cpython/Lib/gettext.py

540 lines
18 KiB
Python
Raw Normal View History

"""Internationalization and localization support.
This module provides internationalization (I18N) and localization (L10N)
support for your Python programs by providing an interface to the GNU gettext
message catalog library.
I18N refers to the operation by which a program is made aware of multiple
languages. L10N refers to the adaptation of your program, once
internationalized, to the local language and cultural habits.
"""
# This module represents the integration of work, contributions, feedback, and
# suggestions from the following people:
#
# Martin von Loewis, who wrote the initial implementation of the underlying
# C-based libintlmodule (later renamed _gettext), along with a skeletal
# gettext.py implementation.
#
# Peter Funk, who wrote fintl.py, a fairly complete wrapper around intlmodule,
# which also included a pure-Python implementation to read .mo files if
# intlmodule wasn't available.
#
# James Henstridge, who also wrote a gettext.py module, which has some
# interesting, but currently unsupported experimental features: the notion of
# a Catalog class and instances, and the ability to add to a catalog file via
# a Python API.
#
# Barry Warsaw integrated these modules, wrote the .install() API and code,
# and conformed all C and Python code to Python's coding standards.
#
# Francois Pinard and Marc-Andre Lemburg also contributed valuably to this
# module.
#
# J. David Ibanez implemented plural forms. Bruno Haible fixed some bugs.
#
# TODO:
# - Lazy loading of .mo files. Currently the entire catalog is loaded into
# memory, but that's probably bad for large translated programs. Instead,
# the lexical sort of original strings in GNU .mo files should be exploited
# to do binary searches and lazy initializations. Or you might want to use
# the undocumented double-hash algorithm for .mo files with hash tables, but
# you'll need to study the GNU gettext code to do this.
#
# - Support Solaris .mo file formats. Unfortunately, we've been unable to
# find this format documented anywhere.
import locale, copy, os, re, struct, sys
from errno import ENOENT
__all__ = ['NullTranslations', 'GNUTranslations', 'Catalog',
'find', 'translation', 'install', 'textdomain', 'bindtextdomain',
'dgettext', 'dngettext', 'gettext', 'ngettext',
]
_default_localedir = os.path.join(sys.prefix, 'share', 'locale')
def test(condition, true, false):
"""
Implements the C expression:
condition ? true : false
Required to correctly interpret plural forms.
"""
if condition:
return true
else:
return false
def c2py(plural):
"""Gets a C expression as used in PO files for plural forms and returns a
Python lambda function that implements an equivalent expression.
"""
# Security check, allow only the "n" identifier
from io import StringIO
import token, tokenize
tokens = tokenize.generate_tokens(StringIO(plural).readline)
try:
danger = [x for x in tokens if x[0] == token.NAME and x[1] != 'n']
except tokenize.TokenError:
2007-08-29 22:19:48 -03:00
raise ValueError('plural forms expression error, maybe unbalanced parenthesis')
else:
if danger:
2007-08-29 22:19:48 -03:00
raise ValueError('plural forms expression could be dangerous')
# Replace some C operators by their Python equivalents
plural = plural.replace('&&', ' and ')
plural = plural.replace('||', ' or ')
expr = re.compile(r'\!([^=])')
plural = expr.sub(' not \\1', plural)
# Regular expression and replacement function used to transform
# "a?b:c" to "test(a,b,c)".
expr = re.compile(r'(.*?)\?(.*?):(.*)')
def repl(x):
return "test(%s, %s, %s)" % (x.group(1), x.group(2),
expr.sub(repl, x.group(3)))
# Code to transform the plural expression, taking care of parentheses
stack = ['']
for c in plural:
if c == '(':
stack.append('')
elif c == ')':
if len(stack) == 1:
# Actually, we never reach this code, because unbalanced
# parentheses get caught in the security check at the
# beginning.
2007-08-29 22:19:48 -03:00
raise ValueError('unbalanced parenthesis in plural form')
s = expr.sub(repl, stack.pop())
stack[-1] += '(%s)' % s
else:
stack[-1] += c
plural = expr.sub(repl, stack.pop())
return eval('lambda n: int(%s)' % plural)
2001-01-14 19:47:14 -04:00
def _expand_lang(locale):
from locale import normalize
locale = normalize(locale)
COMPONENT_CODESET = 1 << 0
COMPONENT_TERRITORY = 1 << 1
COMPONENT_MODIFIER = 1 << 2
# split up the locale into its base components
mask = 0
pos = locale.find('@')
if pos >= 0:
modifier = locale[pos:]
locale = locale[:pos]
mask |= COMPONENT_MODIFIER
else:
modifier = ''
pos = locale.find('.')
if pos >= 0:
codeset = locale[pos:]
locale = locale[:pos]
mask |= COMPONENT_CODESET
else:
codeset = ''
pos = locale.find('_')
if pos >= 0:
territory = locale[pos:]
locale = locale[:pos]
mask |= COMPONENT_TERRITORY
else:
territory = ''
language = locale
ret = []
for i in range(mask+1):
if not (i & ~mask): # if all components for this combo exist ...
val = language
if i & COMPONENT_TERRITORY: val += territory
if i & COMPONENT_CODESET: val += codeset
if i & COMPONENT_MODIFIER: val += modifier
ret.append(val)
ret.reverse()
return ret
2001-01-14 19:47:14 -04:00
class NullTranslations:
def __init__(self, fp=None):
self._info = {}
self._charset = None
self._output_charset = None
self._fallback = None
2002-05-31 22:29:16 -03:00
if fp is not None:
self._parse(fp)
def _parse(self, fp):
pass
def add_fallback(self, fallback):
if self._fallback:
self._fallback.add_fallback(fallback)
else:
self._fallback = fallback
def gettext(self, message):
if self._fallback:
return self._fallback.gettext(message)
return message
def lgettext(self, message):
if self._fallback:
return self._fallback.lgettext(message)
return message
def ngettext(self, msgid1, msgid2, n):
if self._fallback:
return self._fallback.ngettext(msgid1, msgid2, n)
if n == 1:
return msgid1
else:
return msgid2
def lngettext(self, msgid1, msgid2, n):
if self._fallback:
return self._fallback.lngettext(msgid1, msgid2, n)
if n == 1:
return msgid1
else:
return msgid2
def info(self):
return self._info
def charset(self):
return self._charset
def output_charset(self):
return self._output_charset
def set_output_charset(self, charset):
self._output_charset = charset
def install(self, names=None):
import builtins
builtins.__dict__['_'] = self.gettext
if hasattr(names, "__contains__"):
if "gettext" in names:
builtins.__dict__['gettext'] = builtins.__dict__['_']
if "ngettext" in names:
builtins.__dict__['ngettext'] = self.ngettext
if "lgettext" in names:
builtins.__dict__['lgettext'] = self.lgettext
if "lngettext" in names:
builtins.__dict__['lngettext'] = self.lngettext
class GNUTranslations(NullTranslations):
# Magic number of .mo files
LE_MAGIC = 0x950412de
BE_MAGIC = 0xde120495
def _parse(self, fp):
"""Override this method to support alternative .mo formats."""
unpack = struct.unpack
filename = getattr(fp, 'name', '')
# Parse the .mo file header, which consists of 5 little endian 32
# bit words.
self._catalog = catalog = {}
self.plural = lambda n: int(n != 1) # germanic plural by default
buf = fp.read()
buflen = len(buf)
# Are we big endian or little endian?
magic = unpack('<I', buf[:4])[0]
if magic == self.LE_MAGIC:
version, msgcount, masteridx, transidx = unpack('<4I', buf[4:20])
ii = '<II'
elif magic == self.BE_MAGIC:
version, msgcount, masteridx, transidx = unpack('>4I', buf[4:20])
ii = '>II'
else:
raise IOError(0, 'Bad magic number', filename)
# Now put all messages from the .mo file buffer into the catalog
# dictionary.
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for i in range(0, msgcount):
mlen, moff = unpack(ii, buf[masteridx:masteridx+8])
mend = moff + mlen
tlen, toff = unpack(ii, buf[transidx:transidx+8])
tend = toff + tlen
if mend < buflen and tend < buflen:
msg = buf[moff:mend]
tmsg = buf[toff:tend]
else:
raise IOError(0, 'File is corrupt', filename)
# See if we're looking at GNU .mo conventions for metadata
if mlen == 0:
# Catalog description
lastk = k = None
for b_item in tmsg.split('\n'.encode("ascii")):
item = b_item.decode().strip()
if not item:
continue
if ':' in item:
k, v = item.split(':', 1)
k = k.strip().lower()
v = v.strip()
self._info[k] = v
lastk = k
elif lastk:
self._info[lastk] += '\n' + item
if k == 'content-type':
self._charset = v.split('charset=')[1]
elif k == 'plural-forms':
v = v.split(';')
plural = v[1].split('plural=')[1]
self.plural = c2py(plural)
# Note: we unconditionally convert both msgids and msgstrs to
# Unicode using the character encoding specified in the charset
# parameter of the Content-Type header. The gettext documentation
# strongly encourages msgids to be us-ascii, but some appliations
# require alternative encodings (e.g. Zope's ZCML and ZPT). For
# traditional gettext applications, the msgid conversion will
# cause no problems since us-ascii should always be a subset of
# the charset encoding. We may want to fall back to 8-bit msgids
# if the Unicode conversion fails.
charset = self._charset or 'ascii'
if b'\x00' in msg:
# Plural forms
msgid1, msgid2 = msg.split(b'\x00')
tmsg = tmsg.split(b'\x00')
msgid1 = str(msgid1, charset)
for i, x in enumerate(tmsg):
catalog[(msgid1, i)] = str(x, charset)
else:
catalog[str(msg, charset)] = str(tmsg, charset)
# advance to next entry in the seek tables
masteridx += 8
transidx += 8
def lgettext(self, message):
missing = object()
tmsg = self._catalog.get(message, missing)
if tmsg is missing:
if self._fallback:
return self._fallback.lgettext(message)
return message
if self._output_charset:
return tmsg.encode(self._output_charset)
return tmsg.encode(locale.getpreferredencoding())
def lngettext(self, msgid1, msgid2, n):
try:
tmsg = self._catalog[(msgid1, self.plural(n))]
if self._output_charset:
return tmsg.encode(self._output_charset)
return tmsg.encode(locale.getpreferredencoding())
except KeyError:
if self._fallback:
return self._fallback.lngettext(msgid1, msgid2, n)
if n == 1:
return msgid1
else:
return msgid2
def gettext(self, message):
missing = object()
tmsg = self._catalog.get(message, missing)
if tmsg is missing:
if self._fallback:
return self._fallback.gettext(message)
return message
return tmsg
def ngettext(self, msgid1, msgid2, n):
try:
tmsg = self._catalog[(msgid1, self.plural(n))]
except KeyError:
if self._fallback:
return self._fallback.ngettext(msgid1, msgid2, n)
if n == 1:
tmsg = msgid1
else:
tmsg = msgid2
return tmsg
2001-01-14 19:47:14 -04:00
# Locate a .mo file using the gettext strategy
2009-05-17 09:50:58 -03:00
def find(domain, localedir=None, languages=None, all=False):
# Get some reasonable defaults for arguments that were not supplied
if localedir is None:
localedir = _default_localedir
if languages is None:
languages = []
for envar in ('LANGUAGE', 'LC_ALL', 'LC_MESSAGES', 'LANG'):
val = os.environ.get(envar)
if val:
languages = val.split(':')
break
if 'C' not in languages:
languages.append('C')
# now normalize and expand the languages
nelangs = []
for lang in languages:
for nelang in _expand_lang(lang):
if nelang not in nelangs:
nelangs.append(nelang)
# select a language
if all:
result = []
else:
result = None
for lang in nelangs:
if lang == 'C':
break
mofile = os.path.join(localedir, lang, 'LC_MESSAGES', '%s.mo' % domain)
if os.path.exists(mofile):
if all:
result.append(mofile)
else:
return mofile
return result
2001-01-14 19:47:14 -04:00
# a mapping between absolute .mo file path and Translation object
_translations = {}
def translation(domain, localedir=None, languages=None,
class_=None, fallback=False, codeset=None):
if class_ is None:
class_ = GNUTranslations
2009-05-17 09:50:58 -03:00
mofiles = find(domain, localedir, languages, all=True)
if not mofiles:
if fallback:
return NullTranslations()
raise IOError(ENOENT, 'No translation file found for domain', domain)
# Avoid opening, reading, and parsing the .mo file after it's been done
# once.
result = None
for mofile in mofiles:
key = os.path.abspath(mofile)
t = _translations.get(key)
if t is None:
Merged revisions 72506,72525-72526,72551,72558,72616,72654-72655,72689,72745,72750,72802,72812,72822,72824,72826-72827,72833,72876,72890,72923,72946,73026,73042,73045,73047,73065,73068-73069 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r72506 | vinay.sajip | 2009-05-09 07:07:17 -0500 (Sat, 09 May 2009) | 1 line Issue #5971: StreamHandler.handleError now swallows IOErrors which occur when trying to print a traceback. ........ r72525 | benjamin.peterson | 2009-05-09 20:38:02 -0500 (Sat, 09 May 2009) | 1 line close file explicitly ........ r72526 | benjamin.peterson | 2009-05-09 21:29:00 -0500 (Sat, 09 May 2009) | 1 line make sure files are closed using the with statement ........ r72551 | benjamin.peterson | 2009-05-10 09:16:47 -0500 (Sun, 10 May 2009) | 1 line use isinstance ........ r72558 | benjamin.peterson | 2009-05-10 18:52:09 -0500 (Sun, 10 May 2009) | 1 line sys.setdefaultencoding() strikes me as a bad example ........ r72616 | benjamin.peterson | 2009-05-13 19:33:10 -0500 (Wed, 13 May 2009) | 1 line importlib.import_module is better these days ........ r72654 | benjamin.peterson | 2009-05-14 17:37:49 -0500 (Thu, 14 May 2009) | 1 line prevent refleaks from threads ........ r72655 | benjamin.peterson | 2009-05-14 17:40:34 -0500 (Thu, 14 May 2009) | 1 line a useful decorator for cleaning up threads ........ r72689 | benjamin.peterson | 2009-05-16 13:44:34 -0500 (Sat, 16 May 2009) | 1 line use skipTest() ........ r72745 | benjamin.peterson | 2009-05-17 09:16:29 -0500 (Sun, 17 May 2009) | 1 line ignore .rst files in sphinx its self ........ r72750 | benjamin.peterson | 2009-05-17 11:59:27 -0500 (Sun, 17 May 2009) | 1 line chop off slash ........ r72802 | georg.brandl | 2009-05-20 13:35:27 -0500 (Wed, 20 May 2009) | 1 line #6051: refer to email examples for better way to construct email messages. ........ r72812 | michael.foord | 2009-05-21 17:57:02 -0500 (Thu, 21 May 2009) | 1 line Rename TestCase._result to _resultForDoCleanups to avoid potential clashes in TestCase subclasses. Issue 6072. ........ r72822 | georg.brandl | 2009-05-22 04:33:25 -0500 (Fri, 22 May 2009) | 1 line #6084: fix example. ........ r72824 | georg.brandl | 2009-05-22 04:43:17 -0500 (Fri, 22 May 2009) | 1 line Fix references to file-related functions and methods (os.* vs file.*). ........ r72826 | georg.brandl | 2009-05-22 04:49:42 -0500 (Fri, 22 May 2009) | 1 line Fix confusing wording. ........ r72827 | georg.brandl | 2009-05-22 04:50:30 -0500 (Fri, 22 May 2009) | 1 line s/use/call/ ........ r72833 | georg.brandl | 2009-05-22 12:00:17 -0500 (Fri, 22 May 2009) | 1 line #6078: _warnings is a builtin module and has no standard init_warnings function. ........ r72876 | benjamin.peterson | 2009-05-23 15:59:09 -0500 (Sat, 23 May 2009) | 1 line remove mention of old ctypes version ........ r72890 | gregory.p.smith | 2009-05-24 13:00:13 -0500 (Sun, 24 May 2009) | 2 lines add a versionadded tag for set_tunnel ........ r72923 | michael.foord | 2009-05-25 15:36:56 -0500 (Mon, 25 May 2009) | 1 line Make assertSequenceEqual error messages less cryptic, particularly for nested sequences. ........ r72946 | ronald.oussoren | 2009-05-26 13:44:48 -0500 (Tue, 26 May 2009) | 2 lines Fixes issue 6110 ........ r73026 | r.david.murray | 2009-05-29 14:30:27 -0500 (Fri, 29 May 2009) | 3 lines Issue 6141: document that the first item of args is still the command name even when executable is specified. ........ r73042 | benjamin.peterson | 2009-05-29 22:10:52 -0500 (Fri, 29 May 2009) | 1 line no fdatasync on macos ........ r73045 | georg.brandl | 2009-05-30 02:26:04 -0500 (Sat, 30 May 2009) | 1 line #6146: fix markup bug. ........ r73047 | georg.brandl | 2009-05-30 05:33:23 -0500 (Sat, 30 May 2009) | 1 line Fix some more small markup problems. ........ r73065 | antoine.pitrou | 2009-05-30 16:39:25 -0500 (Sat, 30 May 2009) | 3 lines The test for #5330 wasn't correct. ........ r73068 | antoine.pitrou | 2009-05-30 16:45:40 -0500 (Sat, 30 May 2009) | 3 lines Update ACKS ........ r73069 | benjamin.peterson | 2009-05-30 19:42:42 -0500 (Sat, 30 May 2009) | 1 line fix signature ........
2009-06-01 19:42:33 -03:00
with open(mofile, 'rb') as fp:
t = _translations.setdefault(key, class_(fp))
# Copy the translation object to allow setting fallbacks and
# output charset. All other instance data is shared with the
# cached object.
t = copy.copy(t)
if codeset:
t.set_output_charset(codeset)
if result is None:
result = t
else:
result.add_fallback(t)
return result
2001-01-14 19:47:14 -04:00
def install(domain, localedir=None, codeset=None, names=None):
t = translation(domain, localedir, fallback=True, codeset=codeset)
t.install(names)
2001-01-14 19:47:14 -04:00
# a mapping b/w domains and locale directories
_localedirs = {}
# a mapping b/w domains and codesets
_localecodesets = {}
# current global domain, `messages' used for compatibility w/ GNU gettext
_current_domain = 'messages'
def textdomain(domain=None):
global _current_domain
if domain is not None:
_current_domain = domain
return _current_domain
def bindtextdomain(domain, localedir=None):
global _localedirs
if localedir is not None:
_localedirs[domain] = localedir
return _localedirs.get(domain, _default_localedir)
def bind_textdomain_codeset(domain, codeset=None):
global _localecodesets
if codeset is not None:
_localecodesets[domain] = codeset
return _localecodesets.get(domain)
def dgettext(domain, message):
try:
t = translation(domain, _localedirs.get(domain, None),
codeset=_localecodesets.get(domain))
except IOError:
return message
return t.gettext(message)
2001-01-14 19:47:14 -04:00
def ldgettext(domain, message):
try:
t = translation(domain, _localedirs.get(domain, None),
codeset=_localecodesets.get(domain))
except IOError:
return message
return t.lgettext(message)
def dngettext(domain, msgid1, msgid2, n):
try:
t = translation(domain, _localedirs.get(domain, None),
codeset=_localecodesets.get(domain))
except IOError:
if n == 1:
return msgid1
else:
return msgid2
return t.ngettext(msgid1, msgid2, n)
def ldngettext(domain, msgid1, msgid2, n):
try:
t = translation(domain, _localedirs.get(domain, None),
codeset=_localecodesets.get(domain))
except IOError:
if n == 1:
return msgid1
else:
return msgid2
return t.lngettext(msgid1, msgid2, n)
def gettext(message):
return dgettext(_current_domain, message)
def lgettext(message):
return ldgettext(_current_domain, message)
def ngettext(msgid1, msgid2, n):
return dngettext(_current_domain, msgid1, msgid2, n)
def lngettext(msgid1, msgid2, n):
return ldngettext(_current_domain, msgid1, msgid2, n)
# dcgettext() has been deemed unnecessary and is not implemented.
# James Henstridge's Catalog constructor from GNOME gettext. Documented usage
# was:
#
# import gettext
# cat = gettext.Catalog(PACKAGE, localedir=LOCALEDIR)
# _ = cat.gettext
# print _('Hello World')
# The resulting catalog object currently don't support access through a
# dictionary API, which was supported (but apparently unused) in GNOME
# gettext.
Catalog = translation