qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-01 06:29:59 +02:00
Code Issues Releases Wiki Activity

Merge pull request #132 from qurator-spk/fix/uniseg-removed-index-parameter

Browse source 
🐛 Fix for changed API of uniseg's word_break
This commit is contained in:
Mike Gerber 2025-04-16 09:28:31 +02:00 • committed by GitHub
commit a09a624bde
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.github/workflows/test.yml vendored
View file

@ -25,7 +25,7 @@ jobs:
strategy: strategy:
fail-fast: false fail-fast: false
matrix: matrix:
python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12", "3.13" ] python-version: [ "3.9", "3.10", "3.11", "3.12", "3.13" ]
runs-on: "ubuntu-latest" runs-on: "ubuntu-latest"

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