From 764314870867a74c9963ecb78dd99d26434f45ff Mon Sep 17 00:00:00 2001
From: bigliangzao <33975524+bigliangzao@users.noreply.github.com>
Date: Wed, 17 Jun 2026 19:00:05 +0800
Subject: [PATCH] fix(mysql): prevent panic on Chinese characters in WHERE
 clause
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix UTF-8 boundary issues in mysql_top_level_limit, parse_usize_token,
and mysql_keyword_at functions that caused crashes when SQL contains
Chinese characters in string literals.

The issue was introduced in commit 021e1682 which added byte-level
indexing without proper UTF-8 boundary checks. When parsing SQL with
Chinese text (e.g., \"WHERE name LIKE '%批量保存%'\"), the byte index
could point to the middle of a multi-byte UTF-8 character, causing
Rust to panic when slicing the string.

Changes:
- parse_usize_token: Use std::str::from_utf8 to validate slice before parsing
- mysql_keyword_at: Add is_char_boundary checks for safe string slicing
- mysql_top_level_limit: Skip non-UTF-8-boundary bytes after incrementing index

This ensures all byte-level indexing operations stay on valid UTF-8 boundaries,
preventing panics while maintaining the original functionality of detecting
LIMIT clauses for bounded result set collection.

Fixes crash reported by users when executing queries with Chinese conditions.
---
 crates/dbx-core/src/db/mysql.rs | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/crates/dbx-core/src/db/mysql.rs b/crates/dbx-core/src/db/mysql.rs
index 7e5e5989a3..428959072c 100644
--- a/crates/dbx-core/src/db/mysql.rs
+++ b/crates/dbx-core/src/db/mysql.rs
@@ -1468,7 +1468,11 @@ fn mysql_top_level_limit(sql: &str) -> Option<usize> {
         if depth == 0 && mysql_keyword_at(sql, i, "LIMIT") {
             return parse_mysql_limit_value(sql, i + "LIMIT".len());
         }
+        // Move to next byte, but ensure we stay on a UTF-8 boundary
         i += 1;
+        while i < bytes.len() && !sql.is_char_boundary(i) {
+            i += 1;
+        }
     }
 
     None
@@ -1497,13 +1501,20 @@ fn parse_usize_token(sql: &str, i: &mut usize) -> Option<usize> {
     if *i == start {
         return None;
     }
-    sql[start..*i].parse().ok()
+    // Ensure the slice is valid UTF-8 before parsing
+    std::str::from_utf8(&bytes[start..*i]).ok()?.parse().ok()
 }
 
 fn mysql_keyword_at(sql: &str, i: usize, keyword: &str) -> bool {
     let end = i + keyword.len();
-    end <= sql.len()
-        && sql[i..end].eq_ignore_ascii_case(keyword)
+    if end > sql.len() {
+        return false;
+    }
+    // Ensure indices are on UTF-8 boundaries before slicing
+    if !sql.is_char_boundary(i) || !sql.is_char_boundary(end) {
+        return false;
+    }
+    sql[i..end].eq_ignore_ascii_case(keyword)
         && (i == 0 || !is_mysql_identifier_byte(sql.as_bytes()[i - 1]))
         && (end == sql.len() || !is_mysql_identifier_byte(sql.as_bytes()[end]))
 }