qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-09 03:40:12 +02:00
Code Issues Releases Wiki Activity

🐛 Fix for changed API of uniseg's word_break

Browse source
This commit is contained in:
Mike Gerber 2025-04-16 09:10:43 +02:00
parent b72d4f5af9
commit 7f8a8dd564
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
requirements.txt
View file

@ -1,7 +1,7 @@
click click
jinja2 jinja2
lxml lxml
uniseg >= 0.8.0 uniseg >= 0.9.1
numpy numpy
colorama colorama
MarkupSafe MarkupSafe

6
src/dinglehopper/word_error_rate.py
View file

@ -22,11 +22,11 @@ def patch_word_break():
""" """
old_word_break = uniseg.wordbreak.word_break old_word_break = uniseg.wordbreak.word_break
def new_word_break(c, index=0): def new_word_break(c):
if 0xE000 <= ord(c) <= 0xF8FF: # Private Use Area if 0xE000 <= ord(c) <= 0xF8FF: # Private Use Area
return uniseg.wordbreak.WordBreak.ALETTER return uniseg.wordbreak.Word_Break.ALetter
else: else:
return old_word_break(c, index) return old_word_break(c)
uniseg.wordbreak.word_break = new_word_break uniseg.wordbreak.word_break = new_word_break
global word_break_patched global word_break_patched