Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions funasr/tokenizer/char_tokenizer.py
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,8 @@ def load_seg_dict(seg_dict_file):
lines = f.readlines()
for line in lines:
s = line.strip().split()
if not s:
continue
key = s[0]
value = s[1:]
seg_dict[key] = " ".join(value)
Expand Down
22 changes: 22 additions & 0 deletions tests/test_char_tokenizer_seg_dict.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
"""CharTokenizer must skip blank lines in a seg_dict file instead of raising IndexError."""

import os
import tempfile
import unittest

from funasr.tokenizer.char_tokenizer import CharTokenizer, load_seg_dict


class LoadSegDictBlankLineTest(unittest.TestCase):
def test_blank_lines_are_skipped(self):
with tempfile.TemporaryDirectory() as tmpdir:
path = os.path.join(tmpdir, "seg_dict")
with open(path, "w", encoding="utf-8") as f:
f.write("你 你\n\n好 好\n \nhello he@@ llo\n\n")
self.assertEqual(load_seg_dict(path), {"你": "你", "好": "好", "hello": "he@@ llo"})
tokenizer = CharTokenizer(seg_dict=path)
self.assertEqual(tokenizer.text2tokens("你好 hello"), ["你", "好", "he@@", "llo"])


if __name__ == "__main__":
unittest.main()
Loading