tubearchivist/tubearchivist-frontend
1
0
Fork 0
mirror of https://github.com/tubearchivist/tubearchivist-frontend.git synced 2024-11-22 11:50:14 +00:00
Code Issues Projects Releases Wiki Activity

cover edge cases where end timestamp is after start timestamp of new cue

Browse Source
This commit is contained in:
simon 2022-02-12 16:03:04 +07:00
parent d99ce0d98e
commit b494fc10af
No known key found for this signature in database
GPG Key ID: 2C15AA5E89985DD4
1 changed files with 18 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
tubearchivist/home/src/index/video.py
View File

@ -159,6 +159,7 @@ class SubtitleParser:
self._parse_cues() self._parse_cues()
self._match_text_lines() self._match_text_lines()
self._add_id() self._add_id()
self._timestamp_check()
def _parse_cues(self): def _parse_cues(self):
"""split into cues""" """split into cues"""
@ -181,7 +182,8 @@ class SubtitleParser:
clean = re.sub(self.stamp_reg, "", line) clean = re.sub(self.stamp_reg, "", line)
clean = re.sub(self.tag_reg, "", clean) clean = re.sub(self.tag_reg, "", clean)
cue_dict["lines"].append(clean) cue_dict["lines"].append(clean)
if clean and clean not in self.all_text_lines: if clean.strip() and clean not in self.all_text_lines[-4:]:
# remove immediate duplicates
self.all_text_lines.append(clean) self.all_text_lines.append(clean)
return cue_dict return cue_dict
@ -205,6 +207,21 @@ class SubtitleParser:
self.matched.append(new_cue) self.matched.append(new_cue)
def _timestamp_check(self):
"""check if end timestamp is bigger than start timestamp"""
for idx, cue in enumerate(self.matched):
# this
end = int(re.sub("[^0-9]", "", cue.get("end")))
# next
try:
next_cue = self.matched[idx + 1]
except IndexError:
continue
start_next = int(re.sub("[^0-9]", "", next_cue.get("start")))
if end > start_next:
self.matched[idx]["end"] = next_cue.get("start")
def _add_id(self): def _add_id(self):
"""add id to matched cues""" """add id to matched cues"""
for idx, _ in enumerate(self.matched): for idx, _ in enumerate(self.matched):