mirror of
https://github.com/python/cpython.git
synced 2025-11-03 23:21:29 +00:00
9e896b37c7
his copy of test_contains.py seems to be broken -- the lines he deleted were already absent). Checkin messages: New Unicode support for int(), float(), complex() and long(). - new APIs PyInt_FromUnicode() and PyLong_FromUnicode() - added support for Unicode to PyFloat_FromString() - new encoding API PyUnicode_EncodeDecimal() which converts Unicode to a decimal char* string (used in the above new APIs) - shortcuts for calls like int(<int object>) and float(<float obj>) - tests for all of the above Unicode compares and contains checks: - comparing Unicode and non-string types now works; TypeErrors are masked, all other errors such as ValueError during Unicode coercion are passed through (note that PyUnicode_Compare does not implement the masking -- PyObject_Compare does this) - contains now works for non-string types too; TypeErrors are masked and 0 returned; all other errors are passed through Better testing support for the standard codecs. Misc minor enhancements, such as an alias dbcs for the mbcs codec. Changes: - PyLong_FromString() now applies the same error checks as does PyInt_FromString(): trailing garbage is reported as error and not longer silently ignored. The only characters which may be trailing the digits are 'L' and 'l' -- these are still silently ignored. - string.ato?() now directly interface to int(), long() and float(). The error strings are now a little different, but the type still remains the same. These functions are now ready to get declared obsolete ;-) - PyNumber_Int() now also does a check for embedded NULL chars in the input string; PyNumber_Long() already did this (and still does) Followed by: Looks like I've gone a step too far there... (and test_contains.py seem to have a bug too). I've changed back to reporting all errors in PyUnicode_Contains() and added a few more test cases to test_contains.py (plus corrected the join() NameError).
60 lines
1.3 KiB
Python
60 lines
1.3 KiB
Python
""" Encoding Aliases Support
|
|
|
|
This module is used by the encodings package search function to
|
|
map encodings names to module names.
|
|
|
|
Note that the search function converts the encoding names to lower
|
|
case and replaces hyphens with underscores *before* performing the
|
|
lookup.
|
|
|
|
"""
|
|
aliases = {
|
|
|
|
# Latin-1
|
|
'latin': 'latin_1',
|
|
'latin1': 'latin_1',
|
|
|
|
# UTF-8
|
|
'utf': 'utf_8',
|
|
'utf8': 'utf_8',
|
|
'u8': 'utf_8',
|
|
|
|
# UTF-16
|
|
'utf16': 'utf_16',
|
|
'u16': 'utf_16',
|
|
'utf_16be': 'utf_16_be',
|
|
'utf_16le': 'utf_16_le',
|
|
'unicodebigunmarked': 'utf_16_be',
|
|
'unicodelittleunmarked': 'utf_16_le',
|
|
|
|
# ASCII
|
|
'us_ascii': 'ascii',
|
|
|
|
# ISO
|
|
'iso8859_1': 'latin_1',
|
|
'iso_8859_1': 'latin_1',
|
|
'iso_8859_10': 'iso8859_10',
|
|
'iso_8859_13': 'iso8859_13',
|
|
'iso_8859_14': 'iso8859_14',
|
|
'iso_8859_15': 'iso8859_15',
|
|
'iso_8859_2': 'iso8859_2',
|
|
'iso_8859_3': 'iso8859_3',
|
|
'iso_8859_4': 'iso8859_4',
|
|
'iso_8859_5': 'iso8859_5',
|
|
'iso_8859_6': 'iso8859_6',
|
|
'iso_8859_7': 'iso8859_7',
|
|
'iso_8859_8': 'iso8859_8',
|
|
'iso_8859_9': 'iso8859_9',
|
|
|
|
# Mac
|
|
'maccentraleurope': 'mac_latin2',
|
|
'maccyrillic': 'mac_cyrillic',
|
|
'macgreek': 'mac_greek',
|
|
'maciceland': 'mac_iceland',
|
|
'macroman': 'mac_roman',
|
|
'macturkish': 'mac_turkish',
|
|
|
|
# MBCS
|
|
'dbcs': 'mbcs',
|
|
|
|
}
|