= 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
class NullTranslations:
def __init__(self, fp=None):
self._info = {}
self._charset = None
self._output_charset = None
self._fallback = None
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 ugettext(self, message):
if self._fallback:
return self._fallback.ugettext(message)
return unicode(message)
def ungettext(self, msgid1, msgid2, n):
if self._fallback:
return self._fallback.ungettext(msgid1, msgid2, n)
if n == 1:
return unicode(msgid1)
else:
return unicode(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, unicode=False, names=None):
import __builtin__
__builtin__.__dict__['_'] = unicode and self.ugettext or self.gettext
if hasattr(names, "__contains__"):
if "gettext" in names:
__builtin__.__dict__['gettext'] = __builtin__.__dict__['_']
if "ngettext" in names:
__builtin__.__dict__['ngettext'] = (unicode and self.ungettext
or self.ngettext)
if "lgettext" in names:
__builtin__.__dict__['lgettext'] = self.lgettext
if "lngettext" in names:
__builtin__.__dict__['lngettext'] = self.lngettext
class GNUTranslations(NullTranslations):
# Magic number of .mo files
LE_MAGIC = 0x950412deL
BE_MAGIC = 0xde120495L
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('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.
for i in xrange(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 item in tmsg.splitlines():
item = item.strip()
if not item:
continue
if item.startswith("#"):
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 applications
# 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.
if '\x00' in msg:
# Plural forms
msgid1, msgid2 = msg.split('\x00')
tmsg = tmsg.split('\x00')
if self._charset:
msgid1 = unicode(msgid1, self._charset)
tmsg = [unicode(x, self._charset) for x in tmsg]
for i in range(len(tmsg)):
catalog[(msgid1, i)] = tmsg[i]
else:
if self._charset:
msg = unicode(msg, self._charset)
tmsg = unicode(tmsg, self._charset)
catalog[msg] = tmsg
# advance to next entry in the seek tables
masteridx += 8
transidx += 8
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
# Encode the Unicode tmsg back to an 8-bit string, if possible
if self._output_charset:
return tmsg.encode(self._output_charset)
elif self._charset:
return tmsg.encode(self._charset)
return tmsg
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 ngettext(self, msgid1, msgid2, n):
try:
tmsg = self._catalog[(msgid1, self.plural(n))]
if self._output_charset:
return tmsg.encode(self._output_charset)
elif self._charset:
return tmsg.encode(self._charset)
return tmsg
except KeyError:
if self._fallback:
return self._fallback.ngettext(msgid1, msgid2, n)
if n == 1:
return msgid1
else:
return msgid2
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 ugettext(self, message):
missing = object()
tmsg = self._catalog.get(message, missing)
if tmsg is missing:
if self._fallback:
return self._fallback.ugettext(message)
return unicode(message)
return tmsg
def ungettext(self, msgid1, msgid2, n):
try:
tmsg = self._catalog[(msgid1, self.plural(n))]
except KeyError:
if self._fallback:
return self._fallback.ungettext(msgid1, msgid2, n)
if n == 1:
tmsg = unicode(msgid1)
else:
tmsg = unicode(msgid2)
return tmsg
# Locate a .mo file using the gettext strategy
def find(domain, localedir=None, languages=None, all=0):
# 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
# 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
mofiles = find(domain, localedir, languages, all=1)
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 = (class_, os.path.abspath(mofile))
t = _translations.get(key)
if t is None:
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
def install(domain, localedir=None, unicode=False, codeset=None, names=None):
t = translation(domain, localedir, fallback=True, codeset=codeset)
t.install(unicode, names)
# 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)
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