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

cldr-date-harvest.py

# Copyright 2023 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()
   
    months_long = {}
    months_short = {}
    weeks_long = {}
    weeks_short = {}

    for node in root.iter('dates'):
        for month_node in node.iter('months'):
            for month in month_node.iter('monthContext'):
                month_name = month.attrib['type']
                if month_name == 'format':
                    for names in month.iter('monthWidth'):
                        name_type = names.attrib['type']
                        if name_type == 'wide':                                                                 
                            for name in names.iter('month'):                                                    
                                month_string = name.attrib['type']                                         
                                months_long[month_string] = name.text                                           
                        elif name_type == 'abbreviated':                                                        
                            for name in names.iter('month'):                                                    
                                month_string = name.attrib['type']                                         
                                months_short[month_string] = name.text                                          
        for week_node in node.iter('days'):                                                                     
            for week in week_node.iter('dayContext'):                                                           
                week_name = week.attrib['type']                                                                 
                if week_name == 'format':               
                    for names in week.iter('dayWidth'):
                        name_type = names.attrib['type']
                        if name_type == 'wide':
                            for name in names.iter('month'):
                                month_string = name.attrib['type']
                                months_long[month_string] = name.text
                        elif name_type == 'abbreviated':
                            for name in names.iter('month'):
                                month_string = name.attrib['type']
                                months_short[month_string] = name.text
        for week_node in node.iter('days'):
            for week in week_node.iter('dayContext'):
                week_name = week.attrib['type']
                if week_name == 'format':
                    for names in week.iter('dayWidth'):
                        name_type = names.attrib['type']
                        if name_type == 'wide':
                            for name in names.iter('day'):
                                week_string = name.attrib['type']
                                weeks_long[week_string] = name.text
                        elif name_type == 'abbreviated':
                            for name in names.iter('day'):
                                week_string = name.attrib['type']
                                weeks_short[week_string] = name.text

    return months_long, months_short, weeks_long, weeks_short

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 date information
        # and should be skipped.
        if file_name.endswith('.xml') and '_' not in file_name:
            print(file_name)
            months_long, months_short, weeks_long, weeks_short = parse_ldml(dir_path + '/' + file_name)
            print('LONG MONTHS:')
            print(months_long)
            print('SHORT MONTHS:')
            print(months_short)
            print('LONG WEEKS:')
            print(weeks_long)
            print('SHORT WEEKS:')
            print(weeks_short)

if __name__ == '__main__':
    main()