Homec4science
Diffusion invenio-infoscience (maint-1.0) Browse

R3600/modules/miscutil/i18n/i18n-check-translation.py
9cd954f40a45maint-1.0

Last Change
Raw File

i18n-check-translation.py
View Options

This document is not UTF8. It was detected as ISO-8859-1 (Latin 1) and converted to UTF8 for display.
#! /usr/bin/env python
# -*- coding: iso-8859-1 -*-
## This file is part of the CERN Document Server Software (CDSware).
## Copyright (C) 2002, 2003, 2004, 2005 CERN.
##
## The CDSware 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 2 of the
## License, or (at your option) any later version.
##
## The CDSware 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 CDSware; if not, write to the Free Software Foundation, Inc.,
## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
#
# This code is based on a subset of pygettext, which has been written
# by Martin v. Löwis <loewis@informatik.hu-berlin.de>. It adds some
# heuristics to detect problems in po files.
"""Generate binary message catalog from textual translation description.
This program converts a textual Uniforum-style message catalog (.po file) into
a binary GNU catalog (.mo file). This is essentially the same function as the
GNU msgfmt program, however, it is a simpler implementation.
Usage: msgfmt.py [OPTIONS] filename.po
Options:
-o file
--output-file=file
Specify the output file to write to. If omitted, output will go to a
file named filename.mo (based off the input file name).
-h
--help
Print this message and exit.
-V
--version
Display version information and exit.
"""
import sys
import os
import getopt
import struct
import array
import re
__version__ = "1.1"
MESSAGES = {}
def usage(code, msg=''):
print >> sys.stderr, __doc__
if msg:
print >> sys.stderr, msg
sys.exit(code)
def add(id, str, fuzzy):
"Add a non-fuzzy translation to the dictionary."
global MESSAGES
if not fuzzy and str:
MESSAGES[id] = str
_esc = re.compile (r'%(?:\([\w_]+\))?.')
def check ():
errs = 0
for k, v in MESSAGES.items ():
if not v: continue
src = _esc.findall (k)
dst = _esc.findall (v)
if src != dst:
print "warning: original string: %s" % repr (k)
print " translated string: %s" % repr (v)
errs += 1
sys.exit (errs)
def generate():
"Return the generated output."
global MESSAGES
keys = MESSAGES.keys()
# the keys are sorted in the .mo file
keys.sort()
offsets = []
ids = strs = ''
for id in keys:
# For each string, we need size and file offset. Each string is NUL
# terminated; the NUL does not count into the size.
offsets.append((len(ids), len(id), len(strs), len(MESSAGES[id])))
ids += id + '\0'
strs += MESSAGES[id] + '\0'
output = ''
# The header is 7 32-bit unsigned integers. We don't use hash tables, so
# the keys start right after the index tables.
# translated string.
keystart = 7*4+16*len(keys)
# and the values start after the keys
valuestart = keystart + len(ids)
koffsets = []
voffsets = []
# The string table first has the list of keys, then the list of values.
# Each entry has first the size of the string, then the file offset.
for o1, l1, o2, l2 in offsets:
koffsets += [l1, o1+keystart]
voffsets += [l2, o2+valuestart]
offsets = koffsets + voffsets
output = struct.pack("Iiiiiii",
0x950412deL, # Magic
0, # Version
len(keys), # # of entries
7*4, # start of key index
7*4+len(keys)*8, # start of value index
0, 0) # size and offset of hash table
output += array.array("i", offsets).tostring()
output += ids
output += strs
return output
def make(filename):
ID = 1
STR = 2
# Compute .mo name from .po name and arguments
if filename.endswith('.po'):
infile = filename
else:
infile = filename + '.po'
try:
lines = open(infile).readlines()
except IOError, msg:
print >> sys.stderr, msg
sys.exit(1)
section = None
fuzzy = 0
# Parse the catalog
lno = 0
for l in lines:
lno += 1
# If we get a comment line after a msgstr, this is a new entry
if l[0] == '#' and section == STR:
add(msgid, msgstr, fuzzy)
section = None
fuzzy = 0
# Record a fuzzy mark
if l[:2] == '#,' and l.find('fuzzy'):
fuzzy = 1
# Skip comments
if l[0] == '#':
continue
# Now we are in a msgid section, output previous section
if l.startswith('msgid'):
if section == STR:
add(msgid, msgstr, fuzzy)
section = ID
l = l[5:]
msgid = msgstr = ''
# Now we are in a msgstr section
elif l.startswith('msgstr'):
section = STR
l = l[6:]
# Skip empty lines
l = l.strip()
if not l:
continue
# XXX: Does this always follow Python escape semantics?
l = eval(l)
if section == ID:
msgid += l
elif section == STR:
msgstr += l
else:
print >> sys.stderr, 'Syntax error on %s:%d' % (infile, lno), \
'before:'
print >> sys.stderr, l
sys.exit(1)
# Add last entry
if section == STR:
add(msgid, msgstr, fuzzy)
# Compute output
check ()
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
['help', 'version', 'output-file='])
except getopt.error, msg:
usage(1, msg)
outfile = None
# parse options
for opt, arg in opts:
if opt in ('-h', '--help'):
usage(0)
elif opt in ('-V', '--version'):
print >> sys.stderr, "msgfmt.py", __version__
sys.exit(0)
elif opt in ('-o', '--output-file'):
outfile = arg
# do it
if not args:
print >> sys.stderr, 'No input file given'
print >> sys.stderr, "Try `msgfmt --help' for more information."
return
for filename in args:
make(filename)
if __name__ == '__main__':
main()
c4science · Help