tok_nextc() should return unsigned characters, to avoid mistaking

'\377' for EOF.

diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 3dc6c827999d62e1a33fcac49f43eb0be17e0b26..134f00f252bfac35ca4680ebb948bb47ea1aa41f 100644 (file)
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -46,6 +46,14 @@ extern char *PyOS_Readline Py_PROTO((char *));
 /* Don't ever change this -- it would break the portability of Python code */
 #define TABSIZE 8
 
+/* Convert a possibly signed character to a nonnegative int */
+/* XXX This assumes characters are 8 bits wide */
+#ifdef __CHAR_UNSIGNED__
+#define Py_CHARMASK(c)         (c)
+#else
+#define Py_CHARMASK(c)         ((c) & 0xff)
+#endif
+
 /* Forward */
 static struct tok_state *tok_new Py_PROTO((void));
 static int tok_nextc Py_PROTO((struct tok_state *tok));
@@ -178,7 +186,7 @@ tok_nextc(tok)
 {
        for (;;) {
                if (tok->cur != tok->inp) {
-                       return *tok->cur++; /* Fast path */
+                       return Py_CHARMASK(*tok->cur++); /* Fast path */
                }
                if (tok->done != E_OK)
                        return EOF;
@@ -197,7 +205,7 @@ tok_nextc(tok)
                                tok->buf = tok->cur;
                        tok->lineno++;
                        tok->inp = end;
-                       return *tok->cur++;
+                       return Py_CHARMASK(*tok->cur++);
                }
                if (tok->prompt != NULL) {
                        char *new = PyOS_Readline(tok->prompt);