558 lines
17 KiB
Python
Executable File
558 lines
17 KiB
Python
Executable File
#! /usr/bin/env python
|
||
# Originally written by Barry Warsaw <barry@zope.com>
|
||
#
|
||
# Minimally patched to make it even more xgettext compatible
|
||
# by Peter Funk <pf@artcom-gmbh.de>
|
||
#
|
||
# Completely butchered to add glade support for the GRAMPS
|
||
# project by Don Allingham (dallingham@users.sourceforge.net)
|
||
#
|
||
|
||
"""pygettext -- Python equivalent of xgettext(1)
|
||
|
||
Many systems (Solaris, Linux, Gnu) provide extensive tools that ease the
|
||
internationalization of C programs. Most of these tools are independent of
|
||
the programming language and can be used from within Python programs. Martin
|
||
von Loewis' work[1] helps considerably in this regard.
|
||
|
||
There's one problem though; xgettext is the program that scans source code
|
||
looking for message strings, but it groks only C (or C++). Python introduces
|
||
a few wrinkles, such as dual quoting characters, triple quoted strings, and
|
||
raw strings. xgettext understands none of this.
|
||
|
||
Enter pygettext, which uses Python's standard tokenize module to scan Python
|
||
source code, generating .pot files identical to what GNU xgettext[2] generates
|
||
for C and C++ code. From there, the standard GNU tools can be used.
|
||
|
||
A word about marking Python strings as candidates for translation. GNU
|
||
xgettext recognizes the following keywords: gettext, dgettext, dcgettext, and
|
||
gettext_noop. But those can be a lot of text to include all over your code.
|
||
C and C++ have a trick: they use the C preprocessor. Most internationalized C
|
||
source includes a #define for gettext() to _() so that what has to be written
|
||
in the source is much less. Thus these are both translatable strings:
|
||
|
||
gettext("Translatable String")
|
||
_("Translatable String")
|
||
|
||
Python of course has no preprocessor so this doesn't work so well. Thus,
|
||
pygettext searches only for _() by default, but see the -k/--keyword flag
|
||
below for how to augment this.
|
||
|
||
[1] http://www.python.org/workshops/1997-10/proceedings/loewis.html
|
||
[2] http://www.gnu.org/software/gettext/gettext.html
|
||
|
||
NOTE: pygettext attempts to be option and feature compatible with GNU xgettext
|
||
where ever possible. However some options are still missing or are not fully
|
||
implemented. Also, xgettext's use of command line switches with option
|
||
arguments is broken, and in these cases, pygettext just defines additional
|
||
switches.
|
||
|
||
Usage: pygettext [options] inputfile ...
|
||
|
||
Options:
|
||
|
||
-a
|
||
--extract-all
|
||
Extract all strings.
|
||
|
||
-d name
|
||
--default-domain=name
|
||
Rename the default output file from messages.pot to name.pot.
|
||
|
||
-E
|
||
--escape
|
||
Replace non-ASCII characters with octal escape sequences.
|
||
|
||
-h
|
||
--help
|
||
Print this help message and exit.
|
||
|
||
-k word
|
||
--keyword=word
|
||
Keywords to look for in addition to the default set, which are:
|
||
%(DEFAULTKEYWORDS)s
|
||
|
||
You can have multiple -k flags on the command line.
|
||
|
||
-K
|
||
--no-default-keywords
|
||
Disable the default set of keywords (see above). Any keywords
|
||
explicitly added with the -k/--keyword option are still recognized.
|
||
|
||
-o filename
|
||
--output=filename
|
||
Rename the default output file from messages.pot to filename. If
|
||
filename is `-' then the output is sent to standard out.
|
||
|
||
-p dir
|
||
--output-dir=dir
|
||
Output files will be placed in directory dir.
|
||
|
||
-v
|
||
--verbose
|
||
Print the names of the files being processed.
|
||
|
||
-V
|
||
--version
|
||
Print the version of pygettext and exit.
|
||
|
||
-w columns
|
||
--width=columns
|
||
Set width of output to columns.
|
||
|
||
-x filename
|
||
--exclude-file=filename
|
||
Specify a file that contains a list of strings that are not be
|
||
extracted from the input files. Each string to be excluded must
|
||
appear on a line by itself in the file.
|
||
|
||
If `inputfile' is -, standard input is read.
|
||
"""
|
||
|
||
import os
|
||
import sys
|
||
import time
|
||
import getopt
|
||
import tokenize
|
||
import operator
|
||
import re
|
||
|
||
from xml.sax import make_parser,handler,SAXParseException
|
||
|
||
|
||
intRe = re.compile("^\d+$")
|
||
|
||
_ignore = {
|
||
':' : 0,
|
||
}
|
||
|
||
# for selftesting
|
||
try:
|
||
import fintl
|
||
_ = fintl.gettext
|
||
except ImportError:
|
||
def _(s): return s
|
||
|
||
__version__ = '1.4'
|
||
default_keywords = ['_']
|
||
EMPTYSTRING = ''
|
||
|
||
import sys
|
||
import string
|
||
import xmllib
|
||
|
||
class TranslatableStringParser(xmllib.XMLParser):
|
||
def __init__(self,msgs):
|
||
xmllib.XMLParser.__init__(self)
|
||
self.filename = None
|
||
self.strings = msgs
|
||
self.data = ""
|
||
|
||
def add_string(self, string):
|
||
if string == "":
|
||
return
|
||
if _ignore.has_key(string):
|
||
return
|
||
entry = (self.filename, self.lineno)
|
||
if self.strings.has_key(string):
|
||
self.strings[string][entry] = 0
|
||
else:
|
||
self.strings[string] = {entry: 0}
|
||
|
||
def read_file(self, filename):
|
||
self.reset()
|
||
self.filename = filename
|
||
fp = open(filename, "r")
|
||
data = fp.read(8192)
|
||
while data:
|
||
self.feed(data)
|
||
data = fp.read(8192)
|
||
fp.close()
|
||
|
||
def syntax_error(self, message):
|
||
sys.stderr.write("%s:%d: %s\n" % (self.filename, self.lineno,
|
||
message))
|
||
sys.exit(1)
|
||
|
||
def unknown_starttag(self, tag, attrs):
|
||
self.data = ""
|
||
|
||
def handle_data(self, data):
|
||
self.data = self.data + data
|
||
|
||
def translate_this_string(self):
|
||
if not intRe.match(self.data):
|
||
self.add_string(self.data)
|
||
|
||
# this list should include all tags for which translation should occur
|
||
end_label = translate_this_string
|
||
end_title = translate_this_string
|
||
end_text = translate_this_string
|
||
end_format = translate_this_string
|
||
end_copyright = translate_this_string
|
||
end_comments = translate_this_string
|
||
end_preview_text = translate_this_string
|
||
end_tooltip = translate_this_string
|
||
|
||
def end_items(self):
|
||
for item in string.split(self.data, '\n'):
|
||
self.add_string(item)
|
||
|
||
class XMLParser(handler.ContentHandler):
|
||
def __init__(self,name,msgs):
|
||
self.filename = name
|
||
self.strings = msgs
|
||
handler.ContentHandler.__init__(self)
|
||
|
||
def startElement(self,tag,attrs):
|
||
if tag == "filter":
|
||
self.add_string(attrs['name'])
|
||
|
||
def setDocumentLocator(self,locator):
|
||
self.locator = locator
|
||
|
||
def add_string(self, string):
|
||
if string == "":
|
||
return
|
||
if _ignore.has_key(string):
|
||
return
|
||
entry = (self.filename, self.locator.getLineNumber())
|
||
if self.strings.has_key(string):
|
||
self.strings[string][entry] = 0
|
||
else:
|
||
self.strings[string] = {entry: 0}
|
||
|
||
# The normal pot-file header. msgmerge and Emacs's po-mode work better if it's
|
||
# there.
|
||
pot_header = _('''\
|
||
# GRAMPS
|
||
# Copyright (C) YEAR ORGANIZATION
|
||
# FIRST AUTHOR <EMAIL@ADDRESS>, 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 <EMAIL@ADDRESS>\\n"
|
||
"Language-Team: LANGUAGE <LL@li.org>\\n"
|
||
"MIME-Version: 1.0\\n"
|
||
"Content-Type: text/plain; charset=iso-8859-1\\n"
|
||
"Content-Transfer-Encoding: 8bit\\n"
|
||
"Generated-By: pygettext.py %(version)s\\n"
|
||
|
||
''')
|
||
|
||
|
||
def usage(code, msg=''):
|
||
sys.stderr.write(_(__doc__) % globals())
|
||
if msg:
|
||
sys.stderr.write(msg)
|
||
sys.stderr.write('\n')
|
||
sys.exit(code)
|
||
|
||
|
||
|
||
escapes = []
|
||
|
||
def make_escapes(pass_iso8859):
|
||
global escapes
|
||
if pass_iso8859:
|
||
# Allow iso-8859 characters to pass through so that e.g. 'msgid
|
||
# "H<>he"' 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(256):
|
||
if 32 <= (i % mod) <= 126:
|
||
escapes.append(chr(i))
|
||
else:
|
||
escapes.append("\\%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 string.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 = string.split(s,'\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"' + string.join(lines,lineterm) + '"'
|
||
return s
|
||
|
||
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):
|
||
self.__state(ttype, tstring, stup[0])
|
||
|
||
def __waiting(self, ttype, tstring, lineno):
|
||
opts = self.__options
|
||
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(string.join(self.__data,''))
|
||
self.__state = self.__waiting
|
||
elif ttype == tokenize.STRING:
|
||
self.__data.append(safe_eval(tstring))
|
||
# TBD: should we warn if we seen anything else?
|
||
|
||
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)
|
||
if self.__messages.has_key(msg):
|
||
self.__messages[msg][entry] = isdocstring
|
||
else:
|
||
self.__messages[msg] = {entry:isdocstring}
|
||
|
||
def set_filename(self, filename):
|
||
self.__curfile = filename
|
||
self.__freshmodule = 1
|
||
|
||
def get_messages(self):
|
||
return self.__messages
|
||
|
||
def write(self, fp):
|
||
options = self.__options
|
||
timestamp = time.ctime(time.time())
|
||
# The time stamp in the header doesn't have the same format as that
|
||
# generated by xgettext...
|
||
fp.write(pot_header % {'time': timestamp, 'version': __version__})
|
||
fp.write('\n')
|
||
# 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()
|
||
if reverse.has_key(tuple(keys)):
|
||
reverse[tuple(keys)].append((k,v))
|
||
else:
|
||
reverse[tuple(keys)] = [(k,v)]
|
||
# 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()
|
||
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:
|
||
fp.write(locline + "\n");
|
||
locline = "#:" + s
|
||
if len(locline) > 2:
|
||
fp.write(locline + "\n")
|
||
fp.write('msgid ' + normalize(k) + "\n")
|
||
fp.write('msgstr ""\n' + "\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',
|
||
'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
|
||
# defaults
|
||
extractall = 0 # FIXME: currently this option has no effect at all.
|
||
escape = 0
|
||
keywords = []
|
||
outpath = ''
|
||
outfile = 'messages.pot'
|
||
verbose = 0
|
||
width = 78
|
||
excludefilename = ''
|
||
docstrings = 0
|
||
nodocstrings = {}
|
||
|
||
options = Options()
|
||
|
||
# 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 ('-k', '--keyword'):
|
||
options.keywords.append(arg)
|
||
elif opt in ('-K', '--no-default-keywords'):
|
||
default_keywords = []
|
||
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
|
||
|
||
# calculate escapes
|
||
make_escapes(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:
|
||
sys.stderr.write(_("Can't read --exclude-file: %s") % options.excludefilename)
|
||
sys.exit(1)
|
||
else:
|
||
options.toexclude = []
|
||
|
||
# slurp through all the files
|
||
eater = TokenEater(options)
|
||
p = TranslatableStringParser(eater.get_messages())
|
||
|
||
for filename in args:
|
||
if filename[-5:] == 'glade':
|
||
print 'Working on %s' % filename
|
||
p.read_file(filename)
|
||
elif filename[-3:] == 'xml':
|
||
print 'Working on %s' % filename
|
||
try:
|
||
parser = make_parser()
|
||
pxml = XMLParser(filename,eater.get_messages())
|
||
parser.setContentHandler(pxml)
|
||
parser.parse(filename)
|
||
except (IOError,OSError,SAXParseException):
|
||
print 'failed on %s' % filename
|
||
else:
|
||
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:
|
||
sys.stderr.write('%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()
|