gramps/po/check_po

#! /usr/bin/env python
#
# Gramps - a GTK+/GNOME based genealogy program
#
# Copyright (C) 2000-2006  Donald N. Allingham
#
# This program 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.
#
# This program 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 this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

# $Id: check_po,v 1.1.2.6 2006/04/22 18:30:33 rshura Exp $

import sys
import re

f = open('template.po')
template_total = 0
for line in f.xreadlines():
    try:
        if (line.split()[0] == 'msgid'):
            template_total += 1
    except:
        pass
f.close()

NONE   = 0
MSGID  = 1
MSGSTR = 2

all_total = {}
all_fuzzy = {}
all_untranslated = {}
all_percent_s = {}
all_named_s = {}
all_bnamed_s = {}
all_context = {}
all_coverage = {}
all_template_coverage = {}


def strip_quotes(st):
    if len(st.strip()) > 2:
        return st.strip()[1:-1]
    else:
        return ""

args = sys.argv
while len(args) > 1:
    args = args[1:]

    f = open(args[0],"r")
    
    mode = NONE
    fuzzy = False
    fuzzy_count = 0
    string_map = {}
    current_msgid = ""
    current_msgstr = ""
    
    for line in f.xreadlines():
        data = line.split(None,1)
        if mode == NONE:
            if len(data) > 0 and data[0] == "msgid":
                mode = MSGID
                if len(data) > 1:
                    current_msgid = strip_quotes(data[1])
            elif (len(data) > 0) and (data[0] == "#,") \
                     and (data[1] == 'fuzzy\n'):
                fuzzy = True
        elif mode == MSGID:
            if data[0][0] == '"':
                current_msgid += strip_quotes(line)
            elif data[0] == "msgstr":
                mode = MSGSTR
                if len(data) > 1:
                    current_msgstr = strip_quotes(data[1])
        elif mode == MSGSTR:
            if line == "" or line[0] == "#":
                mode = NONE
                if fuzzy:
                    fuzzy = False
                    fuzzy_count += 1
                else:
                    string_map[current_msgid] = current_msgstr
            elif len(data) > 0 and data[0][0] == '"':
                current_msgstr += strip_quotes(line)
    
    f.close()
    
    named = re.compile('%\((\w+)\)\d*s')
    bnamed = re.compile('%\((\w+)\)\d*[^sd]')
    
    total = len(string_map) + fuzzy_count
    untranslated = 0
    percent_s = 0
    percent_s_list = []
    named_s = 0
    named_s_list = []
    bnamed_s = 0
    bnamed_s_list = []
    context = 0
    context_list = []
    
    for (msgid,msgstr) in string_map.items():
        if msgstr == "":
            untranslated += 1
            continue
    
        cnt1 = msgid.count('%s')
        cnt2 = msgstr.count('%s')
        if cnt1 != cnt2:
            percent_s += 1
            percent_s_list.append(msgid)
    
        list1 = named.findall(msgid)
        list2 = named.findall(msgstr)
        if len(list1) != len(list2):
            percent_s += 1
            percent_s_list.append(msgid)
    
        list1.sort()
        list2.sort()
        if list1 != list2:
            named_s += 1
            named_s_list.append(msgid)
    
        match = bnamed.match(msgstr)
        if match:
            bnamed_s +=1
            bnamed_s_list.append(msgstr)

        has_context1 = (msgid.count('|') > 0)
        has_context2 = (msgstr.count('|') > 0)
        if has_context1 and has_context2 and (msgid != msgstr):
            context += 1
            context_list.append(msgid)
        
    
    coverage = (1.0 - (float(untranslated)/float(total))) * 100
    template_coverage = coverage * float(total) / float(template_total)
    
    print "File:            %s" % args[0]
    print "Template total:  %d" % template_total
    print "PO total:        %d" % total
    all_total[args[0]] = total
    print "Fuzzy:           %d" % fuzzy_count
    all_fuzzy[args[0]] = fuzzy_count
    print "Untranslated:    %d" % untranslated
    all_untranslated[args[0]] = untranslated
    print "%%s mismatches:   %d" % percent_s
    all_percent_s[args[0]] = percent_s
    print "%%()s mismatches: %d" % named_s
    all_named_s[args[0]] = named_s
    print "%%() missing s/d: %d" % bnamed_s
    all_bnamed_s[args[0]] = bnamed_s
    print "Runaway context: %d" % context
    all_context[args[0]] = context
    print "PO Coverage:     %5.2f%%" % coverage
    all_coverage[args[0]] = coverage
    print "Template Coverage:  %5.2f%%" % template_coverage
    all_template_coverage[args[0]] = coverage
    
    if percent_s:
        print "\n-------- %s mismatches --------------"
        for i in percent_s_list:
            print "'%s' : '%s'" % (i, string_map[i])
    
    if named_s:
        print "\n-------- %()s mismatches ------------"
        for i in named_s_list:
            print "'%s' : '%s'" % (i, string_map[i])
    
    if bnamed_s:
        print "\n-------- %() missing s or d ---------"
        for i in bnamed_s_list:
            print "'%s' : '%s'" % (i, string_map[i])

    if context:
        print "\n-------- Runaway context in translation  ---------"
        for i in context_list:
            print "'%s' : '%s'" % (i, string_map[i])
    print ""
    

if len(sys.argv) > 2:
    print "\n\nFile \tTotal \tFuzzy \tUntranslated \t%s mismatch \t%()s mismatch \tmissing s/d \tcontext \tCoverage"
    for pofile in sys.argv[1:]:
        print "%s \t%5d \t%7d \t%7d \t%7d \t%7d \t%7d \t%7d \t%3.2f%% \t%3.2f%%" %\
           (pofile,
            all_total[pofile],
            all_fuzzy[pofile],
            all_untranslated[pofile],
            all_percent_s[pofile],
            all_named_s[pofile],
            all_bnamed_s[pofile],
            all_context[pofile],
            all_coverage[pofile],
            all_template_coverage[pofile]
            )

f = open("used_strings.txt","w")
keys = string_map.keys()
keys.sort()
for i in keys:
    f.write(i + "\n")
f.close()