => id.to_le_bytes().as_slice(),
ip_field => ip,
ips_field => ip,
ips_field => ip,
multi_numbers=> id,
multi_numbers => id,
bool_field => (id % 2u64) != 0,
i64_field => id as i64,
f64_field => id as f64,
date_field => DateTime::from_timestamp_secs(id as i64),
multi_bools => (id % 2u64) != 0,
multi_bools => (id % 2u64) == 0,
text_field => id.to_string(),
facet_field => facet,
large_text_field => LOREM,
multi_text_fields => multi_text_field_text1,
multi_text_fields => multi_text_field_text2,
multi_text_fields => multi_text_field_text3,
))?;
}
index_writer.add_document(doc!(id_field=>id,
bytes_field => id.to_le_bytes().as_slice(),
multi_numbers=> id,
multi_numbers => id,
bool_field => (id % 2u64) != 0,
multi_bools => (id % 2u64) != 0,
multi_bools => (id % 2u64) == 0,
text_field => id.to_string(),
facet_field => facet,
large_text_field=> LOREM
))?;
}
IndexingOp::DeleteDoc { id } => {
index_writer.delete_term(Term::from_field_u64(id_field, id));
}
IndexingOp::DeleteDocQuery { id } => {
let term = Term::from_field_u64(id_field, id);
let query = TermQuery::new(term, Default::default());
index_writer.delete_query(Box::new(query))?;
}
IndexingOp::Commit => {
index_writer.commit()?;
}
@@ -1756,7 +1556,6 @@ mod tests {
index_writer.commit()?;
let searcher = index.reader()?.searcher();
let num_segments_before_merge = searcher.segment_readers().len();
if force_end_merge {
index_writer.wait_merging_threads()?;
let mut index_writer = index.writer_for_tests()?;
@@ -1768,7 +1567,6 @@ mod tests {
assert!(index_writer.wait_merging_threads().is_ok());
}
}
let num_segments_after_merge = searcher.segment_readers().len();
old_reader.reload()?;
let old_searcher = old_reader.searcher();
@@ -1780,7 +1578,7 @@ mod tests {
let ff_reader = segment_reader.fast_fields().u64(id_field).unwrap();
segment_reader
.doc_ids_alive()
.map(move |doc| ff_reader.get_val(doc))
.map(move |doc| ff_reader.get_val(doc as u64))
})
.collect();
@@ -1791,27 +1589,11 @@ mod tests {
let ff_reader = segment_reader.fast_fields().u64(id_field).unwrap();
segment_reader
.doc_ids_alive()
.map(move |doc| ff_reader.get_val(doc))
.map(move |doc| ff_reader.get_val(doc as u64))
})
.collect();
let (expected_ids_and_num_occurrences, deleted_ids) = expected_ids(ops);
let id_list = get_id_list(ops);
// multivalue fast field content
let mut all_ips = Vec::new();
let mut num_ips = 0;
for segment_reader in searcher.segment_readers().iter() {
let ip_reader = segment_reader.fast_fields().ip_addrs(ips_field).unwrap();
for doc in segment_reader.doc_ids_alive() {
let mut vals = vec![];
ip_reader.get_vals(doc, &mut vals);
all_ips.extend_from_slice(&vals);
}
num_ips += ip_reader.total_num_vals();
}
let num_docs_expected = expected_ids_and_num_occurrences
.iter()
.map(|(_, id_occurrences)| *id_occurrences as usize)
@@ -1833,84 +1615,6 @@ mod tests {
.collect::<HashSet<_>>()
);
if force_end_merge && num_segments_before_merge > 1 && num_segments_after_merge == 1 {
let mut expected_multi_ips: Vec<_> = id_list
.iter()
.filter(|id| ip_exists(**id))
.flat_map(|id| vec![ip_from_id(*id), ip_from_id(*id)])
.collect();
assert_eq!(num_ips, expected_multi_ips.len() as u32);
expected_multi_ips.sort();
all_ips.sort();
assert_eq!(expected_multi_ips, all_ips);
// Test fastfield num_docs
let num_docs: usize = searcher
.segment_readers()
.iter()
.map(|segment_reader| {
let ff_reader = segment_reader.fast_fields().ip_addrs(ips_field).unwrap();
ff_reader.get_index_reader().num_docs() as usize
})
.sum();
assert_eq!(num_docs, num_docs_expected);
}
// Load all ips addr
let ips: HashSet<Ipv6Addr> = searcher
.segment_readers()
.iter()
.flat_map(|segment_reader| {
let ff_reader = segment_reader.fast_fields().ip_addr(ip_field).unwrap();
segment_reader.doc_ids_alive().flat_map(move |doc| {
let val = ff_reader.get_val(doc);
if val == Ipv6Addr::from_u128(0) {
// TODO Fix null handling
None
} else {
Some(val)
}
})
})
.collect();
let expected_ips = expected_ids_and_num_occurrences
.keys()
.flat_map(|id| {
if !ip_exists(*id) {
None
} else {
Some(Ipv6Addr::from_u128(*id as u128))
}
})
.collect::<HashSet<_>>();
assert_eq!(ips, expected_ips);
let expected_ips = expected_ids_and_num_occurrences
.keys()
.filter_map(|id| {
if !ip_exists(*id) {
None
} else {
Some(Ipv6Addr::from_u128(*id as u128))
}
})
.collect::<HashSet<_>>();
let ips: HashSet<Ipv6Addr> = searcher
.segment_readers()
.iter()
.flat_map(|segment_reader| {
let ff_reader = segment_reader.fast_fields().ip_addrs(ips_field).unwrap();
segment_reader.doc_ids_alive().flat_map(move |doc| {
let mut vals = vec![];
ff_reader.get_vals(doc, &mut vals);
vals.into_iter().filter(|val| val.to_u128() != 0) // TODO Fix null handling
})
})
.collect();
assert_eq!(ips, expected_ips);
// multivalue fast field tests
for segment_reader in searcher.segment_readers().iter() {
let id_reader = segment_reader.fast_fields().u64(id_field).unwrap();
@@ -1921,7 +1625,7 @@ mod tests {
ff_reader.get_vals(doc, &mut vals);
assert_eq!(vals.len(), 2);
assert_eq!(vals[0], vals[1]);
assert_eq!(id_reader.get_val(doc), vals[0]);
assert_eq!(id_reader.get_val(doc as u64), vals[0]);
let mut bool_vals = vec![];
bool_ff_reader.get_vals(doc, &mut bool_vals);
@@ -1975,8 +1679,10 @@ mod tests {
}
}
// test search
let do_search = |term: &str, field| {
let query = QueryParser::for_index(&index, vec![field])
let my_text_field = index.schema().get_field("text_field").unwrap();
let do_search = |term: &str| {
let query = QueryParser::for_index(&index, vec![my_text_field])
.parse_query(term)
.unwrap();
let top_docs: Vec<(f32, DocAddress)> =
@@ -1985,126 +1691,12 @@ mod tests {
top_docs.iter().map(|el| el.1).collect::<Vec<_>>()
};
let do_search2 = |term: Term| {
let query = TermQuery::new(term, IndexRecordOption::Basic);
let top_docs: Vec<(f32, DocAddress)> =
searcher.search(&query, &TopDocs::with_limit(1000)).unwrap();
top_docs.iter().map(|el| el.1).collect::<Vec<_>>()
};
for (existing_id, count) in &expected_ids_and_num_occurrences {
let (existing_id, count) = (*existing_id, *count);
let get_num_hits = |field| do_search(&existing_id.to_string(), field).len() as u64;
assert_eq!(get_num_hits(text_field), count);
assert_eq!(get_num_hits(i64_field), count);
assert_eq!(get_num_hits(f64_field), count);
assert_eq!(get_num_hits(id_field), count);
// Test multi text
assert_eq!(
do_search("\"test1 test2\"", multi_text_fields).len(),
num_docs_expected
);
assert_eq!(
do_search("\"test2 test3\"", multi_text_fields).len(),
num_docs_expected
);
// Test bytes
let term = Term::from_field_bytes(bytes_field, existing_id.to_le_bytes().as_slice());
assert_eq!(do_search2(term).len() as u64, count);
// Test date
let term = Term::from_field_date(
date_field,
DateTime::from_timestamp_secs(existing_id as i64),
);
assert_eq!(do_search2(term).len() as u64, count);
for (existing_id, count) in expected_ids_and_num_occurrences {
assert_eq!(do_search(&existing_id.to_string()).len() as u64, count);
}
for deleted_id in deleted_ids {
let assert_field = |field| {
assert_eq!(do_search(&deleted_id.to_string(), field).len() as u64, 0);
};
assert_field(text_field);
assert_field(f64_field);
assert_field(i64_field);
assert_field(id_field);
// Test bytes
let term = Term::from_field_bytes(bytes_field, deleted_id.to_le_bytes().as_slice());
assert_eq!(do_search2(term).len() as u64, 0);
// Test date
let term =
Term::from_field_date(date_field, DateTime::from_timestamp_secs(deleted_id as i64));
assert_eq!(do_search2(term).len() as u64, 0);
for existing_id in deleted_ids {
assert_eq!(do_search(&existing_id.to_string()).len(), 0);
}
// search ip address
//
for (existing_id, count) in &expected_ids_and_num_occurrences {
let (existing_id, count) = (*existing_id, *count);
if !ip_exists(existing_id) {
continue;
}
let do_search_ip_field = |term: &str| do_search(term, ip_field).len() as u64;
let ip_addr = Ipv6Addr::from_u128(existing_id as u128);
// Test incoming ip as ipv6
assert_eq!(do_search_ip_field(&format!("\"{}\"", ip_addr)), count);
let term = Term::from_field_ip_addr(ip_field, ip_addr);
assert_eq!(do_search2(term).len() as u64, count);
// Test incoming ip as ipv4
if let Some(ip_addr) = ip_addr.to_ipv4_mapped() {
assert_eq!(do_search_ip_field(&format!("\"{}\"", ip_addr)), count);
}
}
// assert data is like expected
//
for (existing_id, count) in expected_ids_and_num_occurrences.iter().take(10) {
let (existing_id, count) = (*existing_id, *count);
if !ip_exists(existing_id) {
continue;
}
let gen_query_inclusive = |field: &str, from: Ipv6Addr, to: Ipv6Addr| {
format!("{}:[{} TO {}]", field, &from.to_string(), &to.to_string())
};
let ip = ip_from_id(existing_id);
let do_search_ip_field = |term: &str| do_search(term, ip_field).len() as u64;
// Range query on single value field
// let query = gen_query_inclusive("ip", ip, ip);
// assert_eq!(do_search_ip_field(&query), count);
// Range query on multi value field
let query = gen_query_inclusive("ips", ip, ip);
assert_eq!(do_search_ip_field(&query), count);
}
// ip range query on fast field
//
for (existing_id, count) in expected_ids_and_num_occurrences.iter().take(10) {
let (existing_id, count) = (*existing_id, *count);
if !ip_exists(existing_id) {
continue;
}
let gen_query_inclusive = |field: &str, from: Ipv6Addr, to: Ipv6Addr| {
format!("{}:[{} TO {}]", field, &from.to_string(), &to.to_string())
};
let ip = ip_from_id(existing_id);
let do_search_ip_field = |term: &str| do_search(term, ip_field).len() as u64;
// Range query on single value field
// let query = gen_query_inclusive("ip", ip, ip);
// assert_eq!(do_search_ip_field(&query), count);
// Range query on multi value field
let query = gen_query_inclusive("ips", ip, ip);
assert_eq!(do_search_ip_field(&query), count);
}
// test facets
for segment_reader in searcher.segment_readers().iter() {
let mut facet_reader = segment_reader.facet_reader(facet_field).unwrap();
@@ -2117,7 +1709,7 @@ mod tests {
facet_reader
.facet_from_ord(facet_ords[0], &mut facet)
.unwrap();
let id = ff_reader.get_val(doc_id);
let id = ff_reader.get_val(doc_id as u64);
let facet_expected = Facet::from(&("/cola/".to_string() + &id.to_string()));
assert_eq!(facet, facet_expected);
@@ -2126,70 +1718,6 @@ mod tests {
Ok(())
}
#[test]
fn test_ip_range_query_multivalue_bug() {
assert!(test_operation_strategy(
&[
IndexingOp::AddDoc { id: 2 },
IndexingOp::Commit,
IndexingOp::AddDoc { id: 1 },
IndexingOp::AddDoc { id: 1 },
IndexingOp::Commit,
IndexingOp::Merge
],
true,
false
)
.is_ok());
}
#[test]
fn test_ff_num_ips_regression() {
assert!(test_operation_strategy(
&[
IndexingOp::AddDoc { id: 13 },
IndexingOp::AddDoc { id: 1 },
IndexingOp::Commit,
IndexingOp::DeleteDocQuery { id: 13 },
IndexingOp::AddDoc { id: 1 },
IndexingOp::Commit,
],
false,
true
)
.is_ok());
}
#[test]
fn test_minimal() {
assert!(test_operation_strategy(
&[
IndexingOp::AddDoc { id: 23 },
IndexingOp::AddDoc { id: 13 },
IndexingOp::DeleteDoc { id: 13 }
],
true,
true
)
.is_ok());
assert!(test_operation_strategy(
&[
IndexingOp::AddDoc { id: 23 },
IndexingOp::AddDoc { id: 13 },
IndexingOp::DeleteDoc { id: 13 }
],
false,
false
)
.is_ok());
}
#[test]
fn test_minimal_sort_merge() {
assert!(test_operation_strategy(&[IndexingOp::AddDoc { id: 3 },], true, true).is_ok());
}
proptest! {
#![proptest_config(ProptestConfig::with_cases(20))]
#[test]
@@ -2282,135 +1810,4 @@ mod tests {
index_writer.commit()?;
Ok(())
}
#[test]
fn test_bug_1617_3() {
assert!(test_operation_strategy(
&[
IndexingOp::DeleteDoc { id: 0 },
IndexingOp::AddDoc { id: 6 },
IndexingOp::DeleteDocQuery { id: 11 },
IndexingOp::Commit,
IndexingOp::Merge,
IndexingOp::Commit,
IndexingOp::Commit
],
false,
false
)
.is_ok());
}
#[test]
fn test_bug_1617_2() {
assert!(test_operation_strategy(
&[
IndexingOp::AddDoc { id: 13 },
IndexingOp::DeleteDoc { id: 13 },
IndexingOp::Commit,
IndexingOp::AddDoc { id: 30 },
IndexingOp::Commit,
IndexingOp::Merge,
],
false,
true
)
.is_ok());
}
#[test]
fn test_bug_1617() -> crate::Result<()> {
let mut schema_builder = schema::Schema::builder();
let id_field = schema_builder.add_u64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::builder().schema(schema).create_in_ram()?;
let mut index_writer = index.writer_for_tests()?;
index_writer.set_merge_policy(Box::new(NoMergePolicy));
let existing_id = 16u64;
let deleted_id = 13u64;
index_writer.add_document(doc!(
id_field=>existing_id,
))?;
index_writer.add_document(doc!(
id_field=>deleted_id,
))?;
index_writer.delete_term(Term::from_field_u64(id_field, deleted_id));
index_writer.commit()?;
// Merge
{
assert!(index_writer.wait_merging_threads().is_ok());
let mut index_writer = index.writer_for_tests()?;
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
index_writer.merge(&segment_ids).wait().unwrap();
assert!(index_writer.wait_merging_threads().is_ok());
}
let searcher = index.reader()?.searcher();
let query = TermQuery::new(
Term::from_field_u64(id_field, existing_id),
IndexRecordOption::Basic,
);
let top_docs: Vec<(f32, DocAddress)> =
searcher.search(&query, &TopDocs::with_limit(10)).unwrap();
assert_eq!(top_docs.len(), 1); // Fails
Ok(())
}
#[test]
fn test_bug_1618() -> crate::Result<()> {
let mut schema_builder = schema::Schema::builder();
let id_field = schema_builder.add_i64_field("id", INDEXED);
let schema = schema_builder.build();
let index = Index::builder().schema(schema).create_in_ram()?;
let mut index_writer = index.writer_for_tests()?;
index_writer.set_merge_policy(Box::new(NoMergePolicy));
index_writer.add_document(doc!(
id_field=>10i64,
))?;
index_writer.add_document(doc!(
id_field=>30i64,
))?;
index_writer.commit()?;
// Merge
{
assert!(index_writer.wait_merging_threads().is_ok());
let mut index_writer = index.writer_for_tests()?;
let segment_ids = index
.searchable_segment_ids()
.expect("Searchable segments failed.");
index_writer.merge(&segment_ids).wait().unwrap();
assert!(index_writer.wait_merging_threads().is_ok());
}
let searcher = index.reader()?.searcher();
let query = TermQuery::new(
Term::from_field_i64(id_field, 10i64),
IndexRecordOption::Basic,
);
let top_docs: Vec<(f32, DocAddress)> =
searcher.search(&query, &TopDocs::with_limit(10)).unwrap();
assert_eq!(top_docs.len(), 1); // Fails
let query = TermQuery::new(
Term::from_field_i64(id_field, 30i64),
IndexRecordOption::Basic,
);
let top_docs: Vec<(f32, DocAddress)> =
searcher.search(&query, &TopDocs::with_limit(10)).unwrap();
assert_eq!(top_docs.len(), 1); // Fails
Ok(())
}
}

219
src/indexer/json_term_writer.rs
View File

@@ -1,6 +1,6 @@
use fastfield_codecs::MonotonicallyMappableToU64;
use fnv::FnvHashMap;
use murmurhash32::murmurhash2;
use rustc_hash::FxHashMap;
use crate::fastfield::FastValue;
use crate::postings::{IndexingContext, IndexingPosition, PostingsWriter};
@@ -52,7 +52,7 @@ use crate::{DatePrecision, DateTime, DocId, Term};
/// path map to the same index position as long as the probability is relatively low.
#[derive(Default)]
struct IndexingPositionsPerPath {
positions_per_path: FxHashMap<u32, IndexingPosition>,
positions_per_path: FnvHashMap<u32, IndexingPosition>,
}
impl IndexingPositionsPerPath {
@@ -67,12 +67,11 @@ pub(crate) fn index_json_values<'a>(
doc: DocId,
json_values: impl Iterator<Item = crate::Result<&'a serde_json::Map<String, serde_json::Value>>>,
text_analyzer: &TextAnalyzer,
expand_dots_enabled: bool,
term_buffer: &mut Term,
postings_writer: &mut dyn PostingsWriter,
ctx: &mut IndexingContext,
) -> crate::Result<()> {
let mut json_term_writer = JsonTermWriter::wrap(term_buffer, expand_dots_enabled);
let mut json_term_writer = JsonTermWriter::wrap(term_buffer);
let mut positions_per_path: IndexingPositionsPerPath = Default::default();
for json_value_res in json_values {
let json_value = json_value_res?;
@@ -243,12 +242,10 @@ pub(crate) fn set_string_and_get_terms(
) -> Vec<(usize, Term)> {
let mut positions_and_terms = Vec::<(usize, Term)>::new();
json_term_writer.close_path_and_set_type(Type::Str);
let term_num_bytes = json_term_writer.term_buffer.len_bytes();
let term_num_bytes = json_term_writer.term_buffer.as_slice().len();
let mut token_stream = text_analyzer.token_stream(value);
token_stream.process(&mut |token| {
json_term_writer
.term_buffer
.truncate_value_bytes(term_num_bytes);
json_term_writer.term_buffer.truncate(term_num_bytes);
json_term_writer
.term_buffer
.append_bytes(token.text.as_bytes());
@@ -260,105 +257,56 @@ pub(crate) fn set_string_and_get_terms(
pub struct JsonTermWriter<'a> {
term_buffer: &'a mut Term,
path_stack: Vec<usize>,
expand_dots_enabled: bool,
}
/// Splits a json path supplied to the query parser in such a way that
/// `.` can be escaped.
///
/// In other words,
/// - `k8s.node` ends up as `["k8s", "node"]`.
/// - `k8s\.node` ends up as `["k8s.node"]`.
fn split_json_path(json_path: &str) -> Vec<String> {
let mut escaped_state: bool = false;
let mut json_path_segments = Vec::new();
let mut buffer = String::new();
for ch in json_path.chars() {
if escaped_state {
buffer.push(ch);
escaped_state = false;
continue;
}
match ch {
'\\' => {
escaped_state = true;
}
'.' => {
let new_segment = std::mem::take(&mut buffer);
json_path_segments.push(new_segment);
}
_ => {
buffer.push(ch);
}
}
}
json_path_segments.push(buffer);
json_path_segments
}
impl<'a> JsonTermWriter<'a> {
pub fn from_field_and_json_path(
field: Field,
json_path: &str,
expand_dots_enabled: bool,
term_buffer: &'a mut Term,
) -> Self {
term_buffer.set_field_and_type(field, Type::Json);
let mut json_term_writer = Self::wrap(term_buffer, expand_dots_enabled);
for segment in split_json_path(json_path) {
json_term_writer.push_path_segment(&segment);
term_buffer.set_field(Type::Json, field);
let mut json_term_writer = Self::wrap(term_buffer);
for segment in json_path.split('.') {
json_term_writer.push_path_segment(segment);
}
json_term_writer
}
pub fn wrap(term_buffer: &'a mut Term, expand_dots_enabled: bool) -> Self {
pub fn wrap(term_buffer: &'a mut Term) -> Self {
term_buffer.clear_with_type(Type::Json);
let mut path_stack = Vec::with_capacity(10);
path_stack.push(0);
path_stack.push(5);
Self {
term_buffer,
path_stack,
expand_dots_enabled,
}
}
fn trim_to_end_of_path(&mut self) {
let end_of_path = *self.path_stack.last().unwrap();
self.term_buffer.truncate_value_bytes(end_of_path);
self.term_buffer.truncate(end_of_path);
}
pub fn close_path_and_set_type(&mut self, typ: Type) {
self.trim_to_end_of_path();
let buffer = self.term_buffer.value_bytes_mut();
let buffer = self.term_buffer.as_mut();
let buffer_len = buffer.len();
buffer[buffer_len - 1] = JSON_END_OF_PATH;
self.term_buffer.append_bytes(&[typ.to_code()]);
buffer.push(typ.to_code());
}
pub fn push_path_segment(&mut self, segment: &str) {
// the path stack should never be empty.
self.trim_to_end_of_path();
let buffer = self.term_buffer.value_bytes_mut();
let buffer = self.term_buffer.as_mut();
let buffer_len = buffer.len();
if self.path_stack.len() > 1 {
buffer[buffer_len - 1] = JSON_PATH_SEGMENT_SEP;
}
if self.expand_dots_enabled && segment.as_bytes().contains(&b'.') {
// We need to replace `.` by JSON_PATH_SEGMENT_SEP.
self.term_buffer
.append_bytes(segment.as_bytes())
.iter_mut()
.for_each(|byte| {
if *byte == b'.' {
*byte = JSON_PATH_SEGMENT_SEP;
}
});
} else {
self.term_buffer.append_bytes(segment.as_bytes());
}
self.term_buffer.push_byte(JSON_PATH_SEGMENT_SEP);
self.path_stack.push(self.term_buffer.len_bytes());
buffer.extend(segment.as_bytes());
buffer.push(JSON_PATH_SEGMENT_SEP);
self.path_stack.push(buffer.len());
}
pub fn pop_path_segment(&mut self) {
@@ -370,8 +318,8 @@ impl<'a> JsonTermWriter<'a> {
/// Returns the json path of the term being currently built.
#[cfg(test)]
pub(crate) fn path(&self) -> &[u8] {
let end_of_path = self.path_stack.last().cloned().unwrap_or(1);
&self.term().value_bytes()[..end_of_path - 1]
let end_of_path = self.path_stack.last().cloned().unwrap_or(6);
&self.term().as_slice()[5..end_of_path - 1]
}
pub fn set_fast_value<T: FastValue>(&mut self, val: T) {
@@ -384,13 +332,14 @@ impl<'a> JsonTermWriter<'a> {
val.to_u64()
};
self.term_buffer
.append_bytes(value.to_be_bytes().as_slice());
.as_mut()
.extend_from_slice(value.to_be_bytes().as_slice());
}
#[cfg(test)]
pub(crate) fn set_str(&mut self, text: &str) {
self.close_path_and_set_type(Type::Str);
self.term_buffer.append_bytes(text.as_bytes());
self.term_buffer.as_mut().extend_from_slice(text.as_bytes());
}
pub fn term(&self) -> &Term {
@@ -400,15 +349,16 @@ impl<'a> JsonTermWriter<'a> {
#[cfg(test)]
mod tests {
use super::{split_json_path, JsonTermWriter};
use super::JsonTermWriter;
use crate::schema::{Field, Type};
use crate::Term;
#[test]
fn test_json_writer() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("attributes");
json_writer.push_path_segment("color");
json_writer.set_str("red");
@@ -441,8 +391,9 @@ mod tests {
#[test]
fn test_string_term() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
json_writer.set_str("red");
assert_eq!(
@@ -454,8 +405,9 @@ mod tests {
#[test]
fn test_i64_term() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
json_writer.set_fast_value(-4i64);
assert_eq!(
@@ -467,8 +419,9 @@ mod tests {
#[test]
fn test_u64_term() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
json_writer.set_fast_value(4u64);
assert_eq!(
@@ -480,8 +433,9 @@ mod tests {
#[test]
fn test_f64_term() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
json_writer.set_fast_value(4.0f64);
assert_eq!(
@@ -493,8 +447,9 @@ mod tests {
#[test]
fn test_bool_term() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
json_writer.set_fast_value(true);
assert_eq!(
@@ -506,8 +461,9 @@ mod tests {
#[test]
fn test_push_after_set_path_segment() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("attribute");
json_writer.set_str("something");
json_writer.push_path_segment("color");
@@ -521,8 +477,9 @@ mod tests {
#[test]
fn test_pop_segment() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
json_writer.push_path_segment("hue");
json_writer.pop_path_segment();
@@ -536,8 +493,9 @@ mod tests {
#[test]
fn test_json_writer_path() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
let mut term = Term::new();
term.set_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term);
json_writer.push_path_segment("color");
assert_eq!(json_writer.path(), b"color");
json_writer.push_path_segment("hue");
@@ -545,79 +503,4 @@ mod tests {
json_writer.set_str("pink");
assert_eq!(json_writer.path(), b"color\x01hue");
}
#[test]
fn test_json_path_expand_dots_disabled() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, false);
json_writer.push_path_segment("color.hue");
assert_eq!(json_writer.path(), b"color.hue");
}
#[test]
fn test_json_path_expand_dots_enabled() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, true);
json_writer.push_path_segment("color.hue");
assert_eq!(json_writer.path(), b"color\x01hue");
}
#[test]
fn test_json_path_expand_dots_enabled_pop_segment() {
let field = Field::from_field_id(1);
let mut term = Term::with_type_and_field(Type::Json, field);
let mut json_writer = JsonTermWriter::wrap(&mut term, true);
json_writer.push_path_segment("hello");
assert_eq!(json_writer.path(), b"hello");
json_writer.push_path_segment("color.hue");
assert_eq!(json_writer.path(), b"hello\x01color\x01hue");
json_writer.pop_path_segment();
assert_eq!(json_writer.path(), b"hello");
}
#[test]
fn test_split_json_path_simple() {
let json_path = split_json_path("titi.toto");
assert_eq!(&json_path, &["titi", "toto"]);
}
#[test]
fn test_split_json_path_single_segment() {
let json_path = split_json_path("toto");
assert_eq!(&json_path, &["toto"]);
}
#[test]
fn test_split_json_path_trailing_dot() {
let json_path = split_json_path("toto.");
assert_eq!(&json_path, &["toto", ""]);
}
#[test]
fn test_split_json_path_heading_dot() {
let json_path = split_json_path(".toto");
assert_eq!(&json_path, &["", "toto"]);
}
#[test]
fn test_split_json_path_escaped_dot() {
let json_path = split_json_path(r#"toto\.titi"#);
assert_eq!(&json_path, &["toto.titi"]);
let json_path_2 = split_json_path(r#"k8s\.container\.name"#);
assert_eq!(&json_path_2, &["k8s.container.name"]);
}
#[test]
fn test_split_json_path_escaped_backslash() {
let json_path = split_json_path(r#"toto\\titi"#);
assert_eq!(&json_path, &[r#"toto\titi"#]);
}
#[test]
fn test_split_json_path_escaped_normal_letter() {
let json_path = split_json_path(r#"toto\titi"#);
assert_eq!(&json_path, &[r#"tototiti"#]);
}
}

215
src/indexer/merger.rs
View File

@@ -6,19 +6,16 @@ use fastfield_codecs::VecColumn;
use itertools::Itertools;
use measure_time::debug_time;
use super::flat_map_with_buffer::FlatMapWithBufferIter;
use super::sorted_doc_id_multivalue_column::RemappedDocIdMultiValueIndexColumn;
use crate::core::{Segment, SegmentReader};
use crate::docset::{DocSet, TERMINATED};
use crate::error::DataCorruption;
use crate::fastfield::{
get_fastfield_codecs_for_multivalue, AliveBitSet, Column, CompositeFastFieldSerializer,
MultiValueIndex, MultiValuedFastFieldReader, MultiValuedU128FastFieldReader,
AliveBitSet, Column, CompositeFastFieldSerializer, MultiValueLength, MultiValuedFastFieldReader,
};
use crate::fieldnorm::{FieldNormReader, FieldNormReaders, FieldNormsSerializer, FieldNormsWriter};
use crate::indexer::doc_id_mapping::{expect_field_id_for_sort_field, SegmentDocIdMapping};
use crate::indexer::sorted_doc_id_column::RemappedDocIdColumn;
use crate::indexer::sorted_doc_id_multivalue_column::RemappedDocIdMultiValueColumn;
use crate::indexer::sorted_doc_id_column::SortedDocIdColumn;
use crate::indexer::sorted_doc_id_multivalue_column::SortedDocIdMultiValueColumn;
use crate::indexer::SegmentSerializer;
use crate::postings::{InvertedIndexSerializer, Postings, SegmentPostings};
use crate::schema::{Cardinality, Field, FieldType, Schema};
@@ -296,24 +293,6 @@ impl IndexMerger {
self.write_bytes_fast_field(field, fast_field_serializer, doc_id_mapping)?;
}
}
FieldType::IpAddr(options) => match options.get_fastfield_cardinality() {
Some(Cardinality::SingleValue) => {
self.write_u128_single_fast_field(
field,
fast_field_serializer,
doc_id_mapping,
)?;
}
Some(Cardinality::MultiValues) => {
self.write_u128_multi_fast_field(
field,
fast_field_serializer,
doc_id_mapping,
)?;
}
None => {}
},
FieldType::JsonObject(_) | FieldType::Facet(_) | FieldType::Str(_) => {
// We don't handle json fast field for the moment
// They can be implemented using what is done
@@ -324,106 +303,6 @@ impl IndexMerger {
Ok(())
}
// used to merge `u128` single fast fields.
fn write_u128_multi_fast_field(
&self,
field: Field,
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
) -> crate::Result<()> {
let segment_and_ff_readers: Vec<(&SegmentReader, MultiValuedU128FastFieldReader<u128>)> =
self.readers
.iter()
.map(|segment_reader| {
let ff_reader: MultiValuedU128FastFieldReader<u128> =
segment_reader.fast_fields().u128s(field).expect(
"Failed to find index for multivalued field. This is a bug in \
tantivy, please report.",
);
(segment_reader, ff_reader)
})
.collect::<Vec<_>>();
Self::write_1_n_fast_field_idx_generic(
field,
fast_field_serializer,
doc_id_mapping,
&segment_and_ff_readers
.iter()
.map(|(segment_reader, u64s_reader)| {
(*segment_reader, u64s_reader.get_index_reader())
})
.collect::<Vec<_>>(),
)?;
let num_vals = segment_and_ff_readers
.iter()
.map(|(segment_reader, reader)| {
// TODO implement generic version, implement reverse scan, all - deletes
if let Some(alive_bitset) = segment_reader.alive_bitset() {
alive_bitset
.iter_alive()
.map(|doc| reader.num_vals(doc))
.sum()
} else {
reader.total_num_vals() as u32
}
})
.sum();
let fast_field_readers = segment_and_ff_readers
.into_iter()
.map(|(_, ff_reader)| ff_reader)
.collect::<Vec<_>>();
let iter_gen = || {
doc_id_mapping
.iter_old_doc_addrs()
.flat_map_with_buffer(|doc_addr, buffer| {
let fast_field_reader = &fast_field_readers[doc_addr.segment_ord as usize];
fast_field_reader.get_vals(doc_addr.doc_id, buffer);
})
};
fast_field_serializer.create_u128_fast_field_with_idx(field, iter_gen, num_vals, 1)?;
Ok(())
}
// used to merge `u128` single fast fields.
fn write_u128_single_fast_field(
&self,
field: Field,
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
) -> crate::Result<()> {
let fast_field_readers = self
.readers
.iter()
.map(|reader| {
let u128_reader: Arc<dyn Column<u128>> = reader.fast_fields().u128(field).expect(
"Failed to find a reader for single fast field. This is a tantivy bug and it \
should never happen.",
);
u128_reader
})
.collect::<Vec<_>>();
let iter_gen = || {
doc_id_mapping.iter_old_doc_addrs().map(|doc_addr| {
let fast_field_reader = &fast_field_readers[doc_addr.segment_ord as usize];
fast_field_reader.get_val(doc_addr.doc_id)
})
};
fast_field_serializer.create_u128_fast_field_with_idx(
field,
iter_gen,
doc_id_mapping.len() as u32,
0,
)?;
Ok(())
}
// used both to merge field norms, `u64/i64` single fast fields.
fn write_single_fast_field(
&self,
@@ -431,7 +310,7 @@ impl IndexMerger {
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
) -> crate::Result<()> {
let fast_field_accessor = RemappedDocIdColumn::new(&self.readers, doc_id_mapping, field);
let fast_field_accessor = SortedDocIdColumn::new(&self.readers, doc_id_mapping, field);
fast_field_serializer.create_auto_detect_u64_fast_field(field, fast_field_accessor)?;
Ok(())
@@ -525,8 +404,8 @@ impl IndexMerger {
doc_id_reader_pair
.into_iter()
.kmerge_by(|a, b| {
let val1 = a.2.get_val(a.0);
let val2 = b.2.get_val(b.0);
let val1 = a.2.get_val(a.0 as u64);
let val2 = b.2.get_val(b.0 as u64);
if sort_by_field.order == Order::Asc {
val1 < val2
} else {
@@ -544,17 +423,33 @@ impl IndexMerger {
// Creating the index file to point into the data, generic over `BytesFastFieldReader` and
// `MultiValuedFastFieldReader`
//
fn write_1_n_fast_field_idx_generic(
fn write_1_n_fast_field_idx_generic<T: MultiValueLength>(
field: Field,
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
segment_and_ff_readers: &[(&SegmentReader, &MultiValueIndex)],
) -> crate::Result<()> {
let column =
RemappedDocIdMultiValueIndexColumn::new(segment_and_ff_readers, doc_id_mapping);
reader_and_field_accessors: &[(&SegmentReader, T)],
) -> crate::Result<Vec<u64>> {
// We can now create our `idx` serializer, and in a second pass,
// can effectively push the different indexes.
fast_field_serializer.create_auto_detect_u64_fast_field(field, column)?;
Ok(())
// copying into a temp vec is not ideal, but the fast field codec api requires random
// access, which is used in the estimation. It's possible to 1. calculate random
// access on the fly or 2. change the codec api to make random access optional, but
// they both have also major drawbacks.
let mut offsets = Vec::with_capacity(doc_id_mapping.len());
let mut offset = 0;
for old_doc_addr in doc_id_mapping.iter_old_doc_addrs() {
let reader = &reader_and_field_accessors[old_doc_addr.segment_ord as usize].1;
offsets.push(offset);
offset += reader.get_len(old_doc_addr.doc_id) as u64;
}
offsets.push(offset);
let fastfield_accessor = VecColumn::from(&offsets[..]);
fast_field_serializer.create_auto_detect_u64_fast_field(field, fastfield_accessor)?;
Ok(offsets)
}
/// Returns the fastfield index (index for the data, not the data).
fn write_multi_value_fast_field_idx(
@@ -562,8 +457,8 @@ impl IndexMerger {
field: Field,
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
) -> crate::Result<()> {
let segment_and_ff_readers = self
) -> crate::Result<Vec<u64>> {
let reader_ordinal_and_field_accessors = self
.readers
.iter()
.map(|reader| {
@@ -582,12 +477,7 @@ impl IndexMerger {
field,
fast_field_serializer,
doc_id_mapping,
&segment_and_ff_readers
.iter()
.map(|(segment_reader, u64s_reader)| {
(*segment_reader, u64s_reader.get_index_reader())
})
.collect::<Vec<_>>(),
&reader_ordinal_and_field_accessors,
)
}
@@ -636,12 +526,7 @@ impl IndexMerger {
}
let col = VecColumn::from(&vals[..]);
fast_field_serializer.create_auto_detect_u64_fast_field_with_idx_and_codecs(
field,
col,
1,
&get_fastfield_codecs_for_multivalue(),
)?;
fast_field_serializer.create_auto_detect_u64_fast_field_with_idx(field, col, 1)?;
}
Ok(())
}
@@ -676,21 +561,20 @@ impl IndexMerger {
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
) -> crate::Result<()> {
// Multifastfield consists of 2 fastfields.
// Multifastfield consists in 2 fastfields.
// The first serves as an index into the second one and is strictly increasing.
// The second contains the actual values.
// First we merge the idx fast field.
self.write_multi_value_fast_field_idx(field, fast_field_serializer, doc_id_mapping)?;
let offsets =
self.write_multi_value_fast_field_idx(field, fast_field_serializer, doc_id_mapping)?;
let fastfield_accessor =
RemappedDocIdMultiValueColumn::new(&self.readers, doc_id_mapping, field);
fast_field_serializer.create_auto_detect_u64_fast_field_with_idx_and_codecs(
SortedDocIdMultiValueColumn::new(&self.readers, doc_id_mapping, &offsets, field);
fast_field_serializer.create_auto_detect_u64_fast_field_with_idx(
field,
fastfield_accessor,
1,
&get_fastfield_codecs_for_multivalue(),
)?;
Ok(())
@@ -702,7 +586,7 @@ impl IndexMerger {
fast_field_serializer: &mut CompositeFastFieldSerializer,
doc_id_mapping: &SegmentDocIdMapping,
) -> crate::Result<()> {
let segment_and_ff_readers = self
let reader_and_field_accessors = self
.readers
.iter()
.map(|reader| {
@@ -713,22 +597,17 @@ impl IndexMerger {
(reader, bytes_reader)
})
.collect::<Vec<_>>();
Self::write_1_n_fast_field_idx_generic(
field,
fast_field_serializer,
doc_id_mapping,
&segment_and_ff_readers
.iter()
.map(|(segment_reader, u64s_reader)| {
(*segment_reader, u64s_reader.get_index_reader())
})
.collect::<Vec<_>>(),
&reader_and_field_accessors,
)?;
let mut serialize_vals = fast_field_serializer.new_bytes_fast_field(field);
for old_doc_addr in doc_id_mapping.iter_old_doc_addrs() {
let bytes_reader = &segment_and_ff_readers[old_doc_addr.segment_ord as usize].1;
let bytes_reader = &reader_and_field_accessors[old_doc_addr.segment_ord as usize].1;
let val = bytes_reader.get_bytes(old_doc_addr.doc_id);
serialize_vals.write_all(val)?;
}
@@ -829,7 +708,7 @@ impl IndexMerger {
// Let's compute the list of non-empty posting lists
for (segment_ord, term_info) in merged_terms.current_segment_ords_and_term_infos() {
let segment_reader = &self.readers[segment_ord];
let inverted_index: &InvertedIndexReader = &field_readers[segment_ord];
let inverted_index: &InvertedIndexReader = &*field_readers[segment_ord];
let segment_postings = inverted_index
.read_postings_from_terminfo(&term_info, segment_postings_option)?;
let alive_bitset_opt = segment_reader.alive_bitset();
@@ -1064,7 +943,7 @@ mod tests {
};
use crate::collector::{Count, FacetCollector};
use crate::core::Index;
use crate::query::{AllQuery, BooleanQuery, EnableScoring, Scorer, TermQuery};
use crate::query::{AllQuery, BooleanQuery, Scorer, TermQuery};
use crate::schema::{
Cardinality, Document, Facet, FacetOptions, IndexRecordOption, NumericOptions, Term,
TextFieldIndexing, INDEXED, TEXT,
@@ -1977,7 +1856,7 @@ mod tests {
let reader = index.reader()?;
let searcher = reader.searcher();
let mut term_scorer = term_query
.specialized_weight(EnableScoring::Enabled(&searcher))?
.specialized_weight(&searcher, true)?
.specialized_scorer(searcher.segment_reader(0u32), 1.0)?;
assert_eq!(term_scorer.doc(), 0);
assert_nearly_equals!(term_scorer.block_max_score(), 0.0079681855);
@@ -1992,7 +1871,7 @@ mod tests {
assert_eq!(searcher.segment_readers().len(), 2);
for segment_reader in searcher.segment_readers() {
let mut term_scorer = term_query
.specialized_weight(EnableScoring::Enabled(&searcher))?
.specialized_weight(&searcher, true)?
.specialized_scorer(segment_reader, 1.0)?;
// the difference compared to before is intrinsic to the bm25 formula. no worries
// there.
@@ -2017,7 +1896,7 @@ mod tests {
let segment_reader = searcher.segment_reader(0u32);
let mut term_scorer = term_query
.specialized_weight(EnableScoring::Enabled(&searcher))?
.specialized_weight(&searcher, true)?
.specialized_scorer(segment_reader, 1.0)?;
// the difference compared to before is intrinsic to the bm25 formula. no worries there.
for doc in segment_reader.doc_ids_alive() {

12
src/indexer/merger_sorted_index_test.rs
View File

@@ -190,13 +190,13 @@ mod tests {
assert_eq!(fast_field.get_val(4), 2u64);
assert_eq!(fast_field.get_val(3), 3u64);
if force_disjunct_segment_sort_values {
assert_eq!(fast_field.get_val(2), 20u64);
assert_eq!(fast_field.get_val(1), 100u64);
assert_eq!(fast_field.get_val(2u64), 20u64);
assert_eq!(fast_field.get_val(1u64), 100u64);
} else {
assert_eq!(fast_field.get_val(2), 10u64);
assert_eq!(fast_field.get_val(1), 20u64);
assert_eq!(fast_field.get_val(2u64), 10u64);
assert_eq!(fast_field.get_val(1u64), 20u64);
}
assert_eq!(fast_field.get_val(0), 1_000u64);
assert_eq!(fast_field.get_val(0u64), 1_000u64);
// test new field norm mapping
{
@@ -545,7 +545,7 @@ mod bench_sorted_index_merge {
// add values in order of the new doc_ids
let mut val = 0;
for (doc_id, _reader, field_reader) in sorted_doc_ids {
val = field_reader.get_val(doc_id);
val = field_reader.get_val(doc_id as u64);
}
val

50
src/indexer/mod.rs
View File

@@ -3,7 +3,6 @@ pub mod delete_queue;
pub mod demuxer;
pub mod doc_id_mapping;
mod doc_opstamp_mapping;
mod flat_map_with_buffer;
pub mod index_writer;
mod index_writer_status;
mod json_term_writer;
@@ -58,15 +57,13 @@ type AddBatchReceiver = channel::Receiver<AddBatch>;
#[cfg(feature = "mmap")]
#[cfg(test)]
mod tests_mmap {
use crate::collector::Count;
use crate::query::QueryParser;
use crate::schema::{JsonObjectOptions, Schema, TEXT};
use crate::schema::{self, Schema};
use crate::{Index, Term};
#[test]
fn test_advance_delete_bug() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let text_field = schema_builder.add_text_field("text", TEXT);
let text_field = schema_builder.add_text_field("text", schema::TEXT);
let index = Index::create_from_tempdir(schema_builder.build())?;
let mut index_writer = index.writer_for_tests()?;
// there must be one deleted document in the segment
@@ -77,48 +74,7 @@ mod tests_mmap {
index_writer.add_document(doc!(text_field=>"c"))?;
}
index_writer.commit()?;
index_writer.commit()?;
Ok(())
}
#[test]
fn test_json_field_expand_dots_disabled_dot_escaped_required() {
let mut schema_builder = Schema::builder();
let json_field = schema_builder.add_json_field("json", TEXT);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests().unwrap();
let json = serde_json::json!({"k8s.container.name": "prometheus", "val": "hello"});
index_writer.add_document(doc!(json_field=>json)).unwrap();
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 1);
let parse_query = QueryParser::for_index(&index, Vec::new());
let query = parse_query
.parse_query(r#"json.k8s\.container\.name:prometheus"#)
.unwrap();
let num_docs = searcher.search(&query, &Count).unwrap();
assert_eq!(num_docs, 1);
}
#[test]
fn test_json_field_expand_dots_enabled_dot_escape_not_required() {
let mut schema_builder = Schema::builder();
let json_options: JsonObjectOptions =
JsonObjectOptions::from(TEXT).set_expand_dots_enabled();
let json_field = schema_builder.add_json_field("json", json_options);
let index = Index::create_in_ram(schema_builder.build());
let mut index_writer = index.writer_for_tests().unwrap();
let json = serde_json::json!({"k8s.container.name": "prometheus", "val": "hello"});
index_writer.add_document(doc!(json_field=>json)).unwrap();
index_writer.commit().unwrap();
let reader = index.reader().unwrap();
let searcher = reader.searcher();
assert_eq!(searcher.num_docs(), 1);
let parse_query = QueryParser::for_index(&index, Vec::new());
let query = parse_query
.parse_query(r#"json.k8s.container.name:prometheus"#)
.unwrap();
let num_docs = searcher.search(&query, &Count).unwrap();
assert_eq!(num_docs, 1);
}
}

13
src/indexer/operation.rs
View File

@@ -1,11 +1,20 @@
use crate::query::Weight;
use crate::schema::{Document, Term};
use crate::Opstamp;
/// Timestamped Delete operation.
#[derive(Clone, Eq, PartialEq, Debug)]
pub struct DeleteOperation {
pub opstamp: Opstamp,
pub target: Box<dyn Weight>,
pub term: Term,
}
impl Default for DeleteOperation {
fn default() -> Self {
DeleteOperation {
opstamp: 0u64,
term: Term::new(),
}
}
}
/// Timestamped Add operation.

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