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

re-allow uniseg 0.8 and py38

.github/workflows/test.yml

@@ -25,7 +25,7 @@ jobs:
     strategy:
       fail-fast: false
       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"
 

pyproject.toml

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

requirements.txt

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

src/dinglehopper/word_error_rate.py

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