diff options
| -rw-r--r-- | Misc/unicode.txt | 80 |
1 files changed, 73 insertions, 7 deletions
diff --git a/Misc/unicode.txt b/Misc/unicode.txt index 68a4228..d4b41a9 100644 --- a/Misc/unicode.txt +++ b/Misc/unicode.txt @@ -1,5 +1,5 @@ ============================================================================= - Python Unicode Integration Proposal Version: 1.3 + Python Unicode Integration Proposal Version: 1.4 ----------------------------------------------------------------------------- @@ -162,6 +162,17 @@ encoding>. For the same reason, Unicode objects should return the same hash value as their UTF-8 equivalent strings. +When compared using cmp() (or PyObject_Compare()) the implementation +should mask TypeErrors raised during the conversion to remain in synch +with the string behavior. All other errors such as ValueErrors raised +during coercion of strings to Unicode should not be masked and passed +through to the user. + +In containment tests ('a' in u'abc' and u'a' in 'abc') both sides +should be coerced to Unicode before applying the test. Errors occuring +during coercion (e.g. None in u'abc') should not be masked. + + Coercion: --------- @@ -380,6 +391,13 @@ class StreamWriter(Codec): data, consumed = self.encode(object,self.errors) self.stream.write(data) + def writelines(self, list): + + """ Writes the concatenated list of strings to the stream + using .write(). + """ + self.write(''.join(list)) + def reset(self): """ Flushes and resets the codec buffers used for keeping state. @@ -463,6 +481,47 @@ class StreamReader(Codec): else: return object + def readline(self, size=None): + + """ Read one line from the input stream and return the + decoded data. + + Note: Unlike the .readlines() method, this method inherits + the line breaking knowledge from the underlying stream's + .readline() method -- there is currently no support for + line breaking using the codec decoder due to lack of line + buffering. Sublcasses should however, if possible, try to + implement this method using their own knowledge of line + breaking. + + size, if given, is passed as size argument to the stream's + .readline() method. + + """ + if size is None: + line = self.stream.readline() + else: + line = self.stream.readline(size) + return self.decode(line)[0] + + def readlines(self, sizehint=0): + + """ Read all lines available on the input stream + and return them as list of lines. + + Line breaks are implemented using the codec's decoder + method and are included in the list entries. + + sizehint, if given, is passed as size argument to the + stream's .read() method. + + """ + if sizehint is None: + data = self.stream.read() + else: + data = self.stream.read(sizehint) + return self.decode(data)[0].splitlines(1) + def reset(self): """ Resets the codec buffers used for keeping state. @@ -482,9 +541,6 @@ class StreamReader(Codec): """ return getattr(self.stream,name) -XXX What about .readline(), .readlines() ? These could be implemented - using .read() as generic functions instead of requiring their - implementation by all codecs. Also see Line Breaks. Stream codec implementors are free to combine the StreamWriter and StreamReader interfaces into one class. Even combining all these with @@ -692,9 +748,10 @@ Format markers are used in Python format strings. If Python strings are used as format strings, the following interpretations should be in effect: - '%s': '%s' does str(u) for Unicode objects embedded - in Python strings, so the output will be - u.encode(<default encoding>) + '%s': For Unicode objects this will cause coercion of the + whole format string to Unicode. Note that + you should use a Unicode format string to start + with for performance reasons. In case the format string is an Unicode object, all parameters are coerced to Unicode first and then put together and formatted according to the format @@ -922,6 +979,9 @@ For comparison: Introducing Unicode to ECMAScript -- http://www-4.ibm.com/software/developer/library/internationalization-support.html +IANA Character Set Names: + ftp://ftp.isi.edu/in-notes/iana/assignments/character-sets + Encodings: Overview: @@ -944,6 +1004,12 @@ Encodings: History of this Proposal: ------------------------- +1.4: Added note about mixed type comparisons and contains tests. + Changed treating of Unicode objects in format strings (if used + with '%s' % u they will now cause the format string to be + coerced to Unicode, thus producing a Unicode object on return). + Added link to IANA charset names (thanks to Lars Marius Garshol). + Added new codec methods .readline(), .readlines() and .writelines(). 1.3: Added new "es" and "es#" parser markers 1.2: Removed POD about codecs.open() 1.1: Added note about comparisons and hash values. Added note about |