fix(normalization): improve punctuation handling and spacing in text normalization

fix(subtitles): enhance ellipsis and paragraph break handling in subtitle processing
feat(gui): implement background update check for new versions
test(tests): add tests for ellipsis handling and paragraph breaks preservation
This commit is contained in:
Deniz Şafak
2026-09-07 17:29:27 +03:00
parent be74c69507
commit 08e2ee8b85
6 changed files with 219 additions and 79 deletions
+7
View File
@@ -90,3 +90,10 @@ def test_manual_override_normalization():
assert normalize_manual_override_token("The") == "the"
assert normalize_manual_override_token(" A ") == "a"
assert normalize_manual_override_token("word") == "word"
def test_paragraph_breaks_and_ellipsis_preserved():
normalized = normalize("Test. Lorem ipsum...\n\nLorem...\n\nLorem ...")
assert "\n\n" in normalized
assert ". . ." not in normalized
assert "Lorem..." in normalized