From a977329b6fb0e4c95cabb9043794de69b27a1099 Mon Sep 17 00:00:00 2001 From: Thomas Wouters Date: Fri, 21 Apr 2006 09:43:23 +0000 Subject: [PATCH] Merge part of the trunk changes into the p3yk branch. This merges from 43030 (branch-creation time) up to 43067. 43068 and 43069 contain a little swapping action between re.py and sre.py, and this mightily confuses svn merge, so later changes are going in separately. This merge should break no additional tests. The last-merged revision is going in a 'last_merge' property on '.' (the branch directory.) Arbitrarily chosen, really; if there's a BCP for this, I couldn't find it, but we can easily change it afterwards ;) --- Doc/lib/libcodecs.tex | 168 +++- Doc/whatsnew/whatsnew25.tex | 6 + Include/codecs.h | 22 +- Lib/StringIO.py | 3 +- Lib/codecs.py | 183 ++++- Lib/encodings/__init__.py | 31 +- Lib/encodings/ascii.py | 19 +- Lib/encodings/base64_codec.py | 21 +- Lib/encodings/bz2_codec.py | 21 +- Lib/encodings/charmap.py | 31 +- Lib/encodings/cp037.py | 23 +- Lib/encodings/cp1006.py | 23 +- Lib/encodings/cp1026.py | 23 +- Lib/encodings/cp1140.py | 23 +- Lib/encodings/cp1250.py | 23 +- Lib/encodings/cp1251.py | 23 +- Lib/encodings/cp1252.py | 23 +- Lib/encodings/cp1253.py | 23 +- Lib/encodings/cp1254.py | 23 +- Lib/encodings/cp1255.py | 23 +- Lib/encodings/cp1256.py | 23 +- Lib/encodings/cp1257.py | 23 +- Lib/encodings/cp1258.py | 23 +- Lib/encodings/cp424.py | 23 +- Lib/encodings/cp437.py | 23 +- Lib/encodings/cp500.py | 23 +- Lib/encodings/cp737.py | 23 +- Lib/encodings/cp775.py | 24 +- Lib/encodings/cp850.py | 21 +- Lib/encodings/cp852.py | 21 +- Lib/encodings/cp855.py | 21 +- Lib/encodings/cp856.py | 23 +- Lib/encodings/cp857.py | 21 +- Lib/encodings/cp860.py | 21 +- Lib/encodings/cp861.py | 21 +- Lib/encodings/cp862.py | 21 +- Lib/encodings/cp863.py | 21 +- Lib/encodings/cp864.py | 21 +- Lib/encodings/cp865.py | 21 +- Lib/encodings/cp866.py | 21 +- Lib/encodings/cp869.py | 21 +- Lib/encodings/cp874.py | 23 +- Lib/encodings/cp875.py | 23 +- Lib/encodings/hex_codec.py | 21 +- Lib/encodings/hp_roman8.py | 21 +- Lib/encodings/idna.py | 19 +- Lib/encodings/iso8859_1.py | 23 +- Lib/encodings/iso8859_10.py | 23 +- Lib/encodings/iso8859_11.py | 23 +- Lib/encodings/iso8859_13.py | 23 +- Lib/encodings/iso8859_14.py | 23 +- Lib/encodings/iso8859_15.py | 23 +- Lib/encodings/iso8859_16.py | 23 +- Lib/encodings/iso8859_2.py | 23 +- Lib/encodings/iso8859_3.py | 23 +- Lib/encodings/iso8859_4.py | 23 +- Lib/encodings/iso8859_5.py | 23 +- Lib/encodings/iso8859_6.py | 23 +- Lib/encodings/iso8859_7.py | 23 +- Lib/encodings/iso8859_8.py | 23 +- Lib/encodings/iso8859_9.py | 23 +- Lib/encodings/koi8_r.py | 23 +- Lib/encodings/koi8_u.py | 23 +- Lib/encodings/latin_1.py | 19 +- Lib/encodings/mac_arabic.py | 21 +- Lib/encodings/mac_centeuro.py | 23 +- Lib/encodings/mac_croatian.py | 23 +- Lib/encodings/mac_cyrillic.py | 23 +- Lib/encodings/mac_farsi.py | 23 +- Lib/encodings/mac_greek.py | 23 +- Lib/encodings/mac_iceland.py | 23 +- Lib/encodings/mac_latin2.py | 21 +- Lib/encodings/mac_roman.py | 23 +- Lib/encodings/mac_romanian.py | 23 +- Lib/encodings/mac_turkish.py | 23 +- Lib/encodings/mbcs.py | 18 +- Lib/encodings/palmos.py | 18 +- Lib/encodings/ptcp154.py | 21 +- Lib/encodings/punycode.py | 24 +- Lib/encodings/quopri_codec.py | 18 +- Lib/encodings/raw_unicode_escape.py | 19 +- Lib/encodings/rot_13.py | 21 +- Lib/encodings/string_escape.py | 19 +- Lib/encodings/tis_620.py | 23 +- Lib/encodings/undefined.py | 23 +- Lib/encodings/unicode_escape.py | 19 +- Lib/encodings/unicode_internal.py | 19 +- Lib/encodings/utf_16.py | 52 +- Lib/encodings/utf_16_be.py | 18 +- Lib/encodings/utf_16_le.py | 19 +- Lib/encodings/utf_7.py | 19 +- Lib/encodings/utf_8.py | 18 +- Lib/encodings/utf_8_sig.py | 47 +- Lib/encodings/uu_codec.py | 20 +- Lib/encodings/zlib_codec.py | 21 +- Lib/logging/__init__.py | 7 +- Lib/runpy.py | 431 ++++++++++ Lib/test/regrtest.py | 3 - Lib/test/test_StringIO.py | 9 + Lib/test/test___all__.py | 3 - Lib/test/test_codecs.py | 57 ++ Lib/test/test_runpy.py | 172 ++++ ...{test_hashlib_speed.py => time_hashlib.py} | 9 +- Makefile.pre.in | 2 + Modules/_ctypes/_ctypes.c | 8 + Modules/_ctypes/cfield.c | 18 +- Modules/_ctypes/ctypes.h | 13 + Modules/_testcapimodule.c | 13 + Modules/cStringIO.c | 3 +- Modules/main.c | 79 +- Modules/xxmodule.c | 14 - Objects/obmalloc.c | 740 +++++++++++++----- Python/codecs.c | 50 ++ Tools/buildbot/clean.bat | 5 +- Tools/unicode/Makefile | 4 +- Tools/unicode/gencodec.py | 61 +- 116 files changed, 3409 insertions(+), 709 deletions(-) create mode 100755 Lib/runpy.py create mode 100644 Lib/test/test_runpy.py rename Lib/test/{test_hashlib_speed.py => time_hashlib.py} (92%) diff --git a/Doc/lib/libcodecs.tex b/Doc/lib/libcodecs.tex index 9e92217baac..1806ef0addd 100644 --- a/Doc/lib/libcodecs.tex +++ b/Doc/lib/libcodecs.tex @@ -24,8 +24,19 @@ It defines the following functions: \begin{funcdesc}{register}{search_function} Register a codec search function. Search functions are expected to take one argument, the encoding name in all lower case letters, and -return a tuple of functions \code{(\var{encoder}, \var{decoder}, \var{stream_reader}, -\var{stream_writer})} taking the following arguments: +return a \class{CodecInfo} object having the following attributes: + +\begin{itemize} + \item \code{name} The name of the encoding; + \item \code{encoder} The stateless encoding function; + \item \code{decoder} The stateless decoding function; + \item \code{incrementalencoder} An incremental encoder class or factory function; + \item \code{incrementaldecoder} An incremental decoder class or factory function; + \item \code{streamwriter} A stream writer class or factory function; + \item \code{streamreader} A stream reader class or factory function. +\end{itemize} + +The various functions or classes take the following arguments: \var{encoder} and \var{decoder}: These must be functions or methods which have the same interface as the @@ -33,7 +44,17 @@ return a tuple of functions \code{(\var{encoder}, \var{decoder}, \var{stream_rea Codec Interface). The functions/methods are expected to work in a stateless mode. - \var{stream_reader} and \var{stream_writer}: These have to be + \var{incrementalencoder} and \var{incrementalencoder}: These have to be + factory functions providing the following interface: + + \code{factory(\var{errors}='strict')} + + The factory functions must return objects providing the interfaces + defined by the base classes \class{IncrementalEncoder} and + \class{IncrementalEncoder}, respectively. Incremental codecs can maintain + state. + + \var{streamreader} and \var{streamwriter}: These have to be factory functions providing the following interface: \code{factory(\var{stream}, \var{errors}='strict')} @@ -58,13 +79,13 @@ return \code{None}. \end{funcdesc} \begin{funcdesc}{lookup}{encoding} -Looks up a codec tuple in the Python codec registry and returns the -function tuple as defined above. +Looks up the codec info in the Python codec registry and returns a +\class{CodecInfo} object as defined above. Encodings are first looked up in the registry's cache. If not found, -the list of registered search functions is scanned. If no codecs tuple -is found, a \exception{LookupError} is raised. Otherwise, the codecs -tuple is stored in the cache and returned to the caller. +the list of registered search functions is scanned. If no \class{CodecInfo} +object is found, a \exception{LookupError} is raised. Otherwise, the +\class{CodecInfo} object is stored in the cache and returned to the caller. \end{funcdesc} To simplify access to the various codecs, the module provides these @@ -85,6 +106,22 @@ function. Raises a \exception{LookupError} in case the encoding cannot be found. \end{funcdesc} +\begin{funcdesc}{getincrementalencoder}{encoding} +Lookup up the codec for the given encoding and return its incremental encoder +class or factory function. + +Raises a \exception{LookupError} in case the encoding cannot be found or the +codec doesn't support an incremental encoder. +\end{funcdesc} + +\begin{funcdesc}{getincrementaldecoder}{encoding} +Lookup up the codec for the given encoding and return its incremental decoder +class or factory function. + +Raises a \exception{LookupError} in case the encoding cannot be found or the +codec doesn't support an incremental decoder. +\end{funcdesc} + \begin{funcdesc}{getreader}{encoding} Lookup up the codec for the given encoding and return its StreamReader class or factory function. @@ -188,6 +225,18 @@ If \var{output} is not given, it defaults to \var{input}. an encoding error occurs. \end{funcdesc} +\begin{funcdesc}{iterencode}{iterable, encoding\optional{, errors}} +Uses an incremental encoder to iteratively encode the input provided by +\var{iterable}. This function is a generator. \var{errors} (as well as +any other keyword argument) is passed through to the incremental encoder. +\end{funcdesc} + +\begin{funcdesc}{iterdecode}{iterable, encoding\optional{, errors}} +Uses an incremental decoder to iteratively decode the input provided by +\var{iterable}. This function is a generator. \var{errors} (as well as +any other keyword argument) is passed through to the incremental encoder. +\end{funcdesc} + The module also provides the following constants which are useful for reading and writing to platform dependent files: @@ -292,6 +341,109 @@ function interfaces of the stateless encoder and decoder: empty object of the output object type in this situation. \end{methoddesc} +The \class{IncrementalEncoder} and \class{IncrementalDecoder} classes provide +the basic interface for incremental encoding and decoding. Encoding/decoding the +input isn't done with one call to the stateless encoder/decoder function, +but with multiple calls to the \method{encode}/\method{decode} method of the +incremental encoder/decoder. The incremental encoder/decoder keeps track of +the encoding/decoding process during method calls. + +The joined output of calls to the \method{encode}/\method{decode} method is the +same as if the all single inputs where joined into one, and this input was +encoded/decoded with the stateless encoder/decoder. + + +\subsubsection{IncrementalEncoder Objects \label{incremental-encoder-objects}} + +The \class{IncrementalEncoder} class is used for encoding an input in multiple +steps. It defines the following methods which every incremental encoder must +define in order to be compatible to the Python codec registry. + +\begin{classdesc}{IncrementalEncoder}{\optional{errors}} + Constructor for a \class{IncrementalEncoder} instance. + + All incremental encoders must provide this constructor interface. They are + free to add additional keyword arguments, but only the ones defined + here are used by the Python codec registry. + + The \class{IncrementalEncoder} may implement different error handling + schemes by providing the \var{errors} keyword argument. These + parameters are predefined: + + \begin{itemize} + \item \code{'strict'} Raise \exception{ValueError} (or a subclass); + this is the default. + \item \code{'ignore'} Ignore the character and continue with the next. + \item \code{'replace'} Replace with a suitable replacement character + \item \code{'xmlcharrefreplace'} Replace with the appropriate XML + character reference + \item \code{'backslashreplace'} Replace with backslashed escape sequences. + \end{itemize} + + The \var{errors} argument will be assigned to an attribute of the + same name. Assigning to this attribute makes it possible to switch + between different error handling strategies during the lifetime + of the \class{IncrementalEncoder} object. + + The set of allowed values for the \var{errors} argument can + be extended with \function{register_error()}. +\end{classdesc} + +\begin{methoddesc}{encode}{object\optional{, final}} + Encodes \var{object} (taking the current state of the encoder into account) + and returns the resulting encoded object. If this is the last call to + \method{encode} \var{final} must be true (the default is false). +\end{methoddesc} + +\begin{methoddesc}{reset}{} + Reset the encoder to the initial state. +\end{methoddesc} + + +\subsubsection{IncrementalDecoder Objects \label{incremental-decoder-objects}} + +The \class{IncrementalDecoder} class is used for decoding an input in multiple +steps. It defines the following methods which every incremental decoder must +define in order to be compatible to the Python codec registry. + +\begin{classdesc}{IncrementalDecoder}{\optional{errors}} + Constructor for a \class{IncrementalDecoder} instance. + + All incremental decoders must provide this constructor interface. They are + free to add additional keyword arguments, but only the ones defined + here are used by the Python codec registry. + + The \class{IncrementalDecoder} may implement different error handling + schemes by providing the \var{errors} keyword argument. These + parameters are predefined: + + \begin{itemize} + \item \code{'strict'} Raise \exception{ValueError} (or a subclass); + this is the default. + \item \code{'ignore'} Ignore the character and continue with the next. + \item \code{'replace'} Replace with a suitable replacement character. + \end{itemize} + + The \var{errors} argument will be assigned to an attribute of the + same name. Assigning to this attribute makes it possible to switch + between different error handling strategies during the lifetime + of the \class{IncrementalEncoder} object. + + The set of allowed values for the \var{errors} argument can + be extended with \function{register_error()}. +\end{classdesc} + +\begin{methoddesc}{decode}{object\optional{, final}} + Decodes \var{object} (taking the current state of the decoder into account) + and returns the resulting decoded object. If this is the last call to + \method{decode} \var{final} must be true (the default is false). +\end{methoddesc} + +\begin{methoddesc}{reset}{} + Reset the decoder to the initial state. +\end{methoddesc} + + The \class{StreamWriter} and \class{StreamReader} classes provide generic working interfaces which can be used to implement new encodings submodules very easily. See \module{encodings.utf_8} for an diff --git a/Doc/whatsnew/whatsnew25.tex b/Doc/whatsnew/whatsnew25.tex index ff64af0c534..57432855ac3 100644 --- a/Doc/whatsnew/whatsnew25.tex +++ b/Doc/whatsnew/whatsnew25.tex @@ -209,6 +209,12 @@ implemented by Richard Jones and Fred Drake.} % XXX write this +%====================================================================== +\section{PEP 338: Executing Modules as Scripts} + +% XXX write this + + %====================================================================== \section{PEP 341: Unified try/except/finally} diff --git a/Include/codecs.h b/Include/codecs.h index 82f18cdc5e7..0d76241dbf5 100644 --- a/Include/codecs.h +++ b/Include/codecs.h @@ -29,15 +29,15 @@ PyAPI_FUNC(int) PyCodec_Register( /* Codec register lookup API. - Looks up the given encoding and returns a tuple (encoder, decoder, - stream reader, stream writer) of functions which implement the - different aspects of processing the encoding. + Looks up the given encoding and returns a CodecInfo object with + function attributes which implement the different aspects of + processing the encoding. The encoding string is looked up converted to all lower-case characters. This makes encodings looked up through this mechanism effectively case-insensitive. - If no codec is found, a KeyError is set and NULL returned. + If no codec is found, a KeyError 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 @@ -101,6 +101,20 @@ PyAPI_FUNC(PyObject *) PyCodec_Decoder( const char *encoding ); +/* Get a IncrementalEncoder object for the given encoding. */ + +PyAPI_FUNC(PyObject *) PyCodec_IncrementalEncoder( + const char *encoding, + const char *errors + ); + +/* Get a IncrementalDecoder object function for the given encoding. */ + +PyAPI_FUNC(PyObject *) PyCodec_IncrementalDecoder( + const char *encoding, + const char *errors + ); + /* Get a StreamReader factory function for the given encoding. */ PyAPI_FUNC(PyObject *) PyCodec_StreamReader( diff --git a/Lib/StringIO.py b/Lib/StringIO.py index 5c463fbc1c9..1e5f25408d7 100644 --- a/Lib/StringIO.py +++ b/Lib/StringIO.py @@ -72,8 +72,7 @@ class StringIO: method is called repeatedly. This method returns the next input line, or raises StopIteration when EOF is hit. """ - if self.closed: - raise StopIteration + _complain_ifclosed(self.closed) r = self.readline() if not r: raise StopIteration diff --git a/Lib/codecs.py b/Lib/codecs.py index 6895a228fed..28856c714e9 100644 --- a/Lib/codecs.py +++ b/Lib/codecs.py @@ -73,6 +73,23 @@ BOM64_BE = BOM_UTF32_BE ### Codec base classes (defining the API) +class CodecInfo(tuple): + + def __new__(cls, encode, decode, streamreader=None, streamwriter=None, + incrementalencoder=None, incrementaldecoder=None, name=None): + self = tuple.__new__(cls, (encode, decode, streamreader, streamwriter)) + self.name = name + self.encode = encode + self.decode = decode + self.incrementalencoder = incrementalencoder + self.incrementaldecoder = incrementaldecoder + self.streamwriter = streamwriter + self.streamreader = streamreader + return self + + def __repr__(self): + return "<%s.%s object for encoding %s at 0x%x>" % (self.__class__.__module__, self.__class__.__name__, self.name, id(self)) + class Codec: """ Defines the interface for stateless encoders/decoders. @@ -137,6 +154,88 @@ class Codec: """ raise NotImplementedError +class IncrementalEncoder(object): + """ + A IncrementalEncoder encodes an input in multiple steps. The input can be + passed piece by piece to the encode() method. The IncrementalEncoder remembers + the state of the Encoding process between calls to encode(). + """ + def __init__(self, errors='strict'): + """ + Creates a IncrementalEncoder instance. + + The IncrementalEncoder may use different error handling schemes by + providing the errors keyword argument. See the module docstring + for a list of possible values. + """ + self.errors = errors + self.buffer = "" + + def encode(self, input, final=False): + """ + Encodes input and returns the resulting object. + """ + raise NotImplementedError + + def reset(self): + """ + Resets the encoder to the initial state. + """ + +class IncrementalDecoder(object): + """ + An IncrementalDecoder decodes an input in multiple steps. The input can be + passed piece by piece to the decode() method. The IncrementalDecoder + remembers the state of the decoding process between calls to decode(). + """ + def __init__(self, errors='strict'): + """ + Creates a IncrementalDecoder instance. + + The IncrementalDecoder may use different error handling schemes by + providing the errors keyword argument. See the module docstring + for a list of possible values. + """ + self.errors = errors + + def decode(self, input, final=False): + """ + Decodes input and returns the resulting object. + """ + raise NotImplementedError + + def reset(self): + """ + Resets the decoder to the initial state. + """ + +class BufferedIncrementalDecoder(IncrementalDecoder): + """ + This subclass of IncrementalDecoder can be used as the baseclass for an + incremental decoder if the decoder must be able to handle incomplete byte + sequences. + """ + def __init__(self, errors='strict'): + IncrementalDecoder.__init__(self, errors) + self.buffer = "" # undecoded input that is kept between calls to decode() + + def _buffer_decode(self, input, errors, final): + # Overwrite this method in subclasses: It must decode input + # and return an (output, length consumed) tuple + raise NotImplementedError + + def decode(self, input, final=False): + # decode input (taking the buffer into account) + data = self.buffer + input + (result, consumed) = self._buffer_decode(data, self.errors, final) + # keep undecoded input until the next call + self.buffer = data[consumed:] + return result + + def reset(self): + IncrementalDecoder.reset(self) + self.bytebuffer = "" + # # The StreamWriter and StreamReader class provide generic working # interfaces which can be used to implement new encoding submodules @@ -666,8 +765,8 @@ def open(filename, mode='rb', encoding=None, errors='strict', buffering=1): file = __builtin__.open(filename, mode, buffering) if encoding is None: return file - (e, d, sr, sw) = lookup(encoding) - srw = StreamReaderWriter(file, sr, sw, errors) + info = lookup(encoding) + srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, errors) # Add attributes to simplify introspection srw.encoding = encoding return srw @@ -699,11 +798,9 @@ def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'): """ if file_encoding is None: file_encoding = data_encoding - encode, decode = lookup(data_encoding)[:2] - Reader, Writer = lookup(file_encoding)[2:] - sr = StreamRecoder(file, - encode, decode, Reader, Writer, - errors) + info = lookup(data_encoding) + sr = StreamRecoder(file, info.encode, info.decode, + info.streamreader, info.streamwriter, errors) # Add attributes to simplify introspection sr.data_encoding = data_encoding sr.file_encoding = file_encoding @@ -719,7 +816,7 @@ def getencoder(encoding): Raises a LookupError in case the encoding cannot be found. """ - return lookup(encoding)[0] + return lookup(encoding).encode def getdecoder(encoding): @@ -729,7 +826,35 @@ def getdecoder(encoding): Raises a LookupError in case the encoding cannot be found. """ - return lookup(encoding)[1] + return lookup(encoding).decode + +def getincrementalencoder(encoding): + + """ Lookup up the codec for the given encoding and return + its IncrementalEncoder class or factory function. + + Raises a LookupError in case the encoding cannot be found + or the codecs doesn't provide an incremental encoder. + + """ + encoder = lookup(encoding).incrementalencoder + if encoder is None: + raise LookupError(encoding) + return encoder + +def getincrementaldecoder(encoding): + + """ Lookup up the codec for the given encoding and return + its IncrementalDecoder class or factory function. + + Raises a LookupError in case the encoding cannot be found + or the codecs doesn't provide an incremental decoder. + + """ + decoder = lookup(encoding).incrementaldecoder + if decoder is None: + raise LookupError(encoding) + return decoder def getreader(encoding): @@ -739,7 +864,7 @@ def getreader(encoding): Raises a LookupError in case the encoding cannot be found. """ - return lookup(encoding)[2] + return lookup(encoding).streamreader def getwriter(encoding): @@ -749,7 +874,43 @@ def getwriter(encoding): Raises a LookupError in case the encoding cannot be found. """ - return lookup(encoding)[3] + return lookup(encoding).streamwriter + +def iterencode(iterator, encoding, errors='strict', **kwargs): + """ + Encoding iterator. + + Encodes the input strings from the iterator using a IncrementalEncoder. + + errors and kwargs are passed through to the IncrementalEncoder + constructor. + """ + encoder = getincrementalencoder(encoding)(errors, **kwargs) + for input in iterator: + output = encoder.encode(input) + if output: + yield output + output = encoder.encode("", True) + if output: + yield output + +def iterdecode(iterator, encoding, errors='strict', **kwargs): + """ + Decoding iterator. + + Decodes the input strings from the iterator using a IncrementalDecoder. + + errors and kwargs are passed through to the IncrementalDecoder + constructor. + """ + decoder = getincrementaldecoder(encoding)(errors, **kwargs) + for input in iterator: + output = decoder.decode(input) + if output: + yield output + output = decoder.decode("", True) + if output: + yield output ### Helpers for charmap-based codecs diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py index ddaacb9e3f2..1f469bf7d65 100644 --- a/Lib/encodings/__init__.py +++ b/Lib/encodings/__init__.py @@ -9,9 +9,10 @@ Each codec module must export the following interface: - * getregentry() -> (encoder, decoder, stream_reader, stream_writer) - The getregentry() API must return callable objects which adhere to - the Python Codec Interface Standard. + * getregentry() -> codecs.CodecInfo object + The getregentry() API must a CodecInfo object with encoder, decoder, + incrementalencoder, incrementaldecoder, streamwriter and streamreader + atttributes which adhere to the Python Codec Interface Standard. In addition, a module may optionally also define the following APIs which are then used by the package's codec search function: @@ -113,16 +114,24 @@ def search_function(encoding): return None # Now ask the module for the registry entry - entry = tuple(getregentry()) - if len(entry) != 4: - raise CodecRegistryError,\ - 'module "%s" (%s) failed to register' % \ - (mod.__name__, mod.__file__) - for obj in entry: - if not callable(obj): + entry = getregentry() + if not isinstance(entry, codecs.CodecInfo): + if not 4 <= len(entry) <= 7: raise CodecRegistryError,\ - 'incompatible codecs in module "%s" (%s)' % \ + 'module "%s" (%s) failed to register' % \ (mod.__name__, mod.__file__) + if not callable(entry[0]) or \ + not callable(entry[1]) or \ + (entry[2] is not None and not callable(entry[2])) or \ + (entry[3] is not None and not callable(entry[3])) or \ + (len(entry) > 4 and entry[4] is not None and not callable(entry[4])) or \ + (len(entry) > 5 and entry[5] is not None and not callable(entry[5])): + raise CodecRegistryError,\ + 'incompatible codecs in module "%s" (%s)' % \ + (mod.__name__, mod.__file__) + if len(entry)<7 or entry[6] is None: + entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],) + entry = codecs.CodecInfo(*entry) # Cache the codec registry entry _cache[encoding] = entry diff --git a/Lib/encodings/ascii.py b/Lib/encodings/ascii.py index 05fc36a5533..2033cde9748 100644 --- a/Lib/encodings/ascii.py +++ b/Lib/encodings/ascii.py @@ -17,6 +17,14 @@ class Codec(codecs.Codec): encode = codecs.ascii_encode decode = codecs.ascii_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.ascii_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.ascii_decode(input, self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -31,5 +39,12 @@ class StreamConverter(StreamWriter,StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='ascii', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/base64_codec.py b/Lib/encodings/base64_codec.py index 085ab147170..f84e7808e99 100644 --- a/Lib/encodings/base64_codec.py +++ b/Lib/encodings/base64_codec.py @@ -49,6 +49,16 @@ class Codec(codecs.Codec): def decode(self, input,errors='strict'): return base64_decode(input,errors) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + assert self.errors == 'strict' + return base64.encodestring(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + assert self.errors == 'strict' + return base64.decodestring(input) + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -58,5 +68,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (base64_encode,base64_decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='base64', + encode=base64_encode, + decode=base64_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/bz2_codec.py b/Lib/encodings/bz2_codec.py index 870474ca177..81e84b6fb89 100644 --- a/Lib/encodings/bz2_codec.py +++ b/Lib/encodings/bz2_codec.py @@ -51,6 +51,16 @@ class Codec(codecs.Codec): def decode(self, input, errors='strict'): return bz2_decode(input, errors) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + assert self.errors == 'strict' + return bz2.compress(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + assert self.errors == 'strict' + return bz2.decompress(input) + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -60,5 +70,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (bz2_encode,bz2_decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name="bz2", + encode=bz2_encode, + decode=bz2_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/charmap.py b/Lib/encodings/charmap.py index 9bd93ecc334..81189b161a6 100644 --- a/Lib/encodings/charmap.py +++ b/Lib/encodings/charmap.py @@ -21,30 +21,49 @@ class Codec(codecs.Codec): encode = codecs.charmap_encode decode = codecs.charmap_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict', mapping=None): + codecs.IncrementalEncoder.__init__(self, errors) + self.mapping = mapping + + def encode(self, input, final=False): + return codecs.charmap_encode(input, self.errors, self.mapping)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def __init__(self, errors='strict', mapping=None): + codecs.IncrementalDecoder.__init__(self, errors) + self.mapping = mapping + + def decode(self, input, final=False): + return codecs.charmap_decode(input, self.errors, self.mapping)[0] + class StreamWriter(Codec,codecs.StreamWriter): def __init__(self,stream,errors='strict',mapping=None): - codecs.StreamWriter.__init__(self,stream,errors) self.mapping = mapping def encode(self,input,errors='strict'): - return Codec.encode(input,errors,self.mapping) class StreamReader(Codec,codecs.StreamReader): def __init__(self,stream,errors='strict',mapping=None): - codecs.StreamReader.__init__(self,stream,errors) self.mapping = mapping def decode(self,input,errors='strict'): - return Codec.decode(input,errors,self.mapping) ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='charmap', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/cp037.py b/Lib/encodings/cp037.py index 5864c4b0bb9..7e589a92a5f 100644 --- a/Lib/encodings/cp037.py +++ b/Lib/encodings/cp037.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py. +""" Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp037', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1006.py b/Lib/encodings/cp1006.py index d94563d14d0..782996951f8 100644 --- a/Lib/encodings/cp1006.py +++ b/Lib/encodings/cp1006.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1006', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1026.py b/Lib/encodings/cp1026.py index 648bed0198a..01c88044d8c 100644 --- a/Lib/encodings/cp1026.py +++ b/Lib/encodings/cp1026.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1026', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1140.py b/Lib/encodings/cp1140.py index 6507552bab2..ac8d41bc7be 100644 --- a/Lib/encodings/cp1140.py +++ b/Lib/encodings/cp1140.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'python-mappings/CP1140.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1140', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1250.py b/Lib/encodings/cp1250.py index 73427bc3066..6e6f57c05ee 100644 --- a/Lib/encodings/cp1250.py +++ b/Lib/encodings/cp1250.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1250', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1251.py b/Lib/encodings/cp1251.py index f3e107efa96..ed835fe2562 100644 --- a/Lib/encodings/cp1251.py +++ b/Lib/encodings/cp1251.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1251', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1252.py b/Lib/encodings/cp1252.py index ea7561d1e6f..e5b6905eaee 100644 --- a/Lib/encodings/cp1252.py +++ b/Lib/encodings/cp1252.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1252', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1253.py b/Lib/encodings/cp1253.py index 5feefb38148..3ce70b25d94 100644 --- a/Lib/encodings/cp1253.py +++ b/Lib/encodings/cp1253.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1253', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1254.py b/Lib/encodings/cp1254.py index 6769e1be141..31cd48c1a50 100644 --- a/Lib/encodings/cp1254.py +++ b/Lib/encodings/cp1254.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1254 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1254', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1255.py b/Lib/encodings/cp1255.py index b994f9d844f..47c43ce90ae 100644 --- a/Lib/encodings/cp1255.py +++ b/Lib/encodings/cp1255.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1255 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1255', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1256.py b/Lib/encodings/cp1256.py index 5da425e3d50..e90393b6a7f 100644 --- a/Lib/encodings/cp1256.py +++ b/Lib/encodings/cp1256.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1256 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1256', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1257.py b/Lib/encodings/cp1257.py index 237a5317954..dcc81c09eb7 100644 --- a/Lib/encodings/cp1257.py +++ b/Lib/encodings/cp1257.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1257 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1257', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp1258.py b/Lib/encodings/cp1258.py index 5de3fd86607..d4d22712e37 100644 --- a/Lib/encodings/cp1258.py +++ b/Lib/encodings/cp1258.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py. +""" Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp1258', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp424.py b/Lib/encodings/cp424.py index d19c756c265..966aecb0991 100644 --- a/Lib/encodings/cp424.py +++ b/Lib/encodings/cp424.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py. +""" Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp424', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp437.py b/Lib/encodings/cp437.py index e9cefaf418b..52cd8829428 100644 --- a/Lib/encodings/cp437.py +++ b/Lib/encodings/cp437.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP437.TXT' with gencodec.py. +""" Python Character Mapping Codec cp437 generated from 'VENDORS/MICSFT/PC/CP437.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp437', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp500.py b/Lib/encodings/cp500.py index 3bbefa086b1..83af090700d 100644 --- a/Lib/encodings/cp500.py +++ b/Lib/encodings/cp500.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py. +""" Python Character Mapping Codec cp500 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp500', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp737.py b/Lib/encodings/cp737.py index 883a8bac73e..d6544482d2d 100644 --- a/Lib/encodings/cp737.py +++ b/Lib/encodings/cp737.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP737.TXT' with gencodec.py. +""" Python Character Mapping Codec cp737 generated from 'VENDORS/MICSFT/PC/CP737.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp737', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp775.py b/Lib/encodings/cp775.py index 1b39188cf47..6a456a5825e 100644 --- a/Lib/encodings/cp775.py +++ b/Lib/encodings/cp775.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py. +""" Python Character Mapping Codec cp775 generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,9 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) - + return codecs.CodecInfo( + name='cp775', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map decoding_map = codecs.make_identity_dict(range(256)) diff --git a/Lib/encodings/cp850.py b/Lib/encodings/cp850.py index 6481ee0a470..0c8478c8b20 100644 --- a/Lib/encodings/cp850.py +++ b/Lib/encodings/cp850.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp850', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp852.py b/Lib/encodings/cp852.py index 749b0da2e1f..069d5473b50 100644 --- a/Lib/encodings/cp852.py +++ b/Lib/encodings/cp852.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp852', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp855.py b/Lib/encodings/cp855.py index 13146c99f0d..241ef9d1e86 100644 --- a/Lib/encodings/cp855.py +++ b/Lib/encodings/cp855.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp855', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp856.py b/Lib/encodings/cp856.py index 5823dff8eeb..c72fcad9f94 100644 --- a/Lib/encodings/cp856.py +++ b/Lib/encodings/cp856.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py. +""" Python Character Mapping Codec cp856 generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp856', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp857.py b/Lib/encodings/cp857.py index 6c5cdbbc84a..c24191b04dc 100644 --- a/Lib/encodings/cp857.py +++ b/Lib/encodings/cp857.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp857', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp860.py b/Lib/encodings/cp860.py index cd7cdf44d7b..4acb0cf3626 100644 --- a/Lib/encodings/cp860.py +++ b/Lib/encodings/cp860.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp860', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp861.py b/Lib/encodings/cp861.py index b140f2e33d3..0939b5b1eef 100644 --- a/Lib/encodings/cp861.py +++ b/Lib/encodings/cp861.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp861', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp862.py b/Lib/encodings/cp862.py index badec0845db..ea0405ca1ba 100644 --- a/Lib/encodings/cp862.py +++ b/Lib/encodings/cp862.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp862', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp863.py b/Lib/encodings/cp863.py index 812bc3d4514..62dfabf66ab 100644 --- a/Lib/encodings/cp863.py +++ b/Lib/encodings/cp863.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp863', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp864.py b/Lib/encodings/cp864.py index 41f2ea385fe..02a0e733a87 100644 --- a/Lib/encodings/cp864.py +++ b/Lib/encodings/cp864.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp864', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp865.py b/Lib/encodings/cp865.py index 8e68c6b54a9..e9f45f1b508 100644 --- a/Lib/encodings/cp865.py +++ b/Lib/encodings/cp865.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp865', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp866.py b/Lib/encodings/cp866.py index 4c0dd8cc721..29cd85a3f10 100644 --- a/Lib/encodings/cp866.py +++ b/Lib/encodings/cp866.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp866', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp869.py b/Lib/encodings/cp869.py index 1747546f81e..b4dc99bf254 100644 --- a/Lib/encodings/cp869.py +++ b/Lib/encodings/cp869.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp869', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/cp874.py b/Lib/encodings/cp874.py index 5e1fea13a77..591e8aa39fa 100644 --- a/Lib/encodings/cp874.py +++ b/Lib/encodings/cp874.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py. +""" Python Character Mapping Codec cp874 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp874', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/cp875.py b/Lib/encodings/cp875.py index ccebb847bbb..879d5a4bc79 100644 --- a/Lib/encodings/cp875.py +++ b/Lib/encodings/cp875.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py. +""" Python Character Mapping Codec cp875 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='cp875', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/hex_codec.py b/Lib/encodings/hex_codec.py index 5c6e4a4e198..91b38d952e1 100644 --- a/Lib/encodings/hex_codec.py +++ b/Lib/encodings/hex_codec.py @@ -49,6 +49,16 @@ class Codec(codecs.Codec): def decode(self, input,errors='strict'): return hex_decode(input,errors) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + assert self.errors == 'strict' + return binascii.b2a_hex(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + assert self.errors == 'strict' + return binascii.a2b_hex(input) + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -58,5 +68,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (hex_encode,hex_decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='hex', + encode=hex_encode, + decode=hex_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/hp_roman8.py b/Lib/encodings/hp_roman8.py index 4f201b8b112..dbaaa72d76d 100644 --- a/Lib/encodings/hp_roman8.py +++ b/Lib/encodings/hp_roman8.py @@ -14,13 +14,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_map) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_map)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -30,8 +36,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='hp-roman8', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) ### Decoding Map diff --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py index 3d3ed23ce61..8bdae32cea7 100644 --- a/Lib/encodings/idna.py +++ b/Lib/encodings/idna.py @@ -194,6 +194,14 @@ class Codec(codecs.Codec): return u".".join(result)+trailing_dot, len(input) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return Codec().encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return Codec().decode(input, self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -203,5 +211,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='idna', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/iso8859_1.py b/Lib/encodings/iso8859_1.py index 6aaea7c0131..b985585b313 100644 --- a/Lib/encodings/iso8859_1.py +++ b/Lib/encodings/iso8859_1.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-1.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_1 generated from 'MAPPINGS/ISO8859/8859-1.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-1', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_10.py b/Lib/encodings/iso8859_10.py index 26b55c969b4..8588430848d 100644 --- a/Lib/encodings/iso8859_10.py +++ b/Lib/encodings/iso8859_10.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-10.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_10 generated from 'MAPPINGS/ISO8859/8859-10.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-10', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_11.py b/Lib/encodings/iso8859_11.py index ef17167a6bd..fffe6922ced 100644 --- a/Lib/encodings/iso8859_11.py +++ b/Lib/encodings/iso8859_11.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-11.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_11 generated from 'MAPPINGS/ISO8859/8859-11.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-11', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_13.py b/Lib/encodings/iso8859_13.py index 0e10c7d1441..a8905806a51 100644 --- a/Lib/encodings/iso8859_13.py +++ b/Lib/encodings/iso8859_13.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-13.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_13 generated from 'MAPPINGS/ISO8859/8859-13.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-13', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_14.py b/Lib/encodings/iso8859_14.py index b9810318958..afa458c9c2e 100644 --- a/Lib/encodings/iso8859_14.py +++ b/Lib/encodings/iso8859_14.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-14.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_14 generated from 'MAPPINGS/ISO8859/8859-14.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-14', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_15.py b/Lib/encodings/iso8859_15.py index f50a90421ef..4a8334e9e99 100644 --- a/Lib/encodings/iso8859_15.py +++ b/Lib/encodings/iso8859_15.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-15.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_15 generated from 'MAPPINGS/ISO8859/8859-15.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-15', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_16.py b/Lib/encodings/iso8859_16.py index ce8bc5b48e9..aeebfb6fde2 100644 --- a/Lib/encodings/iso8859_16.py +++ b/Lib/encodings/iso8859_16.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-16.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_16 generated from 'MAPPINGS/ISO8859/8859-16.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-16', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_2.py b/Lib/encodings/iso8859_2.py index 417b451ef0a..845f3227a73 100644 --- a/Lib/encodings/iso8859_2.py +++ b/Lib/encodings/iso8859_2.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-2.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_2 generated from 'MAPPINGS/ISO8859/8859-2.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-2', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_3.py b/Lib/encodings/iso8859_3.py index c3ad3a99c54..fbc87755223 100644 --- a/Lib/encodings/iso8859_3.py +++ b/Lib/encodings/iso8859_3.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-3.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_3 generated from 'MAPPINGS/ISO8859/8859-3.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-3', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_4.py b/Lib/encodings/iso8859_4.py index b65685aaa30..e705954ca80 100644 --- a/Lib/encodings/iso8859_4.py +++ b/Lib/encodings/iso8859_4.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-4.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_4 generated from 'MAPPINGS/ISO8859/8859-4.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-4', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_5.py b/Lib/encodings/iso8859_5.py index 59fe37245fb..93a4e90246d 100644 --- a/Lib/encodings/iso8859_5.py +++ b/Lib/encodings/iso8859_5.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-5.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_5 generated from 'MAPPINGS/ISO8859/8859-5.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-5', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_6.py b/Lib/encodings/iso8859_6.py index b07661d93d7..f911cc41927 100644 --- a/Lib/encodings/iso8859_6.py +++ b/Lib/encodings/iso8859_6.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-6.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_6 generated from 'MAPPINGS/ISO8859/8859-6.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-6', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_7.py b/Lib/encodings/iso8859_7.py index 54d0997d5f1..4cce6e23472 100644 --- a/Lib/encodings/iso8859_7.py +++ b/Lib/encodings/iso8859_7.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-7.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_7 generated from 'MAPPINGS/ISO8859/8859-7.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-7', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_8.py b/Lib/encodings/iso8859_8.py index 24ba1bbb21c..8c29a87b662 100644 --- a/Lib/encodings/iso8859_8.py +++ b/Lib/encodings/iso8859_8.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-8.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_8 generated from 'MAPPINGS/ISO8859/8859-8.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-8', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/iso8859_9.py b/Lib/encodings/iso8859_9.py index 940d92b75f4..9648e9f8c38 100644 --- a/Lib/encodings/iso8859_9.py +++ b/Lib/encodings/iso8859_9.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/ISO8859/8859-9.TXT' with gencodec.py. +""" Python Character Mapping Codec iso8859_9 generated from 'MAPPINGS/ISO8859/8859-9.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-9', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/koi8_r.py b/Lib/encodings/koi8_r.py index f2723def5bd..3efeb56edd2 100644 --- a/Lib/encodings/koi8_r.py +++ b/Lib/encodings/koi8_r.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/MISC/KOI8-R.TXT' with gencodec.py. +""" Python Character Mapping Codec koi8_r generated from 'MAPPINGS/VENDORS/MISC/KOI8-R.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='koi8-r', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/koi8_u.py b/Lib/encodings/koi8_u.py index 9bbcf7cbbda..5f46db1700c 100644 --- a/Lib/encodings/koi8_u.py +++ b/Lib/encodings/koi8_u.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'python-mappings/KOI8-U.TXT' with gencodec.py. +""" Python Character Mapping Codec koi8_u generated from 'python-mappings/KOI8-U.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='koi8-u', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/latin_1.py b/Lib/encodings/latin_1.py index 0e55917b3da..370160c0cb5 100644 --- a/Lib/encodings/latin_1.py +++ b/Lib/encodings/latin_1.py @@ -17,6 +17,14 @@ class Codec(codecs.Codec): encode = codecs.latin_1_encode decode = codecs.latin_1_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.latin_1_encode(input,self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.latin_1_decode(input,self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -31,5 +39,12 @@ class StreamConverter(StreamWriter,StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='iso8859-1', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/mac_arabic.py b/Lib/encodings/mac_arabic.py index 6c096b4ef49..7a7d3c5f7fe 100644 --- a/Lib/encodings/mac_arabic.py +++ b/Lib/encodings/mac_arabic.py @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-arabic', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/mac_centeuro.py b/Lib/encodings/mac_centeuro.py index d7d67ecbeec..54a1510333a 100644 --- a/Lib/encodings/mac_centeuro.py +++ b/Lib/encodings/mac_centeuro.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/CENTEURO.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_centeuro generated from 'MAPPINGS/VENDORS/APPLE/CENTEURO.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-centeuro', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_croatian.py b/Lib/encodings/mac_croatian.py index 96e11879702..9e93cddf3ce 100644 --- a/Lib/encodings/mac_croatian.py +++ b/Lib/encodings/mac_croatian.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/CROATIAN.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_croatian generated from 'MAPPINGS/VENDORS/APPLE/CROATIAN.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-croatian', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_cyrillic.py b/Lib/encodings/mac_cyrillic.py index f1b1fb0c8e5..8ffd715138a 100644 --- a/Lib/encodings/mac_cyrillic.py +++ b/Lib/encodings/mac_cyrillic.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/CYRILLIC.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_cyrillic generated from 'MAPPINGS/VENDORS/APPLE/CYRILLIC.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-cyrillic', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_farsi.py b/Lib/encodings/mac_farsi.py index 2b61e27058a..6d26a429604 100644 --- a/Lib/encodings/mac_farsi.py +++ b/Lib/encodings/mac_farsi.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/FARSI.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_farsi generated from 'MAPPINGS/VENDORS/APPLE/FARSI.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-farsi', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_greek.py b/Lib/encodings/mac_greek.py index c2dd26fe3ca..7264f9ae9d5 100644 --- a/Lib/encodings/mac_greek.py +++ b/Lib/encodings/mac_greek.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/GREEK.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_greek generated from 'MAPPINGS/VENDORS/APPLE/GREEK.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-greek', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_iceland.py b/Lib/encodings/mac_iceland.py index d305d298215..5d8d9ad93f5 100644 --- a/Lib/encodings/mac_iceland.py +++ b/Lib/encodings/mac_iceland.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/ICELAND.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_iceland generated from 'MAPPINGS/VENDORS/APPLE/ICELAND.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-iceland', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_latin2.py b/Lib/encodings/mac_latin2.py index f5d5225802d..e322be236c3 100644 --- a/Lib/encodings/mac_latin2.py +++ b/Lib/encodings/mac_latin2.py @@ -14,13 +14,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_map) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_map)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -30,8 +36,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-latin2', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/mac_roman.py b/Lib/encodings/mac_roman.py index d23aeba2cc7..9552e531aae 100644 --- a/Lib/encodings/mac_roman.py +++ b/Lib/encodings/mac_roman.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/ROMAN.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_roman generated from 'MAPPINGS/VENDORS/APPLE/ROMAN.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-roman', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_romanian.py b/Lib/encodings/mac_romanian.py index 5c35a644577..51282c3c097 100644 --- a/Lib/encodings/mac_romanian.py +++ b/Lib/encodings/mac_romanian.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/ROMANIAN.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_romanian generated from 'MAPPINGS/VENDORS/APPLE/ROMANIAN.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-romanian', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mac_turkish.py b/Lib/encodings/mac_turkish.py index 79894ba8a8e..4e5641f1812 100644 --- a/Lib/encodings/mac_turkish.py +++ b/Lib/encodings/mac_turkish.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'MAPPINGS/VENDORS/APPLE/TURKISH.TXT' with gencodec.py. +""" Python Character Mapping Codec mac_turkish generated from 'MAPPINGS/VENDORS/APPLE/TURKISH.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mac-turkish', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/mbcs.py b/Lib/encodings/mbcs.py index c79f47c3afc..ff77fdee943 100644 --- a/Lib/encodings/mbcs.py +++ b/Lib/encodings/mbcs.py @@ -18,6 +18,13 @@ class Codec(codecs.Codec): encode = codecs.mbcs_encode decode = codecs.mbcs_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.mbcs_encode(input,self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.mbcs_decode(input,self.errors)[0] class StreamWriter(Codec,codecs.StreamWriter): pass @@ -32,5 +39,12 @@ class StreamConverter(StreamWriter,StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='mbcs', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/palmos.py b/Lib/encodings/palmos.py index c0f06064e4b..4b77e2ba914 100644 --- a/Lib/encodings/palmos.py +++ b/Lib/encodings/palmos.py @@ -15,6 +15,14 @@ class Codec(codecs.Codec): def decode(self,input,errors='strict'): return codecs.charmap_decode(input,errors,decoding_map) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_map)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -24,7 +32,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='palmos', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/ptcp154.py b/Lib/encodings/ptcp154.py index 5cdd98c4aa7..aef897538f5 100644 --- a/Lib/encodings/ptcp154.py +++ b/Lib/encodings/ptcp154.py @@ -14,13 +14,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_map) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_map)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -30,8 +36,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='ptcp154', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Map diff --git a/Lib/encodings/punycode.py b/Lib/encodings/punycode.py index 82fd4585f57..2cde8b93a8e 100644 --- a/Lib/encodings/punycode.py +++ b/Lib/encodings/punycode.py @@ -197,18 +197,27 @@ def punycode_decode(text, errors): ### Codec APIs class Codec(codecs.Codec): - def encode(self,input,errors='strict'): + def encode(self,input,errors='strict'): res = punycode_encode(input) return res, len(input) def decode(self,input,errors='strict'): - if errors not in ('strict', 'replace', 'ignore'): raise UnicodeError, "Unsupported error handling "+errors res = punycode_decode(input, errors) return res, len(input) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return punycode_encode(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + if errors not in ('strict', 'replace', 'ignore'): + raise UnicodeError, "Unsupported error handling "+errors + return punycode_decode(input, errors) + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -218,5 +227,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='punycode', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/quopri_codec.py b/Lib/encodings/quopri_codec.py index d98b5ed04bf..b802ae62d2a 100644 --- a/Lib/encodings/quopri_codec.py +++ b/Lib/encodings/quopri_codec.py @@ -46,6 +46,14 @@ class Codec(codecs.Codec): def decode(self, input,errors='strict'): return quopri_decode(input,errors) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return quopri_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return quopri_decode(input, self.errors)[0] + class StreamWriter(Codec, codecs.StreamWriter): pass @@ -55,4 +63,12 @@ class StreamReader(Codec,codecs.StreamReader): # encodings module API def getregentry(): - return (quopri_encode, quopri_decode, StreamReader, StreamWriter) + return codecs.CodecInfo( + name='quopri', + encode=quopri_encode, + decode=quopri_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/raw_unicode_escape.py b/Lib/encodings/raw_unicode_escape.py index a2f3fffaddb..2b919b40d37 100644 --- a/Lib/encodings/raw_unicode_escape.py +++ b/Lib/encodings/raw_unicode_escape.py @@ -17,6 +17,14 @@ class Codec(codecs.Codec): encode = codecs.raw_unicode_escape_encode decode = codecs.raw_unicode_escape_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.raw_unicode_escape_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.raw_unicode_escape_decode(input, self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -26,5 +34,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='raw-unicode-escape', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/rot_13.py b/Lib/encodings/rot_13.py index c628181bfdc..52b6431cf30 100644 --- a/Lib/encodings/rot_13.py +++ b/Lib/encodings/rot_13.py @@ -14,13 +14,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_map) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_map)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -30,8 +36,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='rot-13', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) ### Decoding Map diff --git a/Lib/encodings/string_escape.py b/Lib/encodings/string_escape.py index c02bfeef2e6..e329a2607de 100644 --- a/Lib/encodings/string_escape.py +++ b/Lib/encodings/string_escape.py @@ -12,6 +12,14 @@ class Codec(codecs.Codec): encode = codecs.escape_encode decode = codecs.escape_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.escape_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.escape_decode(input, self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -19,5 +27,12 @@ class StreamReader(Codec,codecs.StreamReader): pass def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='string-escape', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/tis_620.py b/Lib/encodings/tis_620.py index aa1823efed0..166d93268bf 100644 --- a/Lib/encodings/tis_620.py +++ b/Lib/encodings/tis_620.py @@ -1,4 +1,4 @@ -""" Python Character Mapping Codec generated from 'python-mappings/TIS-620.TXT' with gencodec.py. +""" Python Character Mapping Codec tis_620 generated from 'python-mappings/TIS-620.TXT' with gencodec.py. """#" @@ -9,13 +9,19 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) def decode(self,input,errors='strict'): - return codecs.charmap_decode(input,errors,decoding_table) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -25,8 +31,15 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='tis-620', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) ### Decoding Table diff --git a/Lib/encodings/undefined.py b/Lib/encodings/undefined.py index d2277ac18d7..4690288355c 100644 --- a/Lib/encodings/undefined.py +++ b/Lib/encodings/undefined.py @@ -16,10 +16,18 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - raise UnicodeError, "undefined encoding" + raise UnicodeError("undefined encoding") def decode(self,input,errors='strict'): - raise UnicodeError, "undefined encoding" + raise UnicodeError("undefined encoding") + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + raise UnicodeError("undefined encoding") + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + raise UnicodeError("undefined encoding") class StreamWriter(Codec,codecs.StreamWriter): pass @@ -30,5 +38,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='undefined', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/unicode_escape.py b/Lib/encodings/unicode_escape.py index 8fb629316b6..817f93265a4 100644 --- a/Lib/encodings/unicode_escape.py +++ b/Lib/encodings/unicode_escape.py @@ -17,6 +17,14 @@ class Codec(codecs.Codec): encode = codecs.unicode_escape_encode decode = codecs.unicode_escape_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.unicode_escape_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.unicode_escape_decode(input, self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -26,5 +34,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='unicode-escape', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/unicode_internal.py b/Lib/encodings/unicode_internal.py index 3bd2fa0922c..df3e7752d20 100644 --- a/Lib/encodings/unicode_internal.py +++ b/Lib/encodings/unicode_internal.py @@ -17,6 +17,14 @@ class Codec(codecs.Codec): encode = codecs.unicode_internal_encode decode = codecs.unicode_internal_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.unicode_internal_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.unicode_internal_decode(input, self.errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -26,5 +34,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='unicode-internal', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/Lib/encodings/utf_16.py b/Lib/encodings/utf_16.py index 95abb056248..eff08f38782 100644 --- a/Lib/encodings/utf_16.py +++ b/Lib/encodings/utf_16.py @@ -15,6 +15,47 @@ encode = codecs.utf_16_encode def decode(input, errors='strict'): return codecs.utf_16_decode(input, errors, True) +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + codecs.IncrementalEncoder.__init__(self, errors) + self.encoder = None + + def encode(self, input, final=False): + if self.encoder is None: + result = codecs.utf_16_encode(input, self.errors)[0] + if sys.byteorder == 'little': + self.encoder = codecs.utf_16_le_encode + else: + self.encoder = codecs.utf_16_be_encode + return result + return self.encoder(input, self.errors)[0] + + def reset(self): + codecs.IncrementalEncoder.reset(self) + self.encoder = None + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def __init__(self, errors='strict'): + codecs.BufferedIncrementalDecoder.__init__(self, errors) + self.decoder = None + + def _buffer_decode(self, input, errors, final): + if self.decoder is None: + (output, consumed, byteorder) = \ + codecs.utf_16_ex_decode(input, errors, 0, final) + if byteorder == -1: + self.decoder = codecs.utf_16_le_decode + elif byteorder == 1: + self.decoder = codecs.utf_16_be_decode + elif consumed >= 2: + raise UnicodeError("UTF-16 stream does not start with BOM") + return (output, consumed) + return self.decoder(input, self.errors, final) + + def reset(self): + codecs.BufferedIncrementalDecoder.reset(self) + self.decoder = None + class StreamWriter(codecs.StreamWriter): def __init__(self, stream, errors='strict'): self.bom_written = False @@ -52,5 +93,12 @@ class StreamReader(codecs.StreamReader): ### encodings module API def getregentry(): - - return (encode,decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-16', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/utf_16_be.py b/Lib/encodings/utf_16_be.py index 9a51f8ca101..86b458eb9bc 100644 --- a/Lib/encodings/utf_16_be.py +++ b/Lib/encodings/utf_16_be.py @@ -15,6 +15,13 @@ encode = codecs.utf_16_be_encode def decode(input, errors='strict'): return codecs.utf_16_be_decode(input, errors, True) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_16_be_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_16_be_decode + class StreamWriter(codecs.StreamWriter): encode = codecs.utf_16_be_encode @@ -24,5 +31,12 @@ class StreamReader(codecs.StreamReader): ### encodings module API def getregentry(): - - return (encode,decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-16-be', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/utf_16_le.py b/Lib/encodings/utf_16_le.py index 95ca830484b..ec454142eed 100644 --- a/Lib/encodings/utf_16_le.py +++ b/Lib/encodings/utf_16_le.py @@ -15,15 +15,28 @@ encode = codecs.utf_16_le_encode def decode(input, errors='strict'): return codecs.utf_16_le_decode(input, errors, True) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_16_le_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_16_le_decode + class StreamWriter(codecs.StreamWriter): encode = codecs.utf_16_le_encode class StreamReader(codecs.StreamReader): decode = codecs.utf_16_le_decode - ### encodings module API def getregentry(): - - return (encode,decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-16-le', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/utf_7.py b/Lib/encodings/utf_7.py index ee78d09ee8b..d78d1926b30 100644 --- a/Lib/encodings/utf_7.py +++ b/Lib/encodings/utf_7.py @@ -13,6 +13,14 @@ class Codec(codecs.Codec): encode = codecs.utf_7_encode decode = codecs.utf_7_decode +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_7_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def _buffer_decode(self, input, errors, final): + return codecs.utf_7_decode(input, self.errors) + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -22,5 +30,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec.encode,Codec.decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-7', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/utf_8.py b/Lib/encodings/utf_8.py index 9cb0b4b27b4..1bf63365715 100644 --- a/Lib/encodings/utf_8.py +++ b/Lib/encodings/utf_8.py @@ -15,6 +15,13 @@ encode = codecs.utf_8_encode def decode(input, errors='strict'): return codecs.utf_8_decode(input, errors, True) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_8_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_8_decode + class StreamWriter(codecs.StreamWriter): encode = codecs.utf_8_encode @@ -24,5 +31,12 @@ class StreamReader(codecs.StreamReader): ### encodings module API def getregentry(): - - return (encode,decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-8', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/utf_8_sig.py b/Lib/encodings/utf_8_sig.py index fa437e69290..cd14ab0765e 100644 --- a/Lib/encodings/utf_8_sig.py +++ b/Lib/encodings/utf_8_sig.py @@ -22,6 +22,42 @@ def decode(input, errors='strict'): (output, consumed) = codecs.utf_8_decode(input, errors, True) return (output, consumed+prefix) +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + codecs.IncrementalEncoder.__init__(self, errors) + self.first = True + + def encode(self, input, final=False): + if self.first: + self.first = False + return codecs.BOM_UTF8 + codecs.utf_8_encode(input, errors)[0] + else: + return codecs.utf_8_encode(input, errors)[0] + + def reset(self): + codecs.IncrementalEncoder.reset(self) + self.first = True + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def __init__(self, errors='strict'): + codecs.BufferedIncrementalDecoder.__init__(self, errors) + self.first = True + + def _buffer_decode(self, input, errors, final): + if self.first and codecs.BOM_UTF8.startswith(input): # might be a BOM + if len(input) < 3: + # not enough data to decide if this really is a BOM + # => try again on the next call + return (u"", 0) + (output, consumed) = codecs.utf_8_decode(input[3:], errors, final) + self.first = False + return (output, consumed+3) + return codecs.utf_8_decode(input, errors, final) + + def reset(self): + codecs.BufferedIncrementalDecoder.reset(self) + self.first = True + class StreamWriter(codecs.StreamWriter): def reset(self): codecs.StreamWriter.reset(self) @@ -53,5 +89,12 @@ class StreamReader(codecs.StreamReader): ### encodings module API def getregentry(): - - return (encode,decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='utf-8-sig', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/uu_codec.py b/Lib/encodings/uu_codec.py index a70ff9e8efd..0877fe1ab07 100644 --- a/Lib/encodings/uu_codec.py +++ b/Lib/encodings/uu_codec.py @@ -96,9 +96,18 @@ class Codec(codecs.Codec): def encode(self,input,errors='strict'): return uu_encode(input,errors) + def decode(self,input,errors='strict'): return uu_decode(input,errors) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return uu_encode(input, errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return uu_decode(input, errors)[0] + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -108,5 +117,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (uu_encode,uu_decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='uu', + encode=uu_encode, + decode=uu_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/encodings/zlib_codec.py b/Lib/encodings/zlib_codec.py index 9b6e4d12fef..2694f155116 100644 --- a/Lib/encodings/zlib_codec.py +++ b/Lib/encodings/zlib_codec.py @@ -50,6 +50,16 @@ class Codec(codecs.Codec): def decode(self, input, errors='strict'): return zlib_decode(input, errors) +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + assert self.errors == 'strict' + return zlib.compress(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + assert self.errors == 'strict' + return zlib.decompress(input) + class StreamWriter(Codec,codecs.StreamWriter): pass @@ -59,5 +69,12 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (zlib_encode,zlib_decode,StreamReader,StreamWriter) + return codecs.CodecInfo( + name='zlib', + encode=zlib_encode, + decode=zlib_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/Lib/logging/__init__.py b/Lib/logging/__init__.py index 4b2f8a668ad..7db0dabc9ed 100644 --- a/Lib/logging/__init__.py +++ b/Lib/logging/__init__.py @@ -1058,13 +1058,16 @@ class Logger(Filterer): file name, line number and function name. """ f = currentframe().f_back - while 1: + rv = "(unknown file)", 0, "(unknown function)" + while hasattr(f, "f_code"): co = f.f_code filename = os.path.normcase(co.co_filename) if filename == _srcfile: f = f.f_back continue - return filename, f.f_lineno, co.co_name + rv = (filename, f.f_lineno, co.co_name) + break + return rv def makeRecord(self, name, level, fn, lno, msg, args, exc_info, func=None, extra=None): """ diff --git a/Lib/runpy.py b/Lib/runpy.py new file mode 100755 index 00000000000..afb00982923 --- /dev/null +++ b/Lib/runpy.py @@ -0,0 +1,431 @@ +"""runpy.py - locating and running Python code using the module namespace + +Provides support for locating and running Python scripts using the Python +module namespace instead of the native filesystem. + +This allows Python code to play nicely with non-filesystem based PEP 302 +importers when locating support scripts as well as when importing modules. +""" +# Written by Nick Coghlan +# to implement PEP 338 (Executing Modules as Scripts) + +import sys +import imp + +__all__ = [ + "run_module", +] + +try: + _get_loader = imp.get_loader +except AttributeError: + # get_loader() is not provided by the imp module, so emulate it + # as best we can using the PEP 302 import machinery exposed since + # Python 2.3. The emulation isn't perfect, but the differences + # in the way names are shadowed shouldn't matter in practice. + import os.path + import marshal # Handle compiled Python files + + # This helper is needed in order for the PEP 302 emulation to + # correctly handle compiled files + def _read_compiled_file(compiled_file): + magic = compiled_file.read(4) + if magic != imp.get_magic(): + return None + try: + compiled_file.read(4) # Skip timestamp + return marshal.load(compiled_file) + except Exception: + return None + + class _AbsoluteImporter(object): + """PEP 302 importer wrapper for top level import machinery""" + def find_module(self, mod_name, path=None): + if path is not None: + return None + try: + file, filename, mod_info = imp.find_module(mod_name) + except ImportError: + return None + suffix, mode, mod_type = mod_info + if mod_type == imp.PY_SOURCE: + loader = _SourceFileLoader(mod_name, file, + filename, mod_info) + elif mod_type == imp.PY_COMPILED: + loader = _CompiledFileLoader(mod_name, file, + filename, mod_info) + elif mod_type == imp.PKG_DIRECTORY: + loader = _PackageDirLoader(mod_name, file, + filename, mod_info) + elif mod_type == imp.C_EXTENSION: + loader = _FileSystemLoader(mod_name, file, + filename, mod_info) + else: + loader = _BasicLoader(mod_name, file, + filename, mod_info) + return loader + + + class _FileSystemImporter(object): + """PEP 302 importer wrapper for filesystem based imports""" + def __init__(self, path_item=None): + if path_item is not None: + if path_item != '' and not os.path.isdir(path_item): + raise ImportError("%s is not a directory" % path_item) + self.path_dir = path_item + else: + raise ImportError("Filesystem importer requires " + "a directory name") + + def find_module(self, mod_name, path=None): + if path is not None: + return None + path_dir = self.path_dir + if path_dir == '': + path_dir = os.getcwd() + sub_name = mod_name.rsplit(".", 1)[-1] + try: + file, filename, mod_info = imp.find_module(sub_name, + [path_dir]) + except ImportError: + return None + if not filename.startswith(path_dir): + return None + suffix, mode, mod_type = mod_info + if mod_type == imp.PY_SOURCE: + loader = _SourceFileLoader(mod_name, file, + filename, mod_info) + elif mod_type == imp.PY_COMPILED: + loader = _CompiledFileLoader(mod_name, file, + filename, mod_info) + elif mod_type == imp.PKG_DIRECTORY: + loader = _PackageDirLoader(mod_name, file, + filename, mod_info) + elif mod_type == imp.C_EXTENSION: + loader = _FileSystemLoader(mod_name, file, + filename, mod_info) + else: + loader = _BasicLoader(mod_name, file, + filename, mod_info) + return loader + + + class _BasicLoader(object): + """PEP 302 loader wrapper for top level import machinery""" + def __init__(self, mod_name, file, filename, mod_info): + self.mod_name = mod_name + self.file = file + self.filename = filename + self.mod_info = mod_info + + def _fix_name(self, mod_name): + if mod_name is None: + mod_name = self.mod_name + elif mod_name != self.mod_name: + raise ImportError("Loader for module %s cannot handle " + "module %s" % (self.mod_name, mod_name)) + return mod_name + + def load_module(self, mod_name=None): + mod_name = self._fix_name(mod_name) + mod = imp.load_module(mod_name, self.file, + self.filename, self.mod_info) + mod.__loader__ = self # for introspection + return mod + + def get_code(self, mod_name=None): + return None + + def get_source(self, mod_name=None): + return None + + def is_package(self, mod_name=None): + return False + + def close(self): + if self.file: + self.file.close() + + def __del__(self): + self.close() + + + class _FileSystemLoader(_BasicLoader): + """PEP 302 loader wrapper for filesystem based imports""" + def get_code(self, mod_name=None): + mod_name = self._fix_name(mod_name) + return self._get_code(mod_name) + + def get_data(self, pathname): + return open(pathname, "rb").read() + + def get_filename(self, mod_name=None): + mod_name = self._fix_name(mod_name) + return self._get_filename(mod_name) + + def get_source(self, mod_name=None): + mod_name = self._fix_name(mod_name) + return self._get_source(mod_name) + + def is_package(self, mod_name=None): + mod_name = self._fix_name(mod_name) + return self._is_package(mod_name) + + def _get_code(self, mod_name): + return None + + def _get_filename(self, mod_name): + return self.filename + + def _get_source(self, mod_name): + return None + + def _is_package(self, mod_name): + return False + + class _PackageDirLoader(_FileSystemLoader): + """PEP 302 loader wrapper for PKG_DIRECTORY directories""" + def _is_package(self, mod_name): + return True + + + class _SourceFileLoader(_FileSystemLoader): + """PEP 302 loader wrapper for PY_SOURCE modules""" + def _get_code(self, mod_name): + return compile(self._get_source(mod_name), + self.filename, 'exec') + + def _get_source(self, mod_name): + f = self.file + f.seek(0) + return f.read() + + + class _CompiledFileLoader(_FileSystemLoader): + """PEP 302 loader wrapper for PY_COMPILED modules""" + def _get_code(self, mod_name): + f = self.file + f.seek(0) + return _read_compiled_file(f) + + + def _get_importer(path_item): + """Retrieve a PEP 302 importer for the given path item + + The returned importer is cached in sys.path_importer_cache + if it was newly created by a path hook. + + If there is no importer, a wrapper around the basic import + machinery is returned. This wrapper is never inserted into + the importer cache (None is inserted instead). + + The cache (or part of it) can be cleared manually if a + rescan of sys.path_hooks is necessary. + """ + try: + importer = sys.path_importer_cache[path_item] + except KeyError: + for path_hook in sys.path_hooks: + try: + importer = path_hook(path_item) + break + except ImportError: + pass + else: + importer = None + sys.path_importer_cache[path_item] = importer + if importer is None: + try: + importer = _FileSystemImporter(path_item) + except ImportError: + pass + return importer + + + def _get_path_loader(mod_name, path=None): + """Retrieve a PEP 302 loader using a path importer""" + if path is None: + path = sys.path + absolute_loader = _AbsoluteImporter().find_module(mod_name) + if isinstance(absolute_loader, _FileSystemLoader): + # Found in filesystem, so scan path hooks + # before accepting this one as the right one + loader = None + else: + # Not found in filesystem, so use top-level loader + loader = absolute_loader + else: + loader = absolute_loader = None + if loader is None: + for path_item in path: + importer = _get_importer(path_item) + if importer is not None: + loader = importer.find_module(mod_name) + if loader is not None: + # Found a loader for our module + break + else: + # No path hook found, so accept the top level loader + loader = absolute_loader + return loader + + def _get_package(pkg_name): + """Retrieve a named package""" + pkg = __import__(pkg_name) + sub_pkg_names = pkg_name.split(".") + for sub_pkg in sub_pkg_names[1:]: + pkg = getattr(pkg, sub_pkg) + return pkg + + def _get_loader(mod_name, path=None): + """Retrieve a PEP 302 loader for the given module or package + + If the module or package is accessible via the normal import + mechanism, a wrapper around the relevant part of that machinery + is returned. + + Non PEP 302 mechanisms (e.g. the Windows registry) used by the + standard import machinery to find files in alternative locations + are partially supported, but are searched AFTER sys.path. Normally, + these locations are searched BEFORE sys.path, preventing sys.path + entries from shadowing them. + For this to cause a visible difference in behaviour, there must + be a module or package name that is accessible via both sys.path + and one of the non PEP 302 file system mechanisms. In this case, + the emulation will find the former version, while the builtin + import mechanism will find the latter. + Items of the following types can be affected by this discrepancy: + imp.C_EXTENSION + imp.PY_SOURCE + imp.PY_COMPILED + imp.PKG_DIRECTORY + """ + try: + loader = sys.modules[mod_name].__loader__ + except (KeyError, AttributeError): + loader = None + if loader is None: + imp.acquire_lock() + try: + # Module not in sys.modules, or uses an unhooked loader + parts = mod_name.rsplit(".", 1) + if len(parts) == 2: + # Sub package, so use parent package's path + pkg_name, sub_name = parts + if pkg_name and pkg_name[0] != '.': + if path is not None: + raise ImportError("Path argument must be None " + "for a dotted module name") + pkg = _get_package(pkg_name) + try: + path = pkg.__path__ + except AttributeError: + raise ImportError(pkg_name + + " is not a package") + else: + raise ImportError("Relative import syntax is not " + "supported by _get_loader()") + else: + # Top level module, so stick with default path + sub_name = mod_name + + for importer in sys.meta_path: + loader = importer.find_module(mod_name, path) + if loader is not None: + # Found a metahook to handle the module + break + else: + # Handling via the standard path mechanism + loader = _get_path_loader(mod_name, path) + finally: + imp.release_lock() + return loader + + +# This helper is needed due to a missing component in the PEP 302 +# loader protocol (specifically, "get_filename" is non-standard) +def _get_filename(loader, mod_name): + try: + get_filename = loader.get_filename + except AttributeError: + return None + else: + return get_filename(mod_name) + +# ------------------------------------------------------------ +# Done with the import machinery emulation, on with the code! + +def _run_code(code, run_globals, init_globals, + mod_name, mod_fname, mod_loader): + """Helper for _run_module_code""" + if init_globals is not None: + run_globals.update(init_globals) + run_globals.update(__name__ = mod_name, + __file__ = mod_fname, + __loader__ = mod_loader) + exec code in run_globals + return run_globals + +def _run_module_code(code, init_globals=None, + mod_name=None, mod_fname=None, + mod_loader=None, alter_sys=False): + """Helper for run_module""" + # Set up the top level namespace dictionary + if alter_sys: + # Modify sys.argv[0] and sys.module[mod_name] + temp_module = imp.new_module(mod_name) + mod_globals = temp_module.__dict__ + saved_argv0 = sys.argv[0] + restore_module = mod_name in sys.modules + if restore_module: + saved_module = sys.modules[mod_name] + imp.acquire_lock() + try: + sys.argv[0] = mod_fname + sys.modules[mod_name] = temp_module + try: + _run_code(code, mod_globals, init_globals, + mod_name, mod_fname, mod_loader) + finally: + sys.argv[0] = saved_argv0 + if restore_module: + sys.modules[mod_name] = saved_module + else: + del sys.modules[mod_name] + finally: + imp.release_lock() + # Copy the globals of the temporary module, as they + # may be cleared when the temporary module goes away + return mod_globals.copy() + else: + # Leave the sys module alone + return _run_code(code, {}, init_globals, + mod_name, mod_fname, mod_loader) + + +def run_module(mod_name, init_globals=None, + run_name=None, alter_sys=False): + """Execute a module's code without importing it + + Returns the resulting top level namespace dictionary + """ + loader = _get_loader(mod_name) + if loader is None: + raise ImportError("No module named " + mod_name) + code = loader.get_code(mod_name) + if code is None: + raise ImportError("No code object available for " + mod_name) + filename = _get_filename(loader, mod_name) + if run_name is None: + run_name = mod_name + return _run_module_code(code, init_globals, run_name, + filename, loader, alter_sys) + + +if __name__ == "__main__": + # Run the module specified as the next command line argument + if len(sys.argv) < 2: + print >> sys.stderr, "No module specified for execution" + else: + del sys.argv[0] # Make the requested module sys.argv[0] + run_module(sys.argv[0], run_name="__main__", alter_sys=True) diff --git a/Lib/test/regrtest.py b/Lib/test/regrtest.py index b4c229ac4bc..b8509129c87 100755 --- a/Lib/test/regrtest.py +++ b/Lib/test/regrtest.py @@ -1136,9 +1136,6 @@ class _ExpectedSkips: s = _expectations[sys.platform] self.expected = set(s.split()) - # this isn't a regularly run unit test, it is always skipped - self.expected.add('test_hashlib_speed') - if not os.path.supports_unicode_filenames: self.expected.add('test_pep277') diff --git a/Lib/test/test_StringIO.py b/Lib/test/test_StringIO.py index c61f7cc54a3..cc3367fed8d 100644 --- a/Lib/test/test_StringIO.py +++ b/Lib/test/test_StringIO.py @@ -75,6 +75,13 @@ class TestGenericStringIO(unittest.TestCase): f.close() self.assertEqual(f.closed, True) + def test_isatty(self): + f = self.MODULE.StringIO() + self.assertRaises(TypeError, f.isatty, None) + self.assertEqual(f.isatty(), False) + f.close() + self.assertRaises(ValueError, f.isatty) + def test_iterator(self): eq = self.assertEqual unless = self.failUnless @@ -87,6 +94,8 @@ class TestGenericStringIO(unittest.TestCase): eq(line, self._line + '\n') i += 1 eq(i, 5) + self._fp.close() + self.assertRaises(ValueError, self._fp.next) class TestStringIO(TestGenericStringIO): MODULE = StringIO diff --git a/Lib/test/test___all__.py b/Lib/test/test___all__.py index 7bf53140158..74a9cdf05b5 100644 --- a/Lib/test/test___all__.py +++ b/Lib/test/test___all__.py @@ -5,8 +5,6 @@ from test.test_support import verify, verbose import sys import warnings -warnings.filterwarnings("ignore", ".* 'pre' .*", DeprecationWarning, - r'pre$') warnings.filterwarnings("ignore", ".* regsub .*", DeprecationWarning, r'^regsub$') warnings.filterwarnings("ignore", @@ -122,7 +120,6 @@ class AllTest(unittest.TestCase): self.check_all("poplib") self.check_all("posixpath") self.check_all("pprint") - self.check_all("pre") # deprecated self.check_all("profile") self.check_all("pstats") self.check_all("pty") diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 3944d654525..913aa91168a 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -41,6 +41,33 @@ class ReadTest(unittest.TestCase): self.assertEqual(r.bytebuffer, "") self.assertEqual(r.charbuffer, u"") + # do the check again, this time using a incremental decoder + d = codecs.getincrementaldecoder(self.encoding)() + result = u"" + for (c, partialresult) in zip(input.encode(self.encoding), partialresults): + result += d.decode(c) + self.assertEqual(result, partialresult) + # check that there's nothing left in the buffers + self.assertEqual(d.decode("", True), u"") + self.assertEqual(d.buffer, "") + + # Check whether the rest method works properly + d.reset() + result = u"" + for (c, partialresult) in zip(input.encode(self.encoding), partialresults): + result += d.decode(c) + self.assertEqual(result, partialresult) + # check that there's nothing left in the buffers + self.assertEqual(d.decode("", True), u"") + self.assertEqual(d.buffer, "") + + # check iterdecode() + encoded = input.encode(self.encoding) + self.assertEqual( + input, + u"".join(codecs.iterdecode(encoded, self.encoding)) + ) + def test_readline(self): def getreader(input): stream = StringIO.StringIO(input.encode(self.encoding)) @@ -977,6 +1004,12 @@ class BasicUnicodeTest(unittest.TestCase): def test_basics(self): s = u"abc123" # all codecs should be able to encode these for encoding in all_unicode_encodings: + name = codecs.lookup(encoding).name + if encoding.endswith("_codec"): + name += "_codec" + elif encoding == "latin_1": + name = "latin_1" + self.assertEqual(encoding.replace("_", "-"), name.replace("_", "-")) (bytes, size) = codecs.getencoder(encoding)(s) if encoding != "unicode_internal": self.assertEqual(size, len(s), "%r != %r (encoding=%r)" % (size, len(s), encoding)) @@ -999,6 +1032,30 @@ class BasicUnicodeTest(unittest.TestCase): decodedresult += reader.read() self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) + # check incremental decoder/encoder and iterencode()/iterdecode() + try: + encoder = codecs.getincrementalencoder(encoding)() + except LookupError: # no IncrementalEncoder + pass + else: + # check incremental decoder/encoder + encodedresult = "" + for c in s: + encodedresult += encoder.encode(c) + decoder = codecs.getincrementaldecoder(encoding)() + decodedresult = u"" + for c in encodedresult: + decodedresult += decoder.decode(c) + self.assertEqual(decodedresult, s, "%r != %r (encoding=%r)" % (decodedresult, s, encoding)) + + # check iterencode()/iterdecode() + result = u"".join(codecs.iterdecode(codecs.iterencode(s, encoding), encoding)) + self.assertEqual(result, s, "%r != %r (encoding=%r)" % (result, s, encoding)) + + # check iterencode()/iterdecode() with empty string + result = u"".join(codecs.iterdecode(codecs.iterencode(u"", encoding), encoding)) + self.assertEqual(result, u"") + def test_seek(self): # all codecs should be able to encode these s = u"%s\n%s\n" % (100*u"abc123", 100*u"def456") diff --git a/Lib/test/test_runpy.py b/Lib/test/test_runpy.py new file mode 100644 index 00000000000..88e990098a3 --- /dev/null +++ b/Lib/test/test_runpy.py @@ -0,0 +1,172 @@ +# Test the runpy module +import unittest +import os +import os.path +import sys +import tempfile +from test.test_support import verbose, run_unittest +from runpy import _run_module_code, run_module + +# Set up the test code and expected results + +class RunModuleCodeTest(unittest.TestCase): + + expected_result = ["Top level assignment", "Lower level reference"] + test_source = ( + "# Check basic code execution\n" + "result = ['Top level assignment']\n" + "def f():\n" + " result.append('Lower level reference')\n" + "f()\n" + "# Check the sys module\n" + "import sys\n" + "run_argv0 = sys.argv[0]\n" + "if __name__ in sys.modules:\n" + " run_name = sys.modules[__name__].__name__\n" + "# Check nested operation\n" + "import runpy\n" + "nested = runpy._run_module_code('x=1\\n', mod_name='',\n" + " alter_sys=True)\n" + ) + + + def test_run_module_code(self): + initial = object() + name = "" + file = "Some other nonsense" + loader = "Now you're just being silly" + d1 = dict(initial=initial) + saved_argv0 = sys.argv[0] + d2 = _run_module_code(self.test_source, + d1, + name, + file, + loader, + True) + self.failUnless("result" not in d1) + self.failUnless(d2["initial"] is initial) + self.failUnless(d2["result"] == self.expected_result) + self.failUnless(d2["nested"]["x"] == 1) + self.failUnless(d2["__name__"] is name) + self.failUnless(d2["run_name"] is name) + self.failUnless(d2["__file__"] is file) + self.failUnless(d2["run_argv0"] is file) + self.failUnless(d2["__loader__"] is loader) + self.failUnless(sys.argv[0] is saved_argv0) + self.failUnless(name not in sys.modules) + + def test_run_module_code_defaults(self): + saved_argv0 = sys.argv[0] + d = _run_module_code(self.test_source) + self.failUnless(d["result"] == self.expected_result) + self.failUnless(d["__name__"] is None) + self.failUnless(d["__file__"] is None) + self.failUnless(d["__loader__"] is None) + self.failUnless(d["run_argv0"] is saved_argv0) + self.failUnless("run_name" not in d) + self.failUnless(sys.argv[0] is saved_argv0) + +class RunModuleTest(unittest.TestCase): + + def expect_import_error(self, mod_name): + try: + run_module(mod_name) + except ImportError: + pass + else: + self.fail("Expected import error for " + mod_name) + + def test_invalid_names(self): + self.expect_import_error("sys") + self.expect_import_error("sys.imp.eric") + self.expect_import_error("os.path.half") + self.expect_import_error("a.bee") + self.expect_import_error(".howard") + self.expect_import_error("..eaten") + + def test_library_module(self): + run_module("runpy") + + def _make_pkg(self, source, depth): + pkg_name = "__runpy_pkg__" + init_fname = "__init__"+os.extsep+"py" + test_fname = "runpy_test"+os.extsep+"py" + pkg_dir = sub_dir = tempfile.mkdtemp() + if verbose: print " Package tree in:", sub_dir + sys.path.insert(0, pkg_dir) + if verbose: print " Updated sys.path:", sys.path[0] + for i in range(depth): + sub_dir = os.path.join(sub_dir, pkg_name) + os.mkdir(sub_dir) + if verbose: print " Next level in:", sub_dir + pkg_fname = os.path.join(sub_dir, init_fname) + pkg_file = open(pkg_fname, "w") + pkg_file.close() + if verbose: print " Created:", pkg_fname + mod_fname = os.path.join(sub_dir, test_fname) + mod_file = open(mod_fname, "w") + mod_file.write(source) + mod_file.close() + if verbose: print " Created:", mod_fname + mod_name = (pkg_name+".")*depth + "runpy_test" + return pkg_dir, mod_fname, mod_name + + def _del_pkg(self, top, depth, mod_name): + for i in range(depth+1): # Don't forget the module itself + parts = mod_name.rsplit(".", i) + entry = parts[0] + try: + del sys.modules[entry] + except KeyError, ex: + if verbose: print ex # Persist with cleaning up + if verbose: print " Removed sys.modules entries" + del sys.path[0] + if verbose: print " Removed sys.path entry" + for root, dirs, files in os.walk(top, topdown=False): + for name in files: + try: + os.remove(os.path.join(root, name)) + except OSError, ex: + if verbose: print ex # Persist with cleaning up + for name in dirs: + fullname = os.path.join(root, name) + try: + os.rmdir(fullname) + except OSError, ex: + if verbose: print ex # Persist with cleaning up + try: + os.rmdir(top) + if verbose: print " Removed package tree" + except OSError, ex: + if verbose: print ex # Persist with cleaning up + + def _check_module(self, depth): + pkg_dir, mod_fname, mod_name = ( + self._make_pkg("x=1\n", depth)) + try: + if verbose: print "Running from source:", mod_name + d1 = run_module(mod_name) # Read from source + self.failUnless(d1["x"] == 1) + del d1 # Ensure __loader__ entry doesn't keep file open + __import__(mod_name) + os.remove(mod_fname) + if verbose: print "Running from compiled:", mod_name + d2 = run_module(mod_name) # Read from bytecode + self.failUnless(d2["x"] == 1) + del d2 # Ensure __loader__ entry doesn't keep file open + finally: + self._del_pkg(pkg_dir, depth, mod_name) + if verbose: print "Module executed successfully" + + def test_run_module(self): + for depth in range(4): + if verbose: print "Testing package depth:", depth + self._check_module(depth) + + +def test_main(): + run_unittest(RunModuleCodeTest) + run_unittest(RunModuleTest) + +if __name__ == "__main__": + test_main() diff --git a/Lib/test/test_hashlib_speed.py b/Lib/test/time_hashlib.py similarity index 92% rename from Lib/test/test_hashlib_speed.py rename to Lib/test/time_hashlib.py index c84a62bdf33..1bf707da19b 100644 --- a/Lib/test/test_hashlib_speed.py +++ b/Lib/test/time_hashlib.py @@ -1,15 +1,14 @@ +# It's intended that this script be run by hand. It runs speed tests on +# hashlib functions; it does not test for correctness. import sys, time import hashlib -from test import test_support def creatorFunc(): raise RuntimeError, "eek, creatorFunc not overridden" - def test_scaled_msg(scale, name): - iterations = 106201/scale * 20 longStr = 'Z'*scale @@ -39,10 +38,6 @@ def test_zero(): -### this 'test' is not normally run. skip it if the test runner finds it -if __name__ != '__main__': - raise test_support.TestSkipped, "not a unit test (stand alone benchmark)" - hName = sys.argv[1] # diff --git a/Makefile.pre.in b/Makefile.pre.in index 5f2e98408fd..056b57803ab 100644 --- a/Makefile.pre.in +++ b/Makefile.pre.in @@ -974,6 +974,8 @@ clean: find . -name '*.o' -exec rm -f {} ';' find . -name '*.s[ol]' -exec rm -f {} ';' find $(srcdir) -name '*.py[co]' -exec rm -f {} ';' + find $(srcdir) -name 'fficonfig.h' -exec rm -f {} ';' + find $(srcdir) -name 'fficonfig.py' -exec rm -f {} ';' clobber: clean -rm -f $(BUILDPYTHON) $(PGEN) $(LIBRARY) $(LDLIBRARY) $(DLLLIBRARY) \ diff --git a/Modules/_ctypes/_ctypes.c b/Modules/_ctypes/_ctypes.c index 7c5da64db41..926c85bce8a 100644 --- a/Modules/_ctypes/_ctypes.c +++ b/Modules/_ctypes/_ctypes.c @@ -3674,7 +3674,11 @@ CreateArrayType(PyObject *itemtype, Py_ssize_t length) if (cache == NULL) return NULL; } +#if (PY_VERSION_HEX < 0x02050000) + key = Py_BuildValue("(Oi)", itemtype, length); +#else key = Py_BuildValue("(On)", itemtype, length); +#endif if (!key) return NULL; result = PyDict_GetItem(cache, key); @@ -3698,7 +3702,11 @@ CreateArrayType(PyObject *itemtype, Py_ssize_t length) #endif result = PyObject_CallFunction((PyObject *)&ArrayType_Type, +#if (PY_VERSION_HEX < 0x02050000) + "s(O){s:i,s:O}", +#else "s(O){s:n,s:O}", +#endif name, &Array_Type, "_length_", diff --git a/Modules/_ctypes/cfield.c b/Modules/_ctypes/cfield.c index de41571b101..336f26543f6 100644 --- a/Modules/_ctypes/cfield.c +++ b/Modules/_ctypes/cfield.c @@ -250,11 +250,21 @@ CField_repr(CFieldObject *self) name = ((PyTypeObject *)self->proto)->tp_name; if (bits) - result = PyString_FromFormat("", - name, (int)self->offset, size, bits); + result = PyString_FromFormat( +#if (PY_VERSION_HEX < 0x02050000) + "", +#else + "", +#endif + name, self->offset, size, bits); else - result = PyString_FromFormat("", - name, (int)self->offset, size); + result = PyString_FromFormat( +#if (PY_VERSION_HEX < 0x02050000) + "", +#else + "", +#endif + name, self->offset, size); return result; } diff --git a/Modules/_ctypes/ctypes.h b/Modules/_ctypes/ctypes.h index 9347c99d23b..179dcf16166 100644 --- a/Modules/_ctypes/ctypes.h +++ b/Modules/_ctypes/ctypes.h @@ -1,5 +1,18 @@ /******************************************************************/ +#if (PY_VERSION_HEX < 0x02050000) +typedef int Py_ssize_t; +#define lenfunc inquiry +#define readbufferproc getreadbufferproc +#define writebufferproc getwritebufferproc +#define segcountproc getsegcountproc +#define charbufferproc getcharbufferproc +#define ssizeargfunc intargfunc +#define ssizessizeargfunc intintargfunc +#define ssizeobjargproc intobjargproc +#define ssizessizeobjargproc intintobjargproc +#endif + #ifndef MS_WIN32 #define max(a, b) ((a) > (b) ? (a) : (b)) #define min(a, b) ((a) < (b) ? (a) : (b)) diff --git a/Modules/_testcapimodule.c b/Modules/_testcapimodule.c index 913c49aba72..6d8ea3c6693 100644 --- a/Modules/_testcapimodule.c +++ b/Modules/_testcapimodule.c @@ -522,6 +522,18 @@ test_long_numbits(PyObject *self) return Py_None; } +/* Example passing NULLs to PyObject_Str(NULL) and PyObject_Unicode(NULL). */ + +static PyObject * +test_null_strings(PyObject *self) +{ + PyObject *o1 = PyObject_Str(NULL), *o2 = PyObject_Unicode(NULL); + PyObject *tuple = PyTuple_Pack(2, o1, o2); + Py_XDECREF(o1); + Py_XDECREF(o2); + return tuple; +} + static PyObject * raise_exception(PyObject *self, PyObject *args) { @@ -597,6 +609,7 @@ static PyMethodDef TestMethods[] = { {"test_long_api", (PyCFunction)test_long_api, METH_NOARGS}, {"test_long_numbits", (PyCFunction)test_long_numbits, METH_NOARGS}, {"test_k_code", (PyCFunction)test_k_code, METH_NOARGS}, + {"test_null_strings", (PyCFunction)test_null_strings, METH_NOARGS}, {"getargs_b", (PyCFunction)getargs_b, METH_VARARGS}, {"getargs_B", (PyCFunction)getargs_B, METH_VARARGS}, diff --git a/Modules/cStringIO.c b/Modules/cStringIO.c index fd28aa9324d..bdc9f00d39d 100644 --- a/Modules/cStringIO.c +++ b/Modules/cStringIO.c @@ -144,7 +144,8 @@ PyDoc_STRVAR(IO_isatty__doc__, "isatty(): always returns 0"); static PyObject * IO_isatty(IOobject *self, PyObject *unused) { - Py_INCREF(Py_False); + if (!IO__opencheck(self)) return NULL; + Py_INCREF(Py_False); return Py_False; } diff --git a/Modules/main.c b/Modules/main.c index c8298fbf768..b3ce16e3e25 100644 --- a/Modules/main.c +++ b/Modules/main.c @@ -130,27 +130,42 @@ static void RunStartupFile(PyCompilerFlags *cf) } } -/* Get the path to a top-level module */ -static struct filedescr * FindModule(const char *module, - FILE **fp, char **filename) + +static int RunModule(char *module) { - struct filedescr *fdescr = NULL; - *fp = NULL; - *filename = malloc(MAXPATHLEN); - - if (*filename == NULL) - return NULL; - - /* Find the actual module source code */ - fdescr = _PyImport_FindModule(module, NULL, - *filename, MAXPATHLEN, fp, NULL); - - if (fdescr == NULL) { - free(*filename); - *filename = NULL; + PyObject *runpy, *runmodule, *runargs, *result; + runpy = PyImport_ImportModule("runpy"); + if (runpy == NULL) { + fprintf(stderr, "Could not import runpy module\n"); + return -1; } - - return fdescr; + runmodule = PyObject_GetAttrString(runpy, "run_module"); + if (runmodule == NULL) { + fprintf(stderr, "Could not access runpy.run_module\n"); + Py_DECREF(runpy); + return -1; + } + runargs = Py_BuildValue("sOsO", module, + Py_None, "__main__", Py_True); + if (runargs == NULL) { + fprintf(stderr, + "Could not create arguments for runpy.run_module\n"); + Py_DECREF(runpy); + Py_DECREF(runmodule); + return -1; + } + result = PyObject_Call(runmodule, runargs, NULL); + if (result == NULL) { + PyErr_Print(); + } + Py_DECREF(runpy); + Py_DECREF(runmodule); + Py_DECREF(runargs); + if (result == NULL) { + return -1; + } + Py_DECREF(result); + return 0; } /* Main program */ @@ -410,28 +425,9 @@ Py_Main(int argc, char **argv) } if (module != NULL) { - /* Backup _PyOS_optind and find the real file */ - struct filedescr *fdescr = NULL; + /* Backup _PyOS_optind and force sys.arv[0] = module */ _PyOS_optind--; - if ((fdescr = FindModule(module, &fp, &filename))) { - argv[_PyOS_optind] = filename; - } else { - fprintf(stderr, "%s: module %s not found\n", - argv[0], module); - return 2; - } - if (!fp) { - fprintf(stderr, - "%s: module %s has no associated file\n", - argv[0], module); - return 2; - } - if (!_PyImport_IsScript(fdescr)) { - fprintf(stderr, - "%s: module %s not usable as script\n (%s)\n", - argv[0], module, filename); - return 2; - } + argv[_PyOS_optind] = module; } PySys_SetArgv(argc-_PyOS_optind, argv+_PyOS_optind); @@ -450,9 +446,8 @@ Py_Main(int argc, char **argv) sts = PyRun_SimpleStringFlags(command, &cf) != 0; free(command); } else if (module) { - sts = PyRun_AnyFileExFlags(fp, filename, 1, &cf) != 0; + sts = RunModule(module); free(module); - free(filename); } else { if (filename == NULL && stdin_is_interactive) { diff --git a/Modules/xxmodule.c b/Modules/xxmodule.c index df312eb72a1..ea66eefa0a6 100644 --- a/Modules/xxmodule.c +++ b/Modules/xxmodule.c @@ -197,18 +197,6 @@ xx_bug(PyObject *self, PyObject *args) return Py_None; } -/* Example passing NULLs to PyObject_Str(NULL) and PyObject_Unicode(NULL). */ - -static PyObject * -xx_null(PyObject *self, PyObject *noargs) -{ - PyObject *o1 = PyObject_Str(NULL), *o2 = PyObject_Unicode(NULL); - PyObject *tuple = PyTuple_Pack(2, o1, o2); - Py_XDECREF(o1); - Py_XDECREF(o2); - return tuple; -} - /* Test bad format character */ static PyObject * @@ -343,8 +331,6 @@ static PyMethodDef xx_methods[] = { PyDoc_STR("new() -> new Xx object")}, {"bug", xx_bug, METH_VARARGS, PyDoc_STR("bug(o) -> None")}, - {"null", xx_null, METH_NOARGS, - PyDoc_STR("null(o) -> ('NULL', u'NULL')")}, {NULL, NULL} /* sentinel */ }; diff --git a/Objects/obmalloc.c b/Objects/obmalloc.c index 3ee21e43c31..870f93c7217 100644 --- a/Objects/obmalloc.c +++ b/Objects/obmalloc.c @@ -217,16 +217,16 @@ * I don't care if these are defined in or elsewhere. Axiom. */ #undef uchar -#define uchar unsigned char /* assuming == 8 bits */ +#define uchar unsigned char /* assuming == 8 bits */ #undef uint -#define uint unsigned int /* assuming >= 16 bits */ +#define uint unsigned int /* assuming >= 16 bits */ #undef ulong -#define ulong unsigned long /* assuming >= 32 bits */ +#define ulong unsigned long /* assuming >= 32 bits */ #undef uptr -#define uptr Py_uintptr_t +#define uptr Py_uintptr_t /* When you say memory, my mind reasons in terms of (pointers to) blocks */ typedef uchar block; @@ -246,6 +246,47 @@ struct pool_header { typedef struct pool_header *poolp; +/* Record keeping for arenas. */ +struct arena_object { + /* The address of the arena, as returned by malloc. Note that 0 + * will never be returned by a successful malloc, and is used + * here to mark an arena_object that doesn't correspond to an + * allocated arena. + */ + uptr address; + + /* Pool-aligned pointer to the next pool to be carved off. */ + block* pool_address; + + /* The number of available pools in the arena: free pools + never- + * allocated pools. + */ + uint nfreepools; + + /* The total number of pools in the arena, whether or not available. */ + uint ntotalpools; + + /* Singly-linked list of available pools. */ + struct pool_header* freepools; + + /* Whenever this arena_object is not associated with an allocated + * arena, the nextarena member is used to link all unassociated + * arena_objects in the singly-linked `unused_arena_objects` list. + * The prevarena member is unused in this case. + * + * When this arena_object is associated with an allocated arena + * with at least one available pool, both members are used in the + * doubly-linked `usable_arenas` list, which is maintained in + * increasing order of `nfreepools` values. + * + * Else this arena_object is associated with an allocated arena + * all of whose pools are in use. `nextarena` and `prevarena` + * are both meaningless in this case. + */ + struct arena_object* nextarena; + struct arena_object* prevarena; +}; + #undef ROUNDUP #define ROUNDUP(x) (((x) + ALIGNMENT_MASK) & ~ALIGNMENT_MASK) #define POOL_OVERHEAD ROUNDUP(sizeof(struct pool_header)) @@ -277,8 +318,9 @@ all partially used pools holding small blocks with "size class idx" i. So usedpools[0] corresponds to blocks of size 8, usedpools[2] to blocks of size 16, and so on: index 2*i <-> blocks of size (i+1)< 8 */ }; -/* - * Free (cached) pools - */ -static poolp freepools = NULL; /* free list for cached pools */ +/*========================================================================== +Arena management. -/*==========================================================================*/ -/* Arena management. */ +`arenas` is a vector of arena_objects. It contains maxarenas entries, some of +which may not be currently used (== they're arena_objects that aren't +currently associated with an allocated arena). Note that arenas proper are +separately malloc'ed. -/* arenas is a vector of arena base addresses, in order of allocation time. - * arenas currently contains narenas entries, and has space allocated - * for at most maxarenas entries. - * - * CAUTION: See the long comment block about thread safety in new_arena(): - * the code currently relies in deep ways on that this vector only grows, - * and only grows by appending at the end. For now we never return an arena - * to the OS. - */ -static uptr *volatile arenas = NULL; /* the pointer itself is volatile */ -static volatile uint narenas = 0; +Prior to Python 2.5, arenas were never free()'ed. Starting with Python 2.5, +we do try to free() arenas, and use some mild heuristic strategies to increase +the likelihood that arenas eventually can be freed. + +unused_arena_objects + + This is a singly-linked list of the arena_objects that are currently not + being used (no arena is associated with them). Objects are taken off the + head of the list in new_arena(), and are pushed on the head of the list in + PyObject_Free() when the arena is empty. Key invariant: an arena_object + is on this list if and only if its .address member is 0. + +usable_arenas + + This is a doubly-linked list of the arena_objects associated with arenas + that have pools available. These pools are either waiting to be reused, + or have not been used before. The list is sorted to have the most- + allocated arenas first (ascending order based on the nfreepools member). + This means that the next allocation will come from a heavily used arena, + which gives the nearly empty arenas a chance to be returned to the system. + In my unscientific tests this dramatically improved the number of arenas + that could be freed. + +Note that an arena_object associated with an arena all of whose pools are +currently in use isn't on either list. +*/ + +/* Array of objects used to track chunks of memory (arenas). */ +static struct arena_object* arenas = NULL; +/* Number of slots currently allocated in the `arenas` vector. */ static uint maxarenas = 0; -/* Number of pools still available to be allocated in the current arena. */ -static uint nfreepools = 0; - -/* Free space start address in current arena. This is pool-aligned. */ -static block *arenabase = NULL; - -/* Allocate a new arena and return its base address. If we run out of - * memory, return NULL. +/* The head of the singly-linked, NULL-terminated list of available + * arena_objects. */ -static block * +static struct arena_object* unused_arena_objects = NULL; + +/* The head of the doubly-linked, NULL-terminated at each end, list of + * arena_objects associated with arenas that have pools available. + */ +static struct arena_object* usable_arenas = NULL; + +/* How many arena_objects do we initially allocate? + * 16 = can allocate 16 arenas = 16 * ARENA_SIZE = 4MB before growing the + * `arenas` vector. + */ +#define INITIAL_ARENA_OBJECTS 16 + +/* Number of arenas allocated that haven't been free()'d. */ +static ulong narenas_currently_allocated = 0; + +#ifdef PYMALLOC_DEBUG +/* Total number of times malloc() called to allocate an arena. */ +static ulong ntimes_arena_allocated = 0; +/* High water mark (max value ever seen) for narenas_currently_allocated. */ +static ulong narenas_highwater = 0; +#endif + +/* Allocate a new arena. If we run out of memory, return NULL. Else + * allocate a new arena, and return the address of an arena_object + * describing the new arena. It's expected that the caller will set + * `usable_arenas` to the return value. + */ +static struct arena_object* new_arena(void) { + struct arena_object* arenaobj; uint excess; /* number of bytes above pool alignment */ - block *bp = (block *)malloc(ARENA_SIZE); - if (bp == NULL) - return NULL; #ifdef PYMALLOC_DEBUG if (Py_GETENV("PYTHONMALLOCSTATS")) _PyObject_DebugMallocStats(); #endif + if (unused_arena_objects == NULL) { + uint i; + uint numarenas; + size_t nbytes; - /* arenabase <- first pool-aligned address in the arena - nfreepools <- number of whole pools that fit after alignment */ - arenabase = bp; - nfreepools = ARENA_SIZE / POOL_SIZE; - assert(POOL_SIZE * nfreepools == ARENA_SIZE); - excess = (uint) ((Py_uintptr_t)bp & POOL_SIZE_MASK); - if (excess != 0) { - --nfreepools; - arenabase += POOL_SIZE - excess; - } - - /* Make room for a new entry in the arenas vector. */ - if (arenas == NULL) { - assert(narenas == 0 && maxarenas == 0); - arenas = (uptr *)malloc(16 * sizeof(*arenas)); - if (arenas == NULL) - goto error; - maxarenas = 16; - } - else if (narenas == maxarenas) { - /* Grow arenas. - * - * Exceedingly subtle: Someone may be calling the pymalloc - * free via PyMem_{DEL, Del, FREE, Free} without holding the - *.GIL. Someone else may simultaneously be calling the - * pymalloc malloc while holding the GIL via, e.g., - * PyObject_New. Now the pymalloc free may index into arenas - * for an address check, while the pymalloc malloc calls - * new_arena and we end up here to grow a new arena *and* - * grow the arenas vector. If the value for arenas pymalloc - * free picks up "vanishes" during this resize, anything may - * happen, and it would be an incredibly rare bug. Therefore - * the code here takes great pains to make sure that, at every - * moment, arenas always points to an intact vector of - * addresses. It doesn't matter whether arenas points to a - * wholly up-to-date vector when pymalloc free checks it in - * this case, because the only legal (and that even this is - * legal is debatable) way to call PyMem_{Del, etc} while not - * holding the GIL is if the memory being released is not - * object memory, i.e. if the address check in pymalloc free - * is supposed to fail. Having an incomplete vector can't - * make a supposed-to-fail case succeed by mistake (it could - * only make a supposed-to-succeed case fail by mistake). - * - * In addition, without a lock we can't know for sure when - * an old vector is no longer referenced, so we simply let - * old vectors leak. - * - * And on top of that, since narenas and arenas can't be - * changed as-a-pair atomically without a lock, we're also - * careful to declare them volatile and ensure that we change - * arenas first. This prevents another thread from picking - * up an narenas value too large for the arenas value it - * reads up (arenas never shrinks). - * - * Read the above 50 times before changing anything in this - * block. + /* Double the number of arena objects on each allocation. + * Note that it's possible for `numarenas` to overflow. */ - uptr *p; - uint newmax = maxarenas << 1; - if (newmax <= maxarenas) /* overflow */ - goto error; - p = (uptr *)malloc(newmax * sizeof(*arenas)); - if (p == NULL) - goto error; - memcpy(p, arenas, narenas * sizeof(*arenas)); - arenas = p; /* old arenas deliberately leaked */ - maxarenas = newmax; + numarenas = maxarenas ? maxarenas << 1 : INITIAL_ARENA_OBJECTS; + if (numarenas <= maxarenas) + return NULL; /* overflow */ + nbytes = numarenas * sizeof(*arenas); + if (nbytes / sizeof(*arenas) != numarenas) + return NULL; /* overflow */ + arenaobj = realloc(arenas, nbytes); + if (arenaobj == NULL) + return NULL; + arenas = arenaobj; + + /* We might need to fix pointers that were copied. However, + * new_arena only gets called when all the pages in the + * previous arenas are full. Thus, there are *no* pointers + * into the old array. Thus, we don't have to worry about + * invalid pointers. Just to be sure, some asserts: + */ + assert(usable_arenas == NULL); + assert(unused_arena_objects == NULL); + + /* Put the new arenas on the unused_arena_objects list. */ + for (i = maxarenas; i < numarenas; ++i) { + arenas[i].address = 0; /* mark as unassociated */ + arenas[i].nextarena = i < numarenas - 1 ? + &arenas[i+1] : NULL; + } + + /* Update globals. */ + unused_arena_objects = &arenas[maxarenas]; + maxarenas = numarenas; } - /* Append the new arena address to arenas. */ - assert(narenas < maxarenas); - arenas[narenas] = (uptr)bp; - ++narenas; /* can't overflow, since narenas < maxarenas before */ - return bp; + /* Take the next available arena object off the head of the list. */ + assert(unused_arena_objects != NULL); + arenaobj = unused_arena_objects; + unused_arena_objects = arenaobj->nextarena; + assert(arenaobj->address == 0); + arenaobj->address = (uptr)malloc(ARENA_SIZE); + if (arenaobj->address == 0) { + /* The allocation failed: return NULL after putting the + * arenaobj back. + */ + arenaobj->nextarena = unused_arena_objects; + unused_arena_objects = arenaobj; + return NULL; + } -error: - free(bp); - nfreepools = 0; - return NULL; + ++narenas_currently_allocated; +#ifdef PYMALLOC_DEBUG + ++ntimes_arena_allocated; + if (narenas_currently_allocated > narenas_highwater) + narenas_highwater = narenas_currently_allocated; +#endif + arenaobj->freepools = NULL; + /* pool_address <- first pool-aligned address in the arena + nfreepools <- number of whole pools that fit after alignment */ + arenaobj->pool_address = (block*)arenaobj->address; + arenaobj->nfreepools = ARENA_SIZE / POOL_SIZE; + assert(POOL_SIZE * arenaobj->nfreepools == ARENA_SIZE); + excess = (uint)(arenaobj->address & POOL_SIZE_MASK); + if (excess != 0) { + --arenaobj->nfreepools; + arenaobj->pool_address += POOL_SIZE - excess; + } + arenaobj->ntotalpools = arenaobj->nfreepools; + + return arenaobj; } -/* Return true if and only if P is an address that was allocated by - * pymalloc. I must be the index into arenas that the address claims - * to come from. - * - * Tricky: Letting B be the arena base address in arenas[I], P belongs to the - * arena if and only if - * B <= P < B + ARENA_SIZE - * Subtracting B throughout, this is true iff - * 0 <= P-B < ARENA_SIZE - * By using unsigned arithmetic, the "0 <=" half of the test can be skipped. - * - * Obscure: A PyMem "free memory" function can call the pymalloc free or - * realloc before the first arena has been allocated. arenas is still - * NULL in that case. We're relying on that narenas is also 0 in that case, - * so the (I) < narenas must be false, saving us from trying to index into - * a NULL arenas. - */ -#define Py_ADDRESS_IN_RANGE(P, POOL) \ - ((POOL)->arenaindex < narenas && \ - (uptr)(P) - arenas[(POOL)->arenaindex] < (uptr)ARENA_SIZE) +/* +Py_ADDRESS_IN_RANGE(P, POOL) + +Return true if and only if P is an address that was allocated by pymalloc. +POOL must be the pool address associated with P, i.e., POOL = POOL_ADDR(P) +(the caller is asked to compute this because the macro expands POOL more than +once, and for efficiency it's best for the caller to assign POOL_ADDR(P) to a +variable and pass the latter to the macro; because Py_ADDRESS_IN_RANGE is +called on every alloc/realloc/free, micro-efficiency is important here). + +Tricky: Let B be the arena base address associated with the pool, B = +arenas[(POOL)->arenaindex].address. Then P belongs to the arena if and only if + + B <= P < B + ARENA_SIZE + +Subtracting B throughout, this is true iff + + 0 <= P-B < ARENA_SIZE + +By using unsigned arithmetic, the "0 <=" half of the test can be skipped. + +Obscure: A PyMem "free memory" function can call the pymalloc free or realloc +before the first arena has been allocated. `arenas` is still NULL in that +case. We're relying on that maxarenas is also 0 in that case, so that +(POOL)->arenaindex < maxarenas must be false, saving us from trying to index +into a NULL arenas. + +Details: given P and POOL, the arena_object corresponding to P is AO = +arenas[(POOL)->arenaindex]. Suppose obmalloc controls P. Then (barring wild +stores, etc), POOL is the correct address of P's pool, AO.address is the +correct base address of the pool's arena, and P must be within ARENA_SIZE of +AO.address. In addition, AO.address is not 0 (no arena can start at address 0 +(NULL)). Therefore Py_ADDRESS_IN_RANGE correctly reports that obmalloc +controls P. + +Now suppose obmalloc does not control P (e.g., P was obtained via a direct +call to the system malloc() or realloc()). (POOL)->arenaindex may be anything +in this case -- it may even be uninitialized trash. If the trash arenaindex +is >= maxarenas, the macro correctly concludes at once that obmalloc doesn't +control P. + +Else arenaindex is < maxarena, and AO is read up. If AO corresponds to an +allocated arena, obmalloc controls all the memory in slice AO.address : +AO.address+ARENA_SIZE. By case assumption, P is not controlled by obmalloc, +so P doesn't lie in that slice, so the macro correctly reports that P is not +controlled by obmalloc. + +Finally, if P is not controlled by obmalloc and AO corresponds to an unused +arena_object (one not currently associated with an allocated arena), +AO.address is 0, and the second test in the macro reduces to: + + P < ARENA_SIZE + +If P >= ARENA_SIZE (extremely likely), the macro again correctly concludes +that P is not controlled by obmalloc. However, if P < ARENA_SIZE, this part +of the test still passes, and the third clause (AO.address != 0) is necessary +to get the correct result: AO.address is 0 in this case, so the macro +correctly reports that P is not controlled by obmalloc (despite that P lies in +slice AO.address : AO.address + ARENA_SIZE). + +Note: The third (AO.address != 0) clause was added in Python 2.5. Before +2.5, arenas were never free()'ed, and an arenaindex < maxarena always +corresponded to a currently-allocated arena, so the "P is not controlled by +obmalloc, AO corresponds to an unused arena_object, and P < ARENA_SIZE" case +was impossible. + +Note that the logic is excruciating, and reading up possibly uninitialized +memory when P is not controlled by obmalloc (to get at (POOL)->arenaindex) +creates problems for some memory debuggers. The overwhelming advantage is +that this test determines whether an arbitrary address is controlled by +obmalloc in a small constant time, independent of the number of arenas +obmalloc controls. Since this test is needed at every entry point, it's +extremely desirable that it be this fast. +*/ +#define Py_ADDRESS_IN_RANGE(P, POOL) \ + ((POOL)->arenaindex < maxarenas && \ + (uptr)(P) - arenas[(POOL)->arenaindex].address < (uptr)ARENA_SIZE && \ + arenas[(POOL)->arenaindex].address != 0) + /* This is only useful when running memory debuggers such as * Purify or Valgrind. Uncomment to use. @@ -599,7 +733,7 @@ PyObject_Malloc(size_t nbytes) /* * Most frequent paths first */ - size = (uint )(nbytes - 1) >> ALIGNMENT_SHIFT; + size = (uint)(nbytes - 1) >> ALIGNMENT_SHIFT; pool = usedpools[size + size]; if (pool != pool->nextpool) { /* @@ -614,22 +748,18 @@ PyObject_Malloc(size_t nbytes) return (void *)bp; } /* - * Reached the end of the free list, try to extend it + * Reached the end of the free list, try to extend it. */ if (pool->nextoffset <= pool->maxnextoffset) { - /* - * There is room for another block - */ - pool->freeblock = (block *)pool + + /* There is room for another block. */ + pool->freeblock = (block*)pool + pool->nextoffset; pool->nextoffset += INDEX2SIZE(size); *(block **)(pool->freeblock) = NULL; UNLOCK(); return (void *)bp; } - /* - * Pool is full, unlink from used pools - */ + /* Pool is full, unlink from used pools. */ next = pool->nextpool; pool = pool->prevpool; next->prevpool = pool; @@ -637,19 +767,68 @@ PyObject_Malloc(size_t nbytes) UNLOCK(); return (void *)bp; } - /* - * Try to get a cached free pool + + /* There isn't a pool of the right size class immediately + * available: use a free pool. */ - pool = freepools; + if (usable_arenas == NULL) { + /* No arena has a free pool: allocate a new arena. */ +#ifdef WITH_MEMORY_LIMITS + if (narenas_currently_allocated >= MAX_ARENAS) { + UNLOCK(); + goto redirect; + } +#endif + usable_arenas = new_arena(); + if (usable_arenas == NULL) { + UNLOCK(); + goto redirect; + } + usable_arenas->nextarena = + usable_arenas->prevarena = NULL; + } + assert(usable_arenas->address != 0); + + /* Try to get a cached free pool. */ + pool = usable_arenas->freepools; if (pool != NULL) { - /* - * Unlink from cached pools + /* Unlink from cached pools. */ + usable_arenas->freepools = pool->nextpool; + + /* This arena already had the smallest nfreepools + * value, so decreasing nfreepools doesn't change + * that, and we don't need to rearrange the + * usable_arenas list. However, if the arena has + * become wholly allocated, we need to remove its + * arena_object from usable_arenas. */ - freepools = pool->nextpool; + --usable_arenas->nfreepools; + if (usable_arenas->nfreepools == 0) { + /* Wholly allocated: remove. */ + assert(usable_arenas->freepools == NULL); + assert(usable_arenas->nextarena == NULL || + usable_arenas->nextarena->prevarena == + usable_arenas); + + usable_arenas = usable_arenas->nextarena; + if (usable_arenas != NULL) { + usable_arenas->prevarena = NULL; + assert(usable_arenas->address != 0); + } + } + else { + /* nfreepools > 0: it must be that freepools + * isn't NULL, or that we haven't yet carved + * off all the arena's pools for the first + * time. + */ + assert(usable_arenas->freepools != NULL || + usable_arenas->pool_address <= + (block*)usable_arenas->address + + ARENA_SIZE - POOL_SIZE); + } init_pool: - /* - * Frontlink to used pools - */ + /* Frontlink to used pools. */ next = usedpools[size + size]; /* == prev */ pool->nextpool = next; pool->prevpool = next; @@ -657,8 +836,7 @@ PyObject_Malloc(size_t nbytes) next->prevpool = pool; pool->ref.count = 1; if (pool->szidx == size) { - /* - * Luckily, this pool last contained blocks + /* Luckily, this pool last contained blocks * of the same size class, so its header * and free list are already initialized. */ @@ -682,39 +860,38 @@ PyObject_Malloc(size_t nbytes) UNLOCK(); return (void *)bp; } - /* - * Allocate new pool - */ - if (nfreepools) { - commit_pool: - --nfreepools; - pool = (poolp)arenabase; - arenabase += POOL_SIZE; - pool->arenaindex = narenas - 1; - pool->szidx = DUMMY_SIZE_IDX; - goto init_pool; + + /* Carve off a new pool. */ + assert(usable_arenas->nfreepools > 0); + assert(usable_arenas->freepools == NULL); + pool = (poolp)usable_arenas->pool_address; + assert((block*)pool <= (block*)usable_arenas->address + + ARENA_SIZE - POOL_SIZE); + pool->arenaindex = usable_arenas - arenas; + assert(&arenas[pool->arenaindex] == usable_arenas); + pool->szidx = DUMMY_SIZE_IDX; + usable_arenas->pool_address += POOL_SIZE; + --usable_arenas->nfreepools; + + if (usable_arenas->nfreepools == 0) { + assert(usable_arenas->nextarena == NULL || + usable_arenas->nextarena->prevarena == + usable_arenas); + /* Unlink the arena: it is completely allocated. */ + usable_arenas = usable_arenas->nextarena; + if (usable_arenas != NULL) { + usable_arenas->prevarena = NULL; + assert(usable_arenas->address != 0); + } } - /* - * Allocate new arena - */ -#ifdef WITH_MEMORY_LIMITS - if (!(narenas < MAX_ARENAS)) { - UNLOCK(); - goto redirect; - } -#endif - bp = new_arena(); - if (bp != NULL) - goto commit_pool; - UNLOCK(); - goto redirect; + + goto init_pool; } /* The small block allocator ends here. */ redirect: - /* - * Redirect the original request to the underlying (libc) allocator. + /* Redirect the original request to the underlying (libc) allocator. * We jump here on bigger requests, on error in the code above (as a * last chance to serve the request) or when the max memory limit * has been reached. @@ -742,8 +919,7 @@ PyObject_Free(void *p) if (Py_ADDRESS_IN_RANGE(p, pool)) { /* We allocated this address. */ LOCK(); - /* - * Link p to the start of the pool's freeblock list. Since + /* Link p to the start of the pool's freeblock list. Since * the pool had at least the p block outstanding, the pool * wasn't empty (so it's already in a usedpools[] list, or * was full and is in no list -- it's not in the freeblocks @@ -753,8 +929,10 @@ PyObject_Free(void *p) *(block **)p = lastfree = pool->freeblock; pool->freeblock = (block *)p; if (lastfree) { - /* - * freeblock wasn't NULL, so the pool wasn't full, + struct arena_object* ao; + uint nf; /* ao->nfreepools */ + + /* freeblock wasn't NULL, so the pool wasn't full, * and the pool is in a usedpools[] list. */ if (--pool->ref.count != 0) { @@ -762,8 +940,7 @@ PyObject_Free(void *p) UNLOCK(); return; } - /* - * Pool is now empty: unlink from usedpools, and + /* Pool is now empty: unlink from usedpools, and * link to the front of freepools. This ensures that * previously freed pools will be allocated later * (being not referenced, they are perhaps paged out). @@ -772,16 +949,147 @@ PyObject_Free(void *p) prev = pool->prevpool; next->prevpool = prev; prev->nextpool = next; - /* Link to freepools. This is a singly-linked list, - * and pool->prevpool isn't used there. + + /* Link the pool to freepools. This is a singly-linked + * list, and pool->prevpool isn't used there. */ - pool->nextpool = freepools; - freepools = pool; + ao = &arenas[pool->arenaindex]; + pool->nextpool = ao->freepools; + ao->freepools = pool; + nf = ++ao->nfreepools; + + /* All the rest is arena management. We just freed + * a pool, and there are 4 cases for arena mgmt: + * 1. If all the pools are free, return the arena to + * the system free(). + * 2. If this is the only free pool in the arena, + * add the arena back to the `usable_arenas` list. + * 3. If the "next" arena has a smaller count of free + * pools, we have to "slide this arena right" to + * restore that usable_arenas is sorted in order of + * nfreepools. + * 4. Else there's nothing more to do. + */ + if (nf == ao->ntotalpools) { + /* Case 1. First unlink ao from usable_arenas. + */ + assert(ao->prevarena == NULL || + ao->prevarena->address != 0); + assert(ao ->nextarena == NULL || + ao->nextarena->address != 0); + + /* Fix the pointer in the prevarena, or the + * usable_arenas pointer. + */ + if (ao->prevarena == NULL) { + usable_arenas = ao->nextarena; + assert(usable_arenas == NULL || + usable_arenas->address != 0); + } + else { + assert(ao->prevarena->nextarena == ao); + ao->prevarena->nextarena = + ao->nextarena; + } + /* Fix the pointer in the nextarena. */ + if (ao->nextarena != NULL) { + assert(ao->nextarena->prevarena == ao); + ao->nextarena->prevarena = + ao->prevarena; + } + /* Record that this arena_object slot is + * available to be reused. + */ + ao->nextarena = unused_arena_objects; + unused_arena_objects = ao; + + /* Free the entire arena. */ + free((void *)ao->address); + ao->address = 0; /* mark unassociated */ + --narenas_currently_allocated; + + UNLOCK(); + return; + } + if (nf == 1) { + /* Case 2. Put ao at the head of + * usable_arenas. Note that because + * ao->nfreepools was 0 before, ao isn't + * currently on the usable_arenas list. + */ + ao->nextarena = usable_arenas; + ao->prevarena = NULL; + if (usable_arenas) + usable_arenas->prevarena = ao; + usable_arenas = ao; + assert(usable_arenas->address != 0); + + UNLOCK(); + return; + } + /* If this arena is now out of order, we need to keep + * the list sorted. The list is kept sorted so that + * the "most full" arenas are used first, which allows + * the nearly empty arenas to be completely freed. In + * a few un-scientific tests, it seems like this + * approach allowed a lot more memory to be freed. + */ + if (ao->nextarena == NULL || + nf <= ao->nextarena->nfreepools) { + /* Case 4. Nothing to do. */ + UNLOCK(); + return; + } + /* Case 3: We have to move the arena towards the end + * of the list, because it has more free pools than + * the arena to its right. + * First unlink ao from usable_arenas. + */ + if (ao->prevarena != NULL) { + /* ao isn't at the head of the list */ + assert(ao->prevarena->nextarena == ao); + ao->prevarena->nextarena = ao->nextarena; + } + else { + /* ao is at the head of the list */ + assert(usable_arenas == ao); + usable_arenas = ao->nextarena; + } + ao->nextarena->prevarena = ao->prevarena; + + /* Locate the new insertion point by iterating over + * the list, using our nextarena pointer. + */ + while (ao->nextarena != NULL && + nf > ao->nextarena->nfreepools) { + ao->prevarena = ao->nextarena; + ao->nextarena = ao->nextarena->nextarena; + } + + /* Insert ao at this point. */ + assert(ao->nextarena == NULL || + ao->prevarena == ao->nextarena->prevarena); + assert(ao->prevarena->nextarena == ao->nextarena); + + ao->prevarena->nextarena = ao; + if (ao->nextarena != NULL) + ao->nextarena->prevarena = ao; + + /* Verify that the swaps worked. */ + assert(ao->nextarena == NULL || + nf <= ao->nextarena->nfreepools); + assert(ao->prevarena == NULL || + nf > ao->prevarena->nfreepools); + assert(ao->nextarena == NULL || + ao->nextarena->prevarena == ao); + assert((usable_arenas == ao && + ao->prevarena == NULL) || + ao->prevarena->nextarena == ao); + UNLOCK(); return; } - /* - * Pool was full, so doesn't currently live in any list: + /* Pool was full, so doesn't currently live in any list: * link it to the front of the appropriate usedpools[] list. * This mimics LRU pool usage for new allocations and * targets optimal filling when several pools contain @@ -1302,6 +1610,8 @@ _PyObject_DebugMallocStats(void) * full pools. */ ulong quantization = 0; + /* # of arenas actually allocated. */ + ulong narenas = 0; /* running total -- should equal narenas * ARENA_SIZE */ ulong total; char buf[128]; @@ -1316,36 +1626,38 @@ _PyObject_DebugMallocStats(void) * to march over all the arenas. If we're lucky, most of the memory * will be living in full pools -- would be a shame to miss them. */ - for (i = 0; i < narenas; ++i) { + for (i = 0; i < maxarenas; ++i) { uint poolsinarena; uint j; - uptr base = arenas[i]; + uptr base = arenas[i].address; + + /* Skip arenas which are not allocated. */ + if (arenas[i].address == (uptr)NULL) + continue; + narenas += 1; + + poolsinarena = arenas[i].ntotalpools; + numfreepools += arenas[i].nfreepools; /* round up to pool alignment */ - poolsinarena = ARENA_SIZE / POOL_SIZE; if (base & (uptr)POOL_SIZE_MASK) { - --poolsinarena; arena_alignment += POOL_SIZE; base &= ~(uptr)POOL_SIZE_MASK; base += POOL_SIZE; } - if (i == narenas - 1) { - /* current arena may have raw memory at the end */ - numfreepools += nfreepools; - poolsinarena -= nfreepools; - } - /* visit every pool in the arena */ - for (j = 0; j < poolsinarena; ++j, base += POOL_SIZE) { + assert(base <= (uptr) arenas[i].pool_address); + for (j = 0; + base < (uptr) arenas[i].pool_address; + ++j, base += POOL_SIZE) { poolp p = (poolp)base; const uint sz = p->szidx; uint freeblocks; if (p->ref.count == 0) { /* currently unused */ - ++numfreepools; - assert(pool_is_in_list(p, freepools)); + assert(pool_is_in_list(p, arenas[i].freepools)); continue; } ++numpools[sz]; @@ -1358,6 +1670,7 @@ _PyObject_DebugMallocStats(void) #endif } } + assert(narenas == narenas_currently_allocated); fputc('\n', stderr); fputs("class size num pools blocks in use avail blocks\n" @@ -1383,9 +1696,14 @@ _PyObject_DebugMallocStats(void) fputc('\n', stderr); (void)printone("# times object malloc called", serialno); + (void)printone("# arenas allocated total", ntimes_arena_allocated); + (void)printone("# arenas reclaimed", ntimes_arena_allocated - narenas); + (void)printone("# arenas highwater mark", narenas_highwater); + (void)printone("# arenas allocated current", narenas); + PyOS_snprintf(buf, sizeof(buf), - "%u arenas * %d bytes/arena", narenas, ARENA_SIZE); - (void)printone(buf, (ulong)narenas * ARENA_SIZE); + "%lu arenas * %d bytes/arena", narenas, ARENA_SIZE); + (void)printone(buf, narenas * ARENA_SIZE); fputc('\n', stderr); @@ -1405,12 +1723,14 @@ _PyObject_DebugMallocStats(void) #endif /* PYMALLOC_DEBUG */ #ifdef Py_USING_MEMORY_DEBUGGER -/* Make this function last so gcc won't inline it - since the definition is after the reference. */ +/* Make this function last so gcc won't inline it since the definition is + * after the reference. + */ int Py_ADDRESS_IN_RANGE(void *P, poolp pool) { - return ((pool->arenaindex) < narenas && - (uptr)(P) - arenas[pool->arenaindex] < (uptr)ARENA_SIZE); + return pool->arenaindex < maxarenas && + (uptr)P - arenas[pool->arenaindex].address < (uptr)ARENA_SIZE && + arenas[pool->arenaindex].address != 0; } #endif diff --git a/Python/codecs.c b/Python/codecs.c index 253bc393260..0e8c3749807 100644 --- a/Python/codecs.c +++ b/Python/codecs.c @@ -260,6 +260,56 @@ PyObject *PyCodec_Decoder(const char *encoding) return NULL; } +PyObject *PyCodec_IncrementalEncoder(const char *encoding, + const char *errors) +{ + PyObject *codecs, *ret, *encoder; + + codecs = _PyCodec_Lookup(encoding); + if (codecs == NULL) + goto onError; + encoder = PyObject_GetAttrString(codecs, "incrementalencoder"); + if (encoder == NULL) { + Py_DECREF(codecs); + return NULL; + } + if (errors) + ret = PyObject_CallFunction(encoder, "O", errors); + else + ret = PyObject_CallFunction(encoder, NULL); + Py_DECREF(encoder); + Py_DECREF(codecs); + return ret; + + onError: + return NULL; +} + +PyObject *PyCodec_IncrementalDecoder(const char *encoding, + const char *errors) +{ + PyObject *codecs, *ret, *decoder; + + codecs = _PyCodec_Lookup(encoding); + if (codecs == NULL) + goto onError; + decoder = PyObject_GetAttrString(codecs, "incrementaldecoder"); + if (decoder == NULL) { + Py_DECREF(codecs); + return NULL; + } + if (errors) + ret = PyObject_CallFunction(decoder, "O", errors); + else + ret = PyObject_CallFunction(decoder, NULL); + Py_DECREF(decoder); + Py_DECREF(codecs); + return ret; + + onError: + return NULL; +} + PyObject *PyCodec_StreamReader(const char *encoding, PyObject *stream, const char *errors) diff --git a/Tools/buildbot/clean.bat b/Tools/buildbot/clean.bat index d28262e43c2..4b949225d18 100644 --- a/Tools/buildbot/clean.bat +++ b/Tools/buildbot/clean.bat @@ -1,3 +1,6 @@ @rem Used by the buildbot "clean" step. call "%VS71COMNTOOLS%vsvars32.bat" -devenv.com /clean Debug PCbuild\pcbuild.sln +cd PCbuild +@echo Deleting .pyc/.pyo files ... +python_d.exe rmpyc.py +devenv.com /clean Debug pcbuild.sln diff --git a/Tools/unicode/Makefile b/Tools/unicode/Makefile index 34a9df989bb..f266d4d2183 100644 --- a/Tools/unicode/Makefile +++ b/Tools/unicode/Makefile @@ -44,11 +44,11 @@ windows: build/ $(RM) -f build/readme.* iso: build/ - $(PYTHON) gencodec.py MAPPINGS/ISO8859/ build/iso + $(PYTHON) gencodec.py MAPPINGS/ISO8859/ build/ iso $(RM) -f build/isoreadme.* apple: build/ - $(PYTHON) gencodec.py MAPPINGS/VENDORS/APPLE/ build/mac_ + $(PYTHON) gencodec.py MAPPINGS/VENDORS/APPLE/ build/ mac_ $(RM) build/mac_dingbats.* $(RM) build/mac_japanese.* $(RM) build/mac_chin* diff --git a/Tools/unicode/gencodec.py b/Tools/unicode/gencodec.py index 494164a6908..bb1c9da5f0c 100644 --- a/Tools/unicode/gencodec.py +++ b/Tools/unicode/gencodec.py @@ -248,7 +248,7 @@ def python_tabledef_code(varname, map, comments=1, key_precision=2): append(')') return l -def codegen(name, map, comments=1): +def codegen(name, map, encodingname, comments=1): """ Returns Python source for the given map. @@ -272,7 +272,7 @@ def codegen(name, map, comments=1): l = [ '''\ -""" Python Character Mapping Codec generated from '%s' with gencodec.py. +""" Python Character Mapping Codec %s generated from '%s' with gencodec.py. """#" @@ -283,11 +283,9 @@ import codecs class Codec(codecs.Codec): def encode(self,input,errors='strict'): - return codecs.charmap_encode(input,errors,encoding_map) - def decode(self,input,errors='strict'): -''' % name + def decode(self,input,errors='strict'):''' % (encodingname, name) ] if decoding_table_code: l.append('''\ @@ -296,6 +294,20 @@ class Codec(codecs.Codec): l.append('''\ return codecs.charmap_decode(input,errors,decoding_map)''') + l.append(''' +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False):''') + if decoding_table_code: + l.append('''\ + return codecs.charmap_decode(input,self.errors,decoding_table)[0]''') + else: + l.append('''\ + return codecs.charmap_decode(input,self.errors,decoding_map)[0]''') + l.append(''' class StreamWriter(Codec,codecs.StreamWriter): pass @@ -306,9 +318,16 @@ class StreamReader(Codec,codecs.StreamReader): ### encodings module API def getregentry(): - - return (Codec().encode,Codec().decode,StreamReader,StreamWriter) -''') + return codecs.CodecInfo(( + name=%r, + Codec().encode, + Codec().decode, + streamwriter=StreamWriter, + streamreader=StreamReader, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + )) +''' % encodingname.replace('_', '-')) # Add decoding table or map (with preference to the table) if not decoding_table_code: @@ -331,11 +350,11 @@ def getregentry(): # Final new-line l.append('\n') - return '\n'.join(l) + return '\n'.join(l).expandtabs() -def pymap(name,map,pyfile,comments=1): +def pymap(name,map,pyfile,encodingname,comments=1): - code = codegen(name,map,comments) + code = codegen(name,map,encodingname,comments) f = open(pyfile,'w') f.write(code) f.close() @@ -349,7 +368,7 @@ def marshalmap(name,map,marshalfile): marshal.dump(d,f) f.close() -def convertdir(dir,prefix='',comments=1): +def convertdir(dir, dirprefix='', nameprefix='', comments=1): mapnames = os.listdir(dir) for mapname in mapnames: @@ -360,38 +379,40 @@ def convertdir(dir,prefix='',comments=1): name = name.replace('-','_') name = name.split('.')[0] name = name.lower() + name = nameprefix + name codefile = name + '.py' marshalfile = name + '.mapping' print 'converting %s to %s and %s' % (mapname, - prefix + codefile, - prefix + marshalfile) + dirprefix + codefile, + dirprefix + marshalfile) try: map = readmap(os.path.join(dir,mapname)) if not map: print '* map is empty; skipping' else: - pymap(mappathname, map, prefix + codefile,comments) - marshalmap(mappathname, map, prefix + marshalfile) + pymap(mappathname, map, dirprefix + codefile,name,comments) + marshalmap(mappathname, map, dirprefix + marshalfile) except ValueError, why: print '* conversion failed: %s' % why raise -def rewritepythondir(dir,prefix='',comments=1): +def rewritepythondir(dir, dirprefix='', comments=1): mapnames = os.listdir(dir) for mapname in mapnames: if not mapname.endswith('.mapping'): continue - codefile = mapname[:-len('.mapping')] + '.py' + name = mapname[:-len('.mapping')] + codefile = name + '.py' print 'converting %s to %s' % (mapname, - prefix + codefile) + dirprefix + codefile) try: map = marshal.load(open(os.path.join(dir,mapname), 'rb')) if not map: print '* map is empty; skipping' else: - pymap(mapname, map, prefix + codefile,comments) + pymap(mapname, map, dirprefix + codefile,name,comments) except ValueError, why: print '* conversion failed: %s' % why