From 4b8e8b7e443753fa67609a9decedc4ddf6a69bb3 Mon Sep 17 00:00:00 2001 From: Franck Dary <franck.dary@lis-lab.fr> Date: Mon, 14 Oct 2019 15:57:22 +0200 Subject: [PATCH] Updated conll2text.py --- tools/conll2text.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/conll2text.py b/tools/conll2text.py index 0bb7ec8..24ef74b 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()) -- GitLab