zhaarey/unshackle
1
0
Fork 0
mirror of https://github.com/unshackle-dl/unshackle.git synced 2025-10-23 15:11:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(subtitle): Add filtering for unwanted cues in WebVTT subtitles

Browse Source
This commit is contained in:
Andy
2025-08-03 22:10:17 +00:00
parent 8d12b735ff
commit f8a58d966b
1 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
unshackle/core/tracks/subtitle.py
View File

@@ -233,6 +233,7 @@ class Subtitle(Track):
try: try:
caption_set = pycaption.WebVTTReader().read(text) caption_set = pycaption.WebVTTReader().read(text)
Subtitle.merge_same_cues(caption_set) Subtitle.merge_same_cues(caption_set)
Subtitle.filter_unwanted_cues(caption_set)
subtitle_text = pycaption.WebVTTWriter().write(caption_set) subtitle_text = pycaption.WebVTTWriter().write(caption_set)
self.path.write_text(subtitle_text, encoding="utf8") self.path.write_text(subtitle_text, encoding="utf8")
except pycaption.exceptions.CaptionReadSyntaxError: except pycaption.exceptions.CaptionReadSyntaxError:
@@ -241,6 +242,7 @@ class Subtitle(Track):
try: try:
caption_set = pycaption.WebVTTReader().read(text) caption_set = pycaption.WebVTTReader().read(text)
Subtitle.merge_same_cues(caption_set) Subtitle.merge_same_cues(caption_set)
Subtitle.filter_unwanted_cues(caption_set)
subtitle_text = pycaption.WebVTTWriter().write(caption_set) subtitle_text = pycaption.WebVTTWriter().write(caption_set)
self.path.write_text(subtitle_text, encoding="utf8") self.path.write_text(subtitle_text, encoding="utf8")
except Exception: except Exception:
@@ -444,6 +446,8 @@ class Subtitle(Track):
caption_set = self.parse(self.path.read_bytes(), self.codec) caption_set = self.parse(self.path.read_bytes(), self.codec)
Subtitle.merge_same_cues(caption_set) Subtitle.merge_same_cues(caption_set)
if codec == Subtitle.Codec.WebVTT:
Subtitle.filter_unwanted_cues(caption_set)
subtitle_text = writer().write(caption_set) subtitle_text = writer().write(caption_set)
output_path.write_text(subtitle_text, encoding="utf8") output_path.write_text(subtitle_text, encoding="utf8")
@@ -520,6 +524,8 @@ class Subtitle(Track):
caption_set = self.parse(self.path.read_bytes(), self.codec) caption_set = self.parse(self.path.read_bytes(), self.codec)
Subtitle.merge_same_cues(caption_set) Subtitle.merge_same_cues(caption_set)
if codec == Subtitle.Codec.WebVTT:
Subtitle.filter_unwanted_cues(caption_set)
subtitle_text = writer().write(caption_set) subtitle_text = writer().write(caption_set)
output_path.write_text(subtitle_text, encoding="utf8") output_path.write_text(subtitle_text, encoding="utf8")
@@ -681,6 +687,24 @@ class Subtitle(Track):
if merged_captions: if merged_captions:
caption_set.set_captions(lang, merged_captions) caption_set.set_captions(lang, merged_captions)
@staticmethod
def filter_unwanted_cues(caption_set: pycaption.CaptionSet):
"""
Filter out subtitle cues containing only   or whitespace.
"""
for lang in caption_set.get_languages():
captions = caption_set.get_captions(lang)
filtered_captions = pycaption.CaptionList()
for caption in captions:
text = caption.get_text().strip()
if not text or text == " " or all(c in " \t\n\r\xa0" for c in text.replace(" ", "\xa0")):
continue
filtered_captions.append(caption)
caption_set.set_captions(lang, filtered_captions)
@staticmethod @staticmethod
def merge_segmented_wvtt(data: bytes, period_start: float = 0.0) -> tuple[CaptionList, Optional[str]]: def merge_segmented_wvtt(data: bytes, period_start: float = 0.0) -> tuple[CaptionList, Optional[str]]:
""" """