🐛 Fix word segmentation with uniseg 0.8.0

1 month ago · 4d4ead4cc8
parent 4b64398cec
commit 4d4ead4cc8
2 changed files with 2 additions and 2 deletions
--- a/requirements.txt
+++ b/requirements.txt
@ -1,7 +1,7 @@
 click
 jinja2
 lxml
-uniseg >= 0.7.2
+uniseg >= 0.8.0
 numpy
 colorama
 MarkupSafe
--- a/src/dinglehopper/word_error_rate.py
+++ b/src/dinglehopper/word_error_rate.py
@ -24,7 +24,7 @@ def patch_word_break():

    def new_word_break(c, index=0):
        if 0xE000 <= ord(c) <= 0xF8FF:  # Private Use Area
-            return "ALetter"
+            return uniseg.wordbreak.WordBreak.ALETTER
        else:
            return old_word_break(c, index)