summaryrefslogtreecommitdiff
path: root/Python/codecs.c
diff options
context:
space:
mode:
Diffstat (limited to 'Python/codecs.c')
-rw-r--r--Python/codecs.c792
1 files changed, 402 insertions, 390 deletions
diff --git a/Python/codecs.c b/Python/codecs.c
index 4b0f4cb0d0..57bd0f41ff 100644
--- a/Python/codecs.c
+++ b/Python/codecs.c
@@ -14,7 +14,7 @@ Copyright (c) Corporation for National Research Initiatives.
/* --- Codec Registry ----------------------------------------------------- */
/* Import the standard encodings package which will register the first
- codec search function.
+ codec search function.
This is done in a lazy way so that the Unicode implementation does
not downgrade startup time of scripts not needing it.
@@ -30,14 +30,14 @@ int PyCodec_Register(PyObject *search_function)
{
PyInterpreterState *interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
- goto onError;
+ goto onError;
if (search_function == NULL) {
- PyErr_BadArgument();
- goto onError;
+ PyErr_BadArgument();
+ goto onError;
}
if (!PyCallable_Check(search_function)) {
- PyErr_SetString(PyExc_TypeError, "argument must be callable");
- goto onError;
+ PyErr_SetString(PyExc_TypeError, "argument must be callable");
+ goto onError;
}
return PyList_Append(interp->codec_search_path, search_function);
@@ -55,15 +55,15 @@ PyObject *normalizestring(const char *string)
size_t len = strlen(string);
char *p;
PyObject *v;
-
+
if (len > PY_SSIZE_T_MAX) {
- PyErr_SetString(PyExc_OverflowError, "string is too large");
- return NULL;
+ PyErr_SetString(PyExc_OverflowError, "string is too large");
+ return NULL;
}
-
+
v = PyString_FromStringAndSize(NULL, len);
if (v == NULL)
- return NULL;
+ return NULL;
p = PyString_AS_STRING(v);
for (i = 0; i < len; i++) {
register char ch = string[i];
@@ -71,7 +71,7 @@ PyObject *normalizestring(const char *string)
ch = '-';
else
ch = tolower(Py_CHARMASK(ch));
- p[i] = ch;
+ p[i] = ch;
}
return v;
}
@@ -83,7 +83,7 @@ PyObject *normalizestring(const char *string)
characters. This makes encodings looked up through this mechanism
effectively case-insensitive.
- If no codec is found, a LookupError is set and NULL returned.
+ If no codec is found, a LookupError is set and NULL returned.
As side effect, this tries to load the encodings package, if not
yet done. This is part of the lazy load strategy for the encodings
@@ -98,72 +98,72 @@ PyObject *_PyCodec_Lookup(const char *encoding)
Py_ssize_t i, len;
if (encoding == NULL) {
- PyErr_BadArgument();
- goto onError;
+ PyErr_BadArgument();
+ goto onError;
}
interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
- goto onError;
+ goto onError;
/* Convert the encoding to a normalized Python string: all
characters are converted to lower case, spaces and hyphens are
replaced with underscores. */
v = normalizestring(encoding);
if (v == NULL)
- goto onError;
+ goto onError;
PyString_InternInPlace(&v);
/* First, try to lookup the name in the registry dictionary */
result = PyDict_GetItem(interp->codec_search_cache, v);
if (result != NULL) {
- Py_INCREF(result);
- Py_DECREF(v);
- return result;
+ Py_INCREF(result);
+ Py_DECREF(v);
+ return result;
}
-
+
/* Next, scan the search functions in order of registration */
args = PyTuple_New(1);
if (args == NULL)
- goto onError;
+ goto onError;
PyTuple_SET_ITEM(args,0,v);
len = PyList_Size(interp->codec_search_path);
if (len < 0)
- goto onError;
+ goto onError;
if (len == 0) {
- PyErr_SetString(PyExc_LookupError,
- "no codec search functions registered: "
- "can't find encoding");
- goto onError;
+ PyErr_SetString(PyExc_LookupError,
+ "no codec search functions registered: "
+ "can't find encoding");
+ goto onError;
}
for (i = 0; i < len; i++) {
- PyObject *func;
-
- func = PyList_GetItem(interp->codec_search_path, i);
- if (func == NULL)
- goto onError;
- result = PyEval_CallObject(func, args);
- if (result == NULL)
- goto onError;
- if (result == Py_None) {
- Py_DECREF(result);
- continue;
- }
- if (!PyTuple_Check(result) || PyTuple_GET_SIZE(result) != 4) {
- PyErr_SetString(PyExc_TypeError,
- "codec search functions must return 4-tuples");
- Py_DECREF(result);
- goto onError;
- }
- break;
+ PyObject *func;
+
+ func = PyList_GetItem(interp->codec_search_path, i);
+ if (func == NULL)
+ goto onError;
+ result = PyEval_CallObject(func, args);
+ if (result == NULL)
+ goto onError;
+ if (result == Py_None) {
+ Py_DECREF(result);
+ continue;
+ }
+ if (!PyTuple_Check(result) || PyTuple_GET_SIZE(result) != 4) {
+ PyErr_SetString(PyExc_TypeError,
+ "codec search functions must return 4-tuples");
+ Py_DECREF(result);
+ goto onError;
+ }
+ break;
}
if (i == len) {
- /* XXX Perhaps we should cache misses too ? */
- PyErr_Format(PyExc_LookupError,
+ /* XXX Perhaps we should cache misses too ? */
+ PyErr_Format(PyExc_LookupError,
"unknown encoding: %s", encoding);
- goto onError;
+ goto onError;
}
/* Cache and return the result */
@@ -178,24 +178,24 @@ PyObject *_PyCodec_Lookup(const char *encoding)
static
PyObject *args_tuple(PyObject *object,
- const char *errors)
+ const char *errors)
{
PyObject *args;
-
+
args = PyTuple_New(1 + (errors != NULL));
if (args == NULL)
- return NULL;
+ return NULL;
Py_INCREF(object);
PyTuple_SET_ITEM(args,0,object);
if (errors) {
- PyObject *v;
-
- v = PyString_FromString(errors);
- if (v == NULL) {
- Py_DECREF(args);
- return NULL;
- }
- PyTuple_SET_ITEM(args, 1, v);
+ PyObject *v;
+
+ v = PyString_FromString(errors);
+ if (v == NULL) {
+ Py_DECREF(args);
+ return NULL;
+ }
+ PyTuple_SET_ITEM(args, 1, v);
}
return args;
}
@@ -210,7 +210,7 @@ PyObject *codec_getitem(const char *encoding, int index)
codecs = _PyCodec_Lookup(encoding);
if (codecs == NULL)
- return NULL;
+ return NULL;
v = PyTuple_GET_ITEM(codecs, index);
Py_DECREF(codecs);
Py_INCREF(v);
@@ -221,22 +221,22 @@ PyObject *codec_getitem(const char *encoding, int index)
static
PyObject *codec_getincrementalcodec(const char *encoding,
- const char *errors,
- const char *attrname)
+ const char *errors,
+ const char *attrname)
{
PyObject *codecs, *ret, *inccodec;
codecs = _PyCodec_Lookup(encoding);
if (codecs == NULL)
- return NULL;
+ return NULL;
inccodec = PyObject_GetAttrString(codecs, attrname);
Py_DECREF(codecs);
if (inccodec == NULL)
- return NULL;
+ return NULL;
if (errors)
- ret = PyObject_CallFunction(inccodec, "s", errors);
+ ret = PyObject_CallFunction(inccodec, "s", errors);
else
- ret = PyObject_CallFunction(inccodec, NULL);
+ ret = PyObject_CallFunction(inccodec, NULL);
Py_DECREF(inccodec);
return ret;
}
@@ -245,29 +245,29 @@ PyObject *codec_getincrementalcodec(const char *encoding,
static
PyObject *codec_getstreamcodec(const char *encoding,
- PyObject *stream,
- const char *errors,
- const int index)
+ PyObject *stream,
+ const char *errors,
+ const int index)
{
PyObject *codecs, *streamcodec, *codeccls;
codecs = _PyCodec_Lookup(encoding);
if (codecs == NULL)
- return NULL;
+ return NULL;
codeccls = PyTuple_GET_ITEM(codecs, index);
if (errors != NULL)
- streamcodec = PyObject_CallFunction(codeccls, "Os", stream, errors);
+ streamcodec = PyObject_CallFunction(codeccls, "Os", stream, errors);
else
- streamcodec = PyObject_CallFunction(codeccls, "O", stream);
+ streamcodec = PyObject_CallFunction(codeccls, "O", stream);
Py_DECREF(codecs);
return streamcodec;
}
-/* Convenience APIs to query the Codec registry.
-
+/* Convenience APIs to query the Codec registry.
+
All APIs return a codec object with incremented refcount.
-
+
*/
PyObject *PyCodec_Encoder(const char *encoding)
@@ -281,27 +281,27 @@ PyObject *PyCodec_Decoder(const char *encoding)
}
PyObject *PyCodec_IncrementalEncoder(const char *encoding,
- const char *errors)
+ const char *errors)
{
return codec_getincrementalcodec(encoding, errors, "incrementalencoder");
}
PyObject *PyCodec_IncrementalDecoder(const char *encoding,
- const char *errors)
+ const char *errors)
{
return codec_getincrementalcodec(encoding, errors, "incrementaldecoder");
}
PyObject *PyCodec_StreamReader(const char *encoding,
- PyObject *stream,
- const char *errors)
+ PyObject *stream,
+ const char *errors)
{
return codec_getstreamcodec(encoding, stream, errors, 2);
}
PyObject *PyCodec_StreamWriter(const char *encoding,
- PyObject *stream,
- const char *errors)
+ PyObject *stream,
+ const char *errors)
{
return codec_getstreamcodec(encoding, stream, errors, 3);
}
@@ -312,8 +312,8 @@ PyObject *PyCodec_StreamWriter(const char *encoding,
errors is passed to the encoder factory as argument if non-NULL. */
PyObject *PyCodec_Encode(PyObject *object,
- const char *encoding,
- const char *errors)
+ const char *encoding,
+ const char *errors)
{
PyObject *encoder = NULL;
PyObject *args = NULL, *result = NULL;
@@ -321,21 +321,21 @@ PyObject *PyCodec_Encode(PyObject *object,
encoder = PyCodec_Encoder(encoding);
if (encoder == NULL)
- goto onError;
+ goto onError;
args = args_tuple(object, errors);
if (args == NULL)
- goto onError;
-
+ goto onError;
+
result = PyEval_CallObject(encoder,args);
if (result == NULL)
- goto onError;
+ goto onError;
- if (!PyTuple_Check(result) ||
- PyTuple_GET_SIZE(result) != 2) {
- PyErr_SetString(PyExc_TypeError,
- "encoder must return a tuple (object,integer)");
- goto onError;
+ if (!PyTuple_Check(result) ||
+ PyTuple_GET_SIZE(result) != 2) {
+ PyErr_SetString(PyExc_TypeError,
+ "encoder must return a tuple (object,integer)");
+ goto onError;
}
v = PyTuple_GET_ITEM(result,0);
Py_INCREF(v);
@@ -345,7 +345,7 @@ PyObject *PyCodec_Encode(PyObject *object,
Py_DECREF(encoder);
Py_DECREF(result);
return v;
-
+
onError:
Py_XDECREF(result);
Py_XDECREF(args);
@@ -359,8 +359,8 @@ PyObject *PyCodec_Encode(PyObject *object,
errors is passed to the decoder factory as argument if non-NULL. */
PyObject *PyCodec_Decode(PyObject *object,
- const char *encoding,
- const char *errors)
+ const char *encoding,
+ const char *errors)
{
PyObject *decoder = NULL;
PyObject *args = NULL, *result = NULL;
@@ -368,20 +368,20 @@ PyObject *PyCodec_Decode(PyObject *object,
decoder = PyCodec_Decoder(encoding);
if (decoder == NULL)
- goto onError;
+ goto onError;
args = args_tuple(object, errors);
if (args == NULL)
- goto onError;
-
+ goto onError;
+
result = PyEval_CallObject(decoder,args);
if (result == NULL)
- goto onError;
- if (!PyTuple_Check(result) ||
- PyTuple_GET_SIZE(result) != 2) {
- PyErr_SetString(PyExc_TypeError,
- "decoder must return a tuple (object,integer)");
- goto onError;
+ goto onError;
+ if (!PyTuple_Check(result) ||
+ PyTuple_GET_SIZE(result) != 2) {
+ PyErr_SetString(PyExc_TypeError,
+ "decoder must return a tuple (object,integer)");
+ goto onError;
}
v = PyTuple_GET_ITEM(result,0);
Py_INCREF(v);
@@ -391,7 +391,7 @@ PyObject *PyCodec_Decode(PyObject *object,
Py_DECREF(decoder);
Py_DECREF(result);
return v;
-
+
onError:
Py_XDECREF(args);
Py_XDECREF(decoder);
@@ -409,13 +409,13 @@ int PyCodec_RegisterError(const char *name, PyObject *error)
{
PyInterpreterState *interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
- return -1;
+ return -1;
if (!PyCallable_Check(error)) {
- PyErr_SetString(PyExc_TypeError, "handler must be callable");
- return -1;
+ PyErr_SetString(PyExc_TypeError, "handler must be callable");
+ return -1;
}
return PyDict_SetItemString(interp->codec_error_registry,
- (char *)name, error);
+ (char *)name, error);
}
/* Lookup the error handling callback function registered under the
@@ -427,15 +427,15 @@ PyObject *PyCodec_LookupError(const char *name)
PyInterpreterState *interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
- return NULL;
+ return NULL;
if (name==NULL)
- name = "strict";
+ name = "strict";
handler = PyDict_GetItemString(interp->codec_error_registry, (char *)name);
if (!handler)
- PyErr_Format(PyExc_LookupError, "unknown error handler name '%.400s'", name);
+ PyErr_Format(PyExc_LookupError, "unknown error handler name '%.400s'", name);
else
- Py_INCREF(handler);
+ Py_INCREF(handler);
return handler;
}
@@ -443,18 +443,18 @@ static void wrong_exception_type(PyObject *exc)
{
PyObject *type = PyObject_GetAttrString(exc, "__class__");
if (type != NULL) {
- PyObject *name = PyObject_GetAttrString(type, "__name__");
- Py_DECREF(type);
- if (name != NULL) {
- PyObject *string = PyObject_Str(name);
- Py_DECREF(name);
- if (string != NULL) {
- PyErr_Format(PyExc_TypeError,
- "don't know how to handle %.400s in error callback",
- PyString_AS_STRING(string));
- Py_DECREF(string);
- }
- }
+ PyObject *name = PyObject_GetAttrString(type, "__name__");
+ Py_DECREF(type);
+ if (name != NULL) {
+ PyObject *string = PyObject_Str(name);
+ Py_DECREF(name);
+ if (string != NULL) {
+ PyErr_Format(PyExc_TypeError,
+ "don't know how to handle %.400s in error callback",
+ PyString_AS_STRING(string));
+ Py_DECREF(string);
+ }
+ }
}
}
@@ -463,7 +463,7 @@ PyObject *PyCodec_StrictErrors(PyObject *exc)
if (PyExceptionInstance_Check(exc))
PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
else
- PyErr_SetString(PyExc_TypeError, "codec must pass exception instance");
+ PyErr_SetString(PyExc_TypeError, "codec must pass exception instance");
return NULL;
}
@@ -473,20 +473,20 @@ PyObject *PyCodec_IgnoreErrors(PyObject *exc)
{
Py_ssize_t end;
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
- if (PyUnicodeEncodeError_GetEnd(exc, &end))
- return NULL;
+ if (PyUnicodeEncodeError_GetEnd(exc, &end))
+ return NULL;
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
- if (PyUnicodeDecodeError_GetEnd(exc, &end))
- return NULL;
+ if (PyUnicodeDecodeError_GetEnd(exc, &end))
+ return NULL;
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
- if (PyUnicodeTranslateError_GetEnd(exc, &end))
- return NULL;
+ if (PyUnicodeTranslateError_GetEnd(exc, &end))
+ return NULL;
}
else {
- wrong_exception_type(exc);
- return NULL;
+ wrong_exception_type(exc);
+ return NULL;
}
/* ouch: passing NULL, 0, pos gives None instead of u'' */
return Py_BuildValue("(u#n)", &end, 0, end);
@@ -501,155 +501,155 @@ PyObject *PyCodec_ReplaceErrors(PyObject *exc)
Py_ssize_t i;
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
- PyObject *res;
- Py_UNICODE *p;
- if (PyUnicodeEncodeError_GetStart(exc, &start))
- return NULL;
- if (PyUnicodeEncodeError_GetEnd(exc, &end))
- return NULL;
- res = PyUnicode_FromUnicode(NULL, end-start);
- if (res == NULL)
- return NULL;
- for (p = PyUnicode_AS_UNICODE(res), i = start;
- i<end; ++p, ++i)
- *p = '?';
- restuple = Py_BuildValue("(On)", res, end);
- Py_DECREF(res);
- return restuple;
+ PyObject *res;
+ Py_UNICODE *p;
+ if (PyUnicodeEncodeError_GetStart(exc, &start))
+ return NULL;
+ if (PyUnicodeEncodeError_GetEnd(exc, &end))
+ return NULL;
+ res = PyUnicode_FromUnicode(NULL, end-start);
+ if (res == NULL)
+ return NULL;
+ for (p = PyUnicode_AS_UNICODE(res), i = start;
+ i<end; ++p, ++i)
+ *p = '?';
+ restuple = Py_BuildValue("(On)", res, end);
+ Py_DECREF(res);
+ return restuple;
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
- Py_UNICODE res = Py_UNICODE_REPLACEMENT_CHARACTER;
- if (PyUnicodeDecodeError_GetEnd(exc, &end))
- return NULL;
- return Py_BuildValue("(u#n)", &res, 1, end);
+ Py_UNICODE res = Py_UNICODE_REPLACEMENT_CHARACTER;
+ if (PyUnicodeDecodeError_GetEnd(exc, &end))
+ return NULL;
+ return Py_BuildValue("(u#n)", &res, 1, end);
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
- PyObject *res;
- Py_UNICODE *p;
- if (PyUnicodeTranslateError_GetStart(exc, &start))
- return NULL;
- if (PyUnicodeTranslateError_GetEnd(exc, &end))
- return NULL;
- res = PyUnicode_FromUnicode(NULL, end-start);
- if (res == NULL)
- return NULL;
- for (p = PyUnicode_AS_UNICODE(res), i = start;
- i<end; ++p, ++i)
- *p = Py_UNICODE_REPLACEMENT_CHARACTER;
- restuple = Py_BuildValue("(On)", res, end);
- Py_DECREF(res);
- return restuple;
+ PyObject *res;
+ Py_UNICODE *p;
+ if (PyUnicodeTranslateError_GetStart(exc, &start))
+ return NULL;
+ if (PyUnicodeTranslateError_GetEnd(exc, &end))
+ return NULL;
+ res = PyUnicode_FromUnicode(NULL, end-start);
+ if (res == NULL)
+ return NULL;
+ for (p = PyUnicode_AS_UNICODE(res), i = start;
+ i<end; ++p, ++i)
+ *p = Py_UNICODE_REPLACEMENT_CHARACTER;
+ restuple = Py_BuildValue("(On)", res, end);
+ Py_DECREF(res);
+ return restuple;
}
else {
- wrong_exception_type(exc);
- return NULL;
+ wrong_exception_type(exc);
+ return NULL;
}
}
PyObject *PyCodec_XMLCharRefReplaceErrors(PyObject *exc)
{
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
- PyObject *restuple;
- PyObject *object;
- Py_ssize_t start;
- Py_ssize_t end;
- PyObject *res;
- Py_UNICODE *p;
- Py_UNICODE *startp;
- Py_UNICODE *outp;
- int ressize;
- if (PyUnicodeEncodeError_GetStart(exc, &start))
- return NULL;
- if (PyUnicodeEncodeError_GetEnd(exc, &end))
- return NULL;
- if (!(object = PyUnicodeEncodeError_GetObject(exc)))
- return NULL;
- startp = PyUnicode_AS_UNICODE(object);
- for (p = startp+start, ressize = 0; p < startp+end; ++p) {
- if (*p<10)
- ressize += 2+1+1;
- else if (*p<100)
- ressize += 2+2+1;
- else if (*p<1000)
- ressize += 2+3+1;
- else if (*p<10000)
- ressize += 2+4+1;
+ PyObject *restuple;
+ PyObject *object;
+ Py_ssize_t start;
+ Py_ssize_t end;
+ PyObject *res;
+ Py_UNICODE *p;
+ Py_UNICODE *startp;
+ Py_UNICODE *outp;
+ int ressize;
+ if (PyUnicodeEncodeError_GetStart(exc, &start))
+ return NULL;
+ if (PyUnicodeEncodeError_GetEnd(exc, &end))
+ return NULL;
+ if (!(object = PyUnicodeEncodeError_GetObject(exc)))
+ return NULL;
+ startp = PyUnicode_AS_UNICODE(object);
+ for (p = startp+start, ressize = 0; p < startp+end; ++p) {
+ if (*p<10)
+ ressize += 2+1+1;
+ else if (*p<100)
+ ressize += 2+2+1;
+ else if (*p<1000)
+ ressize += 2+3+1;
+ else if (*p<10000)
+ ressize += 2+4+1;
#ifndef Py_UNICODE_WIDE
- else
- ressize += 2+5+1;
+ else
+ ressize += 2+5+1;
#else
- else if (*p<100000)
- ressize += 2+5+1;
- else if (*p<1000000)
- ressize += 2+6+1;
- else
- ressize += 2+7+1;
+ else if (*p<100000)
+ ressize += 2+5+1;
+ else if (*p<1000000)
+ ressize += 2+6+1;
+ else
+ ressize += 2+7+1;
#endif
- }
- /* allocate replacement */
- res = PyUnicode_FromUnicode(NULL, ressize);
- if (res == NULL) {
- Py_DECREF(object);
- return NULL;
- }
- /* generate replacement */
- for (p = startp+start, outp = PyUnicode_AS_UNICODE(res);
- p < startp+end; ++p) {
- Py_UNICODE c = *p;
- int digits;
- int base;
- *outp++ = '&';
- *outp++ = '#';
- if (*p<10) {
- digits = 1;
- base = 1;
- }
- else if (*p<100) {
- digits = 2;
- base = 10;
- }
- else if (*p<1000) {
- digits = 3;
- base = 100;
- }
- else if (*p<10000) {
- digits = 4;
- base = 1000;
- }
+ }
+ /* allocate replacement */
+ res = PyUnicode_FromUnicode(NULL, ressize);
+ if (res == NULL) {
+ Py_DECREF(object);
+ return NULL;
+ }
+ /* generate replacement */
+ for (p = startp+start, outp = PyUnicode_AS_UNICODE(res);
+ p < startp+end; ++p) {
+ Py_UNICODE c = *p;
+ int digits;
+ int base;
+ *outp++ = '&';
+ *outp++ = '#';
+ if (*p<10) {
+ digits = 1;
+ base = 1;
+ }
+ else if (*p<100) {
+ digits = 2;
+ base = 10;
+ }
+ else if (*p<1000) {
+ digits = 3;
+ base = 100;
+ }
+ else if (*p<10000) {
+ digits = 4;
+ base = 1000;
+ }
#ifndef Py_UNICODE_WIDE
- else {
- digits = 5;
- base = 10000;
- }
+ else {
+ digits = 5;
+ base = 10000;
+ }
#else
- else if (*p<100000) {
- digits = 5;
- base = 10000;
- }
- else if (*p<1000000) {
- digits = 6;
- base = 100000;
- }
- else {
- digits = 7;
- base = 1000000;
- }
+ else if (*p<100000) {
+ digits = 5;
+ base = 10000;
+ }
+ else if (*p<1000000) {
+ digits = 6;
+ base = 100000;
+ }
+ else {
+ digits = 7;
+ base = 1000000;
+ }
#endif
- while (digits-->0) {
- *outp++ = '0' + c/base;
- c %= base;
- base /= 10;
- }
- *outp++ = ';';
- }
- restuple = Py_BuildValue("(On)", res, end);
- Py_DECREF(res);
- Py_DECREF(object);
- return restuple;
+ while (digits-->0) {
+ *outp++ = '0' + c/base;
+ c %= base;
+ base /= 10;
+ }
+ *outp++ = ';';
+ }
+ restuple = Py_BuildValue("(On)", res, end);
+ Py_DECREF(res);
+ Py_DECREF(object);
+ return restuple;
}
else {
- wrong_exception_type(exc);
- return NULL;
+ wrong_exception_type(exc);
+ return NULL;
}
}
@@ -661,72 +661,72 @@ static Py_UNICODE hexdigits[] = {
PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc)
{
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
- PyObject *restuple;
- PyObject *object;
- Py_ssize_t start;
- Py_ssize_t end;
- PyObject *res;
- Py_UNICODE *p;
- Py_UNICODE *startp;
- Py_UNICODE *outp;
- int ressize;
- if (PyUnicodeEncodeError_GetStart(exc, &start))
- return NULL;
- if (PyUnicodeEncodeError_GetEnd(exc, &end))
- return NULL;
- if (!(object = PyUnicodeEncodeError_GetObject(exc)))
- return NULL;
- startp = PyUnicode_AS_UNICODE(object);
- for (p = startp+start, ressize = 0; p < startp+end; ++p) {
+ PyObject *restuple;
+ PyObject *object;
+ Py_ssize_t start;
+ Py_ssize_t end;
+ PyObject *res;
+ Py_UNICODE *p;
+ Py_UNICODE *startp;
+ Py_UNICODE *outp;
+ int ressize;
+ if (PyUnicodeEncodeError_GetStart(exc, &start))
+ return NULL;
+ if (PyUnicodeEncodeError_GetEnd(exc, &end))
+ return NULL;
+ if (!(object = PyUnicodeEncodeError_GetObject(exc)))
+ return NULL;
+ startp = PyUnicode_AS_UNICODE(object);
+ for (p = startp+start, ressize = 0; p < startp+end; ++p) {
#ifdef Py_UNICODE_WIDE
- if (*p >= 0x00010000)
- ressize += 1+1+8;
- else
+ if (*p >= 0x00010000)
+ ressize += 1+1+8;
+ else
#endif
- if (*p >= 0x100) {
- ressize += 1+1+4;
- }
- else
- ressize += 1+1+2;
- }
- res = PyUnicode_FromUnicode(NULL, ressize);
- if (res==NULL)
- return NULL;
- for (p = startp+start, outp = PyUnicode_AS_UNICODE(res);
- p < startp+end; ++p) {
- Py_UNICODE c = *p;
- *outp++ = '\\';
+ if (*p >= 0x100) {
+ ressize += 1+1+4;
+ }
+ else
+ ressize += 1+1+2;
+ }
+ res = PyUnicode_FromUnicode(NULL, ressize);
+ if (res==NULL)
+ return NULL;
+ for (p = startp+start, outp = PyUnicode_AS_UNICODE(res);
+ p < startp+end; ++p) {
+ Py_UNICODE c = *p;
+ *outp++ = '\\';
#ifdef Py_UNICODE_WIDE
- if (c >= 0x00010000) {
- *outp++ = 'U';
- *outp++ = hexdigits[(c>>28)&0xf];
- *outp++ = hexdigits[(c>>24)&0xf];
- *outp++ = hexdigits[(c>>20)&0xf];
- *outp++ = hexdigits[(c>>16)&0xf];
- *outp++ = hexdigits[(c>>12)&0xf];
- *outp++ = hexdigits[(c>>8)&0xf];
- }
- else
+ if (c >= 0x00010000) {
+ *outp++ = 'U';
+ *outp++ = hexdigits[(c>>28)&0xf];
+ *outp++ = hexdigits[(c>>24)&0xf];
+ *outp++ = hexdigits[(c>>20)&0xf];
+ *outp++ = hexdigits[(c>>16)&0xf];
+ *outp++ = hexdigits[(c>>12)&0xf];
+ *outp++ = hexdigits[(c>>8)&0xf];
+ }
+ else
#endif
- if (c >= 0x100) {
- *outp++ = 'u';
- *outp++ = hexdigits[(c>>12)&0xf];
- *outp++ = hexdigits[(c>>8)&0xf];
- }
- else
- *outp++ = 'x';
- *outp++ = hexdigits[(c>>4)&0xf];
- *outp++ = hexdigits[c&0xf];
- }
-
- restuple = Py_BuildValue("(On)", res, end);
- Py_DECREF(res);
- Py_DECREF(object);
- return restuple;
+ if (c >= 0x100) {
+ *outp++ = 'u';
+ *outp++ = hexdigits[(c>>12)&0xf];
+ *outp++ = hexdigits[(c>>8)&0xf];
+ }
+ else
+ *outp++ = 'x';
+ *outp++ = hexdigits[(c>>4)&0xf];
+ *outp++ = hexdigits[c&0xf];
+ }
+
+ restuple = Py_BuildValue("(On)", res, end);
+ Py_DECREF(res);
+ Py_DECREF(object);
+ return restuple;
}
else {
- wrong_exception_type(exc);
- return NULL;
+ wrong_exception_type(exc);
+ return NULL;
}
}
#endif
@@ -765,51 +765,63 @@ static PyObject *backslashreplace_errors(PyObject *self, PyObject *exc)
static int _PyCodecRegistry_Init(void)
{
static struct {
- char *name;
- PyMethodDef def;
+ char *name;
+ PyMethodDef def;
} methods[] =
{
- {
- "strict",
- {
- "strict_errors",
- strict_errors,
- METH_O
- }
- },
+ {
+ "strict",
+ {
+ "strict_errors",
+ strict_errors,
+ METH_O,
+ PyDoc_STR("Implements the 'strict' error handling, which "
+ "raises a UnicodeError on coding errors.")
+ }
+ },
#ifdef Py_USING_UNICODE
- {
- "ignore",
- {
- "ignore_errors",
- ignore_errors,
- METH_O
- }
- },
- {
- "replace",
- {
- "replace_errors",
- replace_errors,
- METH_O
- }
- },
- {
- "xmlcharrefreplace",
- {
- "xmlcharrefreplace_errors",
- xmlcharrefreplace_errors,
- METH_O
- }
- },
- {
- "backslashreplace",
- {
- "backslashreplace_errors",
- backslashreplace_errors,
- METH_O
- }
- }
+ {
+ "ignore",
+ {
+ "ignore_errors",
+ ignore_errors,
+ METH_O,
+ PyDoc_STR("Implements the 'ignore' error handling, which "
+ "ignores malformed data and continues.")
+ }
+ },
+ {
+ "replace",
+ {
+ "replace_errors",
+ replace_errors,
+ METH_O,
+ PyDoc_STR("Implements the 'replace' error handling, which "
+ "replaces malformed data with a replacement marker.")
+ }
+ },
+ {
+ "xmlcharrefreplace",
+ {
+ "xmlcharrefreplace_errors",
+ xmlcharrefreplace_errors,
+ METH_O,
+ PyDoc_STR("Implements the 'xmlcharrefreplace' error handling, "
+ "which replaces an unencodable character with the "
+ "appropriate XML character reference.")
+ }
+ },
+ {
+ "backslashreplace",
+ {
+ "backslashreplace_errors",
+ backslashreplace_errors,
+ METH_O,
+ PyDoc_STR("Implements the 'backslashreplace' error handling, "
+ "which replaces an unencodable character with a "
+ "backslashed escape sequence.")
+ }
+ }
#endif
};
@@ -818,42 +830,42 @@ static int _PyCodecRegistry_Init(void)
unsigned i;
if (interp->codec_search_path != NULL)
- return 0;
+ return 0;
interp->codec_search_path = PyList_New(0);
interp->codec_search_cache = PyDict_New();
interp->codec_error_registry = PyDict_New();
if (interp->codec_error_registry) {
- for (i = 0; i < sizeof(methods)/sizeof(methods[0]); ++i) {
- PyObject *func = PyCFunction_New(&methods[i].def, NULL);
- int res;
- if (!func)
- Py_FatalError("can't initialize codec error registry");
- res = PyCodec_RegisterError(methods[i].name, func);
- Py_DECREF(func);
- if (res)
- Py_FatalError("can't initialize codec error registry");
- }
+ for (i = 0; i < sizeof(methods)/sizeof(methods[0]); ++i) {
+ PyObject *func = PyCFunction_New(&methods[i].def, NULL);
+ int res;
+ if (!func)
+ Py_FatalError("can't initialize codec error registry");
+ res = PyCodec_RegisterError(methods[i].name, func);
+ Py_DECREF(func);
+ if (res)
+ Py_FatalError("can't initialize codec error registry");
+ }
}
if (interp->codec_search_path == NULL ||
- interp->codec_search_cache == NULL ||
- interp->codec_error_registry == NULL)
- Py_FatalError("can't initialize codec registry");
+ interp->codec_search_cache == NULL ||
+ interp->codec_error_registry == NULL)
+ Py_FatalError("can't initialize codec registry");
mod = PyImport_ImportModuleLevel("encodings", NULL, NULL, NULL, 0);
if (mod == NULL) {
- if (PyErr_ExceptionMatches(PyExc_ImportError)) {
- /* Ignore ImportErrors... this is done so that
- distributions can disable the encodings package. Note
- that other errors are not masked, e.g. SystemErrors
- raised to inform the user of an error in the Python
- configuration are still reported back to the user. */
- PyErr_Clear();
- return 0;
- }
- return -1;
+ if (PyErr_ExceptionMatches(PyExc_ImportError)) {
+ /* Ignore ImportErrors... this is done so that
+ distributions can disable the encodings package. Note
+ that other errors are not masked, e.g. SystemErrors
+ raised to inform the user of an error in the Python
+ configuration are still reported back to the user. */
+ PyErr_Clear();
+ return 0;
+ }
+ return -1;
}
Py_DECREF(mod);
return 0;
View Lorry Controller Status