Merge branch 'main' into change-matches-position-phrase-search

dump/src/reader/v4/meta.rs

@@ -74,7 +74,8 @@ impl Display for IndexUidFormatError {
             f,
             "invalid index uid `{}`, the uid must be an integer \
             or a string containing only alphanumeric characters \
-            a-z A-Z 0-9, hyphens - and underscores _.",
+            a-z A-Z 0-9, hyphens - and underscores _, \
+            and can not be more than 400 bytes.",
             self.invalid_uid,
         )
     }

dump/src/reader/v5/meta.rs

@@ -74,7 +74,8 @@ impl Display for IndexUidFormatError {
             f,
             "invalid index uid `{}`, the uid must be an integer \
             or a string containing only alphanumeric characters \
-            a-z A-Z 0-9, hyphens - and underscores _.",
+            a-z A-Z 0-9, hyphens - and underscores _, \
+            and can not be more than 400 bytes.",
             self.invalid_uid,
         )
     }

index-scheduler/src/error.rs

@@ -101,7 +101,7 @@ pub enum Error {
     )]
     InvalidTaskCanceledBy { canceled_by: String },
     #[error(
-        "{index_uid} is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_)."
+        "{index_uid} is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes."
     )]
     InvalidIndexUid { index_uid: String },
     #[error("Task `{0}` not found.")]

meilisearch-types/src/error.rs

@@ -543,7 +543,8 @@ impl fmt::Display for deserr_codes::InvalidSimilarId {
             f,
             "the value of `id` is invalid. \
             A document identifier can be of type integer or string, \
-            only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."
+            only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), \
+            and can not be more than 512 bytes."
         )
     }
 }

meilisearch-types/src/index_uid.rs

@@ -88,7 +88,8 @@ impl fmt::Display for IndexUidFormatError {
             f,
             "`{}` is not a valid index uid. Index uid can be an \
             integer or a string containing only alphanumeric \
-            characters, hyphens (-) and underscores (_).",
+            characters, hyphens (-) and underscores (_), \
+            and can not be more than 512 bytes.",
             self.invalid_uid,
         )
     }

meilisearch/src/routes/tasks.rs

@@ -616,7 +616,7 @@ mod tests {
             let err = deserr_query_params::<TaskDeletionOrCancelationQuery>(params).unwrap_err();
             snapshot!(meili_snap::json_string!(err), @r###"
             {
-              "message": "Invalid value in parameter `indexUids[1]`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+              "message": "Invalid value in parameter `indexUids[1]`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
               "code": "invalid_index_uid",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -628,7 +628,7 @@ mod tests {
             let err = deserr_query_params::<TaskDeletionOrCancelationQuery>(params).unwrap_err();
             snapshot!(meili_snap::json_string!(err), @r###"
             {
-              "message": "Invalid value in parameter `indexUids`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+              "message": "Invalid value in parameter `indexUids`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
               "code": "invalid_index_uid",
               "type": "invalid_request",
               "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

meilisearch/tests/documents/add_documents.rs

@@ -1023,7 +1023,7 @@ async fn error_document_add_create_index_bad_uid() {
     snapshot!(json_string!(response),
         @r###"
     {
-      "message": "`883  fj!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "`883  fj!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -1280,7 +1280,7 @@ async fn error_add_documents_bad_document_id() {
         "indexedDocuments": 0
       },
       "error": {
-        "message": "Document identifier `\"foo & bar\"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_).",
+        "message": "Document identifier `\"foo & bar\"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
         "code": "invalid_document_id",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_id"

meilisearch/tests/documents/update_documents.rs

@@ -11,7 +11,7 @@ async fn error_document_update_create_index_bad_uid() {
     let (response, code) = index.update_documents(json!([{"id": 1}]), None).await;
 
     let expected_response = json!({
-        "message": "`883  fj!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+        "message": "`883  fj!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
         "code": "invalid_index_uid",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -173,7 +173,7 @@ async fn error_update_documents_bad_document_id() {
     assert_eq!(
         response["error"]["message"],
         json!(
-            r#"Document identifier `"foo & bar"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_)."#
+            r#"Document identifier `"foo & bar"` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes."#
         )
     );
     assert_eq!(response["error"]["code"], json!("invalid_document_id"));

meilisearch/tests/index/create_index.rs

@@ -125,11 +125,11 @@ async fn create_index_with_primary_key() {
 
 #[actix_rt::test]
 async fn create_index_with_invalid_primary_key() {
-    let document = json!([ { "id": 2, "title": "Pride and Prejudice" } ]);
+    let documents = json!([ { "id": 2, "title": "Pride and Prejudice" } ]);
 
     let server = Server::new().await;
     let index = server.index("movies");
-    let (_response, code) = index.add_documents(document, Some("title")).await;
+    let (_response, code) = index.add_documents(documents, Some("title")).await;
     assert_eq!(code, 202);
 
     index.wait_task(0).await;
@@ -137,6 +137,17 @@ async fn create_index_with_invalid_primary_key() {
     let (response, code) = index.get().await;
     assert_eq!(code, 200);
     assert_eq!(response["primaryKey"], json!(null));
+
+    let documents = json!([ { "id": "e".repeat(513) } ]);
+
+    let (_response, code) = index.add_documents(documents, Some("id")).await;
+    assert_eq!(code, 202);
+
+    index.wait_task(1).await;
+
+    let (response, code) = index.get().await;
+    assert_eq!(code, 200);
+    assert_eq!(response["primaryKey"], json!(null));
 }
 
 #[actix_rt::test]
@@ -192,7 +203,7 @@ async fn error_create_with_invalid_index_uid() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value at `.uid`: `test test#!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value at `.uid`: `test test#!` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

meilisearch/tests/index/errors.rs

@@ -75,7 +75,7 @@ async fn create_index_bad_uid() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value at `.uid`: `the best doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value at `.uid`: `the best doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -136,7 +136,7 @@ async fn get_index_bad_uid() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "`the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "`the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -232,7 +232,7 @@ async fn update_index_bad_uid() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "`the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "`the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -247,7 +247,7 @@ async fn delete_index_bad_uid() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "`the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "`the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

meilisearch/tests/index/get_index.rs

@@ -186,7 +186,7 @@ async fn get_invalid_index_uid() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "`this is not a valid index name` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "`this is not a valid index name` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

meilisearch/tests/search/multi.rs

@@ -412,7 +412,7 @@ async fn simple_search_illegal_index_uid() {
     snapshot!(code, @"400 Bad Request");
     insta::assert_json_snapshot!(response, @r###"
     {
-      "message": "Invalid value at `.queries[0].indexUid`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value at `.queries[0].indexUid`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -437,7 +437,7 @@ async fn federation_search_illegal_index_uid() {
     snapshot!(code, @"400 Bad Request");
     insta::assert_json_snapshot!(response, @r###"
     {
-      "message": "Invalid value at `.queries[0].indexUid`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value at `.queries[0].indexUid`: `hé` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

meilisearch/tests/settings/get_settings.rs

@@ -330,7 +330,7 @@ async fn error_update_setting_unexisting_index_invalid_uid() {
     meili_snap::snapshot!(code, @"400 Bad Request");
     meili_snap::snapshot!(meili_snap::json_string!(response), @r###"
     {
-      "message": "`test##!  ` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "`test##!  ` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

meilisearch/tests/similar/errors.rs

@@ -79,7 +79,7 @@ async fn similar_bad_id() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_).",
+      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_similar_id",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_similar_id"
@@ -172,7 +172,7 @@ async fn similar_invalid_id() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_).",
+      "message": "Invalid value at `.id`: the value of `id` is invalid. A document identifier can be of type integer or string, only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_similar_id",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_similar_id"

meilisearch/tests/tasks/errors.rs

@@ -173,7 +173,7 @@ async fn task_bad_index_uids() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `indexUids`: `the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value in parameter `indexUids`: `the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -184,7 +184,7 @@ async fn task_bad_index_uids() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `indexUids`: `the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value in parameter `indexUids`: `the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"
@@ -195,7 +195,7 @@ async fn task_bad_index_uids() {
     snapshot!(code, @"400 Bad Request");
     snapshot!(json_string!(response), @r###"
     {
-      "message": "Invalid value in parameter `indexUids`: `the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_).",
+      "message": "Invalid value in parameter `indexUids`: `the good doggo` is not a valid index uid. Index uid can be an integer or a string containing only alphanumeric characters, hyphens (-) and underscores (_), and can not be more than 512 bytes.",
       "code": "invalid_index_uid",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_index_uid"

milli/src/documents/primary_key.rs

@@ -150,12 +150,13 @@ fn starts_with(selector: &str, key: &str) -> bool {
 // FIXME: move to a DocumentId struct
 
 fn validate_document_id(document_id: &str) -> Option<&str> {
-    if !document_id.is_empty()
+    if document_id.is_empty()
-        && document_id.chars().all(|c| matches!(c, 'a'..='z' | 'A'..='Z' | '0'..='9' | '-' | '_'))
+        || document_id.len() > 512
+        || !document_id.chars().all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_')
     {
-        Some(document_id)
-    } else {
         None
+    } else {
+        Some(document_id)
     }
 }
 
@@ -166,6 +167,7 @@ pub fn validate_document_id_value(document_id: Value) -> StdResult<String, UserE
             Some(s) => Ok(s.to_string()),
             None => Err(UserError::InvalidDocumentId { document_id: Value::String(string) }),
         },
+        // a `u64` or `i64` cannot be more than 512 bytes once converted to a string
         Value::Number(number) if !number.is_f64() => Ok(number.to_string()),
         content => Err(UserError::InvalidDocumentId { document_id: content }),
     }

milli/src/error.rs

@@ -106,7 +106,8 @@ pub enum UserError {
     #[error(
         "Document identifier `{}` is invalid. \
 A document identifier can be of type integer or string, \
-only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_).", .document_id.to_string()
+only composed of alphanumeric characters (a-z A-Z 0-9), hyphens (-) and underscores (_), \
+and can not be more than 512 bytes.", .document_id.to_string()
     )]
     InvalidDocumentId { document_id: Value },
     #[error("Invalid facet distribution, {}", format_invalid_filter_distribution(.invalid_facets_name, .valid_facets_name))]