mirror of
https://github.com/meilisearch/meilisearch.git
synced 2024-11-23 10:37:41 +08:00
Merge #2636
2636: Upgrade milli to v0.33.0 r=Kerollmops a=ManyTheFish # Summary - Update milli to v0.33.0 - Classify the new InvalidLmdbOpenOptions error as an Internal error - Update filter error check in tests - Introduce Terms Matching Policies fixes #2479 fixes #2484 fixes #2486 fixes #2516 fixes #2578 fixes #2580 fixes #2583 fixes #2600 fixes #2640 fixes #2672 fixes #2679 fixes #2686 # Terms Matching Policies This PR allows end users to customize matching term policies ## Todo - [x] Update the API to return the number of pages and allow users to directly choose a page instead of computing an offset - [x] Change generation of the query tree depending on the chosen settings https://github.com/meilisearch/milli/pull/598 ## Small Documentation ### Default search query **request**: ```sh curl \ -X POST 'http://localhost:7700/indexes/movies/search' \ -H 'Content-Type: application/json' \ --data-binary '{ "q": "doctor of tokio" }' ``` **result**: ```json { "hits":[...], "estimatedTotalHits":32, "query":"doctor of tokio", "limit":20, "offset":0, "processingTimeMs":7 } ``` The default behavior doesn't change with the current Meilisearch behavior: If we don't have enough documents to fit the requested limit, we remove the query words from the last to the first typed word. ## Search query with `optionalWords` parameter **request**: ```sh curl \ -X POST 'http://localhost:7700/indexes/movies/search' \ -H 'Content-Type: application/json' \ --data-binary '{ "q": "doctor of tokio", "matchingStrategy": "all"}' ``` **result**: ```json { "hits":[...], "estimatedTotalHits":1, "query":"doctor of tokio", "limit":20, "offset":0, "processingTimeMs":7 } ``` ### allowed `matchingStrategy` values #### `last` The default behavior, If we don't have enough documents to fit the requested limit, we remove the query words from the last to the first typed word. #### `all` No word will be removed, If we don't have enough documents to fit the requested limit, we return the number of documents we found. ### In charge of the feature Core: `@ManyTheFish` & `@curquiza` Docs: TBD Integration: `@bidoubiwa` Co-authored-by: ManyTheFish <many@meilisearch.com> Co-authored-by: Many the fish <many@meilisearch.com>
This commit is contained in:
commit
c445334070
118
Cargo.lock
generated
118
Cargo.lock
generated
@ -285,9 +285,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "anyhow"
|
name = "anyhow"
|
||||||
version = "1.0.57"
|
version = "1.0.62"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "08f9b8508dccb7687a1d6c4ce66b2b0ecef467c94667de27d8d7fe1f8d2a9cdc"
|
checksum = "1485d4d2cc45e7b201ee3767015c96faa5904387c9d87c6efdd0fb511f12d305"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"backtrace",
|
"backtrace",
|
||||||
]
|
]
|
||||||
@ -644,9 +644,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "charabia"
|
name = "charabia"
|
||||||
version = "0.5.1"
|
version = "0.6.0"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "2ed19edcd98f5bf6572f48d6f5982d595cb8718e47c6f0066d942b280575ff02"
|
checksum = "d1234c5cd955fb67f2b111b43855a0eabdedc35d9fb4e6a9d24030050e89b779"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"character_converter",
|
"character_converter",
|
||||||
"cow-utils",
|
"cow-utils",
|
||||||
@ -654,7 +654,6 @@ dependencies = [
|
|||||||
"fst",
|
"fst",
|
||||||
"jieba-rs",
|
"jieba-rs",
|
||||||
"lindera",
|
"lindera",
|
||||||
"lindera-core",
|
|
||||||
"once_cell",
|
"once_cell",
|
||||||
"slice-group-by",
|
"slice-group-by",
|
||||||
"unicode-segmentation",
|
"unicode-segmentation",
|
||||||
@ -672,24 +671,18 @@ dependencies = [
|
|||||||
"once_cell",
|
"once_cell",
|
||||||
]
|
]
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "chunked_transfer"
|
|
||||||
version = "1.4.0"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "fff857943da45f546682664a79488be82e69e43c1a7a2307679ab9afb3a66d2e"
|
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "clap"
|
name = "clap"
|
||||||
version = "3.1.18"
|
version = "3.2.17"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "d2dbdf4bdacb33466e854ce889eee8dfd5729abf7ccd7664d0a2d60cd384440b"
|
checksum = "29e724a68d9319343bb3328c9cc2dfde263f4b3142ee1059a9980580171c954b"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"atty",
|
"atty",
|
||||||
"bitflags",
|
"bitflags",
|
||||||
"clap_derive",
|
"clap_derive",
|
||||||
"clap_lex",
|
"clap_lex",
|
||||||
"indexmap",
|
"indexmap",
|
||||||
"lazy_static",
|
"once_cell",
|
||||||
"strsim",
|
"strsim",
|
||||||
"termcolor",
|
"termcolor",
|
||||||
"textwrap",
|
"textwrap",
|
||||||
@ -697,9 +690,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "clap_derive"
|
name = "clap_derive"
|
||||||
version = "3.1.18"
|
version = "3.2.17"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "25320346e922cffe59c0bbc5410c8d8784509efb321488971081313cb1e1a33c"
|
checksum = "13547f7012c01ab4a0e8f8967730ada8f9fdf419e8b6c792788f39cf4e46eefa"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"heck",
|
"heck",
|
||||||
"proc-macro-error",
|
"proc-macro-error",
|
||||||
@ -710,9 +703,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "clap_lex"
|
name = "clap_lex"
|
||||||
version = "0.2.0"
|
version = "0.2.4"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "a37c35f1112dad5e6e0b1adaff798507497a18fceeb30cceb3bae7d1427b9213"
|
checksum = "2850f2f5a82cbf437dd5af4d49848fbdfc27c157c3d010345776f952765261c5"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"os_str_bytes",
|
"os_str_bytes",
|
||||||
]
|
]
|
||||||
@ -1126,8 +1119,8 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "filter-parser"
|
name = "filter-parser"
|
||||||
version = "0.32.0"
|
version = "0.33.0"
|
||||||
source = "git+https://github.com/meilisearch/milli.git?tag=v0.32.0#e1bc610d2722a8010216c45d5a32cbe3db18468e"
|
source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"nom",
|
"nom",
|
||||||
"nom_locate",
|
"nom_locate",
|
||||||
@ -1151,8 +1144,8 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "flatten-serde-json"
|
name = "flatten-serde-json"
|
||||||
version = "0.32.0"
|
version = "0.33.0"
|
||||||
source = "git+https://github.com/meilisearch/milli.git?tag=v0.32.0#e1bc610d2722a8010216c45d5a32cbe3db18468e"
|
source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"serde_json",
|
"serde_json",
|
||||||
]
|
]
|
||||||
@ -1438,8 +1431,8 @@ checksum = "2540771e65fc8cb83cd6e8a237f70c319bd5c29f78ed1084ba5d50eeac86f7f9"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "heed"
|
name = "heed"
|
||||||
version = "0.12.1"
|
version = "0.12.2"
|
||||||
source = "git+https://github.com/meilisearch/heed?tag=v0.12.1#fc017cf3394af737f92fd71e16f0499a78b79d65"
|
source = "git+https://github.com/meilisearch/heed?tag=v0.12.3#076971765f4ce09591ed7e19e45ea817580a53e3"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"byteorder",
|
"byteorder",
|
||||||
"heed-traits",
|
"heed-traits",
|
||||||
@ -1456,12 +1449,12 @@ dependencies = [
|
|||||||
[[package]]
|
[[package]]
|
||||||
name = "heed-traits"
|
name = "heed-traits"
|
||||||
version = "0.7.0"
|
version = "0.7.0"
|
||||||
source = "git+https://github.com/meilisearch/heed?tag=v0.12.1#fc017cf3394af737f92fd71e16f0499a78b79d65"
|
source = "git+https://github.com/meilisearch/heed?tag=v0.12.3#076971765f4ce09591ed7e19e45ea817580a53e3"
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "heed-types"
|
name = "heed-types"
|
||||||
version = "0.7.2"
|
version = "0.7.2"
|
||||||
source = "git+https://github.com/meilisearch/heed?tag=v0.12.1#fc017cf3394af737f92fd71e16f0499a78b79d65"
|
source = "git+https://github.com/meilisearch/heed?tag=v0.12.3#076971765f4ce09591ed7e19e45ea817580a53e3"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"bincode",
|
"bincode",
|
||||||
"heed-traits",
|
"heed-traits",
|
||||||
@ -1664,8 +1657,8 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "json-depth-checker"
|
name = "json-depth-checker"
|
||||||
version = "0.32.0"
|
version = "0.33.0"
|
||||||
source = "git+https://github.com/meilisearch/milli.git?tag=v0.32.0#e1bc610d2722a8010216c45d5a32cbe3db18468e"
|
source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"serde_json",
|
"serde_json",
|
||||||
]
|
]
|
||||||
@ -1752,9 +1745,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera"
|
name = "lindera"
|
||||||
version = "0.13.5"
|
version = "0.14.0"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "7d1c5db4b1d12637aa316dc1adb215f78fe79025080af750942516c5ff17d1a0"
|
checksum = "4dddd011921cac0ec59025a6b6e26c2cd9af3adce384b56c753c31df71a07965"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -1774,9 +1767,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-cc-cedict-builder"
|
name = "lindera-cc-cedict-builder"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "73a3509fb497340571d49feddb57e1db2ce5248c4d449f2548d0ee8cb745eb1e"
|
checksum = "584491a91b758f92ef3202aaf969d837522f2c11390c4de0049a356d63bc0b0f"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -1794,9 +1787,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-core"
|
name = "lindera-core"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "5d20d1b2c085393aed58625d741beca69410e1143fc35bc67ebc35c9885f9f74"
|
checksum = "c726ee1bf3282621a802d50f5e03d3f88aae41456815e1d0cb2271a538ff83ec"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -1810,9 +1803,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-decompress"
|
name = "lindera-decompress"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "b96b8050cded13927a99bcb8cbb0987f89fc8f35429fc153b4bc05ddc7a53a44"
|
checksum = "6f9df38ea9310a1256cdee64ff0ebe3f17c49314e3176e53d2213371729d6744"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"lzma-rs",
|
"lzma-rs",
|
||||||
@ -1821,9 +1814,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-dictionary"
|
name = "lindera-dictionary"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "5abe3dddc22303402957edb4472ab0c996e0d93b3b00643de3bee8b28c2f9297"
|
checksum = "0a525b654642ff9f27927c5abba33f4c651e984b54a65e4f787c0b8c8e22e4a6"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -1833,9 +1826,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-ipadic"
|
name = "lindera-ipadic"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "b8f4c111f6ad9eb9e015d02061af2ed36fc0255f29359294415c7c2f1ea5b5b6"
|
checksum = "4797e016fc7dc0709ddb8c31da3b9e923e33e14043a4ff58431dd9c447ffacd2"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"bincode",
|
"bincode",
|
||||||
"byteorder",
|
"byteorder",
|
||||||
@ -1845,14 +1838,13 @@ dependencies = [
|
|||||||
"lindera-ipadic-builder",
|
"lindera-ipadic-builder",
|
||||||
"once_cell",
|
"once_cell",
|
||||||
"tar",
|
"tar",
|
||||||
"ureq",
|
|
||||||
]
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-ipadic-builder"
|
name = "lindera-ipadic-builder"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "a2b9893f22a4a7511ac70ff7d96cda9b8d7259b7d7121784183c73bc593ce6e7"
|
checksum = "9bd3ecfb07e8810f5ba313fa836804b66120f0ea76c2d93948c2ddcf4f81fd90"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -1870,9 +1862,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-ko-dic-builder"
|
name = "lindera-ko-dic-builder"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "14282600ebfe7ab6fd4f3042143024ff9d74c09d58fd983d0c587839cf940d4a"
|
checksum = "fc86f26560ea69e91413eecc078d8e13f39b3c1fdc5a242d79d7622f6fab3a83"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -1890,9 +1882,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "lindera-unidic-builder"
|
name = "lindera-unidic-builder"
|
||||||
version = "0.13.4"
|
version = "0.13.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "b20825d46c95854e47c532c3e548dfec07c8f187c1ed89383cb6c35790338088"
|
checksum = "05c1bb8b7d38ffec7d949ee2c603b6ef96dfa7cf4937e91bad295a2d2b267b82"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"anyhow",
|
"anyhow",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -2203,8 +2195,8 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "milli"
|
name = "milli"
|
||||||
version = "0.32.0"
|
version = "0.33.0"
|
||||||
source = "git+https://github.com/meilisearch/milli.git?tag=v0.32.0#e1bc610d2722a8010216c45d5a32cbe3db18468e"
|
source = "git+https://github.com/meilisearch/milli.git?tag=v0.33.0#a79ff8a1a98a807f40f970131c8de2ab11560de5"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"bimap",
|
"bimap",
|
||||||
"bincode",
|
"bincode",
|
||||||
@ -3133,9 +3125,9 @@ checksum = "388a1df253eca08550bef6c72392cfe7c30914bf41df5269b68cbd6ff8f570a3"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "serde"
|
name = "serde"
|
||||||
version = "1.0.137"
|
version = "1.0.144"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "61ea8d54c77f8315140a05f4c7237403bf38b72704d031543aa1d16abbf517d1"
|
checksum = "0f747710de3dcd43b88c9168773254e809d8ddbdf9653b84e2554ab219f17860"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"serde_derive",
|
"serde_derive",
|
||||||
]
|
]
|
||||||
@ -3151,9 +3143,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "serde_derive"
|
name = "serde_derive"
|
||||||
version = "1.0.137"
|
version = "1.0.144"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "1f26faba0c3959972377d3b2d306ee9f71faee9714294e41bb777f83f88578be"
|
checksum = "94ed3a816fb1d101812f83e789f888322c34e291f894f19590dc310963e87a00"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"proc-macro2 1.0.39",
|
"proc-macro2 1.0.39",
|
||||||
"quote 1.0.18",
|
"quote 1.0.18",
|
||||||
@ -3162,9 +3154,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "serde_json"
|
name = "serde_json"
|
||||||
version = "1.0.81"
|
version = "1.0.85"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "9b7ce2b32a1aed03c558dc61a5cd328f15aff2dbc17daad8fb8af04d2100e15c"
|
checksum = "e55a28e3aaef9d5ce0506d0a14dbba8054ddc7e499ef522dd8b26859ec9d4a44"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"indexmap",
|
"indexmap",
|
||||||
"itoa 1.0.2",
|
"itoa 1.0.2",
|
||||||
@ -3669,22 +3661,6 @@ version = "0.7.1"
|
|||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "a156c684c91ea7d62626509bce3cb4e1d9ed5c4d978f7b4352658f96a4c26b4a"
|
checksum = "a156c684c91ea7d62626509bce3cb4e1d9ed5c4d978f7b4352658f96a4c26b4a"
|
||||||
|
|
||||||
[[package]]
|
|
||||||
name = "ureq"
|
|
||||||
version = "2.4.0"
|
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
||||||
checksum = "9399fa2f927a3d327187cbd201480cee55bee6ac5d3c77dd27f0c6814cff16d5"
|
|
||||||
dependencies = [
|
|
||||||
"base64",
|
|
||||||
"chunked_transfer",
|
|
||||||
"log",
|
|
||||||
"once_cell",
|
|
||||||
"rustls",
|
|
||||||
"url",
|
|
||||||
"webpki",
|
|
||||||
"webpki-roots",
|
|
||||||
]
|
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "url"
|
name = "url"
|
||||||
version = "2.2.2"
|
version = "2.2.2"
|
||||||
|
@ -7,10 +7,10 @@ edition = "2021"
|
|||||||
enum-iterator = "0.7.0"
|
enum-iterator = "0.7.0"
|
||||||
hmac = "0.12.1"
|
hmac = "0.12.1"
|
||||||
meilisearch-types = { path = "../meilisearch-types" }
|
meilisearch-types = { path = "../meilisearch-types" }
|
||||||
milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.32.0" }
|
milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.33.0" }
|
||||||
rand = "0.8.4"
|
rand = "0.8.4"
|
||||||
serde = { version = "1.0.136", features = ["derive"] }
|
serde = { version = "1.0.136", features = ["derive"] }
|
||||||
serde_json = { version = "1.0.79", features = ["preserve_order"] }
|
serde_json = { version = "1.0.85", features = ["preserve_order"] }
|
||||||
sha2 = "0.10.2"
|
sha2 = "0.10.2"
|
||||||
thiserror = "1.0.30"
|
thiserror = "1.0.30"
|
||||||
time = { version = "0.3.7", features = ["serde-well-known", "formatting", "parsing", "macros"] }
|
time = { version = "0.3.7", features = ["serde-well-known", "formatting", "parsing", "macros"] }
|
||||||
|
@ -11,7 +11,7 @@ name = "meilisearch"
|
|||||||
path = "src/main.rs"
|
path = "src/main.rs"
|
||||||
|
|
||||||
[build-dependencies]
|
[build-dependencies]
|
||||||
anyhow = { version = "1.0.56", optional = true }
|
anyhow = { version = "1.0.62", optional = true }
|
||||||
cargo_toml = { version = "0.11.4", optional = true }
|
cargo_toml = { version = "0.11.4", optional = true }
|
||||||
hex = { version = "0.4.3", optional = true }
|
hex = { version = "0.4.3", optional = true }
|
||||||
reqwest = { version = "0.11.9", features = ["blocking", "rustls-tls"], default-features = false, optional = true }
|
reqwest = { version = "0.11.9", features = ["blocking", "rustls-tls"], default-features = false, optional = true }
|
||||||
@ -25,7 +25,7 @@ zip = { version = "0.5.13", optional = true }
|
|||||||
actix-cors = "0.6.1"
|
actix-cors = "0.6.1"
|
||||||
actix-web = { version = "4.0.1", default-features = false, features = ["macros", "compress-brotli", "compress-gzip", "cookies", "rustls"] }
|
actix-web = { version = "4.0.1", default-features = false, features = ["macros", "compress-brotli", "compress-gzip", "cookies", "rustls"] }
|
||||||
actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
|
actix-web-static-files = { git = "https://github.com/kilork/actix-web-static-files.git", rev = "2d3b6160", optional = true }
|
||||||
anyhow = { version = "1.0.56", features = ["backtrace"] }
|
anyhow = { version = "1.0.62", features = ["backtrace"] }
|
||||||
async-stream = "0.3.3"
|
async-stream = "0.3.3"
|
||||||
async-trait = "0.1.52"
|
async-trait = "0.1.52"
|
||||||
bstr = "0.2.17"
|
bstr = "0.2.17"
|
||||||
@ -64,7 +64,7 @@ rustls-pemfile = "0.3.0"
|
|||||||
segment = { version = "0.2.0", optional = true }
|
segment = { version = "0.2.0", optional = true }
|
||||||
serde = { version = "1.0.136", features = ["derive"] }
|
serde = { version = "1.0.136", features = ["derive"] }
|
||||||
serde-cs = "0.2.3"
|
serde-cs = "0.2.3"
|
||||||
serde_json = { version = "1.0.79", features = ["preserve_order"] }
|
serde_json = { version = "1.0.85", features = ["preserve_order"] }
|
||||||
sha2 = "0.10.2"
|
sha2 = "0.10.2"
|
||||||
siphasher = "0.3.10"
|
siphasher = "0.3.10"
|
||||||
slice-group-by = "0.3.0"
|
slice-group-by = "0.3.0"
|
||||||
|
@ -366,6 +366,9 @@ pub struct SearchAggregator {
|
|||||||
// The maximum number of terms in a q request
|
// The maximum number of terms in a q request
|
||||||
max_terms_number: usize,
|
max_terms_number: usize,
|
||||||
|
|
||||||
|
// everytime a search is done, we increment the counter linked to the used settings
|
||||||
|
matching_strategy: HashMap<String, usize>,
|
||||||
|
|
||||||
// pagination
|
// pagination
|
||||||
max_limit: usize,
|
max_limit: usize,
|
||||||
max_offset: usize,
|
max_offset: usize,
|
||||||
@ -423,6 +426,9 @@ impl SearchAggregator {
|
|||||||
ret.max_terms_number = q.split_whitespace().count();
|
ret.max_terms_number = q.split_whitespace().count();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
ret.matching_strategy
|
||||||
|
.insert(format!("{:?}", query.matching_strategy), 1);
|
||||||
|
|
||||||
ret.max_limit = query.limit;
|
ret.max_limit = query.limit;
|
||||||
ret.max_offset = query.offset.unwrap_or_default();
|
ret.max_offset = query.offset.unwrap_or_default();
|
||||||
|
|
||||||
@ -476,6 +482,11 @@ impl SearchAggregator {
|
|||||||
}
|
}
|
||||||
// q
|
// q
|
||||||
self.max_terms_number = self.max_terms_number.max(other.max_terms_number);
|
self.max_terms_number = self.max_terms_number.max(other.max_terms_number);
|
||||||
|
|
||||||
|
for (key, value) in other.matching_strategy.into_iter() {
|
||||||
|
let matching_strategy = self.matching_strategy.entry(key).or_insert(0);
|
||||||
|
*matching_strategy = matching_strategy.saturating_add(value);
|
||||||
|
}
|
||||||
// pagination
|
// pagination
|
||||||
self.max_limit = self.max_limit.max(other.max_limit);
|
self.max_limit = self.max_limit.max(other.max_limit);
|
||||||
self.max_offset = self.max_offset.max(other.max_offset);
|
self.max_offset = self.max_offset.max(other.max_offset);
|
||||||
@ -517,6 +528,7 @@ impl SearchAggregator {
|
|||||||
},
|
},
|
||||||
"q": {
|
"q": {
|
||||||
"max_terms_number": self.max_terms_number,
|
"max_terms_number": self.max_terms_number,
|
||||||
|
"most_used_matching_strategy": self.matching_strategy.iter().max_by_key(|(_, v)| *v).map(|(k, _)| json!(k)).unwrap_or_else(|| json!(null)),
|
||||||
},
|
},
|
||||||
"pagination": {
|
"pagination": {
|
||||||
"max_limit": self.max_limit,
|
"max_limit": self.max_limit,
|
||||||
|
@ -2,8 +2,8 @@ use actix_web::{web, HttpRequest, HttpResponse};
|
|||||||
use log::debug;
|
use log::debug;
|
||||||
use meilisearch_auth::IndexSearchRules;
|
use meilisearch_auth::IndexSearchRules;
|
||||||
use meilisearch_lib::index::{
|
use meilisearch_lib::index::{
|
||||||
SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER, DEFAULT_HIGHLIGHT_POST_TAG,
|
MatchingStrategy, SearchQuery, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
|
||||||
DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
|
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
|
||||||
};
|
};
|
||||||
use meilisearch_lib::MeiliSearch;
|
use meilisearch_lib::MeiliSearch;
|
||||||
use meilisearch_types::error::ResponseError;
|
use meilisearch_types::error::ResponseError;
|
||||||
@ -45,6 +45,8 @@ pub struct SearchQueryGet {
|
|||||||
highlight_post_tag: String,
|
highlight_post_tag: String,
|
||||||
#[serde(default = "DEFAULT_CROP_MARKER")]
|
#[serde(default = "DEFAULT_CROP_MARKER")]
|
||||||
crop_marker: String,
|
crop_marker: String,
|
||||||
|
#[serde(default)]
|
||||||
|
matching_strategy: MatchingStrategy,
|
||||||
}
|
}
|
||||||
|
|
||||||
impl From<SearchQueryGet> for SearchQuery {
|
impl From<SearchQueryGet> for SearchQuery {
|
||||||
@ -76,6 +78,7 @@ impl From<SearchQueryGet> for SearchQuery {
|
|||||||
highlight_pre_tag: other.highlight_pre_tag,
|
highlight_pre_tag: other.highlight_pre_tag,
|
||||||
highlight_post_tag: other.highlight_post_tag,
|
highlight_post_tag: other.highlight_post_tag,
|
||||||
crop_marker: other.crop_marker,
|
crop_marker: other.crop_marker,
|
||||||
|
matching_strategy: other.matching_strategy,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -74,7 +74,7 @@ async fn filter_invalid_syntax_object() {
|
|||||||
index.wait_task(1).await;
|
index.wait_task(1).await;
|
||||||
|
|
||||||
let expected_response = json!({
|
let expected_response = json!({
|
||||||
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` at `title & Glass`.\n1:14 title & Glass",
|
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXISTS`, `NOT EXISTS`, or `_geoRadius` at `title & Glass`.\n1:14 title & Glass",
|
||||||
"code": "invalid_filter",
|
"code": "invalid_filter",
|
||||||
"type": "invalid_request",
|
"type": "invalid_request",
|
||||||
"link": "https://docs.meilisearch.com/errors#invalid_filter"
|
"link": "https://docs.meilisearch.com/errors#invalid_filter"
|
||||||
@ -101,7 +101,7 @@ async fn filter_invalid_syntax_array() {
|
|||||||
index.wait_task(1).await;
|
index.wait_task(1).await;
|
||||||
|
|
||||||
let expected_response = json!({
|
let expected_response = json!({
|
||||||
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` at `title & Glass`.\n1:14 title & Glass",
|
"message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXISTS`, `NOT EXISTS`, or `_geoRadius` at `title & Glass`.\n1:14 title & Glass",
|
||||||
"code": "invalid_filter",
|
"code": "invalid_filter",
|
||||||
"type": "invalid_request",
|
"type": "invalid_request",
|
||||||
"link": "https://docs.meilisearch.com/errors#invalid_filter"
|
"link": "https://docs.meilisearch.com/errors#invalid_filter"
|
||||||
|
@ -5,7 +5,7 @@ edition = "2021"
|
|||||||
|
|
||||||
[dependencies]
|
[dependencies]
|
||||||
actix-web = { version = "4.0.1", default-features = false }
|
actix-web = { version = "4.0.1", default-features = false }
|
||||||
anyhow = { version = "1.0.56", features = ["backtrace"] }
|
anyhow = { version = "1.0.62", features = ["backtrace"] }
|
||||||
async-stream = "0.3.3"
|
async-stream = "0.3.3"
|
||||||
async-trait = "0.1.52"
|
async-trait = "0.1.52"
|
||||||
atomic_refcell = "0.1.8"
|
atomic_refcell = "0.1.8"
|
||||||
@ -28,7 +28,7 @@ lazy_static = "1.4.0"
|
|||||||
log = "0.4.14"
|
log = "0.4.14"
|
||||||
meilisearch-auth = { path = "../meilisearch-auth" }
|
meilisearch-auth = { path = "../meilisearch-auth" }
|
||||||
meilisearch-types = { path = "../meilisearch-types" }
|
meilisearch-types = { path = "../meilisearch-types" }
|
||||||
milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.32.0" }
|
milli = { git = "https://github.com/meilisearch/milli.git", tag = "v0.33.0" }
|
||||||
mime = "0.3.16"
|
mime = "0.3.16"
|
||||||
num_cpus = "1.13.1"
|
num_cpus = "1.13.1"
|
||||||
obkv = "0.2.0"
|
obkv = "0.2.0"
|
||||||
@ -43,7 +43,7 @@ reqwest = { version = "0.11.9", features = ["json", "rustls-tls"], default-featu
|
|||||||
roaring = "0.9.0"
|
roaring = "0.9.0"
|
||||||
rustls = "0.20.4"
|
rustls = "0.20.4"
|
||||||
serde = { version = "1.0.136", features = ["derive"] }
|
serde = { version = "1.0.136", features = ["derive"] }
|
||||||
serde_json = { version = "1.0.79", features = ["preserve_order"] }
|
serde_json = { version = "1.0.85", features = ["preserve_order"] }
|
||||||
siphasher = "0.3.10"
|
siphasher = "0.3.10"
|
||||||
slice-group-by = "0.3.0"
|
slice-group-by = "0.3.0"
|
||||||
sysinfo = "0.23.5"
|
sysinfo = "0.23.5"
|
||||||
|
@ -24,6 +24,7 @@ impl ErrorCode for MilliError<'_> {
|
|||||||
match error {
|
match error {
|
||||||
// TODO: wait for spec for new error codes.
|
// TODO: wait for spec for new error codes.
|
||||||
UserError::SerdeJson(_)
|
UserError::SerdeJson(_)
|
||||||
|
| UserError::InvalidLmdbOpenOptions
|
||||||
| UserError::DocumentLimitReached
|
| UserError::DocumentLimitReached
|
||||||
| UserError::AccessingSoftDeletedDocument { .. }
|
| UserError::AccessingSoftDeletedDocument { .. }
|
||||||
| UserError::UnknownInternalDocumentId { .. } => Code::Internal,
|
| UserError::UnknownInternalDocumentId { .. } => Code::Internal,
|
||||||
|
@ -1,5 +1,5 @@
|
|||||||
pub use search::{
|
pub use search::{
|
||||||
SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
|
MatchingStrategy, SearchQuery, SearchResult, DEFAULT_CROP_LENGTH, DEFAULT_CROP_MARKER,
|
||||||
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
|
DEFAULT_HIGHLIGHT_POST_TAG, DEFAULT_HIGHLIGHT_PRE_TAG, DEFAULT_SEARCH_LIMIT,
|
||||||
};
|
};
|
||||||
pub use updates::{apply_settings_to_builder, Checked, Facets, Settings, Unchecked};
|
pub use updates::{apply_settings_to_builder, Checked, Facets, Settings, Unchecked};
|
||||||
|
@ -7,7 +7,7 @@ use either::Either;
|
|||||||
use milli::tokenizer::TokenizerBuilder;
|
use milli::tokenizer::TokenizerBuilder;
|
||||||
use milli::{
|
use milli::{
|
||||||
AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, MatchBounds, MatcherBuilder, SortError,
|
AscDesc, FieldId, FieldsIdsMap, Filter, FormatOptions, MatchBounds, MatcherBuilder, SortError,
|
||||||
DEFAULT_VALUES_PER_FACET,
|
TermsMatchingStrategy, DEFAULT_VALUES_PER_FACET,
|
||||||
};
|
};
|
||||||
use regex::Regex;
|
use regex::Regex;
|
||||||
use serde::{Deserialize, Serialize};
|
use serde::{Deserialize, Serialize};
|
||||||
@ -55,6 +55,32 @@ pub struct SearchQuery {
|
|||||||
pub highlight_post_tag: String,
|
pub highlight_post_tag: String,
|
||||||
#[serde(default = "DEFAULT_CROP_MARKER")]
|
#[serde(default = "DEFAULT_CROP_MARKER")]
|
||||||
pub crop_marker: String,
|
pub crop_marker: String,
|
||||||
|
#[serde(default)]
|
||||||
|
pub matching_strategy: MatchingStrategy,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Deserialize, Debug, Clone, PartialEq, Eq)]
|
||||||
|
#[serde(rename_all = "camelCase")]
|
||||||
|
pub enum MatchingStrategy {
|
||||||
|
/// Remove query words from last to first
|
||||||
|
Last,
|
||||||
|
/// All query words are mandatory
|
||||||
|
All,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Default for MatchingStrategy {
|
||||||
|
fn default() -> Self {
|
||||||
|
Self::Last
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl From<MatchingStrategy> for TermsMatchingStrategy {
|
||||||
|
fn from(other: MatchingStrategy) -> Self {
|
||||||
|
match other {
|
||||||
|
MatchingStrategy::Last => Self::Last,
|
||||||
|
MatchingStrategy::All => Self::All,
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
#[derive(Debug, Clone, Serialize, PartialEq)]
|
#[derive(Debug, Clone, Serialize, PartialEq)]
|
||||||
@ -91,6 +117,8 @@ impl Index {
|
|||||||
search.query(query);
|
search.query(query);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
search.terms_matching_strategy(query.matching_strategy.into());
|
||||||
|
|
||||||
let max_total_hits = self
|
let max_total_hits = self
|
||||||
.pagination_max_total_hits(&rtxn)?
|
.pagination_max_total_hits(&rtxn)?
|
||||||
.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
|
.unwrap_or(DEFAULT_PAGINATION_MAX_TOTAL_HITS);
|
||||||
|
@ -704,6 +704,7 @@ mod test {
|
|||||||
highlight_pre_tag: DEFAULT_HIGHLIGHT_PRE_TAG(),
|
highlight_pre_tag: DEFAULT_HIGHLIGHT_PRE_TAG(),
|
||||||
highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
|
highlight_post_tag: DEFAULT_HIGHLIGHT_POST_TAG(),
|
||||||
crop_marker: DEFAULT_CROP_MARKER(),
|
crop_marker: DEFAULT_CROP_MARKER(),
|
||||||
|
matching_strategy: Default::default(),
|
||||||
};
|
};
|
||||||
|
|
||||||
let result = SearchResult {
|
let result = SearchResult {
|
||||||
|
Loading…
Reference in New Issue
Block a user