Skip to content

gh-129813, PEP 782: Use PyBytesWriter in utf8_encoder() #138874

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Sep 23, 2025
Merged

gh-129813, PEP 782: Use PyBytesWriter in utf8_encoder() #138874

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
051d070
gh-129813, PEP 782: Use PyBytesWriter in utf8_encoder()
vstinner Sep 13, 2025
7181b30
Fix leak: call PyBytesWriter_Discard()
vstinner Sep 15, 2025
8dcf030
Merge branch 'main' into pybyteswriter_encode_utf8
vstinner Sep 17, 2025
ecdece1
Restore code to disable overallocation
vstinner Sep 17, 2025
65e90a6
Fix test_codeccallbacks
vstinner Sep 18, 2025
90981ee
Merge branch 'main' into pybyteswriter_encode_utf8
vstinner Sep 18, 2025
c9abefd
Restore min_size optimization
vstinner Sep 18, 2025
7212e74
Address Serhiy's review
vstinner Sep 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 35 additions & 23 deletions Objects/stringlib/codecs.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -257,16 +257,14 @@ STRINGLIB(utf8_decode)(const char **inptr, const char *end,
/* UTF-8 encoder specialized for a Unicode kind to avoid the slow
PyUnicode_READ() macro. Delete some parts of the code depending on the kind:
UCS-1 strings don't need to handle surrogates for example. */
Py_LOCAL_INLINE(char *)
STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,
PyObject *unicode,
Py_LOCAL_INLINE(PyBytesWriter*)
STRINGLIB(utf8_encoder)(PyObject *unicode,
const STRINGLIB_CHAR *data,
Py_ssize_t size,
_Py_error_handler error_handler,
const char *errors)
const char *errors,
char **end)
{
Py_ssize_t i; /* index into data of next input character */
char *p; /* next free byte in output buffer */
#if STRINGLIB_SIZEOF_CHAR > 1
PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
Expand All @@ -284,14 +282,19 @@ STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,
if (size > PY_SSIZE_T_MAX / max_char_size) {
/* integer overflow */
PyErr_NoMemory();
*end = NULL;
return NULL;
}

_PyBytesWriter_Init(writer);
p = _PyBytesWriter_Alloc(writer, size * max_char_size);
if (p == NULL)
PyBytesWriter *writer = PyBytesWriter_Create(size * max_char_size);
if (writer == NULL) {
*end = NULL;
return NULL;
}
/* next free byte in output buffer */
char *p = PyBytesWriter_GetData(writer);

Py_ssize_t i; /* index into data of next input character */
for (i = 0; i < size;) {
Py_UCS4 ch = data[i++];

Expand Down Expand Up @@ -348,7 +351,7 @@ STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,

case _Py_ERROR_BACKSLASHREPLACE:
/* subtract preallocated bytes */
writer->min_size -= max_char_size * (endpos - startpos);
writer->size -= max_char_size * (endpos - startpos);
p = backslashreplace(writer, p,
unicode, startpos, endpos);
if (p == NULL)
Expand All @@ -358,7 +361,7 @@ STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,

case _Py_ERROR_XMLCHARREFREPLACE:
/* subtract preallocated bytes */
writer->min_size -= max_char_size * (endpos - startpos);
writer->size -= max_char_size * (endpos - startpos);
p = xmlcharrefreplace(writer, p,
unicode, startpos, endpos);
if (p == NULL)
Expand Down Expand Up @@ -389,22 +392,25 @@ STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,

if (newpos < startpos) {
writer->overallocate = 1;
p = _PyBytesWriter_Prepare(writer, p,
max_char_size * (startpos - newpos));
if (p == NULL)
p = PyBytesWriter_GrowAndUpdatePointer(writer,
max_char_size * (startpos - newpos),
p);
if (p == NULL) {
goto error;
}
}
else {
/* subtract preallocated bytes */
writer->min_size -= max_char_size * (newpos - startpos);
writer->size -= max_char_size * (newpos - startpos);
/* Only overallocate the buffer if it's not the last write */
writer->overallocate = (newpos < size);
}

char *rep_str;
Py_ssize_t rep_len;
if (PyBytes_Check(rep)) {
p = _PyBytesWriter_WriteBytes(writer, p,
PyBytes_AS_STRING(rep),
PyBytes_GET_SIZE(rep));
rep_str = PyBytes_AS_STRING(rep);
rep_len = PyBytes_GET_SIZE(rep);
}
else {
/* rep is unicode */
Expand All @@ -415,13 +421,16 @@ STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,
goto error;
}

p = _PyBytesWriter_WriteBytes(writer, p,
PyUnicode_DATA(rep),
PyUnicode_GET_LENGTH(rep));
rep_str = PyUnicode_DATA(rep);
rep_len = PyUnicode_GET_LENGTH(rep);
}

if (p == NULL)
p = PyBytesWriter_GrowAndUpdatePointer(writer, rep_len, p);
if (p == NULL) {
goto error;
}
memcpy(p, rep_str, rep_len);
p += rep_len;
Py_CLEAR(rep);

i = newpos;
Expand Down Expand Up @@ -458,13 +467,16 @@ STRINGLIB(utf8_encoder)(_PyBytesWriter *writer,
Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
#endif
return p;
*end = p;
return writer;

#if STRINGLIB_SIZEOF_CHAR > 1
error:
PyBytesWriter_Discard(writer);
Py_XDECREF(rep);
Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
*end = NULL;
return NULL;
#endif
}
Expand Down
Loading
Loading