Merge #5144

5144: Exactly 512 bytes docid fails r=Kerollmops a=dureuill

# Pull Request

## Related issue
Fixes #5050 

## What does this PR do?
- Return a user error rather than an internal one for docids of exactly 512 bytes
- Fix up error message to indicate that exactly 512 bytes long docids are not supported.
- Fix up error message to reflect that index uids are actually limited to 400 bytes in length

## Impact

- Impacts docs: 
    - update [this paragraph](https://www.meilisearch.com/docs/learn/resources/known_limitations#length-of-primary-key-values) to say 511 bytes instead of 512 

Co-authored-by: Louis Dureuil <louis@meilisearch.com>

crates/index-scheduler/src/error.rs

@@ -1,12 +1,13 @@
 use std::fmt::Display;
 
-use crate::TaskId;
 use meilisearch_types::batches::BatchId;
 use meilisearch_types::error::{Code, ErrorCode};
 use meilisearch_types::tasks::{Kind, Status};
 use meilisearch_types::{heed, milli};
 use thiserror::Error;
 
+use crate::TaskId;
+
 #[derive(Copy, Clone, Debug, PartialEq, Eq)]
 pub enum DateField {
     BeforeEnqueuedAt,
@@ -103,7 +104,7 @@ 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 (_), and can not be more than 512 bytes."
+        "{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 400 bytes."
     )]
     InvalidIndexUid { index_uid: String },
     #[error("Task `{0}` not found.")]

crates/meilisearch-types/src/error.rs

@@ -550,7 +550,7 @@ impl fmt::Display for deserr_codes::InvalidSimilarId {
             "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."
+            and can not be more than 511 bytes."
         )
     }
 }

crates/meilisearch/tests/documents/add_documents.rs

@@ -1264,15 +1264,18 @@ async fn error_add_documents_bad_document_id() {
     let server = Server::new().await;
     let index = server.index("test");
     index.create(Some("docid")).await;
+
+    // unsupported characters
+
     let documents = json!([
         {
             "docid": "foo & bar",
             "content": "foobar"
         }
     ]);
-    index.add_documents(documents, None).await;
+    let (value, _code) = index.add_documents(documents, None).await;
-    index.wait_task(1).await;
+    index.wait_task(value.uid()).await;
-    let (response, code) = index.get_task(1).await;
+    let (response, code) = index.get_task(value.uid()).await;
     snapshot!(code, @"200 OK");
     snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
         @r###"
@@ -1288,7 +1291,81 @@ 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 (_), and can not be more than 512 bytes.",
+        "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 511 bytes.",
+        "code": "invalid_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_document_id"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    // More than 512 bytes
+    let documents = json!([
+        {
+            "docid": "a".repeat(600),
+            "content": "foobar"
+        }
+    ]);
+    let (value, _code) = index.add_documents(documents, None).await;
+    index.wait_task(value.uid()).await;
+    let (response, code) = index.get_task(value.uid()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
+      @r###"
+    {
+      "uid": 2,
+      "batchUid": 2,
+      "indexUid": "test",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Document identifier `\"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\"` 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 511 bytes.",
+        "code": "invalid_document_id",
+        "type": "invalid_request",
+        "link": "https://docs.meilisearch.com/errors#invalid_document_id"
+      },
+      "duration": "[duration]",
+      "enqueuedAt": "[date]",
+      "startedAt": "[date]",
+      "finishedAt": "[date]"
+    }
+    "###);
+
+    // Exactly 512 bytes
+    let documents = json!([
+        {
+            "docid": "a".repeat(512),
+            "content": "foobar"
+        }
+    ]);
+    let (value, _code) = index.add_documents(documents, None).await;
+    index.wait_task(value.uid()).await;
+    let (response, code) = index.get_task(value.uid()).await;
+    snapshot!(code, @"200 OK");
+    snapshot!(json_string!(response, { ".duration" => "[duration]", ".enqueuedAt" => "[date]", ".startedAt" => "[date]", ".finishedAt" => "[date]" }),
+    @r###"
+    {
+      "uid": 3,
+      "batchUid": 3,
+      "indexUid": "test",
+      "status": "failed",
+      "type": "documentAdditionOrUpdate",
+      "canceledBy": null,
+      "details": {
+        "receivedDocuments": 1,
+        "indexedDocuments": 0
+      },
+      "error": {
+        "message": "Document identifier `\"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa\"` 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 511 bytes.",
         "code": "invalid_document_id",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_document_id"

crates/meilisearch/tests/documents/update_documents.rs

@@ -172,7 +172,7 @@ 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 (_), and can not be more than 512 bytes."#
+            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 511 bytes."#
         )
     );
     assert_eq!(response["error"]["code"], json!("invalid_document_id"));

crates/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 (_), and can not be more than 512 bytes.",
+      "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 511 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 (_), and can not be more than 512 bytes.",
+      "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 511 bytes.",
       "code": "invalid_similar_id",
       "type": "invalid_request",
       "link": "https://docs.meilisearch.com/errors#invalid_similar_id"

crates/milli/src/documents/primary_key.rs

@@ -280,7 +280,7 @@ fn starts_with(selector: &str, key: &str) -> bool {
 
 pub fn validate_document_id_str(document_id: &str) -> Option<&str> {
     if document_id.is_empty()
-        || document_id.len() > 512
+        || document_id.len() >= 512
         || !document_id.chars().all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_')
     {
         None

crates/milli/src/error.rs

@@ -114,7 +114,7 @@ pub enum UserError {
         "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 (_), \
-and can not be more than 512 bytes.", .document_id.to_string()
+and can not be more than 511 bytes.", .document_id.to_string()
     )]
     InvalidDocumentId { document_id: Value },
     #[error("Invalid facet distribution, {}", format_invalid_filter_distribution(.invalid_facets_name, .valid_facets_name))]