diff --git a/Doc/c-api/codec.rst b/Doc/c-api/codec.rst new file mode 100644 index 00000000000..31a6bdef4c6 --- /dev/null +++ b/Doc/c-api/codec.rst @@ -0,0 +1,120 @@ +.. _codec-registry: + +Codec registry and support functions +==================================== + +.. c:function:: int PyCodec_Register(PyObject *search_function) + + Register a new codec search function. + + As side effect, this tries to load the :mod:`encodings` package, if not yet + done, to make sure that it is always first in the list of search functions. + +.. c:function:: int PyCodec_KnownEncoding(const char *encoding) + + Return ``1`` or ``0`` depending on whether there is a registered codec for + the given *encoding*. + +.. c:function:: PyObject* PyCodec_Encode(PyObject *object, const char *encoding, const char *errors) + + Generic codec based encoding API. + + *object* is passed through the encoder function found for the given + *encoding* using the error handling method defined by *errors*. *errors* may + be *NULL* to use the default method defined for the codec. Raises a + :exc:`LookupError` if no encoder can be found. + +.. c:function:: PyObject* PyCodec_Decode(PyObject *object, const char *encoding, const char *errors) + + Generic codec based decoding API. + + *object* is passed through the decoder function found for the given + *encoding* using the error handling method defined by *errors*. *errors* may + be *NULL* to use the default method defined for the codec. Raises a + :exc:`LookupError` if no encoder can be found. + + +Codec lookup API +---------------- + +In the following functions, the *encoding* string is looked up converted to all +lower-case characters, which makes encodings looked up through this mechanism +effectively case-insensitive. If no codec is found, a :exc:`KeyError` is set +and *NULL* returned. + +.. c:function:: PyObject* PyCodec_Encoder(const char *encoding) + + Get an encoder function for the given *encoding*. + +.. c:function:: PyObject* PyCodec_Decoder(const char *encoding) + + Get a decoder function for the given *encoding*. + +.. c:function:: PyObject* PyCodec_IncrementalEncoder(const char *encoding, const char *errors) + + Get an :class:`IncrementalEncoder` object for the given *encoding*. + +.. c:function:: PyObject* PyCodec_IncrementalDecoder(const char *encoding, const char *errors) + + Get an :class:`IncrementalDecoder` object for the given *encoding*. + +.. c:function:: PyObject* PyCodec_StreamReader(const char *encoding, PyObject *stream, const char *errors) + + Get a :class:`StreamReader` factory function for the given *encoding*. + +.. c:function:: PyObject* PyCodec_StreamWriter(const char *encoding, PyObject *stream, const char *errors) + + Get a :class:`StreamWriter` factory function for the given *encoding*. + + +Registry API for Unicode encoding error handlers +------------------------------------------------ + +.. c:function:: int PyCodec_RegisterError(const char *name, PyObject *error) + + Register the error handling callback function *error* under the given *name*. + This callback function will be called by a codec when it encounters + unencodable characters/undecodable bytes and *name* is specified as the error + parameter in the call to the encode/decode function. + + The callback gets a single argument, an instance of + :exc:`UnicodeEncodeError`, :exc:`UnicodeDecodeError` or + :exc:`UnicodeTranslateError` that holds information about the problematic + sequence of characters or bytes and their offset in the original string. The + callback must either raise the given exception, or return a two-item tuple + containing the replacement for the problematic sequence, and an integer + giving the offset in the original string at which encoding/decoding should be + resumed. + + .. XXX once they are documented, link to PyUnicode*Error access functions + to show how to get at the exception properties + + Return ``0`` on success, ``-1`` on error. + +.. c:function:: PyObject* PyCodec_LookupError(const char *name) + + Lookup the error handling callback function registered under *name*. As a + special case *NULL* can be passed, in which case the error handling callback + for "strict" will be returned. + +.. c:function:: PyObject* PyCodec_StrictErrors(PyObject *exc) + + Raise *exc* as an exception. + +.. c:function:: PyObject* PyCodec_IgnoreErrors(PyObject *exc) + + Ignore the unicode error, skipping the faulty input. + +.. c:function:: PyObject* PyCodec_ReplaceErrors(PyObject *exc) + + Replace the unicode encode error with ``?`` or ``U+FFFD``. + +.. c:function:: PyObject* PyCodec_XMLCharRefReplaceErrors(PyObject *exc) + + Replace the unicode encode error with XML character references. + +.. c:function:: PyObject* PyCodec_BackslashReplaceErrors(PyObject *exc) + + Replace the unicode encode error with backslash escapes (``\x``, ``\u`` and + ``\U``). + diff --git a/Doc/c-api/utilities.rst b/Doc/c-api/utilities.rst index 6cb4d0dfb86..d4484fb2712 100644 --- a/Doc/c-api/utilities.rst +++ b/Doc/c-api/utilities.rst @@ -18,3 +18,4 @@ and parsing function arguments and constructing Python values from C values. arg.rst conversion.rst reflection.rst + codec.rst diff --git a/Include/codecs.h b/Include/codecs.h index c979e86a2fc..4ea934e861d 100644 --- a/Include/codecs.h +++ b/Include/codecs.h @@ -144,7 +144,7 @@ PyAPI_FUNC(PyObject *) PyCodec_StreamWriter( /* Unicode encoding error handling callback registry API */ -/* Register the error handling callback function error under the name +/* Register the error handling callback function error under the given name. This function will be called by the codec when it encounters unencodable characters/undecodable bytes and doesn't know the callback name, when name is specified as the error parameter @@ -152,8 +152,8 @@ PyAPI_FUNC(PyObject *) PyCodec_StreamWriter( Return 0 on success, -1 on error */ PyAPI_FUNC(int) PyCodec_RegisterError(const char *name, PyObject *error); -/* Lookup the error handling callback function registered under the - name error. As a special case NULL can be passed, in which case +/* Lookup the error handling callback function registered under the given + name. As a special case NULL can be passed, in which case the error handling callback for "strict" will be returned. */ PyAPI_FUNC(PyObject *) PyCodec_LookupError(const char *name); @@ -163,7 +163,7 @@ PyAPI_FUNC(PyObject *) PyCodec_StrictErrors(PyObject *exc); /* ignore the unicode error, skipping the faulty input */ PyAPI_FUNC(PyObject *) PyCodec_IgnoreErrors(PyObject *exc); -/* replace the unicode error with ? or U+FFFD */ +/* replace the unicode encode error with ? or U+FFFD */ PyAPI_FUNC(PyObject *) PyCodec_ReplaceErrors(PyObject *exc); /* replace the unicode encode error with XML character references */