Created
July 3, 2024 19:04
-
-
Save pricklywiggles/dfd50d4b2fc64e465b88754e372f0c9e to your computer and use it in GitHub Desktop.
Google cloud translate script for YML files
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import yaml | |
import sys | |
import os | |
from google.cloud import translate_v2 as translate | |
def translate_text(text, target_language): | |
if isinstance(text, str): | |
result = translate_client.translate(text, target_language=target_language) | |
return result['translatedText'] | |
elif isinstance(text, list): | |
return [translate_text(item, target_language) for item in text] | |
elif isinstance(text, dict): | |
return {key: translate_text(value, target_language) for key, value in text.items()} | |
else: | |
return text | |
def translate_and_save(yaml_content, target_language, output_file): | |
original_key = list(yaml_content.keys())[0] | |
content_to_translate = yaml_content[original_key] | |
translated_content = translate_text(content_to_translate, target_language) | |
yaml_content_translated = {target_language: translated_content} | |
# Create the output directory if it doesn't exist | |
os.makedirs(os.path.dirname(output_file), exist_ok=True) | |
# Write the translated content back to a new YAML file | |
with open(output_file, 'w') as file: | |
yaml.dump(yaml_content_translated, file, allow_unicode=True, default_flow_style=False) | |
print(f"Translation to '{target_language}' complete. Check '{output_file}'.") | |
if __name__ == "__main__": | |
if len(sys.argv) < 2: | |
print("Usage: python translate_yaml.py input_file [target_language_code]") | |
sys.exit(1) | |
input_file = sys.argv[1] | |
target_languages = sys.argv[2:] | |
if not target_languages: | |
target_languages = [ | |
"af", "am", "ar", "az", "be", "bn", "bs", "cs", "da", "de", "el", "es", "et", | |
"fa", "fi", "fr", "hi", "hr", "hu", "hy", "id", "is", "it", "ja", "ka", "kk", | |
"km", "ko", "lb", "lo", "lt", "mk", "mn", "mt", "my", "ne", "nl", "no", "ny", | |
"pa", "pl", "ps", "pt", "ro", "ru", "si", "sk", "sl", "sm", "so", "sq", "sr", | |
"su", "sv", "sw", "ta", "tg", "th", "tk", "tl", "tr", "uk", "ur", "uz", "vi", | |
"xh", "zh", "zh-TW", "zu" | |
] | |
# Initialize the translate client | |
translate_client = translate.Client() | |
# Read the YAML file | |
with open(input_file, 'r') as file: | |
yaml_content = yaml.safe_load(file) | |
base_name = os.path.splitext(os.path.basename(input_file))[0] | |
for target_language in target_languages: | |
output_file = f"output/{base_name}.{target_language}.yml" | |
translate_and_save(yaml_content, target_language, output_file) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment