Merge branch 'release-v0.19.0' into stable

CHANGELOG.md

@@ -1,3 +1,9 @@
+## v0.19.0
+
+  - The snapshots are now created and then renamed in atomically (#1172)
+  - Fix a race condition when an update and a document addition are processed immediately one after the other (#1176)
+  - Latin synonyms are normalized during indexation (#1174)
+
 ## v0.18.1
 
   - Fix unexpected CORS error (#1185)
@@ -64,7 +70,7 @@
 
 ## v0.11.1
 
-  - Fix facet cache on document update (#789) 
+  - Fix facet cache on document update (#789)
   - Improvements on settings consistency (#778)
 
 ## v0.11.0

Cargo.lock

@@ -1639,7 +1639,7 @@ checksum = "7ffc5c5338469d4d3ea17d269fa8ea3512ad247247c30bd2df69e68309ed0a08"
 
 [[package]]
 name = "meilisearch-core"
-version = "0.18.1"
+version = "0.19.0"
 dependencies = [
  "arc-swap",
  "assert_matches",
@@ -1686,14 +1686,14 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-error"
-version = "0.18.1"
+version = "0.19.0"
 dependencies = [
  "actix-http",
 ]
 
 [[package]]
 name = "meilisearch-http"
-version = "0.18.1"
+version = "0.19.0"
 dependencies = [
  "actix-cors",
  "actix-http",
@@ -1734,6 +1734,7 @@ dependencies = [
  "tempfile",
  "tokio",
  "ureq",
+ "uuid",
  "vergen",
  "walkdir",
  "whoami",
@@ -1741,7 +1742,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-schema"
-version = "0.18.1"
+version = "0.19.0"
 dependencies = [
  "indexmap",
  "meilisearch-error",
@@ -1753,7 +1754,7 @@ dependencies = [
 [[package]]
 name = "meilisearch-tokenizer"
 version = "0.1.1"
-source = "git+https://github.com/meilisearch/Tokenizer.git?tag=v0.1.2#8d91cd52f30aa4b651a085c15056938f7b599646"
+source = "git+https://github.com/meilisearch/Tokenizer.git?tag=v0.1.3#d3fe5311a66c1f31682a297df8a8b6b8916f4252"
 dependencies = [
  "character_converter",
  "cow-utils",
@@ -1768,7 +1769,7 @@ dependencies = [
 
 [[package]]
 name = "meilisearch-types"
-version = "0.18.1"
+version = "0.19.0"
 dependencies = [
  "serde",
  "zerocopy",

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2019-2020 Meili SAS
+Copyright (c) 2019-2021 Meili SAS
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -48,7 +48,7 @@ For more information about features go to [our documentation](https://docs.meili
 
 ### Deploy the Server
 
-#### Brew (Mac OS)
+#### Homebrew (Mac OS)
 
 ```bash
 brew update && brew install meilisearch

meilisearch-core/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "meilisearch-core"
-version = "0.18.1"
+version = "0.19.0"
 license = "MIT"
 authors = ["Kerollmops <clement@meilisearch.com>"]
 edition = "2018"
@@ -24,10 +24,10 @@ intervaltree = "0.2.6"
 itertools = "0.10.0"
 levenshtein_automata = { version = "0.2.0", features = ["fst_automaton"] }
 log = "0.4.11"
-meilisearch-error = { path = "../meilisearch-error", version = "0.18.1" }
-meilisearch-schema = { path = "../meilisearch-schema", version = "0.18.1" }
-meilisearch-tokenizer = { git = "https://github.com/meilisearch/Tokenizer.git", tag = "v0.1.2" }
-meilisearch-types = { path = "../meilisearch-types", version = "0.18.1" }
+meilisearch-error = { path = "../meilisearch-error", version = "0.19.0" }
+meilisearch-schema = { path = "../meilisearch-schema", version = "0.19.0" }
+meilisearch-tokenizer = { git = "https://github.com/meilisearch/Tokenizer.git", tag = "v0.1.3" }
+meilisearch-types = { path = "../meilisearch-types", version = "0.19.0" }
 once_cell = "1.5.2"
 ordered-float = { version = "2.0.1", features = ["serde"] }
 pest = { git = "https://github.com/pest-parser/pest.git", rev = "51fd1d49f1041f7839975664ef71fe15c7dcaf67" }

meilisearch-core/src/lib.rs

@@ -39,6 +39,7 @@ pub use self::update::{EnqueuedUpdateResult, ProcessedUpdateResult, UpdateStatus
 pub use meilisearch_types::{DocIndex, DocumentId, Highlight};
 pub use meilisearch_schema::Schema;
 pub use query_words_mapper::QueryWordsMapper;
+pub use query_tree::MAX_QUERY_LEN;
 
 use compact_arena::SmallArena;
 use log::{error, trace};

meilisearch-core/src/query_tree.rs

@@ -16,6 +16,8 @@ use crate::{store, DocumentId, DocIndex, MResult, FstSetCow};
 use crate::automaton::{build_dfa, build_prefix_dfa, build_exact_dfa};
 use crate::QueryWordsMapper;
 
+pub const MAX_QUERY_LEN: usize = 10;
+
 #[derive(Clone, PartialEq, Eq, Hash)]
 pub enum Operation {
     And(Vec<Operation>),
@@ -181,6 +183,7 @@ fn split_query_string<'a, A: AsRef<[u8]>>(s: &str, stop_words: &'a fst::Set<A>)
         .tokens()
         .filter(|t| t.is_word())
         .map(|t| t.word.to_string())
+        .take(MAX_QUERY_LEN)
         .enumerate()
         .collect()
 }

meilisearch-core/src/update/documents_addition.rs

@@ -23,6 +23,8 @@ pub struct DocumentsAddition<D> {
     updates_store: store::Updates,
     updates_results_store: store::UpdatesResults,
     updates_notifier: UpdateEventsEmitter,
+    // Whether the user explicitly set the primary key in the update
+    primary_key: Option<String>,
     documents: Vec<D>,
     is_partial: bool,
 }
@@ -39,6 +41,7 @@ impl<D> DocumentsAddition<D> {
             updates_notifier,
             documents: Vec::new(),
             is_partial: false,
+            primary_key: None,
         }
     }
 
@@ -53,9 +56,14 @@ impl<D> DocumentsAddition<D> {
             updates_notifier,
             documents: Vec::new(),
             is_partial: true,
+            primary_key: None,
         }
     }
 
+    pub fn set_primary_key(&mut self, primary_key: String) {
+        self.primary_key = Some(primary_key);
+    }
+
     pub fn update_document(&mut self, document: D) {
         self.documents.push(document);
     }
@@ -71,6 +79,7 @@ impl<D> DocumentsAddition<D> {
             self.updates_results_store,
             self.documents,
             self.is_partial,
+            self.primary_key,
         )?;
         Ok(update_id)
     }
@@ -88,6 +97,7 @@ pub fn push_documents_addition<D: serde::Serialize>(
     updates_results_store: store::UpdatesResults,
     addition: Vec<D>,
     is_partial: bool,
+    primary_key: Option<String>,
 ) -> MResult<u64> {
     let mut values = Vec::with_capacity(addition.len());
     for add in addition {
@@ -99,9 +109,9 @@ pub fn push_documents_addition<D: serde::Serialize>(
     let last_update_id = next_update_id(writer, updates_store, updates_results_store)?;
 
     let update = if is_partial {
-        Update::documents_partial(values)
+        Update::documents_partial(primary_key, values)
     } else {
-        Update::documents_addition(values)
+        Update::documents_addition(primary_key, values)
     };
 
     updates_store.put_update(writer, last_update_id, &update)?;
@@ -149,7 +159,8 @@ pub fn apply_addition(
     writer: &mut heed::RwTxn<MainT>,
     index: &store::Index,
     new_documents: Vec<IndexMap<String, Value>>,
-    partial: bool
+    partial: bool,
+    primary_key: Option<String>,
 ) -> MResult<()>
 {
     let mut schema = match index.main.schema(writer)? {
@@ -162,7 +173,14 @@ pub fn apply_addition(
     let internal_docids = index.main.internal_docids(writer)?;
     let mut available_ids = DiscoverIds::new(&internal_docids);
 
-    let primary_key = schema.primary_key().ok_or(Error::MissingPrimaryKey)?;
+    let primary_key = match schema.primary_key() {
+        Some(primary_key) => primary_key.to_string(),
+        None => {
+            let name = primary_key.ok_or(Error::MissingPrimaryKey)?;
+            schema.set_primary_key(&name)?;
+            name
+        }
+    };
 
     // 1. store documents ids for future deletion
     let mut documents_additions = HashMap::new();
@@ -275,16 +293,18 @@ pub fn apply_documents_partial_addition(
     writer: &mut heed::RwTxn<MainT>,
     index: &store::Index,
     new_documents: Vec<IndexMap<String, Value>>,
+    primary_key: Option<String>,
 ) -> MResult<()> {
-    apply_addition(writer, index, new_documents, true)
+    apply_addition(writer, index, new_documents, true, primary_key)
 }
 
 pub fn apply_documents_addition(
     writer: &mut heed::RwTxn<MainT>,
     index: &store::Index,
     new_documents: Vec<IndexMap<String, Value>>,
+    primary_key: Option<String>,
 ) -> MResult<()> {
-    apply_addition(writer, index, new_documents, false)
+    apply_addition(writer, index, new_documents, false, primary_key)
 }
 
 pub fn reindex_all_documents(writer: &mut heed::RwTxn<MainT>, index: &store::Index) -> MResult<()> {

meilisearch-core/src/update/mod.rs

@@ -52,16 +52,16 @@ impl Update {
         }
     }
 
-    fn documents_addition(documents: Vec<IndexMap<String, Value>>) -> Update {
+    fn documents_addition(primary_key: Option<String>, documents: Vec<IndexMap<String, Value>>) -> Update {
         Update {
-            data: UpdateData::DocumentsAddition(documents),
+            data: UpdateData::DocumentsAddition{ documents, primary_key },
             enqueued_at: Utc::now(),
         }
     }
 
-    fn documents_partial(documents: Vec<IndexMap<String, Value>>) -> Update {
+    fn documents_partial(primary_key: Option<String>, documents: Vec<IndexMap<String, Value>>) -> Update {
         Update {
-            data: UpdateData::DocumentsPartial(documents),
+            data: UpdateData::DocumentsPartial{ documents, primary_key },
             enqueued_at: Utc::now(),
         }
     }
@@ -85,8 +85,15 @@ impl Update {
 pub enum UpdateData {
     ClearAll,
     Customs(Vec<u8>),
-    DocumentsAddition(Vec<IndexMap<String, Value>>),
-    DocumentsPartial(Vec<IndexMap<String, Value>>),
+    // (primary key, documents)
+    DocumentsAddition {
+        primary_key: Option<String>,
+        documents: Vec<IndexMap<String, Value>>
+    },
+    DocumentsPartial {
+        primary_key: Option<String>,
+        documents: Vec<IndexMap<String, Value>>,
+    },
     DocumentsDeletion(Vec<String>),
     Settings(Box<SettingsUpdate>)
 }
@@ -96,11 +103,11 @@ impl UpdateData {
         match self {
             UpdateData::ClearAll => UpdateType::ClearAll,
             UpdateData::Customs(_) => UpdateType::Customs,
-            UpdateData::DocumentsAddition(addition) => UpdateType::DocumentsAddition {
-                number: addition.len(),
+            UpdateData::DocumentsAddition{ documents, .. } => UpdateType::DocumentsAddition {
+                number: documents.len(),
             },
-            UpdateData::DocumentsPartial(addition) => UpdateType::DocumentsPartial {
-                number: addition.len(),
+            UpdateData::DocumentsPartial{ documents, .. } => UpdateType::DocumentsPartial {
+                number: documents.len(),
             },
             UpdateData::DocumentsDeletion(deletion) => UpdateType::DocumentsDeletion {
                 number: deletion.len(),
@@ -239,25 +246,25 @@ pub fn update_task(
 
             (update_type, result, start.elapsed())
         }
-        UpdateData::DocumentsAddition(documents) => {
+        UpdateData::DocumentsAddition { documents, primary_key } => {
             let start = Instant::now();
 
             let update_type = UpdateType::DocumentsAddition {
                 number: documents.len(),
             };
 
-            let result = apply_documents_addition(writer, index, documents);
+            let result = apply_documents_addition(writer, index, documents, primary_key);
 
             (update_type, result, start.elapsed())
         }
-        UpdateData::DocumentsPartial(documents) => {
+        UpdateData::DocumentsPartial{ documents, primary_key } => {
             let start = Instant::now();
 
             let update_type = UpdateType::DocumentsPartial {
                 number: documents.len(),
             };
 
-            let result = apply_documents_partial_addition(writer, index, documents);
+            let result = apply_documents_partial_addition(writer, index, documents, primary_key);
 
             (update_type, result, start.elapsed())
         }

meilisearch-core/src/update/settings_update.rs

@@ -1,9 +1,10 @@
-use std::collections::{BTreeMap, BTreeSet};
+use std::{borrow::Cow, collections::{BTreeMap, BTreeSet}};
 
 use heed::Result as ZResult;
-use fst::{set::OpBuilder, SetBuilder};
+use fst::{SetBuilder, set::OpBuilder};
 use sdset::SetBuf;
 use meilisearch_schema::Schema;
+use meilisearch_tokenizer::analyzer::{Analyzer, AnalyzerConfig};
 
 use crate::database::{MainT, UpdateT};
 use crate::settings::{UpdateState, SettingsUpdate, RankingRule};
@@ -289,10 +290,28 @@ pub fn apply_synonyms_update(
 
     let main_store = index.main;
     let synonyms_store = index.synonyms;
+    let stop_words = index.main.stop_words_fst(writer)?.map_data(Cow::into_owned)?;
+    let analyzer = Analyzer::new(AnalyzerConfig::default_with_stopwords(&stop_words));
 
+    fn normalize<T: AsRef<[u8]>>(analyzer: &Analyzer<T>, text: &str) -> String {
+        analyzer.analyze(&text)
+            .tokens()
+            .fold(String::new(), |s, t| s + t.text())
+    }
+    
+    // normalize synonyms and reorder them creating a BTreeMap
+    let synonyms: BTreeMap<String, Vec<String>> = synonyms.into_iter().map( |(word, alternatives)| {
+        let word = normalize(&analyzer, &word);
+        let alternatives = alternatives.into_iter().map(|text| normalize(&analyzer, &text)).collect();
+
+        (word, alternatives)
+    }).collect();
+
+    // index synonyms,
+    // synyonyms have to be ordered by key before indexation
     let mut synonyms_builder = SetBuilder::memory();
     synonyms_store.clear(writer)?;
-    for (word, alternatives) in synonyms.clone() {
+    for (word, alternatives) in synonyms {
         synonyms_builder.insert(&word)?;
 
         let alternatives = {

meilisearch-error/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "meilisearch-error"
-version = "0.18.1"
+version = "0.19.0"
 authors = ["marin <postma.marin@protonmail.com>"]
 edition = "2018"
 

meilisearch-http/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "meilisearch-http"
 description = "MeiliSearch HTTP server"
-version = "0.18.1"
+version = "0.19.0"
 license = "MIT"
 authors = [
     "Quentin de Quelen <quentin@dequelen.me>",
@@ -32,9 +32,9 @@ http = "0.2.2"
 indexmap = { version = "1.6.1", features = ["serde-1"] }
 log = "0.4.11"
 main_error = "0.1.1"
-meilisearch-core = { path = "../meilisearch-core", version = "0.18.0" }
-meilisearch-error = { path = "../meilisearch-error", version = "0.18.1" }
-meilisearch-schema = { path = "../meilisearch-schema", version = "0.18.1" }
+meilisearch-core = { path = "../meilisearch-core", version = "0.19.0" }
+meilisearch-error = { path = "../meilisearch-error", version = "0.19.0" }
+meilisearch-schema = { path = "../meilisearch-schema", version = "0.19.0" }
 mime = "0.3.16"
 once_cell = "1.5.2"
 rand = "0.8.1"
@@ -51,6 +51,7 @@ tar = "0.4.30"
 tempfile = "3.1.0"
 tokio = { version = "0.2", features = ["macros"] }
 ureq = { version = "2.0.0", features = ["tls"], default-features = false }
+uuid = "0.8"
 walkdir = "2.3.1"
 whoami = "1.0.3"
 

meilisearch-http/src/dump.rs

@@ -128,15 +128,15 @@ fn import_index_v1(
         // push document in buffer
         values.push(document?);
         // if buffer is full, create and apply a batch, and clean buffer
-        if values.len() == document_batch_size { 
+        if values.len() == document_batch_size {
             let batch = std::mem::replace(&mut values, Vec::with_capacity(document_batch_size));
-            apply_documents_addition(write_txn, &index, batch)?;
+            apply_documents_addition(write_txn, &index, batch, None)?;
         }
     }
 
-    // apply documents remaining in the buffer 
-    if !values.is_empty() { 
-        apply_documents_addition(write_txn, &index, values)?;
+    // apply documents remaining in the buffer
+    if !values.is_empty() {
+        apply_documents_addition(write_txn, &index, values, None)?;
     }
 
     // sync index information: stats, updated_at, last_update
@@ -289,7 +289,6 @@ fn dump_index_documents(data: &web::Data<Data>, reader: &MainReader, dir_path: &
 /// Write error with a context.
 fn fail_dump_process<E: std::error::Error>(data: &web::Data<Data>, dump_info: DumpInfo, context: &str, error: E) {
         let error_message = format!("{}; {}", context, error);
-        
         error!("Something went wrong during dump process: {}", &error_message);
         data.set_current_dump_info(dump_info.with_error(Error::dump_failed(error_message).into()))
 }
@@ -405,7 +404,7 @@ pub fn init_dump_process(data: &web::Data<Data>, dumps_dir: &Path) -> Result<Dum
     let dumps_dir = dumps_dir.to_path_buf();
     let info_cloned = info.clone();
     // run dump process in a new thread
-    thread::spawn(move || 
+    thread::spawn(move ||
         dump_process(data, dumps_dir, info_cloned)
     );
 

meilisearch-http/src/helpers/compression.rs

@@ -1,19 +1,27 @@
 use flate2::Compression;
 use flate2::read::GzDecoder;
 use flate2::write::GzEncoder;
-use std::fs::{create_dir_all, File};
+use std::fs::{create_dir_all, rename, File};
 use std::path::Path;
 use tar::{Builder, Archive};
+use uuid::Uuid;
 
 use crate::error::Error;
 
 pub fn to_tar_gz(src: &Path, dest: &Path) -> Result<(), Error> {
-    let f = File::create(dest)?;
+    let file_name = format!(".{}", Uuid::new_v4().to_urn());
+    let p = dest.with_file_name(file_name);
+    let tmp_dest = p.as_path();
+
+    let f = File::create(tmp_dest)?;
     let gz_encoder = GzEncoder::new(f, Compression::default());
     let mut tar_encoder = Builder::new(gz_encoder);
     tar_encoder.append_dir_all(".", src)?;
     let gz_encoder = tar_encoder.into_inner()?;
     gz_encoder.finish()?;
+
+    rename(tmp_dest, dest)?;
+
     Ok(())
 }
 

meilisearch-http/src/routes/document.rs

@@ -132,7 +132,7 @@ async fn get_all_documents(
     let limit = params.limit.unwrap_or(20);
     let index_uid = &path.index_uid;
     let reader = data.db.main_read_txn()?;
-    
+
     let documents = get_all_documents_sync(
         &data,
         &reader,
@@ -145,15 +145,6 @@ async fn get_all_documents(
     Ok(HttpResponse::Ok().json(documents))
 }
 
-fn find_primary_key(document: &IndexMap<String, Value>) -> Option<String> {
-    for key in document.keys() {
-        if key.to_lowercase().contains("id") {
-            return Some(key.to_string());
-        }
-    }
-    None
-}
-
 #[derive(Deserialize)]
 #[serde(rename_all = "camelCase", deny_unknown_fields)]
 struct UpdateDocumentsQuery {
@@ -168,26 +159,6 @@ async fn update_multiple_documents(
     is_partial: bool,
 ) -> Result<HttpResponse, ResponseError> {
     let update_id = data.get_or_create_index(&path.index_uid, |index| {
-        let reader = data.db.main_read_txn()?;
-
-        let mut schema = index
-            .main
-            .schema(&reader)?
-            .ok_or(meilisearch_core::Error::SchemaMissing)?;
-
-        if schema.primary_key().is_none() {
-            let id = match &params.primary_key {
-                Some(id) => id.to_string(),
-                None => body
-                    .first()
-                    .and_then(find_primary_key)
-                    .ok_or(meilisearch_core::Error::MissingPrimaryKey)?,
-            };
-
-            schema.set_primary_key(&id).map_err(Error::bad_request)?;
-
-            data.db.main_write(|w| index.main.put_schema(w, &schema))?;
-        }
 
         let mut document_addition = if is_partial {
             index.documents_partial_addition()
@@ -195,6 +166,26 @@ async fn update_multiple_documents(
             index.documents_addition()
         };
 
+        // Return an early error if primary key is already set, otherwise, try to set it up in the
+        // update later.
+        let reader = data.db.main_read_txn()?;
+        let schema = index
+            .main
+            .schema(&reader)?
+            .ok_or(meilisearch_core::Error::SchemaMissing)?;
+
+        match (params.into_inner().primary_key, schema.primary_key()) {
+            (Some(key), None) => document_addition.set_primary_key(key),
+            (None, None) => {
+                let key = body
+                    .first()
+                    .and_then(find_primary_key)
+                    .ok_or(meilisearch_core::Error::MissingPrimaryKey)?;
+                document_addition.set_primary_key(key);
+            }
+            _ => ()
+        }
+
         for document in body.into_inner() {
             document_addition.update_document(document);
         }
@@ -204,6 +195,15 @@ async fn update_multiple_documents(
     return Ok(HttpResponse::Accepted().json(IndexUpdateResponse::with_id(update_id)));
 }
 
+fn find_primary_key(document: &IndexMap<String, Value>) -> Option<String> {
+    for key in document.keys() {
+        if key.to_lowercase().contains("id") {
+            return Some(key.to_string());
+        }
+    }
+    None
+}
+
 #[post("/indexes/{index_uid}/documents", wrap = "Authentication::Private")]
 async fn add_documents(
     data: web::Data<Data>,

meilisearch-http/tests/index_update.rs

@@ -94,13 +94,21 @@ async fn return_update_status_of_pushed_documents() {
     ];
 
     let mut update_ids = Vec::new();
-    
+    let mut bodies = bodies.into_iter();
+
     let url = "/indexes/test/documents?primaryKey=title";
+    let (response, status_code) = server.post_request(&url, bodies.next().unwrap()).await;
+    assert_eq!(status_code, 202);
+    let update_id = response["updateId"].as_u64().unwrap();
+    update_ids.push(update_id);
+    server.wait_update_id(update_id).await;
+
+    let url = "/indexes/test/documents";
     for body in bodies {
-      let (response, status_code) = server.post_request(&url, body).await;
-      assert_eq!(status_code, 202);
-      let update_id = response["updateId"].as_u64().unwrap();
-      update_ids.push(update_id);
+        let (response, status_code) = server.post_request(&url, body).await;
+        assert_eq!(status_code, 202);
+        let update_id = response["updateId"].as_u64().unwrap();
+        update_ids.push(update_id);
     }
 
     // 2. Fetch the status of index.
@@ -173,7 +181,7 @@ async fn should_return_existing_update() {
     let (response, status_code) = server.create_index(body).await;
     assert_eq!(status_code, 201);
     assert_eq!(response["primaryKey"], json!(null));
-    
+
     let body = json!([{
         "title": "Test",
         "comment": "comment test"

meilisearch-http/tests/search.rs

@@ -1945,3 +1945,32 @@ async fn test_filter_nb_hits_search_normal() {
     println!("result: {}", response);
     assert_eq!(response["nbHits"], 1);
 }
+
+#[actix_rt::test]
+async fn test_max_word_query() {
+    use meilisearch_core::MAX_QUERY_LEN;
+
+    let mut server = common::Server::with_uid("test");
+    let body = json!({
+        "uid": "test",
+        "primaryKey": "id",
+    });
+    server.create_index(body).await;
+    let documents = json!([
+        {"id": 1, "value": "1 2 3 4 5 6 7 8 9 10 11"},
+        {"id": 2, "value": "1 2 3 4 5 6 7 8 9 10"}]
+    );
+    server.add_or_update_multiple_documents(documents).await;
+
+    // We want to create a request where the 11 will be ignored. We have 2 documents, where a query
+    // with only one should return both, but a query with 1 and 11 should return only the first.
+    // This is how we know that outstanding query words have been ignored
+    let query = (0..MAX_QUERY_LEN)
+        .map(|_| "1")
+        .chain(std::iter::once("11"))
+        .fold(String::new(), |s, w| s + " " + w);
+    let (response, _) = server.search_post(json!({"q": query})).await;
+    assert_eq!(response["nbHits"], 2);
+    let (response, _) = server.search_post(json!({"q": "1 11"})).await;
+    assert_eq!(response["nbHits"], 1);
+}

meilisearch-http/tests/search_settings.rs

@@ -167,6 +167,89 @@ async fn search_with_settings_stop_words() {
 async fn search_with_settings_synonyms() {
     let mut server = common::Server::test_server().await;
 
+    let config = json!({
+      "rankingRules": [
+        "typo",
+        "words",
+        "proximity",
+        "attribute",
+        "wordsPosition",
+        "desc(age)",
+        "exactness",
+        "desc(balance)"
+      ],
+      "distinctAttribute": null,
+      "searchableAttributes": [
+        "name",
+        "age",
+        "color",
+        "gender",
+        "email",
+        "address",
+        "about"
+      ],
+      "displayedAttributes": [
+        "name",
+        "age",
+        "gender",
+        "color",
+        "email",
+        "phone",
+        "address",
+        "balance"
+      ],
+      "stopWords": null,
+      "synonyms": {
+          "Application": [
+              "Exercitation"
+          ]
+      },
+    });
+
+    server.update_all_settings(config).await;
+
+    let query = "q=application&limit=3";
+    let expect = json!([
+      {
+        "balance": "$1,921.58",
+        "age": 31,
+        "color": "Green",
+        "name": "Harper Carson",
+        "gender": "male",
+        "email": "harpercarson@chorizon.com",
+        "phone": "+1 (912) 430-3243",
+        "address": "883 Dennett Place, Knowlton, New Mexico, 9219"
+      },
+      {
+        "balance": "$1,706.13",
+        "age": 27,
+        "color": "Green",
+        "name": "Cherry Orr",
+        "gender": "female",
+        "email": "cherryorr@chorizon.com",
+        "phone": "+1 (995) 479-3174",
+        "address": "442 Beverly Road, Ventress, New Mexico, 3361"
+      },
+      {
+        "balance": "$1,476.39",
+        "age": 28,
+        "color": "brown",
+        "name": "Maureen Dale",
+        "gender": "female",
+        "email": "maureendale@chorizon.com",
+        "phone": "+1 (984) 538-3684",
+        "address": "817 Newton Street, Bannock, Wyoming, 1468"
+      }
+    ]);
+
+    let (response, _status_code) = server.search_get(query).await;
+    assert_json_eq!(expect, response["hits"].clone(), ordered: false);
+}
+
+#[actix_rt::test]
+async fn search_with_settings_normalized_synonyms() {
+    let mut server = common::Server::test_server().await;
+
     let config = json!({
       "rankingRules": [
         "typo",

meilisearch-http/tests/settings.rs

@@ -171,6 +171,8 @@ async fn write_all_and_update() {
         "synonyms": {
             "road": ["street", "avenue"],
             "street": ["avenue"],
+            "HP": ["Harry Potter"],
+            "Harry Potter": ["HP"]
         },
         "attributesForFaceting": ["title"],
     });
@@ -208,6 +210,8 @@ async fn write_all_and_update() {
         "synonyms": {
             "road": ["street", "avenue"],
             "street": ["avenue"],
+            "hp": ["harry potter"],
+            "harry potter": ["hp"]
         },
         "attributesForFaceting": ["title"],
     });

meilisearch-schema/Cargo.toml

@@ -1,13 +1,13 @@
 [package]
 name = "meilisearch-schema"
-version = "0.18.1"
+version = "0.19.0"
 license = "MIT"
 authors = ["Kerollmops <renault.cle@gmail.com>"]
 edition = "2018"
 
 [dependencies]
 indexmap = { version = "1.6.1", features = ["serde-1"] }
-meilisearch-error = { path = "../meilisearch-error", version = "0.18.1" }
+meilisearch-error = { path = "../meilisearch-error", version = "0.19.0" }
 serde = { version = "1.0.118", features = ["derive"] }
 serde_json = { version = "1.0.61", features = ["preserve_order"] }
 zerocopy = "0.3.0"

meilisearch-tokenizer/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "meilisearch-tokenizer"
-version = "0.18.1"
+version = "0.19.0"
 license = "MIT"
 authors = ["Kerollmops <renault.cle@gmail.com>"]
 edition = "2018"

meilisearch-types/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "meilisearch-types"
-version = "0.18.1"
+version = "0.19.0"
 license = "MIT"
 authors = ["Clément Renault <renault.cle@gmail.com>"]
 edition = "2018"