Align SQL comment parsing with CPython

ever0de · ever0de · commit 5cd5b4dfdda3 · 2025-07-17T17:38:11.000+09:00
diff --git a/Lib/test/test_sqlite3/test_dbapi.py b/Lib/test/test_sqlite3/test_dbapi.py
@@ -769,8 +769,6 @@ def test_execute_illegal_sql(self):
         with self.assertRaises(sqlite.OperationalError):
             self.cu.execute("select asdf")
 
-    # TODO: RUSTPYTHON
-    @unittest.expectedFailure
     def test_execute_multiple_statements(self):
         msg = "You can only execute one statement at a time"
         dataset = (
@@ -793,8 +791,6 @@ def test_execute_multiple_statements(self):
                 with self.assertRaisesRegex(sqlite.ProgrammingError, msg):
                     self.cu.execute(query)
 
-    # TODO: RUSTPYTHON
-    @unittest.expectedFailure
     def test_execute_with_appended_comments(self):
         dataset = (
             "select 1; -- foo bar",
@@ -963,8 +959,6 @@ def test_rowcount_update_returning(self):
         self.assertEqual(self.cu.fetchone()[0], 1)
         self.assertEqual(self.cu.rowcount, 1)
 
-    # TODO: RUSTPYTHON
-    @unittest.expectedFailure
     def test_rowcount_prefixed_with_comment(self):
         # gh-79579: rowcount is updated even if query is prefixed with comments
         self.cu.execute("""
diff --git a/stdlib/src/sqlite.rs b/stdlib/src/sqlite.rs
@@ -3068,36 +3068,58 @@ mod _sqlite {
     }
 
     fn lstrip_sql(sql: &[u8]) -> Option<&[u8]> {
-        let mut pos = sql;
-        loop {
-            match pos.first()? {
+        let mut pos = 0;
+        while let Some(current_char) = sql.get(pos) {
+            match current_char {
                 b' ' | b'\t' | b'\x0c' | b'\n' | b'\r' => {
-                    pos = &pos[1..];
+                    // Skip whitespace.
+                    pos += 1;
                 }
                 b'-' => {
-                    if *pos.get(1)? == b'-' {
-                        // line comments
-                        pos = &pos[2..];
-                        while *pos.first()? != b'\n' {
-                            pos = &pos[1..];
+                    // Skip line comments.
+                    if sql.get(pos + 1) == Some(&b'-') {
+                        pos += 2;
+                        while let Some(ch) = sql.get(pos) {
+                            if *ch == b'\n' {
+                                break;
+                            }
+                            pos += 1;
+                        }
+                        // CPython: if (pos[0] == '\0') return NULL;
+                        if sql.get(pos).is_none() {
+                            return None;
                         }
+                        // CPython: continue; (The outer for loop handles pos++)
+                        // Rust: The outer while loop will continue naturally
                     } else {
-                        return Some(pos);
+                        return Some(&sql[pos..]);
                     }
                 }
                 b'/' => {
-                    if *pos.get(1)? == b'*' {
-                        // c style comments
-                        pos = &pos[2..];
-                        while *pos.first()? != b'*' || *pos.get(1)? != b'/' {
-                            pos = &pos[1..];
+                    // Skip C style comments.
+                    if sql.get(pos + 1) == Some(&b'*') {
+                        pos += 2;
+                        while let Some(ch) = sql.get(pos) {
+                            if *ch == b'*' && sql.get(pos + 1) == Some(&b'/') {
+                                break;
+                            }
+                            pos += 1;
                         }
+                        // CPython: if (pos[0] == '\0') return NULL;
+                        if sql.get(pos).is_none() {
+                            return None; // Unclosed comment
+                        }
+                        // CPython: pos++; continue; (Handles '*' then '/' in the next loop)
+                        pos += 2; // Skip "*/"
                     } else {
-                        return Some(pos);
+                        return Some(&sql[pos..]);
                     }
                 }
-                _ => return Some(pos),
+                _ => {
+                    return Some(&sql[pos..]);
+                }
             }
         }
+        None
     }
 }
