Merge #2207

2207: Fix: avoid embedding the user input into the error response. r=Kerollmops a=CNLHC

# Pull Request

## What does this PR do?
Fix #2107. 

The problem is meilisearch embeds the user input to the error message. 

The reason for this problem is `milli` throws a `serde_json: Error` whose `Display` implementation will do this embedding.  

I tried to solve this problem in this PR by manually implementing the `Display` trait for `DocumentFormatError` instead of deriving automatically.

<!-- Please link the issue you're trying to fix with this PR, if none then please create an issue first. -->

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Thank you so much for contributing to Meilisearch!


Co-authored-by: Liu Hancheng <cn_lhc@qq.com>
Co-authored-by: LiuHanCheng <2463765697@qq.com>

meilisearch-http/tests/documents/add_documents.rs

@@ -212,7 +212,7 @@ async fn error_add_malformed_csv_documents() {
     assert_eq!(
         response["message"],
         json!(
-            r#"The `csv` payload provided is malformed. `CSV error: record 1 (line: 2, byte: 12): found record with 3 fields, but the previous record has 2 fields`."#
+            r#"The `csv` payload provided is malformed: `CSV error: record 1 (line: 2, byte: 12): found record with 3 fields, but the previous record has 2 fields`."#
         )
     );
     assert_eq!(response["code"], json!("malformed_payload"));
@@ -236,7 +236,7 @@ async fn error_add_malformed_csv_documents() {
     assert_eq!(
         response["message"],
         json!(
-            r#"The `csv` payload provided is malformed. `CSV error: record 1 (line: 2, byte: 12): found record with 3 fields, but the previous record has 2 fields`."#
+            r#"The `csv` payload provided is malformed: `CSV error: record 1 (line: 2, byte: 12): found record with 3 fields, but the previous record has 2 fields`."#
         )
     );
     assert_eq!(response["code"], json!("malformed_payload"));
@@ -307,6 +307,58 @@ async fn error_add_malformed_json_documents() {
         response["link"],
         json!("https://docs.meilisearch.com/errors#malformed_payload")
     );
+
+    // truncate
+
+    // length = 100
+    let long = "0123456789".repeat(10);
+
+    let document = format!("\"{}\"", long);
+    let req = test::TestRequest::put()
+        .uri("/indexes/dog/documents")
+        .set_payload(document)
+        .insert_header(("content-type", "application/json"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 400);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The `json` payload provided is malformed. `Couldn't serialize document value: invalid type: string "0123456789012345678901234567...890123456789", expected a documents, or a sequence of documents. at line 1 column 102`."#
+        )
+    );
+    assert_eq!(response["code"], json!("malformed_payload"));
+    assert_eq!(response["type"], json!("invalid_request"));
+    assert_eq!(
+        response["link"],
+        json!("https://docs.meilisearch.com/errors#malformed_payload")
+    );
+
+    // add one more char to the long string to test if the truncating works.
+    let document = format!("\"{}m\"", long);
+    let req = test::TestRequest::put()
+        .uri("/indexes/dog/documents")
+        .set_payload(document)
+        .insert_header(("content-type", "application/json"))
+        .to_request();
+    let res = test::call_service(&app, req).await;
+    let body = test::read_body(res).await;
+    let response: Value = serde_json::from_slice(&body).unwrap_or_default();
+    assert_eq!(status_code, 400);
+    assert_eq!(
+        response["message"],
+        json!(
+            r#"The `json` payload provided is malformed. `Couldn't serialize document value: invalid type: string "0123456789012345678901234567...90123456789m", expected a documents, or a sequence of documents. at line 1 column 103`."#
+        )
+    );
+    assert_eq!(response["code"], json!("malformed_payload"));
+    assert_eq!(response["type"], json!("invalid_request"));
+    assert_eq!(
+        response["link"],
+        json!("https://docs.meilisearch.com/errors#malformed_payload")
+    );
 }
 
 #[actix_rt::test]

meilisearch-lib/src/document_formats.rs

@@ -1,4 +1,5 @@
-use std::fmt;
+use std::borrow::Borrow;
+use std::fmt::{self, Debug, Display};
 use std::io::{self, BufRead, BufReader, BufWriter, Cursor, Read, Seek, Write};
 
 use meilisearch_error::{internal_error, Code, ErrorCode};
@@ -23,17 +24,40 @@ impl fmt::Display for PayloadType {
     }
 }
 
-#[derive(thiserror::Error, Debug)]
+#[derive(Debug)]
 pub enum DocumentFormatError {
-    #[error("An internal error has occurred. `{0}`.")]
     Internal(Box<dyn std::error::Error + Send + Sync + 'static>),
-    #[error("The `{1}` payload provided is malformed. `{0}`.")]
+    MalformedPayload(Box<milli::documents::Error>, PayloadType),
-    MalformedPayload(
-        Box<dyn std::error::Error + Send + Sync + 'static>,
-        PayloadType,
-    ),
 }
 
+impl Display for DocumentFormatError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            Self::Internal(e) => write!(f, "An internal error has occurred: `{}`.", e),
+            Self::MalformedPayload(me, b) => match me.borrow() {
+                milli::documents::Error::JsonError(se) => {
+                    // https://github.com/meilisearch/meilisearch/issues/2107
+                    // The user input maybe insanely long. We need to truncate it.
+                    let mut serde_msg = se.to_string();
+                    let ellipsis = "...";
+                    if serde_msg.len() > 100 + ellipsis.len() {
+                        serde_msg.replace_range(50..serde_msg.len() - 85, ellipsis);
+                    }
+
+                    write!(
+                        f,
+                        "The `{}` payload provided is malformed. `Couldn't serialize document value: {}`.",
+                        b, serde_msg
+                )
+                }
+                _ => write!(f, "The `{}` payload provided is malformed: `{}`.", b, me),
+            },
+        }
+    }
+}
+
+impl std::error::Error for DocumentFormatError {}
+
 impl From<(PayloadType, milli::documents::Error)> for DocumentFormatError {
     fn from((ty, error): (PayloadType, milli::documents::Error)) -> Self {
         match error {