Code by Inyeol Lee, submitted to SF bug 595350, to implement
the string/unicode method .replace() with a zero-lengt first argument.
Inyeol contributed tests for this too.
diff --git a/Objects/stringobject.c b/Objects/stringobject.c
index 9f41317..0b79a06 100644
--- a/Objects/stringobject.c
+++ b/Objects/stringobject.c
@@ -2215,11 +2215,11 @@
char *new_s;
int nfound, offset, new_len;
- if (len == 0 || pat_len > len)
+ if (len == 0 || (pat_len == 0 && sub_len == 0) || pat_len > len)
goto return_same;
/* find length of output string */
- nfound = mymemcnt(str, len, pat, pat_len);
+ nfound = (pat_len > 0) ? mymemcnt(str, len, pat, pat_len) : len + 1;
if (count < 0)
count = INT_MAX;
else if (nfound > count)
@@ -2242,25 +2242,38 @@
return NULL;
out_s = new_s;
- for (; count > 0 && len > 0; --count) {
- /* find index of next instance of pattern */
- offset = mymemfind(str, len, pat, pat_len);
- if (offset == -1)
- break;
+ if (pat_len > 0) {
+ for (; nfound > 0; --nfound) {
+ /* find index of next instance of pattern */
+ offset = mymemfind(str, len, pat, pat_len);
+ if (offset == -1)
+ break;
- /* copy non matching part of input string */
- memcpy(new_s, str, offset);
- str += offset + pat_len;
- len -= offset + pat_len;
+ /* copy non matching part of input string */
+ memcpy(new_s, str, offset);
+ str += offset + pat_len;
+ len -= offset + pat_len;
- /* copy substitute into the output string */
- new_s += offset;
- memcpy(new_s, sub, sub_len);
- new_s += sub_len;
+ /* copy substitute into the output string */
+ new_s += offset;
+ memcpy(new_s, sub, sub_len);
+ new_s += sub_len;
+ }
+ /* copy any remaining values into output string */
+ if (len > 0)
+ memcpy(new_s, str, len);
}
- /* copy any remaining values into output string */
- if (len > 0)
- memcpy(new_s, str, len);
+ else {
+ for (;;++str, --len) {
+ memcpy(new_s, sub, sub_len);
+ new_s += sub_len;
+ if (--nfound <= 0) {
+ memcpy(new_s, str, len);
+ break;
+ }
+ *new_s++ = *str;
+ }
+ }
}
*out_len = new_len;
return out_s;
@@ -2317,10 +2330,6 @@
else if (PyObject_AsCharBuffer(replobj, &repl, &repl_len))
return NULL;
- if (sub_len <= 0) {
- PyErr_SetString(PyExc_ValueError, "empty pattern string");
- return NULL;
- }
new_s = mymemreplace(str,len,sub,sub_len,repl,repl_len,count,&out_len);
if (new_s == NULL) {
PyErr_NoMemory();
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index b264936..6dea94f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3494,11 +3494,6 @@
{
PyUnicodeObject *u;
- if (str1->length == 0) {
- PyErr_SetString(PyExc_ValueError, "empty pattern string");
- return NULL;
- }
-
if (maxcount < 0)
maxcount = INT_MAX;
@@ -3549,19 +3544,30 @@
if (u) {
i = 0;
p = u->str;
- while (i <= self->length - str1->length)
- if (Py_UNICODE_MATCH(self, i, str1)) {
- /* replace string segment */
+ if (str1->length > 0) {
+ while (i <= self->length - str1->length)
+ if (Py_UNICODE_MATCH(self, i, str1)) {
+ /* replace string segment */
+ Py_UNICODE_COPY(p, str2->str, str2->length);
+ p += str2->length;
+ i += str1->length;
+ if (--n <= 0) {
+ /* copy remaining part */
+ Py_UNICODE_COPY(p, self->str+i, self->length-i);
+ break;
+ }
+ } else
+ *p++ = self->str[i++];
+ } else {
+ while (n > 0) {
Py_UNICODE_COPY(p, str2->str, str2->length);
p += str2->length;
- i += str1->length;
- if (--n <= 0) {
- /* copy remaining part */
- Py_UNICODE_COPY(p, self->str+i, self->length-i);
+ if (--n <= 0)
break;
- }
- } else
*p++ = self->str[i++];
+ }
+ Py_UNICODE_COPY(p, self->str+i, self->length-i);
+ }
}
}
}