Scans a CLDR folder heirarchy for language files, and extracts the language names out of them.

cldr-harvest-language-maps.py

# Copyright 2022 Ali Sherief
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import os
import sys
import xml.etree.ElementTree as ET 

def parse_ldml(file_name):
    tree = ET.parse(file_name)
    root = tree.getroot()

    language_map = {}

    for node in root.iter('localeDisplayNames'):
        for language in node.iter('languages'):
            for name in language.iter('language'):
                short_name = name.attrib['type']
                long_name = name.text
                language_map[short_name] = long_name

    return language_map                                 

def main():
    dir_path = sys.argv[1]
    for file_name in os.listdir(dir_path):
		# Only parse the language files e.g. "en", "es", "fr".
        # The language-country files such as en_US do not have language information
        # and should be skipped.
        if file_name.endswith('.xml') and '_' not in file_name:
            language_map = parse_ldml(dir_path + '/' + file_name)
            print(language_map)

if __name__ == '__main__':
    main()