Index: Objects/unicodeobject.c
===================================================================
--- Objects/unicodeobject.c	(révision 68360)
+++ Objects/unicodeobject.c	(copie de travail)
@@ -2006,11 +2006,11 @@
 			                const char *errors,
 			                Py_ssize_t *consumed)
 {
-    const char *starts = s;
     int n;
     Py_ssize_t startinpos;
     Py_ssize_t endinpos;
     Py_ssize_t outpos;
+    Py_ssize_t i;
     const char *e;
     PyUnicodeObject *unicode;
     Py_UNICODE *p;
@@ -2033,23 +2033,23 @@
     p = unicode->str;
     e = s + size;
 
-    while (s < e) {
-        Py_UCS4 ch = (unsigned char)*s;
+    for (i = 0; i < size;) {
+        Py_UCS4 ch = (unsigned char) s[i];
 
         if (ch < 0x80) {
+            i++;
             *p++ = (Py_UNICODE)ch;
-            s++;
             continue;
         }
 
         n = utf8_code_length[ch];
 
-        if (s + n > e) {
+        if (i + n > size) {
 	    if (consumed)
 		break;
 	    else {
 		errmsg = "unexpected end of data";
-		startinpos = s-starts;
+		startinpos = i;
 		endinpos = size;
 		goto utf8Error;
 	    }
@@ -2059,43 +2059,43 @@
 
         case 0:
             errmsg = "unexpected code byte";
-	    startinpos = s-starts;
-	    endinpos = startinpos+1;
+	    startinpos = i;
+	    endinpos = i + 1;
 	    goto utf8Error;
 
         case 1:
             errmsg = "internal error";
-	    startinpos = s-starts;
-	    endinpos = startinpos+1;
+	    startinpos = i;
+	    endinpos = i + 1;
 	    goto utf8Error;
 
         case 2:
-            if ((s[1] & 0xc0) != 0x80) {
+            if ((s[i+1] & 0xc0) != 0x80) {
                 errmsg = "invalid data";
-		startinpos = s-starts;
-		endinpos = startinpos+2;
+		startinpos = i;
+		endinpos = i + 2;
 		goto utf8Error;
 	    }
-            ch = ((s[0] & 0x1f) << 6) + (s[1] & 0x3f);
+            ch = ((s[i] & 0x1f) << 6) + (s[i+1] & 0x3f);
             if (ch < 0x80) {
-		startinpos = s-starts;
-		endinpos = startinpos+2;
+		startinpos = i;
+		endinpos = i + 2;
                 errmsg = "illegal encoding";
 		goto utf8Error;
 	    }
-	    else
-		*p++ = (Py_UNICODE)ch;
+            i += 2;
+            *p++ = (Py_UNICODE)ch;
             break;
 
         case 3:
-            if ((s[1] & 0xc0) != 0x80 ||
-                (s[2] & 0xc0) != 0x80) {
+            if ((s[i+1] & 0xc0) != 0x80 ||
+                (s[i+2] & 0xc0) != 0x80) {
                 errmsg = "invalid data";
-		startinpos = s-starts;
-		endinpos = startinpos+3;
+		startinpos = i;
+		endinpos = i + 3;
 		goto utf8Error;
 	    }
-            ch = ((s[0] & 0x0f) << 12) + ((s[1] & 0x3f) << 6) + (s[2] & 0x3f);
+            ch = ((s[i] & 0x0f) << 12) + ((s[i+1] & 0x3f) << 6) + (s[i+2] & 0x3f);
             if (ch < 0x0800) {
 		/* Note: UTF-8 encodings of surrogates are considered
 		   legal UTF-8 sequences;
@@ -2105,25 +2105,25 @@
 		       unit.
 		*/
                 errmsg = "illegal encoding";
-		startinpos = s-starts;
-		endinpos = startinpos+3;
+		startinpos = i;
+		endinpos = i + 3;
 		goto utf8Error;
 	    }
-	    else
-		*p++ = (Py_UNICODE)ch;
+            i += 3;
+            *p++ = (Py_UNICODE)ch;
             break;
 
         case 4:
-            if ((s[1] & 0xc0) != 0x80 ||
-                (s[2] & 0xc0) != 0x80 ||
-                (s[3] & 0xc0) != 0x80) {
+            if ((s[i+1] & 0xc0) != 0x80 ||
+                (s[i+2] & 0xc0) != 0x80 ||
+                (s[i+3] & 0xc0) != 0x80) {
                 errmsg = "invalid data";
-		startinpos = s-starts;
-		endinpos = startinpos+4;
+		startinpos = i;
+		endinpos = i + 4;
 		goto utf8Error;
 	    }
-            ch = ((s[0] & 0x7) << 18) + ((s[1] & 0x3f) << 12) +
-                 ((s[2] & 0x3f) << 6) + (s[3] & 0x3f);
+            ch = ((s[i] & 0x7) << 18) + ((s[i+1] & 0x3f) << 12) +
+                 ((s[i+2] & 0x3f) << 6) + (s[i+3] & 0x3f);
             /* validate and convert to UTF-16 */
             if ((ch < 0x10000)        /* minimum value allowed for 4
 					 byte encoding */
@@ -2131,10 +2131,11 @@
 					 UTF-16 */
 	    {
                 errmsg = "illegal encoding";
-		startinpos = s-starts;
-		endinpos = startinpos+4;
+		startinpos = i;
+		endinpos = i + 4;
 		goto utf8Error;
 	    }
+            i += 4;
 #ifdef Py_UNICODE_WIDE
 	    *p++ = (Py_UNICODE)ch;
 #else
@@ -2154,24 +2155,27 @@
         default:
             /* Other sizes are only needed for UCS-4 */
             errmsg = "unsupported Unicode code range";
-	    startinpos = s-starts;
-	    endinpos = startinpos+n;
+	    startinpos = i;
+	    endinpos = i + n;
 	    goto utf8Error;
         }
-        s += n;
 	continue;
 
     utf8Error:
-    outpos = p-PyUnicode_AS_UNICODE(unicode);
-    if (unicode_decode_call_errorhandler(
-	     errors, &errorHandler,
-	     "utf8", errmsg,
-	     &starts, &e, &startinpos, &endinpos, &exc, &s,
-	     &unicode, &outpos, &p))
-	goto onError;
+        {
+            const char *nexts = &s[i];
+            outpos = p-PyUnicode_AS_UNICODE(unicode);
+            if (unicode_decode_call_errorhandler(
+                     errors, &errorHandler,
+                     "utf8", errmsg,
+                     &s, &e, &startinpos, &endinpos, &exc, &nexts,
+                     &unicode, &outpos, &p))
+                goto onError;
+            i = nexts - s;
+        }
     }
     if (consumed)
-	*consumed = s-starts;
+	*consumed = i;
 
     /* Adjust length */
     if (_PyUnicode_Resize(&unicode, p - unicode->str) < 0)