Dustin/jp_text_parsing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add ruby to a vtt file

Browse Source
This commit is contained in:
Nitsud Yarg 2026-05-15 11:46:39 -07:00
parent 4b33f6e113
commit 7bb75ae7d9
1 changed files with 28 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
subtitle_processor.py
View File

@ -32,7 +32,7 @@ def main():
vocab = load_vocab('foo.json')
with open("/run/media/deck/YF8SD/Video/[Retimed and Corrected] Yu-Gi-Oh! Duel Monsters - 001.srt", "r", encoding="utf-8") as f:
with open("/run/media/deck/YF8SD/Video/Yu-Gi-Oh! Duel Monsters - 001.vtt", "r", encoding="utf-8") as f:
lines = f.readlines()
@ -54,39 +54,42 @@ def main():
print(result['kana_reading'])
notes_lines.append(result["ruby_html"] + "\n" )
notes_lines.append (result['notes_link'] + "\n")
if lines[i] != result['kana_reading']:
lines[i] = result['kana_reading'] + "\n" # lost the new line
if lines[i] != result['ruby_html']:
lines[i] = result['ruby_html'] + "\n" # lost the new line
# if lines[i] != result['kana_reading']:
# lines[i] = result['kana_reading'] + "\n" # lost the new line
else:
#notes_lines.append("`" + lines[i].strip() + "`" + "\n")
notes_lines.append(lines[i])
i+=1
## Lookup vocab
for word in vocab:
#vocab_hash = hashlib.shake_256((word + dictionary_name).encode()).hexdigest(4)
if Path(destination_path.joinpath('vocab/' + word + '.md')).exists() == False:
definitions = anki_fields_term(word)
if definitions.get("fields"):
with open(destination_path.as_posix() + '/vocab/' + word + '.md', 'w') as vocab_note:
for entry in definitions.get("fields"):
vocab_note.write("\n")
print(entry['expression'], file=vocab_note)
#print(entry['furigana-plain'], file=vocab_note)
if entry['expression'] != entry['reading']:
print(entry['reading'], file=vocab_note)
print(entry['furigana'], file=vocab_note)
#print(f"Part of Speech: {entry['part-of-speech']}", file=vocab_note)
print(f"Frequency: {entry['frequency-average-rank']}", file=vocab_note)
#print(entry['glossary-plain-no-dictionary'], file=vocab_note)
vocab_note.write(entry['glossary-first'])
print("##### Other Definitions", file=vocab_note)
print(entry['glossary-plain-no-dictionary'], file=vocab_note)
if False:
for word in vocab:
#vocab_hash = hashlib.shake_256((word + dictionary_name).encode()).hexdigest(4)
if Path(destination_path.joinpath('vocab/' + word + '.md')).exists() == False:
definitions = anki_fields_term(word)
if definitions.get("fields"):
with open(destination_path.as_posix() + '/vocab/' + word + '.md', 'w') as vocab_note:
for entry in definitions.get("fields"):
vocab_note.write("\n")
print(entry['expression'], file=vocab_note)
#print(entry['furigana-plain'], file=vocab_note)
if entry['expression'] != entry['reading']:
print(entry['reading'], file=vocab_note)
print(entry['furigana'], file=vocab_note)
#print(f"Part of Speech: {entry['part-of-speech']}", file=vocab_note)
print(f"Frequency: {entry['frequency-average-rank']}", file=vocab_note)
#print(entry['glossary-plain-no-dictionary'], file=vocab_note)
vocab_note.write(entry['glossary-first'])
print("##### Other Definitions", file=vocab_note)
print(entry['glossary-plain-no-dictionary'], file=vocab_note)
with open("subtitle.srt", "w", encoding="utf-8") as f:
with open("/run/media/deck/YF8SD/Video/Yu-Gi-Oh! Duel Monsters - 001.vtt", "w", encoding="utf-8") as f:
f.writelines(lines)
with open("notestest-newchunks.md", "w", encoding="utf-8") as f:
f.writelines(notes_lines)
# with open("notestest-newchunks.md", "w", encoding="utf-8") as f:
# f.writelines(notes_lines)
#vocab = load_vocab(args.vocab_file)
#result = analyze(text, vocab)