aeidon/encodings.py¶
Source code for module aeidon.encodings from file aeidon/encodings.py.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 | # -*- coding: utf-8 -*-
# Copyright (C) 2005 Osmo Salomaa
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
"""
Codes, names and descriptions of character encodings.
For functions dealing with character encodings, see also :mod:`aeidon.util`.
"""
import aeidon
import codecs
import locale
import re
_ = aeidon.i18n._
# Tuples of code, name and description for each supported character encoding.
# Codes are the official names used by Python. Names are mostly taken from
# IANA. Descriptions are mostly copied from gedit.
_encodings = (
# Translators: Most of the character encoding descriptions are copied from
# gedit, which is translated to very many languages. Check the gedit .po
# files for a reference: <http://git.gnome.org/browse/gedit/tree/po/>.
("ascii" , "US-ASCII" , _("English")),
("big5" , "Big5" , _("Chinese traditional")),
("big5hkscs" , "Big5-HKSCS" , _("Chinese traditional")),
("cp037" , "IBM037" , _("English")),
("cp424" , "IBM242" , _("Hebrew")),
("cp437" , "IBM437" , _("English")),
("cp500" , "IBM500" , _("Western")),
("cp720" , "IBM720" , _("Arabic")),
("cp737" , "IBM737" , _("Greek")),
("cp775" , "IBM775" , _("Baltic")),
("cp850" , "IBM850" , _("Western")),
("cp852" , "IBM852" , _("Central European")),
("cp855" , "IBM855" , _("Cyrillic")),
("cp856" , "IBM856" , _("Hebrew")),
("cp857" , "IBM857" , _("Turkish")),
("cp860" , "IBM860" , _("Portuguese")),
("cp861" , "IBM861" , _("Icelandic")),
("cp862" , "IBM862" , _("Hebrew")),
("cp863" , "IBM863" , _("Canadian")),
("cp864" , "IBM864" , _("Arabic")),
("cp865" , "IBM865" , _("Nordic")),
("cp866" , "IBM866" , _("Russian")),
("cp869" , "IBM869" , _("Greek")),
("cp874" , "IBM874" , _("Thai")),
("cp875" , "IBM875" , _("Greek")),
("cp932" , "IBM932" , _("Japanese")),
("cp949" , "IBM949" , _("Korean")),
("cp950" , "IBM950" , _("Chinese traditional")),
("cp1006" , "IBM1006" , _("Urdu")),
("cp1026" , "IBM1026" , _("Turkish")),
("cp1140" , "IBM1140" , _("Western")),
("cp1250" , "windows-1250" , _("Central European")),
("cp1251" , "windows-1251" , _("Cyrillic")),
("cp1252" , "windows-1252" , _("Western")),
("cp1253" , "windows-1253" , _("Greek")),
("cp1254" , "windows-1254" , _("Turkish")),
("cp1255" , "windows-1255" , _("Hebrew")),
("cp1256" , "windows-1256" , _("Arabic")),
("cp1257" , "windows-1257" , _("Baltic")),
("cp1258" , "windows-1258" , _("Vietnamese")),
("euc_jp" , "EUC-JP" , _("Japanese")),
("euc_jis_2004" , "EUC-JIS-2004" , _("Japanese")),
("euc_jisx0213" , "EUC-JISX0213" , _("Japanese")),
("euc_kr" , "EUC-KR" , _("Korean")),
("gb2312" , "GB2312" , _("Chinese simplified")),
("gbk" , "GBK" , _("Chinese unified")),
("gb18030" , "GB18030" , _("Chinese unified")),
("hz" , "HZ" , _("Chinese simplified")),
("iso2022_jp" , "ISO-2022-JP" , _("Japanese")),
("iso2022_jp_1" , "ISO-2022-JP-1" , _("Japanese")),
("iso2022_jp_2" , "ISO-2022-JP-2" , _("Japanese")),
("iso2022_jp_2004", "ISO-2022-JP-2004", _("Japanese")),
("iso2022_jp_3" , "ISO-2022-JP-3" , _("Japanese")),
("iso2022_jp_ext" , "ISO-2022-JP-EXT" , _("Japanese")),
("iso2022_kr" , "ISO-2022-KR" , _("Korean")),
("latin_1" , "ISO-8859-1" , _("Western")),
("iso8859_2" , "ISO-8859-2" , _("Central European")),
("iso8859_3" , "ISO-8859-3" , _("South European")),
("iso8859_4" , "ISO-8859-4" , _("Baltic")),
("iso8859_5" , "ISO-8859-5" , _("Cyrillic")),
("iso8859_6" , "ISO-8859-6" , _("Arabic")),
("iso8859_7" , "ISO-8859-7" , _("Greek")),
("iso8859_8" , "ISO-8859-8" , _("Hebrew")),
("iso8859_9" , "ISO-8859-9" , _("Turkish")),
("iso8859_10" , "ISO-8859-10" , _("Nordic")),
("iso8859_13" , "ISO-8859-13" , _("Baltic")),
("iso8859_14" , "ISO-8859-14" , _("Celtic")),
("iso8859_15" , "ISO-8859-15" , _("Western")),
("johab" , "Johab" , _("Korean")),
("koi8_r" , "KOI8-R" , _("Russian")),
("koi8_u" , "KOI8-U" , _("Ukrainian")),
("mac_cyrillic" , "MacCyrillic" , _("Cyrillic")),
("mac_greek" , "MacGreek" , _("Greek")),
("mac_iceland" , "MacIceland" , _("Icelandic")),
("mac_latin2" , "MacCentralEurope", _("Central European")),
("mac_roman" , "MacRoman" , _("Western")),
("mac_turkish" , "MacTurkish" , _("Turkish")),
("ptcp154" , "PTCP154" , _("Cyrillic Asian")),
("shift_jis" , "Shift_JIS" , _("Japanese")),
("shift_jis_2004" , "Shift_JIS-2004" , _("Japanese")),
("shift_jisx0213" , "Shift_JISX0213" , _("Japanese")),
("utf_32" , "UTF-32" , _("Unicode")),
("utf_32_be" , "UTF-32BE" , _("Unicode")),
("utf_32_le" , "UTF-32LE" , _("Unicode")),
("utf_16" , "UTF-16" , _("Unicode")),
("utf_16_be" , "UTF-16BE" , _("Unicode")),
("utf_16_le" , "UTF-16LE" , _("Unicode")),
("utf_7" , "UTF-7" , _("Unicode")),
("utf_8" , "UTF-8" , _("Unicode")),
("utf_8_sig" , "UTF-8-SIG" , _("Unicode")),)
CODE, NAME, DESC = range(3)
# Illegal characters in encoding codes.
_re_illegal = re.compile(r"[^a-z0-9_]")
def code_to_description(code):
"""
Convert encoding `code` to localized description.
Raise :exc:`ValueError` if not found.
>>> aeidon.encodings.code_to_description("utf_8")
'Unicode'
"""
for item in _encodings:
if item[CODE] == code:
return item[DESC]
raise ValueError("Code {} not found"
.format(repr(code)))
def code_to_long_name(code):
"""
Convert encoding `code` to localized long name.
Raise :exc:`ValueError` if not found.
Return localized ``DESCRIPTION (DISPLAY NAME)``.
>>> aeidon.encodings.code_to_long_name("utf_8")
'Unicode (UTF-8)'
"""
for item in _encodings:
if item[CODE] == code:
return (_("{description} ({name})")
.format(name=item[NAME],
description=item[DESC]))
raise ValueError("Code {} not found"
.format(repr(code)))
def code_to_name(code):
"""
Convert encoding `code` to name.
Raise :exc:`ValueError` if not found.
>>> aeidon.encodings.code_to_name("utf_8")
'UTF-8'
"""
for item in _encodings:
if item[CODE] == code:
return item[NAME]
raise ValueError("Code {} not found"
.format(repr(code)))
def detect(path):
"""
Detect the encoding of file at `path` and return code or ``None``.
Raise :exc:`IOError` if reading fails.
"""
bom_encoding = detect_bom(path)
if bom_encoding is not None:
return bom_encoding
from chardet import universaldetector
detector = universaldetector.UniversalDetector()
with open(path, "rb") as f:
detector.reset()
for line in f:
detector.feed(line)
if detector.done: break
detector.close()
code = detector.result["encoding"]
if code is None: return None
try:
# chardet returns what seem to be IANA names. They need to be
# translated to their Python equivalents. Some of the encodings
# returned by chardet are not supported by Python.
return translate_code(code)
except ValueError:
return None
def detect_bom(path):
"""Return corresponding encoding if BOM found, else ``None``."""
with open(path, "rb") as f:
line = f.readline()
if (line.startswith(codecs.BOM_UTF32_BE) and
is_valid_code("utf_32_be")):
return "utf_32_be"
if (line.startswith(codecs.BOM_UTF32_LE) and
is_valid_code("utf_32_le")):
return "utf_32_le"
if (line.startswith(codecs.BOM_UTF8) and
is_valid_code("utf_8_sig")):
return "utf_8_sig"
if (line.startswith(codecs.BOM_UTF16_BE) and
is_valid_code("utf_16_be")):
return "utf_16_be"
if (line.startswith(codecs.BOM_UTF16_LE) and
is_valid_code("utf_16_le")):
return "utf_16_le"
return None
@aeidon.deco.once
def get_locale_code():
"""Return code of the locale encoding or ``None``."""
code = locale.getpreferredencoding()
if code is None: return None
code = _re_illegal.sub("_", code.lower())
code = aeidon.util.get_encoding_alias(code)
return code
@aeidon.deco.once
def get_locale_long_name():
"""
Return localized long name for locale encoding.
Raise :exc:`ValueError` if not found.
Return localized ``Current locale (NAME)``.
"""
name = code_to_name(get_locale_code())
return _("Current locale ({})").format(name)
@aeidon.deco.once
def get_valid():
"""
Return a sequence of valid encodings.
Return a list of tuples of code, name, description.
"""
valid_encodings = []
for i, item in enumerate(_encodings):
if is_valid_code(item[CODE]):
valid_encodings.append(item)
return valid_encodings
def is_valid_code(code):
"""Return ``True`` if encoding `code` is valid."""
try:
codecs.lookup(code)
return True
except LookupError:
return False
def name_to_code(name):
"""
Convert encoding `name` to code.
Raise :exc:`ValueError` if not found.
>>> aeidon.encodings.name_to_code("UTF-8")
'utf_8'
"""
for item in _encodings:
if item[NAME] == name:
return item[CODE]
raise ValueError("Name {} not found"
.format(repr(name)))
def translate_code(code):
"""
Translate weird encoding `code`.
Raise :exc:`ValueError` if not found.
Return normalized encoding code.
>>> aeidon.encodings.translate_code("ISO-8859-1")
'latin_1'
"""
code = _re_illegal.sub("_", code.lower())
code = aeidon.util.get_encoding_alias(code)
for item in _encodings:
if item[CODE] == code:
return item[CODE]
raise ValueError("Code {} not found"
.format(repr(code)))
|