diff --git a/scripts/conll2text.py b/scripts/conll2text.py new file mode 100755 index 0000000000000000000000000000000000000000..268981f2498d1f531f457dc35832802605674c8e --- /dev/null +++ b/scripts/conll2text.py @@ -0,0 +1,19 @@ +#! /usr/bin/python + +import sys + +def printUsageAndExit() : + print("Usage : %s file.conllu delimiterSymbol"%sys.argv[0]) + exit(1) + +if __name__ == "__main__" : + if len(sys.argv) != 3 : + printUsageAndExit() + + for line in open(sys.argv[1]) : + if len(line.strip()) < 2 : + continue + + if line.startswith("# text") : + print(line.strip()[9:], end=sys.argv[2]) +