mirror of
https://github.com/meilisearch/meilisearch.git
synced 2024-11-23 10:37:41 +08:00
add sort result struct
This commit is contained in:
parent
a88f6c3241
commit
effbb7f7f1
92
Cargo.lock
generated
92
Cargo.lock
generated
@ -522,9 +522,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "bstr"
|
name = "bstr"
|
||||||
version = "0.2.12"
|
version = "0.2.13"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "2889e6d50f394968c8bf4240dc3f2a7eb4680844d27308f798229ac9d4725f41"
|
checksum = "31accafdb70df7871592c058eca3985b71104e15ac32f64706022c58867da931"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"lazy_static",
|
"lazy_static",
|
||||||
"memchr",
|
"memchr",
|
||||||
@ -616,9 +616,9 @@ checksum = "5b89647f09b9f4c838cb622799b2843e4e13bff64661dab9a0362bb92985addd"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "clap"
|
name = "clap"
|
||||||
version = "2.33.0"
|
version = "2.33.1"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "5067f5bb2d80ef5d68b4c87db81601f0b75bca627bc2ef76b141d7b846a3c6d9"
|
checksum = "bdfa80d47f954d53a35a64987ca1422f495b8d6483c0fe9f7117b36c2a792129"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"ansi_term",
|
"ansi_term",
|
||||||
"atty",
|
"atty",
|
||||||
@ -1008,9 +1008,9 @@ checksum = "3dcaa9ae7725d12cdb85b3ad99a434db70b468c09ded17e012d86b5c1010f7a7"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures"
|
name = "futures"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "5c329ae8753502fb44ae4fc2b622fa2a94652c41e795143765ba0927f92ab780"
|
checksum = "1e05b85ec287aac0dc34db7d4a569323df697f9c55b99b15d6b4ef8cde49f613"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"futures-channel",
|
"futures-channel",
|
||||||
"futures-core",
|
"futures-core",
|
||||||
@ -1023,9 +1023,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-channel"
|
name = "futures-channel"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "f0c77d04ce8edd9cb903932b608268b3fffec4163dc053b3b402bf47eac1f1a8"
|
checksum = "f366ad74c28cca6ba456d95e6422883cfb4b252a83bed929c83abfdbbf2967d5"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"futures-core",
|
"futures-core",
|
||||||
"futures-sink",
|
"futures-sink",
|
||||||
@ -1033,15 +1033,15 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-core"
|
name = "futures-core"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "f25592f769825e89b92358db00d26f965761e094951ac44d3663ef25b7ac464a"
|
checksum = "59f5fff90fd5d971f936ad674802482ba441b6f09ba5e15fd8b39145582ca399"
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-executor"
|
name = "futures-executor"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "f674f3e1bcb15b37284a90cedf55afdba482ab061c407a9c0ebbd0f3109741ba"
|
checksum = "10d6bb888be1153d3abeb9006b11b02cf5e9b209fda28693c31ae1e4e012e314"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"futures-core",
|
"futures-core",
|
||||||
"futures-task",
|
"futures-task",
|
||||||
@ -1050,15 +1050,15 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-io"
|
name = "futures-io"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "a638959aa96152c7a4cddf50fcb1e3fede0583b27157c26e67d6f99904090dc6"
|
checksum = "de27142b013a8e869c14957e6d2edeef89e97c289e69d042ee3a49acd8b51789"
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-macro"
|
name = "futures-macro"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "9a5081aa3de1f7542a794a397cde100ed903b0630152d0973479018fd85423a7"
|
checksum = "d0b5a30a4328ab5473878237c447333c093297bded83a4983d10f4deea240d39"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"proc-macro-hack",
|
"proc-macro-hack",
|
||||||
"proc-macro2",
|
"proc-macro2",
|
||||||
@ -1068,21 +1068,24 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-sink"
|
name = "futures-sink"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "3466821b4bc114d95b087b850a724c6f83115e929bc88f1fa98a3304a944c8a6"
|
checksum = "3f2032893cb734c7a05d85ce0cc8b8c4075278e93b24b66f9de99d6eb0fa8acc"
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-task"
|
name = "futures-task"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "7b0a34e53cf6cdcd0178aa573aed466b646eb3db769570841fda0c7ede375a27"
|
checksum = "bdb66b5f09e22019b1ab0830f7785bcea8e7a42148683f99214f73f8ec21a626"
|
||||||
|
dependencies = [
|
||||||
|
"once_cell",
|
||||||
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "futures-util"
|
name = "futures-util"
|
||||||
version = "0.3.4"
|
version = "0.3.5"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "22766cf25d64306bedf0384da004d05c9974ab104fcc4528f1236181c18004c5"
|
checksum = "8764574ff08b701a084482c3c7031349104b07ac897393010494beaa18ce32c6"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"futures-channel",
|
"futures-channel",
|
||||||
"futures-core",
|
"futures-core",
|
||||||
@ -1091,6 +1094,7 @@ dependencies = [
|
|||||||
"futures-sink",
|
"futures-sink",
|
||||||
"futures-task",
|
"futures-task",
|
||||||
"memchr",
|
"memchr",
|
||||||
|
"pin-project",
|
||||||
"pin-utils",
|
"pin-utils",
|
||||||
"proc-macro-hack",
|
"proc-macro-hack",
|
||||||
"proc-macro-nested",
|
"proc-macro-nested",
|
||||||
@ -1398,9 +1402,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "intervaltree"
|
name = "intervaltree"
|
||||||
version = "0.2.5"
|
version = "0.2.6"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "8254add2ea664734c9d001f8151cc3d7696b135f7e40e5a2efa814a662cb3a44"
|
checksum = "566d5aa3b5cc5c5809cc1a9c9588d917a634248bfc58f7ea14e354e71595a32c"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"smallvec",
|
"smallvec",
|
||||||
]
|
]
|
||||||
@ -1842,9 +1846,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "ntapi"
|
name = "ntapi"
|
||||||
version = "0.3.3"
|
version = "0.3.4"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "f26e041cd983acbc087e30fcba770380cfa352d0e392e175b2344ebaf7ea0602"
|
checksum = "7a31937dea023539c72ddae0e3571deadc1414b300483fa7aaec176168cfa9d2"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"winapi 0.3.8",
|
"winapi 0.3.8",
|
||||||
]
|
]
|
||||||
@ -1918,9 +1922,9 @@ checksum = "77af24da69f9d9341038eba93a073b1fdaaa1b788221b00a69bce9e762cb32de"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "openssl-sys"
|
name = "openssl-sys"
|
||||||
version = "0.9.55"
|
version = "0.9.56"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "7717097d810a0f2e2323f9e5d11e71608355e24828410b55b9d4f18aa5f9a5d8"
|
checksum = "f02309a7f127000ed50594f0b50ecc69e7c654e16d41b4e8156d1b3df8e0b52e"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"autocfg",
|
"autocfg",
|
||||||
"cc",
|
"cc",
|
||||||
@ -2038,18 +2042,18 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "pin-project"
|
name = "pin-project"
|
||||||
version = "0.4.13"
|
version = "0.4.16"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "82c3bfbfb5bb42f99498c7234bbd768c220eb0cea6818259d0d18a1aa3d2595d"
|
checksum = "81d480cb4e89522ccda96d0eed9af94180b7a5f93fb28f66e1fd7d68431663d1"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"pin-project-internal",
|
"pin-project-internal",
|
||||||
]
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "pin-project-internal"
|
name = "pin-project-internal"
|
||||||
version = "0.4.13"
|
version = "0.4.16"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "ccbf6449dcfb18562c015526b085b8df1aa3cdab180af8ec2ebd300a3bd28f63"
|
checksum = "a82996f11efccb19b685b14b5df818de31c1edcee3daa256ab5775dd98e72feb"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"proc-macro2",
|
"proc-macro2",
|
||||||
"quote",
|
"quote",
|
||||||
@ -2466,9 +2470,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "schannel"
|
name = "schannel"
|
||||||
version = "0.1.18"
|
version = "0.1.19"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "039c25b130bd8c1321ee2d7de7fde2659fa9c2744e4bb29711cfc852ea53cd19"
|
checksum = "8f05ba609c234e60bee0d547fe94a4c7e9da733d1c962cf6e59efa4cd9c8bc75"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"lazy_static",
|
"lazy_static",
|
||||||
"winapi 0.3.8",
|
"winapi 0.3.8",
|
||||||
@ -2498,9 +2502,9 @@ checksum = "cbb21fe0588557792176c89bc7b943027b14f346d03c6be6a199c2860277d93a"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "security-framework"
|
name = "security-framework"
|
||||||
version = "0.4.3"
|
version = "0.4.4"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "3f331b9025654145cd425b9ded0caf8f5ae0df80d418b326e2dc1c3dc5eb0620"
|
checksum = "64808902d7d99f78eaddd2b4e2509713babc3dc3c85ad6f4c447680f3c01e535"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"bitflags",
|
"bitflags",
|
||||||
"core-foundation",
|
"core-foundation",
|
||||||
@ -2575,18 +2579,18 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "serde"
|
name = "serde"
|
||||||
version = "1.0.106"
|
version = "1.0.110"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "36df6ac6412072f67cf767ebbde4133a5b2e88e76dc6187fa7104cd16f783399"
|
checksum = "99e7b308464d16b56eba9964e4972a3eee817760ab60d88c3f86e1fecb08204c"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"serde_derive",
|
"serde_derive",
|
||||||
]
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "serde_derive"
|
name = "serde_derive"
|
||||||
version = "1.0.106"
|
version = "1.0.110"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "9e549e3abf4fb8621bd1609f11dfc9f5e50320802273b12f3811a67e6716ea6c"
|
checksum = "818fbf6bfa9a42d3bfcaca148547aa00c7b915bec71d1757aa2d44ca68771984"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"proc-macro2",
|
"proc-macro2",
|
||||||
"quote",
|
"quote",
|
||||||
@ -2595,9 +2599,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "serde_json"
|
name = "serde_json"
|
||||||
version = "1.0.52"
|
version = "1.0.53"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "a7894c8ed05b7a3a279aeb79025fdec1d3158080b75b98a08faf2806bb799edd"
|
checksum = "993948e75b189211a9b31a7528f950c6adc21f9720b6438ff80a7fa2f864cea2"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"indexmap",
|
"indexmap",
|
||||||
"itoa",
|
"itoa",
|
||||||
@ -2853,9 +2857,9 @@ dependencies = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "threadpool"
|
name = "threadpool"
|
||||||
version = "1.8.0"
|
version = "1.8.1"
|
||||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||||
checksum = "e8dae184447c15d5a6916d973c642aec485105a13cd238192a6927ae3e077d66"
|
checksum = "d050e60b33d41c19108b32cea32164033a9013fe3b46cbd4457559bfbf77afaa"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"num_cpus",
|
"num_cpus",
|
||||||
]
|
]
|
||||||
|
@ -11,12 +11,13 @@ use std::fmt;
|
|||||||
use compact_arena::{SmallArena, Idx32, mk_arena};
|
use compact_arena::{SmallArena, Idx32, mk_arena};
|
||||||
use log::debug;
|
use log::debug;
|
||||||
use meilisearch_types::DocIndex;
|
use meilisearch_types::DocIndex;
|
||||||
use sdset::{Set, SetBuf, exponential_search, SetOperation};
|
use sdset::{Set, SetBuf, exponential_search, SetOperation, Counter, duo::OpBuilder};
|
||||||
use slice_group_by::{GroupBy, GroupByMut};
|
use slice_group_by::{GroupBy, GroupByMut};
|
||||||
|
|
||||||
use crate::error::Error;
|
use crate::error::Error;
|
||||||
use crate::criterion::{Criteria, Context, ContextMut};
|
use crate::criterion::{Criteria, Context, ContextMut};
|
||||||
use crate::distinct_map::{BufferedDistinctMap, DistinctMap};
|
use crate::distinct_map::{BufferedDistinctMap, DistinctMap};
|
||||||
|
use crate::facets::FacetKey;
|
||||||
use crate::raw_document::RawDocument;
|
use crate::raw_document::RawDocument;
|
||||||
use crate::{database::MainT, reordered_attrs::ReorderedAttrs};
|
use crate::{database::MainT, reordered_attrs::ReorderedAttrs};
|
||||||
use crate::{store, Document, DocumentId, MResult};
|
use crate::{store, Document, DocumentId, MResult};
|
||||||
@ -24,11 +25,20 @@ use crate::query_tree::{create_query_tree, traverse_query_tree};
|
|||||||
use crate::query_tree::{Operation, QueryResult, QueryKind, QueryId, PostingsKey};
|
use crate::query_tree::{Operation, QueryResult, QueryKind, QueryId, PostingsKey};
|
||||||
use crate::query_tree::Context as QTContext;
|
use crate::query_tree::Context as QTContext;
|
||||||
|
|
||||||
|
#[derive(Debug, Default)]
|
||||||
|
pub struct SortResult {
|
||||||
|
pub documents: Vec<Document>,
|
||||||
|
pub nb_hits: usize,
|
||||||
|
pub is_exhaustive: bool,
|
||||||
|
pub facets: Option<HashMap<FacetKey, usize>>,
|
||||||
|
}
|
||||||
|
|
||||||
pub fn bucket_sort<'c, FI>(
|
pub fn bucket_sort<'c, FI>(
|
||||||
reader: &heed::RoTxn<MainT>,
|
reader: &heed::RoTxn<MainT>,
|
||||||
query: &str,
|
query: &str,
|
||||||
range: Range<usize>,
|
range: Range<usize>,
|
||||||
facets_docids: Option<SetBuf<DocumentId>>,
|
facets_docids: Option<SetBuf<DocumentId>>,
|
||||||
|
facet_count_docids: Option<HashMap<FacetKey, Cow<Set<DocumentId>>>>,
|
||||||
filter: Option<FI>,
|
filter: Option<FI>,
|
||||||
criteria: Criteria<'c>,
|
criteria: Criteria<'c>,
|
||||||
searchable_attrs: Option<ReorderedAttrs>,
|
searchable_attrs: Option<ReorderedAttrs>,
|
||||||
@ -38,7 +48,7 @@ pub fn bucket_sort<'c, FI>(
|
|||||||
synonyms_store: store::Synonyms,
|
synonyms_store: store::Synonyms,
|
||||||
prefix_documents_cache_store: store::PrefixDocumentsCache,
|
prefix_documents_cache_store: store::PrefixDocumentsCache,
|
||||||
prefix_postings_lists_cache_store: store::PrefixPostingsListsCache,
|
prefix_postings_lists_cache_store: store::PrefixPostingsListsCache,
|
||||||
) -> MResult<(Vec<Document>, usize)>
|
) -> MResult<SortResult>
|
||||||
where
|
where
|
||||||
FI: Fn(DocumentId) -> bool,
|
FI: Fn(DocumentId) -> bool,
|
||||||
{
|
{
|
||||||
@ -52,6 +62,7 @@ where
|
|||||||
query,
|
query,
|
||||||
range,
|
range,
|
||||||
facets_docids,
|
facets_docids,
|
||||||
|
facet_count_docids,
|
||||||
filter,
|
filter,
|
||||||
distinct,
|
distinct,
|
||||||
distinct_size,
|
distinct_size,
|
||||||
@ -66,9 +77,11 @@ where
|
|||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
let mut result = SortResult::default();
|
||||||
|
|
||||||
let words_set = match unsafe { main_store.static_words_fst(reader)? } {
|
let words_set = match unsafe { main_store.static_words_fst(reader)? } {
|
||||||
Some(words) => words,
|
Some(words) => words,
|
||||||
None => return Ok((Vec::new(), 0)),
|
None => return Ok(SortResult::default()),
|
||||||
};
|
};
|
||||||
|
|
||||||
let stop_words = main_store.stop_words_fst(reader)?.unwrap_or_default();
|
let stop_words = main_store.stop_words_fst(reader)?.unwrap_or_default();
|
||||||
@ -107,6 +120,17 @@ where
|
|||||||
docids = Cow::Owned(intersection);
|
docids = Cow::Owned(intersection);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if let Some(facet_count_docids) = facet_count_docids {
|
||||||
|
let mut facets = HashMap::new();
|
||||||
|
for (key, document_ids) in facet_count_docids {
|
||||||
|
let mut counter = Counter::new();
|
||||||
|
let op = OpBuilder::new(document_ids.as_ref(), document_ids.as_ref()).intersection();
|
||||||
|
SetOperation::<DocumentId>::extend_collection(op, &mut counter);
|
||||||
|
facets.insert(key, counter.0);
|
||||||
|
}
|
||||||
|
result.facets = Some(facets);
|
||||||
|
}
|
||||||
|
|
||||||
let before = Instant::now();
|
let before = Instant::now();
|
||||||
mk_arena!(arena);
|
mk_arena!(arena);
|
||||||
let mut bare_matches = cleanup_bare_matches(&mut arena, &docids, queries);
|
let mut bare_matches = cleanup_bare_matches(&mut arena, &docids, queries);
|
||||||
@ -181,7 +205,10 @@ where
|
|||||||
|
|
||||||
debug!("bucket sort took {:.02?}", before_bucket_sort.elapsed());
|
debug!("bucket sort took {:.02?}", before_bucket_sort.elapsed());
|
||||||
|
|
||||||
Ok((documents, docids.len()))
|
result.documents = documents;
|
||||||
|
result.nb_hits = docids.len();
|
||||||
|
|
||||||
|
Ok(result)
|
||||||
}
|
}
|
||||||
|
|
||||||
pub fn bucket_sort_with_distinct<'c, FI, FD>(
|
pub fn bucket_sort_with_distinct<'c, FI, FD>(
|
||||||
@ -189,6 +216,7 @@ pub fn bucket_sort_with_distinct<'c, FI, FD>(
|
|||||||
query: &str,
|
query: &str,
|
||||||
range: Range<usize>,
|
range: Range<usize>,
|
||||||
facets_docids: Option<SetBuf<DocumentId>>,
|
facets_docids: Option<SetBuf<DocumentId>>,
|
||||||
|
facet_count_docids: Option<HashMap<FacetKey, Cow<Set<DocumentId>>>>,
|
||||||
filter: Option<FI>,
|
filter: Option<FI>,
|
||||||
distinct: FD,
|
distinct: FD,
|
||||||
distinct_size: usize,
|
distinct_size: usize,
|
||||||
@ -200,14 +228,16 @@ pub fn bucket_sort_with_distinct<'c, FI, FD>(
|
|||||||
synonyms_store: store::Synonyms,
|
synonyms_store: store::Synonyms,
|
||||||
_prefix_documents_cache_store: store::PrefixDocumentsCache,
|
_prefix_documents_cache_store: store::PrefixDocumentsCache,
|
||||||
prefix_postings_lists_cache_store: store::PrefixPostingsListsCache,
|
prefix_postings_lists_cache_store: store::PrefixPostingsListsCache,
|
||||||
) -> MResult<(Vec<Document>, usize)>
|
) -> MResult<SortResult>
|
||||||
where
|
where
|
||||||
FI: Fn(DocumentId) -> bool,
|
FI: Fn(DocumentId) -> bool,
|
||||||
FD: Fn(DocumentId) -> Option<u64>,
|
FD: Fn(DocumentId) -> Option<u64>,
|
||||||
{
|
{
|
||||||
|
let mut result = SortResult::default();
|
||||||
|
|
||||||
let words_set = match unsafe { main_store.static_words_fst(reader)? } {
|
let words_set = match unsafe { main_store.static_words_fst(reader)? } {
|
||||||
Some(words) => words,
|
Some(words) => words,
|
||||||
None => return Ok((Vec::new(), 0)),
|
None => return Ok(SortResult::default()),
|
||||||
};
|
};
|
||||||
|
|
||||||
let stop_words = main_store.stop_words_fst(reader)?.unwrap_or_default();
|
let stop_words = main_store.stop_words_fst(reader)?.unwrap_or_default();
|
||||||
@ -240,12 +270,23 @@ where
|
|||||||
debug!("number of postings {:?}", queries.len());
|
debug!("number of postings {:?}", queries.len());
|
||||||
|
|
||||||
if let Some(facets_docids) = facets_docids {
|
if let Some(facets_docids) = facets_docids {
|
||||||
let intersection = sdset::duo::OpBuilder::new(docids.as_ref(), facets_docids.as_set())
|
let intersection = OpBuilder::new(docids.as_ref(), facets_docids.as_set())
|
||||||
.intersection()
|
.intersection()
|
||||||
.into_set_buf();
|
.into_set_buf();
|
||||||
docids = Cow::Owned(intersection);
|
docids = Cow::Owned(intersection);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if let Some(facet_count_docids) = facet_count_docids {
|
||||||
|
let mut facets = HashMap::new();
|
||||||
|
for (key, document_ids) in facet_count_docids {
|
||||||
|
let mut counter = Counter::new();
|
||||||
|
let op = OpBuilder::new(document_ids.as_ref(), document_ids.as_ref()).intersection();
|
||||||
|
SetOperation::<DocumentId>::extend_collection(op, &mut counter);
|
||||||
|
facets.insert(key, counter.0);
|
||||||
|
}
|
||||||
|
result.facets = Some(facets);
|
||||||
|
}
|
||||||
|
|
||||||
let before = Instant::now();
|
let before = Instant::now();
|
||||||
mk_arena!(arena);
|
mk_arena!(arena);
|
||||||
let mut bare_matches = cleanup_bare_matches(&mut arena, &docids, queries);
|
let mut bare_matches = cleanup_bare_matches(&mut arena, &docids, queries);
|
||||||
@ -379,8 +420,10 @@ where
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
result.documents = documents;
|
||||||
|
result.nb_hits = docids.len();
|
||||||
|
|
||||||
Ok((documents, docids.len()))
|
Ok(result)
|
||||||
}
|
}
|
||||||
|
|
||||||
fn cleanup_bare_matches<'tag, 'txn>(
|
fn cleanup_bare_matches<'tag, 'txn>(
|
||||||
|
@ -1,27 +1,31 @@
|
|||||||
use std::borrow::Cow;
|
use std::borrow::Cow;
|
||||||
|
use std::collections::HashMap;
|
||||||
use std::ops::{Range, Deref};
|
use std::ops::{Range, Deref};
|
||||||
use std::time::Duration;
|
use std::time::Duration;
|
||||||
|
|
||||||
use crate::database::MainT;
|
use crate::database::MainT;
|
||||||
use crate::bucket_sort::{bucket_sort, bucket_sort_with_distinct};
|
use crate::bucket_sort::{bucket_sort, bucket_sort_with_distinct, SortResult};
|
||||||
use crate::{criterion::Criteria, Document, DocumentId};
|
use crate::{criterion::Criteria, DocumentId};
|
||||||
use crate::{reordered_attrs::ReorderedAttrs, store, MResult};
|
use crate::{reordered_attrs::ReorderedAttrs, store, MResult};
|
||||||
use crate::facets::FacetFilter;
|
use crate::facets::FacetFilter;
|
||||||
|
|
||||||
use either::Either;
|
use either::Either;
|
||||||
use sdset::SetOperation;
|
use sdset::SetOperation;
|
||||||
|
|
||||||
pub struct QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
use meilisearch_schema::FieldId;
|
||||||
|
|
||||||
|
pub struct QueryBuilder<'c, 'f, 'd, 'i, 'q> {
|
||||||
criteria: Criteria<'c>,
|
criteria: Criteria<'c>,
|
||||||
searchable_attrs: Option<ReorderedAttrs>,
|
searchable_attrs: Option<ReorderedAttrs>,
|
||||||
filter: Option<Box<dyn Fn(DocumentId) -> bool + 'f>>,
|
filter: Option<Box<dyn Fn(DocumentId) -> bool + 'f>>,
|
||||||
distinct: Option<(Box<dyn Fn(DocumentId) -> Option<u64> + 'd>, usize)>,
|
distinct: Option<(Box<dyn Fn(DocumentId) -> Option<u64> + 'd>, usize)>,
|
||||||
timeout: Option<Duration>,
|
timeout: Option<Duration>,
|
||||||
index: &'i store::Index,
|
index: &'i store::Index,
|
||||||
facets: Option<&'fa FacetFilter>,
|
facet_fitlers: Option<&'q FacetFilter>,
|
||||||
|
facets: Option<&'q [FieldId]>,
|
||||||
}
|
}
|
||||||
|
|
||||||
impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
impl<'c, 'f, 'd, 'i, 'q> QueryBuilder<'c, 'f, 'd, 'i, 'q> {
|
||||||
pub fn new(index: &'i store::Index) -> Self {
|
pub fn new(index: &'i store::Index) -> Self {
|
||||||
QueryBuilder::with_criteria(
|
QueryBuilder::with_criteria(
|
||||||
index,
|
index,
|
||||||
@ -29,7 +33,13 @@ impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
|||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
pub fn set_facets(&mut self, facets: Option<&'fa FacetFilter>) {
|
/// sets facet attributes to filter on
|
||||||
|
pub fn set_facet_filters(&mut self, facets: Option<&'q FacetFilter>) {
|
||||||
|
self.facet_fitlers = facets;
|
||||||
|
}
|
||||||
|
|
||||||
|
/// sets facet attributes for which to return the count
|
||||||
|
pub fn set_facets(&mut self, facets: Option<&'q [FieldId]>) {
|
||||||
self.facets = facets;
|
self.facets = facets;
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -44,6 +54,7 @@ impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
|||||||
distinct: None,
|
distinct: None,
|
||||||
timeout: None,
|
timeout: None,
|
||||||
index,
|
index,
|
||||||
|
facet_fitlers: None,
|
||||||
facets: None,
|
facets: None,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@ -76,8 +87,8 @@ impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
|||||||
reader: &heed::RoTxn<MainT>,
|
reader: &heed::RoTxn<MainT>,
|
||||||
query: &str,
|
query: &str,
|
||||||
range: Range<usize>,
|
range: Range<usize>,
|
||||||
) -> MResult<(Vec<Document>, usize)> {
|
) -> MResult<SortResult> {
|
||||||
let facets_docids = match self.facets {
|
let facets_docids = match self.facet_fitlers {
|
||||||
Some(facets) => {
|
Some(facets) => {
|
||||||
let mut ands = Vec::with_capacity(facets.len());
|
let mut ands = Vec::with_capacity(facets.len());
|
||||||
let mut ors = Vec::new();
|
let mut ors = Vec::new();
|
||||||
@ -98,7 +109,7 @@ impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
|||||||
match self.index.facets.facet_document_ids(reader, &key)? {
|
match self.index.facets.facet_document_ids(reader, &key)? {
|
||||||
Some(docids) => ands.push(docids),
|
Some(docids) => ands.push(docids),
|
||||||
// no candidates for search, early return.
|
// no candidates for search, early return.
|
||||||
None => return Ok((vec![], 0)),
|
None => return Ok(SortResult::default()),
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
};
|
};
|
||||||
@ -109,12 +120,29 @@ impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
|||||||
None => None
|
None => None
|
||||||
};
|
};
|
||||||
|
|
||||||
|
let facet_count_docids = match self.facets {
|
||||||
|
Some(field_ids) => {
|
||||||
|
let mut facet_count_map = HashMap::new();
|
||||||
|
for field_id in field_ids {
|
||||||
|
for pair in self.index.facets.field_document_ids(reader, *field_id)? {
|
||||||
|
let (facet_key, document_ids) = pair?;
|
||||||
|
let facet_key_string = facet_key.to_parts(schema)?;
|
||||||
|
facet_count_map.insert(facet_key, document_ids);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Some(facet_count_map)
|
||||||
|
}
|
||||||
|
None => None,
|
||||||
|
};
|
||||||
|
|
||||||
|
|
||||||
match self.distinct {
|
match self.distinct {
|
||||||
Some((distinct, distinct_size)) => bucket_sort_with_distinct(
|
Some((distinct, distinct_size)) => bucket_sort_with_distinct(
|
||||||
reader,
|
reader,
|
||||||
query,
|
query,
|
||||||
range,
|
range,
|
||||||
facets_docids,
|
facets_docids,
|
||||||
|
facet_count_docids,
|
||||||
self.filter,
|
self.filter,
|
||||||
distinct,
|
distinct,
|
||||||
distinct_size,
|
distinct_size,
|
||||||
@ -132,6 +160,7 @@ impl<'c, 'f, 'd, 'fa, 'i> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
|||||||
query,
|
query,
|
||||||
range,
|
range,
|
||||||
facets_docids,
|
facets_docids,
|
||||||
|
facet_count_docids,
|
||||||
self.filter,
|
self.filter,
|
||||||
self.criteria,
|
self.criteria,
|
||||||
self.searchable_attrs,
|
self.searchable_attrs,
|
||||||
|
@ -1,10 +1,11 @@
|
|||||||
use std::borrow::Cow;
|
use std::borrow::Cow;
|
||||||
use std::collections::HashMap;
|
use std::collections::HashMap;
|
||||||
|
|
||||||
use heed::{RwTxn, RoTxn, Result as ZResult};
|
use heed::{RwTxn, RoTxn, Result as ZResult, RoRange};
|
||||||
use sdset::{SetBuf, Set, SetOperation};
|
use sdset::{SetBuf, Set, SetOperation};
|
||||||
|
|
||||||
use meilisearch_types::DocumentId;
|
use meilisearch_types::DocumentId;
|
||||||
|
use meilisearch_schema::FieldId;
|
||||||
|
|
||||||
use crate::database::MainT;
|
use crate::database::MainT;
|
||||||
use crate::facets::FacetKey;
|
use crate::facets::FacetKey;
|
||||||
@ -22,6 +23,10 @@ impl Facets {
|
|||||||
self.facets.put(writer, &facet_key, doc_ids)
|
self.facets.put(writer, &facet_key, doc_ids)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
pub fn field_document_ids<'txn>(&self, reader: &'txn RoTxn<MainT>, field_id: FieldId) -> ZResult<RoRange<'txn, FacetKey, CowSet<DocumentId>>> {
|
||||||
|
self.facets.prefix_iter(reader, &FacetKey::new(field_id, "".to_string()))
|
||||||
|
}
|
||||||
|
|
||||||
pub fn facet_document_ids<'txn>(&self, reader: &'txn RoTxn<MainT>, facet_key: &FacetKey) -> ZResult<Option<Cow<'txn, Set<DocumentId>>>> {
|
pub fn facet_document_ids<'txn>(&self, reader: &'txn RoTxn<MainT>, facet_key: &FacetKey) -> ZResult<Option<Cow<'txn, Set<DocumentId>>>> {
|
||||||
self.facets.get(reader, &facet_key)
|
self.facets.get(reader, &facet_key)
|
||||||
}
|
}
|
||||||
|
@ -363,10 +363,10 @@ impl Index {
|
|||||||
QueryBuilder::new(self)
|
QueryBuilder::new(self)
|
||||||
}
|
}
|
||||||
|
|
||||||
pub fn query_builder_with_criteria<'c, 'f, 'd, 'fa, 'i>(
|
pub fn query_builder_with_criteria<'c, 'f, 'd, 'fa, 'i, 'q>(
|
||||||
&'i self,
|
&'i self,
|
||||||
criteria: Criteria<'c>,
|
criteria: Criteria<'c>,
|
||||||
) -> QueryBuilder<'c, 'f, 'd, 'fa, 'i> {
|
) -> QueryBuilder<'c, 'f, 'd, 'i, 'q> {
|
||||||
QueryBuilder::with_criteria(self, criteria)
|
QueryBuilder::with_criteria(self, criteria)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -36,6 +36,7 @@ impl IndexSearchExt for Index {
|
|||||||
filters: None,
|
filters: None,
|
||||||
matches: false,
|
matches: false,
|
||||||
facet_filters: None,
|
facet_filters: None,
|
||||||
|
facets: None,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@ -51,6 +52,7 @@ pub struct SearchBuilder<'a> {
|
|||||||
filters: Option<String>,
|
filters: Option<String>,
|
||||||
matches: bool,
|
matches: bool,
|
||||||
facet_filters: Option<FacetFilter>,
|
facet_filters: Option<FacetFilter>,
|
||||||
|
facets: Option<Vec<FieldId>>
|
||||||
}
|
}
|
||||||
|
|
||||||
impl<'a> SearchBuilder<'a> {
|
impl<'a> SearchBuilder<'a> {
|
||||||
@ -100,6 +102,11 @@ impl<'a> SearchBuilder<'a> {
|
|||||||
self
|
self
|
||||||
}
|
}
|
||||||
|
|
||||||
|
pub fn add_facets(&mut self, facets: Vec<FieldId>) -> &SearchBuilder {
|
||||||
|
self.facets = Some(facets);
|
||||||
|
self
|
||||||
|
}
|
||||||
|
|
||||||
pub fn search(&self, reader: &heed::RoTxn<MainT>) -> Result<SearchResult, ResponseError> {
|
pub fn search(&self, reader: &heed::RoTxn<MainT>) -> Result<SearchResult, ResponseError> {
|
||||||
let schema = self
|
let schema = self
|
||||||
.index
|
.index
|
||||||
@ -146,11 +153,12 @@ impl<'a> SearchBuilder<'a> {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
query_builder.set_facets(self.facet_filters.as_ref());
|
query_builder.set_facet_filters(self.facet_filters.as_ref());
|
||||||
|
query_builder.set_facets(self.facets.as_deref());
|
||||||
|
|
||||||
let start = Instant::now();
|
let start = Instant::now();
|
||||||
let result = query_builder.query(reader, &self.query, self.offset..(self.offset + self.limit));
|
let result = query_builder.query(reader, &self.query, self.offset..(self.offset + self.limit));
|
||||||
let (docs, nb_hits) = result.map_err(ResponseError::search_documents)?;
|
let search_result = result.map_err(ResponseError::search_documents)?;
|
||||||
let time_ms = start.elapsed().as_millis() as usize;
|
let time_ms = start.elapsed().as_millis() as usize;
|
||||||
|
|
||||||
let mut all_attributes: HashSet<&str> = HashSet::new();
|
let mut all_attributes: HashSet<&str> = HashSet::new();
|
||||||
@ -181,7 +189,7 @@ impl<'a> SearchBuilder<'a> {
|
|||||||
}
|
}
|
||||||
|
|
||||||
let mut hits = Vec::with_capacity(self.limit);
|
let mut hits = Vec::with_capacity(self.limit);
|
||||||
for doc in docs {
|
for doc in search_result.documents {
|
||||||
let mut document: IndexMap<String, Value> = self
|
let mut document: IndexMap<String, Value> = self
|
||||||
.index
|
.index
|
||||||
.document(reader, Some(&all_attributes), doc.id)
|
.document(reader, Some(&all_attributes), doc.id)
|
||||||
@ -235,10 +243,11 @@ impl<'a> SearchBuilder<'a> {
|
|||||||
hits,
|
hits,
|
||||||
offset: self.offset,
|
offset: self.offset,
|
||||||
limit: self.limit,
|
limit: self.limit,
|
||||||
nb_hits,
|
nb_hits: search_result.nb_hits,
|
||||||
exhaustive_nb_hits: false,
|
exhaustive_nb_hits: search_result.is_exhaustive,
|
||||||
processing_time_ms: time_ms,
|
processing_time_ms: time_ms,
|
||||||
query: self.query.to_string(),
|
query: self.query.to_string(),
|
||||||
|
facets: search_result.facets
|
||||||
};
|
};
|
||||||
|
|
||||||
Ok(results)
|
Ok(results)
|
||||||
|
@ -5,6 +5,7 @@ use actix_web::web;
|
|||||||
use actix_web::HttpResponse;
|
use actix_web::HttpResponse;
|
||||||
use actix_web_macros::get;
|
use actix_web_macros::get;
|
||||||
use serde::Deserialize;
|
use serde::Deserialize;
|
||||||
|
use serde_json::Value;
|
||||||
|
|
||||||
use crate::error::ResponseError;
|
use crate::error::ResponseError;
|
||||||
use crate::helpers::meilisearch::IndexSearchExt;
|
use crate::helpers::meilisearch::IndexSearchExt;
|
||||||
@ -13,6 +14,7 @@ use crate::routes::IndexParam;
|
|||||||
use crate::Data;
|
use crate::Data;
|
||||||
|
|
||||||
use meilisearch_core::facets::FacetFilter;
|
use meilisearch_core::facets::FacetFilter;
|
||||||
|
use meilisearch_schema::{Schema, FieldId};
|
||||||
|
|
||||||
pub fn services(cfg: &mut web::ServiceConfig) {
|
pub fn services(cfg: &mut web::ServiceConfig) {
|
||||||
cfg.service(search_with_url_query);
|
cfg.service(search_with_url_query);
|
||||||
@ -31,6 +33,7 @@ struct SearchQuery {
|
|||||||
filters: Option<String>,
|
filters: Option<String>,
|
||||||
matches: Option<bool>,
|
matches: Option<bool>,
|
||||||
facet_filters: Option<String>,
|
facet_filters: Option<String>,
|
||||||
|
facets: Option<String>
|
||||||
}
|
}
|
||||||
|
|
||||||
#[get("/indexes/{index_uid}/search", wrap = "Authentication::Public")]
|
#[get("/indexes/{index_uid}/search", wrap = "Authentication::Public")]
|
||||||
@ -91,6 +94,14 @@ async fn search_with_url_query(
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if let Some(ref facets) = params.facets {
|
||||||
|
match index.main.attributes_for_faceting(&reader)? {
|
||||||
|
Some(ref attrs) => { search_builder.add_facets(prepare_facet_list(facets, &schema, attrs)?); },
|
||||||
|
None => return Err(ResponseError::FacetExpression("can't return facets count, as no facet is set".to_string()))
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
if let Some(attributes_to_crop) = ¶ms.attributes_to_crop {
|
if let Some(attributes_to_crop) = ¶ms.attributes_to_crop {
|
||||||
let default_length = params.crop_length.unwrap_or(200);
|
let default_length = params.crop_length.unwrap_or(200);
|
||||||
let mut final_attributes: HashMap<String, usize> = HashMap::new();
|
let mut final_attributes: HashMap<String, usize> = HashMap::new();
|
||||||
@ -150,3 +161,27 @@ async fn search_with_url_query(
|
|||||||
|
|
||||||
Ok(HttpResponse::Ok().json(search_builder.search(&reader)?))
|
Ok(HttpResponse::Ok().json(search_builder.search(&reader)?))
|
||||||
}
|
}
|
||||||
|
|
||||||
|
fn prepare_facet_list<'fa>(facets: &str, schema: &Schema, facet_attrs: &'fa [FieldId]) -> Result<Vec<FieldId>, ResponseError> {
|
||||||
|
let facet_array = serde_json::from_str(facets).expect("do error handling"); // TODO
|
||||||
|
match facet_array {
|
||||||
|
Value::Array(facet_array) => {
|
||||||
|
let wild_card = Value::String("*".to_string());
|
||||||
|
if facet_array.iter().any(|it| it == &wild_card) {
|
||||||
|
return Ok(Vec::from(facet_attrs)); // TODO can make cow?
|
||||||
|
}
|
||||||
|
let mut fields = Vec::with_capacity(facet_attrs.len());
|
||||||
|
for v in facet_array {
|
||||||
|
match v {
|
||||||
|
Value::String(name) => {
|
||||||
|
let id = schema.id(&name).expect("not found error"); // TODO
|
||||||
|
fields.push(id);
|
||||||
|
}
|
||||||
|
_ => todo!("expected string, found {}", v),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return Ok(fields);
|
||||||
|
}
|
||||||
|
_ => todo!("error, bad syntax, expected array")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user