Byte order mark management in TSV glue reading.

This commit is contained in:
LysandreJik
2019-07-11 20:16:28 -04:00
parent e3fb4310d6
commit 3821ecbf4a

View File

@@ -78,7 +78,7 @@ class DataProcessor(object):
@classmethod @classmethod
def _read_tsv(cls, input_file, quotechar=None): def _read_tsv(cls, input_file, quotechar=None):
"""Reads a tab separated value file.""" """Reads a tab separated value file."""
with open(input_file, "r", encoding="utf-8") as f: with open(input_file, "r", encoding="utf-8-sig") as f:
reader = csv.reader(f, delimiter="\t", quotechar=quotechar) reader = csv.reader(f, delimiter="\t", quotechar=quotechar)
lines = [] lines = []
for line in reader: for line in reader: