diff --git a/tools/conll2text.py b/tools/conll2text.py index 0bb7ec8bf84d2cb30de70fc8e9eba439a3b50431..24ef74b965f24496ba2952330feae974504fec28 100755 --- a/tools/conll2text.py +++ b/tools/conll2text.py @@ -1,16 +1,20 @@ #! /usr/bin/python3 import sys +import random def printUsageAndExit() : - print("Usage : %s file.conllu delimiterSymbol"%sys.argv[0]) + print("Usage : %s file.conllu"%sys.argv[0], file=sys.stderr) exit(1) +def choseDelimiter() : + return random.choices(["\n", " "], k=1, weights=[10, 50])[0] + if __name__ == "__main__" : sys.stdout = open(1, 'w', encoding='utf-8', closefd=False) - if len(sys.argv) != 3 : + if len(sys.argv) != 2 : printUsageAndExit() for line in open(sys.argv[1], encoding='utf-8') : @@ -18,5 +22,5 @@ if __name__ == "__main__" : continue if line.startswith("# text") : - print(line.strip()[9:], end=sys.argv[2]) + print(line.strip()[9:], end=choseDelimiter())