, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\\n"
"POT-Creation-Date: %(time)s\\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\\n"
"Last-Translator: FULL NAME \\n"
"Language-Team: LANGUAGE \\n"
"MIME-Version: 1.0\\n"
"Content-Type: text/plain; charset=CHARSET\\n"
"Content-Transfer-Encoding: ENCODING\\n"
"Generated-By: pygettext.py %(version)s\\n"
''')
def usage(code, msg=''):
print >> sys.stderr, __doc__ % globals()
if msg:
print >> sys.stderr, msg
sys.exit(code)
escapes = []
def make_escapes(pass_iso8859):
global escapes
escapes = [chr(i) for i in range(256)]
if pass_iso8859:
# Allow iso-8859 characters to pass through so that e.g. 'msgid
# "Höhe"' would result not result in 'msgid "H\366he"'. Otherwise we
# escape any character outside the 32..126 range.
mod = 128
else:
mod = 256
for i in range(mod):
if not(32 <= i <= 126):
escapes[i] = "\\%03o" % i
escapes[ord('\\')] = '\\\\'
escapes[ord('\t')] = '\\t'
escapes[ord('\r')] = '\\r'
escapes[ord('\n')] = '\\n'
escapes[ord('\"')] = '\\"'
def escape(s):
global escapes
s = list(s)
for i in range(len(s)):
s[i] = escapes[ord(s[i])]
return EMPTYSTRING.join(s)
def safe_eval(s):
# unwrap quotes, safely
return eval(s, {'__builtins__':{}}, {})
def normalize(s):
# This converts the various Python string types into a format that is
# appropriate for .po files, namely much closer to C style.
lines = s.split('\n')
if len(lines) == 1:
s = '"' + escape(s) + '"'
else:
if not lines[-1]:
del lines[-1]
lines[-1] = lines[-1] + '\n'
for i in range(len(lines)):
lines[i] = escape(lines[i])
lineterm = '\\n"\n"'
s = '""\n"' + lineterm.join(lines) + '"'
return s
def containsAny(str, set):
"""Check whether 'str' contains ANY of the chars in 'set'"""
return 1 in [c in str for c in set]
def _visit_pyfiles(list, dirname, names):
"""Helper for getFilesForName()."""
# get extension for python source files
if not globals().has_key('_py_ext'):
global _py_ext
_py_ext = [triple[0] for triple in imp.get_suffixes()
if triple[2] == imp.PY_SOURCE][0]
# don't recurse into CVS directories
if 'CVS' in names:
names.remove('CVS')
# add all *.py files to list
list.extend(
[os.path.join(dirname, file) for file in names
if os.path.splitext(file)[1] == _py_ext]
)
def _get_modpkg_path(dotted_name, pathlist=None):
"""Get the filesystem path for a module or a package.
Return the file system path to a file for a module, and to a directory for
a package. Return None if the name is not found, or is a builtin or
extension module.
"""
# split off top-most name
parts = dotted_name.split('.', 1)
if len(parts) > 1:
# we have a dotted path, import top-level package
try:
file, pathname, description = imp.find_module(parts[0], pathlist)
if file: file.close()
except ImportError:
return None
# check if it's indeed a package
if description[2] == imp.PKG_DIRECTORY:
# recursively handle the remaining name parts
pathname = _get_modpkg_path(parts[1], [pathname])
else:
pathname = None
else:
# plain name
try:
file, pathname, description = imp.find_module(
dotted_name, pathlist)
if file:
file.close()
if description[2] not in [imp.PY_SOURCE, imp.PKG_DIRECTORY]:
pathname = None
except ImportError:
pathname = None
return pathname
def getFilesForName(name):
"""Get a list of module files for a filename, a module or package name,
or a directory.
"""
if not os.path.exists(name):
# check for glob chars
if containsAny(name, "*?[]"):
files = glob.glob(name)
list = []
for file in files:
list.extend(getFilesForName(file))
return list
# try to find module or package
name = _get_modpkg_path(name)
if not name:
return []
if os.path.isdir(name):
# find all python files in directory
list = []
os.path.walk(name, _visit_pyfiles, list)
return list
elif os.path.exists(name):
# a single file
return [name]
return []
class TokenEater:
def __init__(self, options):
self.__options = options
self.__messages = {}
self.__state = self.__waiting
self.__data = []
self.__lineno = -1
self.__freshmodule = 1
self.__curfile = None
def __call__(self, ttype, tstring, stup, etup, line):
# dispatch
## import token
## print >> sys.stderr, 'ttype:', token.tok_name[ttype], \
## 'tstring:', tstring
self.__state(ttype, tstring, stup[0])
def __waiting(self, ttype, tstring, lineno):
opts = self.__options
# Do docstring extractions, if enabled
if opts.docstrings and not opts.nodocstrings.get(self.__curfile):
# module docstring?
if self.__freshmodule:
if ttype == tokenize.STRING:
self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
self.__freshmodule = 0
elif ttype not in (tokenize.COMMENT, tokenize.NL):
self.__freshmodule = 0
return
# class docstring?
if ttype == tokenize.NAME and tstring in ('class', 'def'):
self.__state = self.__suiteseen
return
if ttype == tokenize.NAME and tstring in opts.keywords:
self.__state = self.__keywordseen
def __suiteseen(self, ttype, tstring, lineno):
# ignore anything until we see the colon
if ttype == tokenize.OP and tstring == ':':
self.__state = self.__suitedocstring
def __suitedocstring(self, ttype, tstring, lineno):
# ignore any intervening noise
if ttype == tokenize.STRING:
self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
self.__state = self.__waiting
elif ttype not in (tokenize.NEWLINE, tokenize.INDENT,
tokenize.COMMENT):
# there was no class docstring
self.__state = self.__waiting
def __keywordseen(self, ttype, tstring, lineno):
if ttype == tokenize.OP and tstring == '(':
self.__data = []
self.__lineno = lineno
self.__state = self.__openseen
else:
self.__state = self.__waiting
def __openseen(self, ttype, tstring, lineno):
if ttype == tokenize.OP and tstring == ')':
# We've seen the last of the translatable strings. Record the
# line number of the first line of the strings and update the list
# of messages seen. Reset state for the next batch. If there
# were no strings inside _(), then just ignore this entry.
if self.__data:
self.__addentry(EMPTYSTRING.join(self.__data))
self.__state = self.__waiting
elif ttype == tokenize.STRING:
self.__data.append(safe_eval(tstring))
elif ttype not in [tokenize.COMMENT, token.INDENT, token.DEDENT,
token.NEWLINE, tokenize.NL]:
# warn if we see anything else than STRING or whitespace
print >> sys.stderr, _(
'*** %(file)s:%(lineno)s: Seen unexpected token "%(token)s"'
) % {
'token': tstring,
'file': self.__curfile,
'lineno': self.__lineno
}
self.__state = self.__waiting
def __addentry(self, msg, lineno=None, isdocstring=0):
if lineno is None:
lineno = self.__lineno
if not msg in self.__options.toexclude:
entry = (self.__curfile, lineno)
self.__messages.setdefault(msg, {})[entry] = isdocstring
def set_filename(self, filename):
self.__curfile = filename
self.__freshmodule = 1
def write(self, fp):
options = self.__options
timestamp = time.strftime('%Y-%m-%d %H:%M+%Z')
# The time stamp in the header doesn't have the same format as that
# generated by xgettext...
print >> fp, pot_header % {'time': timestamp, 'version': __version__}
# Sort the entries. First sort each particular entry's keys, then
# sort all the entries by their first item.
reverse = {}
for k, v in self.__messages.items():
keys = v.keys()
keys.sort()
reverse.setdefault(tuple(keys), []).append((k, v))
rkeys = reverse.keys()
rkeys.sort()
for rkey in rkeys:
rentries = reverse[rkey]
rentries.sort()
for k, v in rentries:
isdocstring = 0
# If the entry was gleaned out of a docstring, then add a
# comment stating so. This is to aid translators who may wish
# to skip translating some unimportant docstrings.
if reduce(operator.__add__, v.values()):
isdocstring = 1
# k is the message string, v is a dictionary-set of (filename,
# lineno) tuples. We want to sort the entries in v first by
# file name and then by line number.
v = v.keys()
v.sort()
if not options.writelocations:
pass
# location comments are different b/w Solaris and GNU:
elif options.locationstyle == options.SOLARIS:
for filename, lineno in v:
d = {'filename': filename, 'lineno': lineno}
print >>fp, _(
'# File: %(filename)s, line: %(lineno)d') % d
elif options.locationstyle == options.GNU:
# fit as many locations on one line, as long as the
# resulting line length doesn't exceeds 'options.width'
locline = '#:'
for filename, lineno in v:
d = {'filename': filename, 'lineno': lineno}
s = _(' %(filename)s:%(lineno)d') % d
if len(locline) + len(s) <= options.width:
locline = locline + s
else:
print >> fp, locline
locline = "#:" + s
if len(locline) > 2:
print >> fp, locline
if isdocstring:
print >> fp, '#, docstring'
print >> fp, 'msgid', normalize(k)
print >> fp, 'msgstr ""\n'
def main():
global default_keywords
try:
opts, args = getopt.getopt(
sys.argv[1:],
'ad:DEhk:Kno:p:S:Vvw:x:X:',
['extract-all', 'default-domain=', 'escape', 'help',
'keyword=', 'no-default-keywords',
'add-location', 'no-location', 'output=', 'output-dir=',
'style=', 'verbose', 'version', 'width=', 'exclude-file=',
'docstrings', 'no-docstrings',
])
except getopt.error, msg:
usage(1, msg)
# for holding option values
class Options:
# constants
GNU = 1
SOLARIS = 2
# defaults
extractall = 0 # FIXME: currently this option has no effect at all.
escape = 0
keywords = []
outpath = ''
outfile = 'messages.pot'
writelocations = 1
locationstyle = GNU
verbose = 0
width = 78
excludefilename = ''
docstrings = 0
nodocstrings = {}
options = Options()
locations = {'gnu' : options.GNU,
'solaris' : options.SOLARIS,
}
# parse options
for opt, arg in opts:
if opt in ('-h', '--help'):
usage(0)
elif opt in ('-a', '--extract-all'):
options.extractall = 1
elif opt in ('-d', '--default-domain'):
options.outfile = arg + '.pot'
elif opt in ('-E', '--escape'):
options.escape = 1
elif opt in ('-D', '--docstrings'):
options.docstrings = 1
elif opt in ('-k', '--keyword'):
options.keywords.append(arg)
elif opt in ('-K', '--no-default-keywords'):
default_keywords = []
elif opt in ('-n', '--add-location'):
options.writelocations = 1
elif opt in ('--no-location',):
options.writelocations = 0
elif opt in ('-S', '--style'):
options.locationstyle = locations.get(arg.lower())
if options.locationstyle is None:
usage(1, _('Invalid value for --style: %s') % arg)
elif opt in ('-o', '--output'):
options.outfile = arg
elif opt in ('-p', '--output-dir'):
options.outpath = arg
elif opt in ('-v', '--verbose'):
options.verbose = 1
elif opt in ('-V', '--version'):
print _('pygettext.py (xgettext for Python) %s') % __version__
sys.exit(0)
elif opt in ('-w', '--width'):
try:
options.width = int(arg)
except ValueError:
usage(1, _('--width argument must be an integer: %s') % arg)
elif opt in ('-x', '--exclude-file'):
options.excludefilename = arg
elif opt in ('-X', '--no-docstrings'):
fp = open(arg)
try:
while 1:
line = fp.readline()
if not line:
break
options.nodocstrings[line[:-1]] = 1
finally:
fp.close()
# calculate escapes
make_escapes(not options.escape)
# calculate all keywords
options.keywords.extend(default_keywords)
# initialize list of strings to exclude
if options.excludefilename:
try:
fp = open(options.excludefilename)
options.toexclude = fp.readlines()
fp.close()
except IOError:
print >> sys.stderr, _(
"Can't read --exclude-file: %s") % options.excludefilename
sys.exit(1)
else:
options.toexclude = []
# resolve args to module lists
expanded = []
for arg in args:
if arg == '-':
expanded.append(arg)
else:
expanded.extend(getFilesForName(arg))
args = expanded
# slurp through all the files
eater = TokenEater(options)
for filename in args:
if filename == '-':
if options.verbose:
print _('Reading standard input')
fp = sys.stdin
closep = 0
else:
if options.verbose:
print _('Working on %s') % filename
fp = open(filename)
closep = 1
try:
eater.set_filename(filename)
try:
tokenize.tokenize(fp.readline, eater)
except tokenize.TokenError, e:
print >> sys.stderr, '%s: %s, line %d, column %d' % (
e[0], filename, e[1][0], e[1][1])
finally:
if closep:
fp.close()
# write the output
if options.outfile == '-':
fp = sys.stdout
closep = 0
else:
if options.outpath:
options.outfile = os.path.join(options.outpath, options.outfile)
fp = open(options.outfile, 'w')
closep = 1
try:
eater.write(fp)
finally:
if closep:
fp.close()
if __name__ == '__main__':
main()
# some more test strings
_(u'a unicode string')
# this one creates a warning
_('*** Seen unexpected token "%(token)s"') % {'token': 'test'}
_('more' 'than' 'one' 'string')