po/postats.py

   1 #! /usr/bin/env python
   2 # -*- coding: utf-8 -*-
   3 # Copyright (C) 2007 Michael Gerz <michael.gerz@teststep.org>
   4 # Copyright (C) 2007 José Matos <jamatos@lyx.org>
   5 #
   6 # This program is free software; you can redistribute it and/or
   7 # modify it under the terms of the GNU General Public License
   8 # as published by the Free Software Foundation; either version 2
   9 # of the License, or (at your option) any later version.
  10 #
  11 # This program is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 # GNU General Public License for more details.
  15 #
  16 # You should have received a copy of the GNU General Public License
  17 # along with this program; if not, write to the Free Software
  18 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  19
  20 """
  21 This script extracts some information from the po file headers (last
  22 translator, revision date), generates the corresponding gmo files
  23 to retrieve the number of translated/fuzzy/untranslated messages,
  24 and generates a PHP web page.
  25
  26 Invocation:
  27    postats.py lyx_version po_files > "pathToWebPages"/i18n.inc
  28 """
  29
  30 # modify this when you change branch
  31 # Note that an empty lyx_branch variable (ie svn trunk)
  32 # will "do the right thing".
  33 lyx_branch=""
  34 # these po-files will be skipped:
  35 ommitted = ('en.po')
  36
  37 import os
  38 import sys
  39
  40 # Reset the locale
  41 import locale
  42 locale.setlocale(locale.LC_ALL, 'C')
  43 os.environ['LC_ALL'] = 'C'
  44
  45 def extract_number(line, issues, prop):
  46     """
  47     line is a string like
  48     '588 translated messages, 1248 fuzzy translations, 2 untranslated messages.'
  49     Any one of these substrings may not appear if the associated number is 0.
  50
  51     issues is the set of words following the number to be extracted,
  52     ie, 'translated', 'fuzzy', or 'untranslated'.
  53
  54     extract_number returns a list with those numbers, or sets it to
  55     zero if the word is not found in the string.
  56     """
  57
  58     for issue in issues:
  59         i = line.find(issue)
  60
  61         if i == -1:
  62             prop[issue] = 0
  63         else:
  64             prop[issue] = int(line[:i].split()[-1])
  65
  66
  67 def read_pofile(pofile):
  68     """ Read the header of the pofile and return it as a dictionary"""
  69     header = {}
  70     read_header = False
  71     for line in open(pofile):
  72         line = line[:-1]
  73         if line[:5] == 'msgid':
  74             if read_header:
  75                 break
  76             read_header = True
  77             continue
  78
  79         if not line or line[0] == '#' or line == 'msgstr ""' or not read_header:
  80             continue
  81
  82         line = line.strip('"')
  83         args = line.split(': ')
  84         if len(args) == 1:
  85             continue
  86         header[args[0]] = args[1].strip()[:-2]
  87
  88     return header
  89
  90
  91 def run_msgfmt(pofile):
  92     """ pofile is the name of the po file.
  93  The function runs msgfmt on it and returns corresponding php code.
  94 """
  95     if not pofile.endswith('.po'):
  96         print >> sys.stderr, "%s is not a po file" % pofile
  97         sys.exit(1)
  98
  99     dirname = os.path.dirname(pofile)
 100     gmofile = pofile.replace('.po', '.gmo')
 101
 102     header = read_pofile(pofile)
 103     charset= header['Content-Type'].split('charset=')[1]
 104
 105     # po file properties
 106     prop = {}
 107     prop["langcode"] = os.path.basename(pofile)[:-3]
 108     prop["date"] = header['PO-Revision-Date'].split()[0]
 109     prop["email"] = header['Last-Translator'].split('<')[1][:-1]
 110     prop["email"] = prop["email"].replace("@", " () ")
 111     prop["email"] = prop["email"].replace(".", " ! ")
 112     translator = header['Last-Translator'].split('<')[0].strip()
 113     try:
 114         prop["translator"] = translator.decode(charset).encode('ascii','xmlcharrefreplace')
 115     except LookupError:
 116         prop["translator"] = translator
 117
 118     p_in, p_out = os.popen4("msgfmt --statistics -o %s %s" % (gmofile, pofile))
 119     extract_number(p_out.readline(),
 120                    ('translated', 'fuzzy', 'untranslated'),
 121                    prop)
 122     return """
 123 array ( 'langcode' => '%(langcode)s', "date" => "%(date)s",
 124 "msg_tr" => %(translated)d, "msg_fu" => %(fuzzy)d, "msg_nt" => %(untranslated)d,
 125 "translator" => "%(translator)s", "email" => "%(email)s")""" % prop
 126
 127
 128 if __name__ == "__main__":
 129     if lyx_branch:
 130         branch_tag = "branches/%s" % lyx_branch
 131     else:
 132         branch_tag = "trunk"
 133
 134
 135     print """<?php
 136 // The current version
 137 $lyx_version = "%s";
 138 // The branch tag
 139 $branch_tag = "%s";
 140
 141 // The data itself
 142 $podata = array (%s
 143 )?>""" % (sys.argv[1], branch_tag, ",".join([run_msgfmt(po) for po in sys.argv[2:] if po not in ommitted]))