Merged revisions 78603 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r78603 | victor.stinner | 2010-03-03 00:20:02 +0100 (mer., 03 mars 2010) | 5 lines

  Issue #7820: The parser tokenizer restores all bytes in the right if the BOM
  check fails.

  Fix an assertion in pydebug mode.
........

diff --git a/Lib/test/test_pep263.py b/Lib/test/test_pep263.py
index 8c1fbe770ac2e78749ec3c12c2a656985ce80da1..e136a9ccb023d2d3931e189ddbf8c24f3afe41bb 100644 (file)
--- a/Lib/test/test_pep263.py
+++ b/Lib/test/test_pep263.py
@@ -44,6 +44,17 @@ class PEP263Test(unittest.TestCase):
         self.assertEqual(len(d['a']), len(d['b']))
         self.assertEqual(ascii(d['a']), ascii(d['b']))
 
+    def test_issue7820(self):
+        # Ensure that check_bom() restores all bytes in the right order if
+        # check_bom() fails in pydebug mode: a buffer starts with the first
+        # byte of a valid BOM, but next bytes are different
+
+        # one byte in common with the UTF-16-LE BOM
+        self.assertRaises(SyntaxError, eval, b'\xff\x20')
+
+        # two bytes in common with the UTF-8 BOM
+        self.assertRaises(SyntaxError, eval, b'\xef\xbb\x20')
+
 def test_main():
     support.run_unittest(PEP263Test)
 

diff --git a/Misc/NEWS b/Misc/NEWS
index fddba76fe67efc1f565d95b972fa877e7f67301e..e8f37ab8b964eb3dbd47d9aa3d00b02d147ce28c 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -12,6 +12,9 @@ What's New in Python 3.2 Alpha 1?
 Core and Builtins
 -----------------
 
+- Issue #7820: The parser tokenizer restores all bytes in the right if
+  the BOM check fails.
+
 - Handle errors from looking up __prepare__ correctly.
 
 - Issue #5939: Add additional runtime checking to ensure a valid capsule

diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 5a1c268378cdfeb99261d1c14a726e16a6d5cdf6..50b0ff193d3c9cf577bc8e5f875b7cb73cbead58 100644 (file)
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -318,46 +318,51 @@ check_bom(int get_char(struct tok_state *),
          int set_readline(struct tok_state *, const char *),
          struct tok_state *tok)
 {
-       int ch = get_char(tok);
+       int ch1, ch2, ch3;
+       ch1 = get_char(tok);
        tok->decoding_state = STATE_RAW;
-       if (ch == EOF) {
+       if (ch1 == EOF) {
                return 1;
-       } else if (ch == 0xEF) {
-               ch = get_char(tok); 
-               if (ch != 0xBB) {
-                       unget_char(ch, tok);
-                       unget_char(0xEF, tok);
-                       /* any token beginning with '\xEF' is a bad token */
+       } else if (ch1 == 0xEF) {
+               ch2 = get_char(tok);
+               if (ch2 != 0xBB) {
+                       unget_char(ch2, tok);
+                       unget_char(ch1, tok);
                        return 1;
                }
-               ch = get_char(tok); 
-               if (ch != 0xBF) {
-                       unget_char(ch, tok);
-                       unget_char(0xBB, tok);
-                       unget_char(0xEF, tok);
-                       /* any token beginning with '\xEF' is a bad token */
+               ch3 = get_char(tok);
+               if (ch3 != 0xBF) {
+                       unget_char(ch3, tok);
+                       unget_char(ch2, tok);
+                       unget_char(ch1, tok);
                        return 1;
                }
 #if 0
        /* Disable support for UTF-16 BOMs until a decision
           is made whether this needs to be supported.  */
-       } else if (ch == 0xFE) {
-               ch = get_char(tok);
-               if (ch != 0xFF)
-                       goto NON_BOM;
+       } else if (ch1 == 0xFE) {
+               ch2 = get_char(tok);
+               if (ch2 != 0xFF) {
+                       unget_char(ch2, tok);
+                       unget_char(ch1, tok);
+                       return 1;
+               }
                if (!set_readline(tok, "utf-16-be"))
                        return 0;
                tok->decoding_state = STATE_NORMAL;
-       } else if (ch == 0xFF) {
-               ch = get_char(tok);
-               if (ch != 0xFE)
-                       goto NON_BOM;
+       } else if (ch1 == 0xFF) {
+               ch2 = get_char(tok);
+               if (ch2 != 0xFE) {
+                       unget_char(ch2, tok);
+                       unget_char(ch1, tok);
+                       return 1;
+               }
                if (!set_readline(tok, "utf-16-le"))
                        return 0;
                tok->decoding_state = STATE_NORMAL;
 #endif
        } else {
-               unget_char(ch, tok);
+               unget_char(ch1, tok);
                return 1;
        }
        if (tok->encoding != NULL)