Merge #4804

4804: Implements the experimental contains filter operator r=irevoire a=irevoire # Pull Request Related PRD: (private link) https://www.notion.so/meilisearch/Contains-Like-Filter-Operator-0d8ad53c6761466f913432eb1d843f1e Public usage page: https://meilisearch.notion.site/Contains-filter-operator-usage-3e7421b0aacf45f48ab09abe259a1de6 ## Related issue Fixes https://github.com/meilisearch/meilisearch/issues/3613 ## What does this PR do? - Extract the contains operator from this PR: https://github.com/meilisearch/meilisearch/pull/3751 - Gate it behind a feature flag - Add tests Co-authored-by: Tamo <tamo@meilisearch.com>
2025-07-03 11:57:07 +02:00 · 2024-07-17 15:47:11 +00:00 · 2024-07-17 15:47:11 +00:00 · ea73615abf
commit ea73615abf
parent 8f416e8f34 02c61eabfa
34 changed files with 487 additions and 121 deletions
--- a/meilisearch/tests/common/mod.rs
+++ b/meilisearch/tests/common/mod.rs
@ -26,6 +26,15 @@ impl Value {
            panic!("Didn't find any task id in: {self}");
        }
    }
+
+    // Panic if the json doesn't contain the `status` field set to "succeeded"
+    #[track_caller]
+    pub fn succeeded(&self) -> &Self {
+        if self["status"] != serde_json::Value::String(String::from("succeeded")) {
+            panic!("Called succeeded on {}", serde_json::to_string_pretty(&self.0).unwrap());
+        }
+        self
+    }
 }

 impl From<serde_json::Value> for Value {
--- a/meilisearch/tests/documents/errors.rs
+++ b/meilisearch/tests/documents/errors.rs
@ -168,7 +168,7 @@ async fn get_all_documents_bad_filter() {
    snapshot!(code, @"400 Bad Request");
    snapshot!(json_string!(response), @r###"
    {
-      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `doggo`.\n1:6 doggo",
+      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `doggo`.\n1:6 doggo",
      "code": "invalid_document_filter",
      "type": "invalid_request",
      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@ -569,7 +569,7 @@ async fn delete_document_by_filter() {
    snapshot!(code, @"400 Bad Request");
    snapshot!(json_string!(response), @r###"
    {
-      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `hello`.\n1:6 hello",
+      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `hello`.\n1:6 hello",
      "code": "invalid_document_filter",
      "type": "invalid_request",
      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
@ -776,7 +776,7 @@ async fn fetch_document_by_filter() {
    snapshot!(code, @"400 Bad Request");
    snapshot!(response, @r###"
    {
-      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `cool doggo`.\n1:11 cool doggo",
+      "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `cool doggo`.\n1:11 cool doggo",
      "code": "invalid_document_filter",
      "type": "invalid_request",
      "link": "https://docs.meilisearch.com/errors#invalid_document_filter"
--- a/meilisearch/tests/documents/get_documents.rs
+++ b/meilisearch/tests/documents/get_documents.rs
@ -536,7 +536,8 @@ async fn get_document_with_vectors() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

--- a/meilisearch/tests/dumps/mod.rs
+++ b/meilisearch/tests/dumps/mod.rs
@ -1860,7 +1860,8 @@ async fn import_dump_v6_containing_experimental_features() {
      "vectorStore": false,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -1954,7 +1955,8 @@ async fn generate_and_import_dump_containing_vectors() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);
    let index = server.index("pets");
@ -2025,7 +2027,8 @@ async fn generate_and_import_dump_containing_vectors() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

--- a/meilisearch/tests/features/mod.rs
+++ b/meilisearch/tests/features/mod.rs
@ -21,7 +21,8 @@ async fn experimental_features() {
      "vectorStore": false,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -33,7 +34,8 @@ async fn experimental_features() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -45,7 +47,8 @@ async fn experimental_features() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -58,7 +61,8 @@ async fn experimental_features() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -71,7 +75,8 @@ async fn experimental_features() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);
 }
@ -91,7 +96,8 @@ async fn experimental_feature_metrics() {
      "vectorStore": false,
      "metrics": true,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -146,7 +152,7 @@ async fn errors() {
    meili_snap::snapshot!(code, @"400 Bad Request");
    meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
    {
-      "message": "Unknown field `NotAFeature`: expected one of `vectorStore`, `metrics`, `logsRoute`, `editDocumentsByFunction`",
+      "message": "Unknown field `NotAFeature`: expected one of `vectorStore`, `metrics`, `logsRoute`, `editDocumentsByFunction`, `containsFilter`",
      "code": "bad_request",
      "type": "invalid_request",
      "link": "https://docs.meilisearch.com/errors#bad_request"
--- a/meilisearch/tests/search/errors.rs
+++ b/meilisearch/tests/search/errors.rs
@ -645,19 +645,20 @@ async fn filter_invalid_syntax_object() {
    index.update_settings(json!({"filterableAttributes": ["title"]})).await;

    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.add_documents(documents, None).await;
+    index.wait_task(task.uid()).await;

-    let expected_response = json!({
-        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
-        "code": "invalid_search_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
-    });
    index
        .search(json!({"filter": "title & Glass"}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
+            snapshot!(response, @r###"
+            {
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "code": "invalid_search_filter",
+              "type": "invalid_request",
+              "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
+            }
+            "###);
+            snapshot!(code, @"400 Bad Request");
        })
        .await;
 }
@ -670,19 +671,20 @@ async fn filter_invalid_syntax_array() {
    index.update_settings(json!({"filterableAttributes": ["title"]})).await;

    let documents = DOCUMENTS.clone();
-    index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    let (task, _code) = index.add_documents(documents, None).await;
+    index.wait_task(task.uid()).await;

-    let expected_response = json!({
-        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
-        "code": "invalid_search_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
-    });
    index
        .search(json!({"filter": ["title & Glass"]}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
+            snapshot!(response, @r###"
+            {
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "code": "invalid_search_filter",
+              "type": "invalid_request",
+              "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
+            }
+            "###);
+            snapshot!(code, @"400 Bad Request");
        })
        .await;
 }
@ -1203,3 +1205,68 @@ async fn distinct_at_search_time() {
    }
    "###);
 }
+
+#[actix_rt::test]
+async fn search_with_contains_without_enabling_the_feature() {
+    // Since a filter is deserialized as a json Value it will never fail to deserialize.
+    // Thus the error message is not generated by deserr but written by us.
+    let server = Server::new().await;
+    let index = server.index("doggo");
+    // Also, to trigger the error message we need to effectively create the index or else it'll throw an
+    // index does not exists error.
+    let (task, _code) = index.create(None).await;
+    server.wait_task(task.uid()).await.succeeded();
+
+    index
+        .search(json!({ "filter": "doggo CONTAINS kefir" }), |response, code| {
+            snapshot!(code, @"400 Bad Request");
+            snapshot!(json_string!(response), @r###"
+            {
+              "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+              "code": "feature_not_enabled",
+              "type": "invalid_request",
+              "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+            }
+            "###);
+        })
+        .await;
+    index
+        .search(json!({ "filter": "doggo != echo AND doggo CONTAINS kefir" }), |response, code| {
+            snapshot!(code, @"400 Bad Request");
+            snapshot!(json_string!(response), @r###"
+            {
+              "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n25:33 doggo != echo AND doggo CONTAINS kefir",
+              "code": "feature_not_enabled",
+              "type": "invalid_request",
+              "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+            }
+            "###);
+        })
+        .await;
+
+    // For the post search we can also use the arrays syntaxes
+    let (response, code) =
+        index.search_post(json!({ "filter": ["doggo != echo", "doggo CONTAINS kefir"] })).await;
+
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+      "code": "feature_not_enabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+    }
+    "###);
+    let (response, code) =
+        index.search_post(json!({ "filter": ["doggo != echo", ["doggo CONTAINS kefir"]] })).await;
+
+    snapshot!(code, @"400 Bad Request");
+    snapshot!(json_string!(response), @r###"
+    {
+      "message": "Using `CONTAINS` in a filter requires enabling the `contains filter` experimental feature. See https://github.com/orgs/meilisearch/discussions/763\n7:15 doggo CONTAINS kefir",
+      "code": "feature_not_enabled",
+      "type": "invalid_request",
+      "link": "https://docs.meilisearch.com/errors#feature_not_enabled"
+    }
+    "###);
+}
--- a/meilisearch/tests/search/hybrid.rs
+++ b/meilisearch/tests/search/hybrid.rs
@ -19,7 +19,8 @@ async fn index_with_documents_user_provided<'a>(
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -48,7 +49,8 @@ async fn index_with_documents_hf<'a>(server: &'a Server, documents: &Value) -> I
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

--- a/meilisearch/tests/search/mod.rs
+++ b/meilisearch/tests/search/mod.rs
@ -13,9 +13,11 @@ mod pagination;
 mod restrict_searchable;
 mod search_queue;

+use meilisearch::Opt;
 use once_cell::sync::Lazy;
+use tempfile::TempDir;

-use crate::common::{Server, Value};
+use crate::common::{default_settings, Server, Value};
 use crate::json;

 static DOCUMENTS: Lazy<Value> = Lazy::new(|| {
@ -576,6 +578,32 @@ async fn search_with_filter_array_notation() {
    assert_eq!(response["hits"].as_array().unwrap().len(), 3);
 }

+#[actix_rt::test]
+async fn search_with_contains_filter() {
+    let temp = TempDir::new().unwrap();
+    let server = Server::new_with_options(Opt {
+        experimental_contains_filter: true,
+        ..default_settings(temp.path())
+    })
+    .await
+    .unwrap();
+    let index = server.index("movies");
+
+    index.update_settings(json!({"filterableAttributes": ["title"]})).await;
+
+    let documents = DOCUMENTS.clone();
+    let (request, _code) = index.add_documents(documents, None).await;
+    index.wait_task(request.uid()).await.succeeded();
+
+    let (response, code) = index
+        .search_post(json!({
+            "filter": "title CONTAINS cap"
+        }))
+        .await;
+    assert_eq!(code, 200, "{}", response);
+    assert_eq!(response["hits"].as_array().unwrap().len(), 2);
+}
+
 #[actix_rt::test]
 async fn search_with_sort_on_numbers() {
    let server = Server::new().await;
--- a/meilisearch/tests/settings/get_settings.rs
+++ b/meilisearch/tests/settings/get_settings.rs
@ -99,7 +99,8 @@ async fn secrets_are_hidden_in_settings() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

--- a/meilisearch/tests/similar/errors.rs
+++ b/meilisearch/tests/similar/errors.rs
@ -360,16 +360,17 @@ async fn filter_invalid_syntax_object() {
    snapshot!(code, @"202 Accepted");
    index.wait_task(value.uid()).await;

-    let expected_response = json!({
-        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
    index
        .similar(json!({"id": 287947, "filter": "title & Glass"}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
+            snapshot!(response, @r###"
+            {
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "code": "invalid_similar_filter",
+              "type": "invalid_request",
+              "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+            }
+            "###);
+            snapshot!(code, @"400 Bad Request");
        })
        .await;
 }
@ -398,16 +399,17 @@ async fn filter_invalid_syntax_array() {
    snapshot!(code, @"202 Accepted");
    index.wait_task(value.uid()).await;

-    let expected_response = json!({
-        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
-        "code": "invalid_similar_filter",
-        "type": "invalid_request",
-        "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
-    });
    index
        .similar(json!({"id": 287947, "filter": ["title & Glass"]}), |response, code| {
-            assert_eq!(response, expected_response);
-            assert_eq!(code, 400);
+            snapshot!(response, @r###"
+            {
+              "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `NOT CONTAINS`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+              "code": "invalid_similar_filter",
+              "type": "invalid_request",
+              "link": "https://docs.meilisearch.com/errors#invalid_similar_filter"
+            }
+            "###);
+            snapshot!(code, @"400 Bad Request");
        })
        .await;
 }
--- a/meilisearch/tests/similar/mod.rs
+++ b/meilisearch/tests/similar/mod.rs
@ -56,7 +56,8 @@ async fn basic() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -246,7 +247,8 @@ async fn ranking_score_threshold() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -526,7 +528,8 @@ async fn filter() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -654,7 +657,8 @@ async fn limit_and_offset() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

--- a/meilisearch/tests/vector/mod.rs
+++ b/meilisearch/tests/vector/mod.rs
@ -17,7 +17,8 @@ async fn add_remove_user_provided() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -171,7 +172,8 @@ async fn generate_default_user_provided_documents(server: &Server) -> Index {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

@ -622,7 +624,8 @@ async fn add_remove_one_vector_4588() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);

--- a/meilisearch/tests/vector/settings.rs
+++ b/meilisearch/tests/vector/settings.rs
@ -15,7 +15,8 @@ async fn update_embedder() {
      "vectorStore": true,
      "metrics": false,
      "logsRoute": false,
-      "editDocumentsByFunction": false
+      "editDocumentsByFunction": false,
+      "containsFilter": false
    }
    "###);