[PYTHON] Script to convert between Xcode language files and tab-delimited text

A script that converts Xcode language files (Localizable.strings) into easy-to-handle tab-separated texts (tsv). Until now, I used to manage language files with Linguan, but as the project became huge, it became difficult to manage. To manage with tab-delimited text.

Python module installation

bash

pip install unicodecsv

Convert Localizable.strings to Localizable.tsv

i18n_po2tsv.py

import sys, re
import unicodecsv as csv
from collections import OrderedDict

#
# Default encoding
#

reload(sys)
sys.setdefaultencoding('utf8')

#
# File paths
#

tsv_path = 'Localization/Localizable.tsv'
loc_paths = 'PROJECT_NAME/PROJECT_NAME/Resources/UI/{}.lproj/Localizable.strings'

#
# Convert Localizable.strings to Localizable.tsv
#

langs = [
	'ja',
	'en',
]
rows = {}

for lang_code in langs:
	loc_path = loc_paths.format(lang_code)

	print('Reading loc file... ' + loc_path)

	lines = [line.encode('utf-8').rstrip('\n') for line in open(loc_path)]
	for line in lines:
		# print line
		pattern = re.compile(r'\"(.*)\" = \"(.*)\"')
		match = pattern.search(line)
		if match:
			loc_key = match.group(1).encode('utf-8')
			loc_str = match.group(2).encode('utf-8')
	        if loc_key in rows.keys():
	            rows[loc_key].append(loc_str)
	        else:
	            rows[loc_key] = [loc_key, loc_str]

rows_orderd = OrderedDict(sorted(rows.items()))

print('Saving tsv file... ' + tsv_path)
print('')

with open(tsv_path, 'wb') as f:
    writer = csv.writer(f, csv.excel_tab)
    writer.writerows(rows_orderd.values())

print('All done!')

Convert Localizable.tsv to Localizable.strings

i18n_tsv2po.py

import sys
import unicodecsv as csv
import codecs
from collections import OrderedDict

#
# Default encoding
#

reload(sys)
sys.setdefaultencoding('utf8')

#
# File paths
#

tsv_path = 'Localization/Localizable.tsv'
loc_paths = 'PROJECT_NAME/PROJECT_NAME/Resources/UI/{}.lproj/Localizable.strings'

#
# Read Localizable.tsv
#

langs = {
    'ja': {},
    'en': {},
}

print('Reading tsv file... ' + tsv_path)

with open(tsv_path, 'rb') as tsv_in:
    tsv_in = csv.reader(tsv_in, delimiter='\t')
    # next(tsv_in, None)
    for row in tsv_in:
        loc_key = row[0]
        if row[1]:
            loc_str = row[1].encode('utf-8')
            langs['ja'][loc_key] = loc_str
        if row[2]:
            loc_str = row[2].encode('utf-8')
            langs['en'][loc_key] = loc_str

#
# Save Localizable.string
#

print('')

for key, value in langs.iteritems():
    lang_code = key
    loc_path = loc_paths.format(lang_code)

    print('Saving loc file... ' + loc_path)

    with open(loc_path, 'w') as loc_out:
        loc_orderd = OrderedDict(sorted(value.items()))
        for loc_key, loc_str in loc_orderd.iteritems():
            loc_out.write('"' + loc_key + '" = "' + loc_str +  '";\n')
        loc_out.close()

    print('Done!')
    print('')

print('All done!')