traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

bpo-37751: Fix codecs.lookup() normalization (GH-15092) 

Fix codecs.lookup() to normalize the encoding name the same way
than encodings.normalize_encoding(), except that codecs.lookup()
also converts the name to lower case.
This commit is contained in:
Jordon Xu 2019-08-21 21:26:20 +08:00 committed by Victor Stinner
parent 87bc3b7a0b
commit 20f59fe1f7
2 changed files with 17 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Misc/NEWS.d/next/Core and Builtins/2019-08-20-04-36-37.bpo-37751.CSFzUd.rst Normal file
View File

@ -0,0 +1 @@
Fix :func:`codecs.lookup` to normalize the encoding name the same way than :func:`encodings.normalize_encoding`, except that :func:`codecs.lookup` also converts the name to lower case.

32
Python/codecs.c
View File

@ -49,15 +49,16 @@ int PyCodec_Register(PyObject *search_function)
return -1;
}
/* Convert a string to a normalized Python string: all characters are
converted to lower case, spaces are replaced with underscores. */
extern int _Py_normalize_encoding(const char *, char *, size_t);
/* Convert a string to a normalized Python string(decoded from UTF-8): all characters are
converted to lower case, spaces and hyphens are replaced with underscores. */
static
PyObject *normalizestring(const char *string)
{
size_t i;
size_t len = strlen(string);
char *p;
char *encoding;
PyObject *v;
if (len > PY_SSIZE_T_MAX) {
@ -65,20 +66,19 @@ PyObject *normalizestring(const char *string)
return NULL;
}
p = PyMem_Malloc(len + 1);
if (p == NULL)
encoding = PyMem_Malloc(len + 1);
if (encoding == NULL)
return PyErr_NoMemory();
for (i = 0; i < len; i++) {
char ch = string[i];
if (ch == ' ')
ch = '-';
else
ch = Py_TOLOWER(Py_CHARMASK(ch));
p[i] = ch;
if (!_Py_normalize_encoding(string, encoding, len + 1))
{
PyErr_SetString(PyExc_RuntimeError, "_Py_normalize_encoding() failed");
PyMem_Free(encoding);
return NULL;
}
p[i] = '\0';
v = PyUnicode_FromString(p);
PyMem_Free(p);
v = PyUnicode_FromString(encoding);
PyMem_Free(encoding);
return v;
}