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

🐛 Fix for changed API of uniseg's word_break

Author: mikegerber

.github/workflows/test.yml

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

requirements.txt

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

src/dinglehopper/word_error_rate.py

@@ -22,11 +22,11 @@ def patch_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
-            return uniseg.wordbreak.WordBreak.ALETTER
+            return uniseg.wordbreak.Word_Break.ALetter
         else:
-            return old_word_break(c, index)
+            return old_word_break(c)
 
     uniseg.wordbreak.word_break = new_word_break
     global word_break_patched