qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-01 14:40:00 +02:00
Code Issues Releases Wiki Activity

Merge pull request #139 from bertsky/allow-uniseg-py38

Browse source 
re-allow uniseg 0.8 and py38
This commit is contained in:
Mike Gerber 2025-04-22 10:09:51 +02:00 • committed by GitHub
commit 3d7c7ee1e3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 9 additions and 4 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: [ "3.9", "3.10", "3.11", "3.12", "3.13" ] python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12", "3.13" ]
runs-on: "ubuntu-latest" runs-on: "ubuntu-latest"

2
pyproject.toml
View file

@ -10,7 +10,7 @@ authors = [
description = "An OCR evaluation tool" description = "An OCR evaluation tool"
readme = "README.md" readme = "README.md"
license.file = "LICENSE" license.file = "LICENSE"
requires-python = ">=3.9" requires-python = ">=3.8"
keywords = ["qurator", "ocr", "evaluation", "ocr-d"] keywords = ["qurator", "ocr", "evaluation", "ocr-d"]
dynamic = ["version", "dependencies", "optional-dependencies"] dynamic = ["version", "dependencies", "optional-dependencies"]

2
requirements.txt
View file

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

7
src/dinglehopper/word_error_rate.py
View file

@ -21,10 +21,15 @@ def patch_word_break():
https://www.unicode.org/Public/UCD/latest/ucd/auxiliary/WordBreakProperty.txt https://www.unicode.org/Public/UCD/latest/ucd/auxiliary/WordBreakProperty.txt
""" """
old_word_break = uniseg.wordbreak.word_break old_word_break = uniseg.wordbreak.word_break
if hasattr(uniseg.wordbreak, 'Word_Break'):
aletter = uniseg.wordbreak.Word_Break.ALetter
else:
# uniseg<0.9
aletter = uniseg.wordbreak.WordBreak.ALETTER
def new_word_break(c): def new_word_break(c):
if 0xE000 <= ord(c) <= 0xF8FF: # Private Use Area if 0xE000 <= ord(c) <= 0xF8FF: # Private Use Area
return uniseg.wordbreak.Word_Break.ALetter return aletter
else: else:
return old_word_break(c) return old_word_break(c)