Merge remote-tracking branch 'origin/development' into development

libs/subzero/modification/mods/hearing_impaired.py

@@ -34,7 +34,7 @@ class HearingImpaired(SubtitleTextModification):
 
         # uppercase text before colon (at least 3 uppercase chars); at start or after a sentence,
         # possibly with a dash in front; ignore anything ending with a quote
-        NReProcessor(re.compile(r'(?u)(?:(?<=^)|(?<=[.\-!?\"\']))([\s\->~]*(?=[A-ZÀ-Ž&+]\s*[A-ZÀ-Ž&+]\s*[A-ZÀ-Ž&+])'
+        NReProcessor(re.compile(r'(?u)(?:(?<=^)|(?<=[.\-!?\"\'])\s)([\s\->~]*(?=[A-ZÀ-Ž&+]\s*[A-ZÀ-Ž&+]\s*[A-ZÀ-Ž&+])'
                                 r'[A-zÀ-ž-_0-9\s\"\'&+()\[\],:]+:(?![\"\'’ʼ❜‘‛”“‟„])(?:\s+|$))(?![0-9])'), "",
                      name="HI_before_colon_caps"),
 

libs/subzero/modification/mods/ocr_fixes.py

@@ -39,9 +39,9 @@ class FixOCR(SubtitleTextModification):
         return [
             # remove broken HI tag colons (ANNOUNCER'., ". instead of :) after at least 3 uppercase chars
             # don't modify stuff inside quotes
-            NReProcessor(re.compile(r'(?u)(^[^"\'’ʼ❜‘‛”“‟„]*(?<=[A-ZÀ-Ž]{3})[A-ZÀ-Ž-_\s0-9]+)'
-                                    r'(["\'’ʼ❜‘‛”“‟„]*[.,‚،⹁、;]+)(\s*)(?!["\'’ʼ❜‘‛”“‟„])'),
-                         r"\1:\3", name="OCR_fix_HI_colons", supported=lambda p: not p.only_uppercase),
+            #NReProcessor(re.compile(r'(?u)(^[^"\'’ʼ❜‘‛”“‟„]*(?<=[A-ZÀ-Ž]{3})[A-ZÀ-Ž-_\s0-9]+)'
+            #                        r'(["\'’ʼ❜‘‛”“‟„]*[.,‚،⹁、;]+)(\s*)(?!["\'’ʼ❜‘‛”“‟„])'),
+            #             r"\1:\3", name="OCR_fix_HI_colons", supported=lambda p: not p.only_uppercase),
             # fix F'bla
             NReProcessor(re.compile(r'(?u)(\bF)(\')([A-zÀ-ž]*\b)'), r"\1\3", name="OCR_fix_F"),
             WholeLineProcessor(self.data_dict["WholeLines"], name="OCR_replace_line"),

tests/subliminal_patch/test_mods.py

@@ -0,0 +1,16 @@
+import pytest
+import os
+from subliminal_patch import Subtitle
+
+
+@pytest.fixture
+def test_file(data):
+    return os.path.join(data, "subs_for_mods.srt")
+
+
+def test_apply_mods_remove_hi(languages, test_file):
+    sub = Subtitle(languages["en"], mods=["remove_HI", "OCR_fixes"])
+    with open(test_file, "rb") as f:
+        sub.content = f.read()
+
+    assert sub.get_modified_content(debug=True)