bpo-44396: Update multi-line-start location when reallocating tokenizer buffers (GH-26676)

Automerge-Triggered-By: GH:pablogsal

Lib/test/test_eof.py

@@ -29,6 +29,13 @@ class EOFTestCase(unittest.TestCase):
         else:
             raise support.TestFailed
 
+    def test_EOFS_with_file(self):
+        expect = ("(<string>, line 1)")
+        with os_helper.temp_dir() as temp_dir:
+            file_name = script_helper.make_script(temp_dir, 'foo', """'''this is \na \ntest""")
+            rc, out, err = script_helper.assert_python_failure(file_name)
+        self.assertIn(b'unterminated triple-quoted string literal (detected at line 3)', err)
+
     def test_eof_with_line_continuation(self):
         expect = "unexpected EOF while parsing (<string>, line 1)"
         try:

Misc/NEWS.d/next/Core and Builtins/2021-06-11-18-17-42.bpo-44396.Z9EKim.rst

@@ -0,0 +1,2 @@
+Fix a possible crash in the tokenizer when raising syntax errors for
+unclosed strings. Patch by Pablo Galindo.

Parser/tokenizer.c

@@ -372,6 +372,8 @@ tok_reserve_buf(struct tok_state *tok, Py_ssize_t size)
     if (newsize > tok->end - tok->buf) {
         char *newbuf = tok->buf;
         Py_ssize_t start = tok->start == NULL ? -1 : tok->start - tok->buf;
+        Py_ssize_t line_start = tok->start == NULL ? -1 : tok->line_start - tok->buf;
+        Py_ssize_t multi_line_start = tok->multi_line_start - tok->buf;
         newbuf = (char *)PyMem_Realloc(newbuf, newsize);
         if (newbuf == NULL) {
             tok->done = E_NOMEM;
@@ -382,6 +384,8 @@ tok_reserve_buf(struct tok_state *tok, Py_ssize_t size)
         tok->inp = tok->buf + oldsize;
         tok->end = tok->buf + newsize;
         tok->start = start < 0 ? NULL : tok->buf + start;
+        tok->line_start = line_start < 0 ? NULL : tok->buf + line_start;
+        tok->multi_line_start = multi_line_start < 0 ? NULL : tok->buf + multi_line_start;
     }
     return 1;
 }
@@ -1883,6 +1887,7 @@ tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
         while (end_quote_size != quote_size) {
             c = tok_nextc(tok);
             if (c == EOF || (quote_size == 1 && c == '\n')) {
+                assert(tok->multi_line_start != NULL);
                 // shift the tok_state's location into
                 // the start of string, and report the error
                 // from the initial quote character