Last active
May 31, 2017 21:14
-
-
Save spotco/85bd8ca0f0a738ee3613f9f36a07f122 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 sys | |
| import json | |
| import io | |
| def use_i_token(i_token, i_token_to_key): | |
| key = i_token_to_key[i_token] | |
| return key == "en-US" or key == "fr" or key == "de" or key == "it" or key == "ja" or key == "pt-BR" or key == "ru" or key == "es" | |
| i_line = 0 | |
| i_token_to_key = {} | |
| js_out = [] | |
| for line in open(sys.argv[1],'r').read().split("\n"): | |
| itr_token = {} | |
| line_key = "" | |
| i_token = 0 | |
| for token in line.split("\t"): | |
| if i_line == 0: | |
| i_token_to_key[i_token] = token | |
| elif i_token == 0: | |
| line_key = token | |
| else: | |
| if use_i_token(i_token, i_token_to_key) and len(token) > 0: | |
| itr_token[i_token_to_key[i_token]] = token | |
| i_token = i_token + 1 | |
| if len(itr_token) > 1: | |
| js_out.append({ | |
| "key": line_key, | |
| "values": itr_token | |
| }) | |
| i_line = i_line + 1 | |
| print json.dumps(js_out, ensure_ascii=False, encoding='utf8',indent=4).encode('utf-8') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment