[Bf-docboard] Translations Tracker

[Anton Felix Lorenzen]

Hi all,

I re-wrote the script in python,
it's now around 360 times as fast using python3
(and even 675 times when using pypy).

I overused grep before,
so it took the script 9 minutes to finish,
now it runs in approx. 1 second.

It also shows files with fuzzy strings in it
and should also run on windows.

Sincerely,
Anton Felix Lorenzen

Usage:
|- Paste into file named translations.py
|- "cd" into folder
|- execute python translations.py "C:\path\to\LC_MESSAGES"

Script:

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
#
#  Translations Tracker 1.0
#  works best with pypy
#
#  Copyright 2015 Anton Felix Lorenzen <anfelor at web.de>
#
#  Permission is hereby granted, free of charge,
#  to any person obtaining a copy of this software
#  and associated documentation files (the "Software"),
#  to deal in the Software without restriction,
#  including without limitation the rights to use, copy,
#  modify, merge, publish, distribute, sublicense,
#  and/or sell copies of the Software,
#  and to permit persons to whom the Software is furnished to do so,
#  subject to the following conditions:
#
#  The above copyright notice and this permission notice
#  shall be included in all copies or substantial portions of the Software.
#
#  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
#  EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY,
#  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
#  IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
CLAIM,
#  DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
#  TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE
#  OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

import os
import codecs
import sys

if(sys.argv and sys.argv[1]):
	path = sys.argv[1]
else:
	path = "~/locale/fr/LC_MESSAGES"

# Configuration
fileinfo  = '{0[file]:>3} empty, {1[file]:>3} fuzzy of {2[file]:>3}; or
{3:.3f}% in {4}'
allinfo   = 'Summary: {0[all]} empty of {1[all]}; or {2:.3f}%'
fuzzyinfo = 'Fuzzy:   {0[all]} fuzzy strings in {0[filelist]}'

msgstrs = {'file': 0, 'all':0}
empty_msgstrs = {'file': 0, 'all': 0}
fuzzy = {'file': 0, 'all': 0, 'filelist': []}
lastLineWasEmptyMsgstr = False

def forAllInMap(m, fnk, cond):
	for key in m:
		if(cond(m[key])):
			m[key] = fnk(m[key])

def forAllIntsInMap(m, fnk):
	forAllInMap(m, fnk, lambda x: type(x)==int)

def increaseAllInMap(m):
	forAllIntsInMap(m, lambda x: x+1)

def decreseAllInMap(m):
	forAllIntsInMap(m, lambda x: x-1)

for (root, subs, files) in os.walk(path):
	for name in files:
		msgstrs['file'] = -1 # First lines contain a "fake" msgstr
		msgstrs['all'] -= 1
		empty_msgstrs['file'] = 0
		fuzzy['file'] = 0
		if name.endswith('.po'):
			for line in codecs.open(os.path.join(root, name), encoding='utf8'):
				if(line[0] == 'm'):
					if(line[0:6] == 'msgstr'):
						increaseAllInMap(msgstrs)
						if(line[0:9] == 'msgstr ""'):
							increaseAllInMap(empty_msgstrs)
							lastLineWasEmptyMsgstr = True
				else:
					if(line[0] == '"'):
						if(lastLineWasEmptyMsgstr):
							decreseAllInMap(empty_msgstrs)
							lastLineWasEmptyMsgstr = False
					else:
						lastLineWasEmptyMsgstr = False
						if('fuzzy' in line):
							increaseAllInMap(fuzzy)
							fuzzy['filelist'] += [name]
		
		print(fileinfo.format(empty_msgstrs, fuzzy, msgstrs,
			float(empty_msgstrs['file'] + fuzzy['file']) / msgstrs['file'],
			os.path.join(root[len(path):], name)))

print(allinfo.format(empty_msgstrs, msgstrs, float(empty_msgstrs['all'])
/ msgstrs['all']))
print(fuzzyinfo.format(fuzzy))