Bug 415514 reported that e.g.

    "%#x" % 0
blew up, at heart because C sprintf supplies a base marker if and only if
the value is not 0.  I then fixed that, by tolerating C's inconsistency
when it does %#x, and taking away that *Python* produced 0x0 when
formatting 0L (the "long" flavor of 0) under %#x itself.  But after talking
with Guido, we agreed it would be better to supply 0x for the short int
case too, despite that it's inconsistent with C, because C is inconsistent
with itself and with Python's hex(0) (plus, while "%#x" % 0 didn't work
before, "%#x" % 0L *did*, and returned "0x0").  Similarly for %#X conversion.

2 files changed, 43 insertions, 38 deletions

diff --git a/Objects/stringobject.c b/Objects/stringobject.c
index 8e11536..1701b2f 100644
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -2575,16 +2575,8 @@ _PyString_FormatLong(PyObject *val, int flags, int prec, int type,
 	numdigits = len - numnondigits;
 	assert(numdigits > 0);
 
-	/* Get rid of base marker unless F_ALT.  Even if F_ALT, leading 0x
-	 * must be stripped if the *value* is 0.
-	 */
-	if ((flags & F_ALT) == 0 ||
-	    ((flags & F_ALT) &&
-	     (type == 'x' || type == 'X') &&
-	     numdigits == 1 &&
-	     !sign &&
-	     buf[2] == '0'
-	    )) {
+	/* Get rid of base marker unless F_ALT */
+	if ((flags & F_ALT) == 0) {
 		/* Need to skip 0x, 0X or 0. */
 		int skipped = 0;
 		switch (type) {
@@ -2678,6 +2670,16 @@ formatint(char *buf, size_t buflen, int flags,
 		return -1;
 	}
 	sprintf(buf, fmt, x);
+	/* When converting 0 under %#x or %#X, C leaves off the base marker,
+	 * but we want it (for consistency with other %#x conversions, and
+	 * for consistency with Python's hex() function).
+	 */
+	if (x == 0 && (flags & F_ALT) && (type == 'x' || type == 'X')) {
+		assert(buf[1] != type);  /* else this C *is* adding 0x/0X */
+		memmove(buf+2, buf, strlen(buf) + 1);
+		buf[0] = '0';
+		buf[1] = (char)type;
+	}
 	return strlen(buf);
 }
 
@@ -3023,21 +3025,17 @@ PyString_Format(PyObject *format, PyObject *args)
 					width--;
 			}
 			if ((flags & F_ALT) && (c == 'x' || c == 'X')) {
-				/* There's a base marker ("0x" or "0X") if and
-				 * only if the value is non-zero.
-				 */
 				assert(pbuf[0] == '0');
-				if (pbuf[1] == c) {
-					if (fill != ' ') {
-						*res++ = *pbuf++;
-						*res++ = *pbuf++;
-					}
-					rescnt -= 2;
-					width -= 2;
-					if (width < 0)
-						width = 0;
-					len -= 2;
+				assert(pbuf[1] == c);
+				if (fill != ' ') {
+					*res++ = *pbuf++;
+					*res++ = *pbuf++;
 				}
+				rescnt -= 2;
+				width -= 2;
+				if (width < 0)
+					width = 0;
+				len -= 2;
 			}
 			if (width > len && !(flags & F_LJUST)) {
 				do {
@@ -3049,8 +3047,9 @@ PyString_Format(PyObject *format, PyObject *args)
 				if (sign)
 					*res++ = sign;
 				if ((flags & F_ALT) &&
-				    (c == 'x' || c == 'X') &&
-				    pbuf[1] == c) {
+				    (c == 'x' || c == 'X')) {
+					assert(pbuf[0] == '0');
+					assert(pbuf[1] == c);
 					*res++ = *pbuf++;
 					*res++ = *pbuf++;
 				}
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index aecc261..b623c20 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -4683,7 +4683,14 @@ formatint(Py_UNICODE *buf,
             "formatted integer is too long (precision too long?)");
         return -1;
     }
-    sprintf(fmt, "%%%s.%dl%c", (flags & F_ALT) ? "#" : "", prec, type);
+    /* When converting 0 under %#x or %#X, C leaves off the base marker,
+     * but we want it (for consistency with other %#x conversions, and
+     * for consistency with Python's hex() function).
+     */
+    if (x == 0 && (flags & F_ALT) && (type == 'x' || type == 'X'))
+        sprintf(fmt, "0%c%%%s.%dl%c", type, "#", prec, type);
+    else
+        sprintf(fmt, "%%%s.%dl%c", (flags & F_ALT) ? "#" : "", prec, type);
     return usprintf(buf, fmt, x);
 }
 
@@ -5081,17 +5088,16 @@ PyObject *PyUnicode_Format(PyObject *format,
 	    }
 	    if ((flags & F_ALT) && (c == 'x' || c == 'X')) {
 		assert(pbuf[0] == '0');
-		if (pbuf[1] == c) {
-			if (fill != ' ') {
-			    *res++ = *pbuf++;
-			    *res++ = *pbuf++;
-			}
-			rescnt -= 2;
-			width -= 2;
-			if (width < 0)
-			    width = 0;
-			len -= 2;
+		assert(pbuf[1] == c);
+		if (fill != ' ') {
+		    *res++ = *pbuf++;
+		    *res++ = *pbuf++;
 		}
+		rescnt -= 2;
+		width -= 2;
+		if (width < 0)
+		    width = 0;
+		len -= 2;
 	    }
 	    if (width > len && !(flags & F_LJUST)) {
 		do {
@@ -5102,9 +5108,9 @@ PyObject *PyUnicode_Format(PyObject *format,
 	    if (fill == ' ') {
 		if (sign)
 		    *res++ = sign;
-		if ((flags & F_ALT) && (c == 'x' || c == 'X') &&
-		    pbuf[1] == c) {
+		if ((flags & F_ALT) && (c == 'x' || c == 'X')) {
 		    assert(pbuf[0] == '0');
+		    assert(pbuf[1] == c);
 		    *res++ = *pbuf++;
 		    *res++ = *pbuf++;
 		}