gramps/po/check_po

#! /usr/bin/env python

NONE   = 0
MSGID  = 1
MSGSTR = 2

import sys
import re

all_total = {}
all_untranslated = {}
all_percent_s = {}
all_named_s = {}
all_bnamed_s = {}
all_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
    
    string_map = {}
    current_msgid = ""
    current_msgstr = ""
    
    for line in f.readlines():
        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 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
                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)
    untranslated = 0
    percent_s = 0
    percent_s_list = []
    named_s = 0
    named_s_list = []
    bnamed_s = 0
    bnamed_s_list = []
    
    
    for i in string_map.keys():
        if string_map[i] == "":
            untranslated += 1
            continue
    
        cnt1 = i.count('%s')
        cnt2 = string_map[i].count('%s')
        if cnt1 != cnt2:
            percent_s += 1
            percent_s_list.append(i)
    
        list1 = named.findall(i)
        list2 = named.findall(string_map[i])
        if len(list1) != len(list2):
            percent_s += 1
            percent_s_list.append(i)
    
        list1.sort()
        list2.sort()
        if list1 != list2:
            named_s += 1
            named_s_list.append(i)
    
        match = bnamed.match(string_map[i])
        if match:
            bnamed_s +=1
            bnamed_s_list.append(i)
    
    coverage = (1.0 - (float(untranslated)/float(total))) * 100
    
    print "File:            %s" % args[0]
    print "Total:           %d" % total
    all_total[args[0]] = total
    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 "Coverage:        %5.2f%%" % coverage
    all_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])
    print ""
    

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

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