99 lines
3.8 KiB
Python
99 lines
3.8 KiB
Python
from fugashi_parser import *
|
|
|
|
import os
|
|
from pathlib import Path
|
|
import shutil
|
|
import hashlib
|
|
|
|
|
|
destination_directory_name = '/run/media/deck/YF8SD/Sync/Notebooks/Obsidian/Japanese/Yu-Gi-Oh/AnimeSubs/'
|
|
destination_path = Path(destination_directory_name)
|
|
|
|
dictionary_name = 'Jitendex.org [2026-04-04]'
|
|
|
|
#print(annotate_phrase("私は学校へ行きます"))
|
|
|
|
## Make sure directories exist
|
|
if not destination_path.exists():
|
|
destination_path.mkdir(parents=True, exist_ok=True)
|
|
if not destination_path.joinpath('_attachments').exists():
|
|
destination_path.joinpath('_attachments').mkdir(parents=True, exist_ok=True)
|
|
if not destination_path.joinpath('vocab').exists():
|
|
destination_path.joinpath('vocab').mkdir(parents=True, exist_ok=True)
|
|
|
|
|
|
# ---------- CLI ----------
|
|
|
|
def main():
|
|
# parser = argparse.ArgumentParser()
|
|
# parser.add_argument("--vocab-file", required=True)
|
|
# parser.add_argument("text", nargs="*")
|
|
# args = parser.parse_args()
|
|
|
|
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:
|
|
lines = f.readlines()
|
|
|
|
|
|
notes_lines = []
|
|
|
|
# Example: Modify the 3rd line (index 2)
|
|
#lines[2] = "This is the new subtitle text\n"
|
|
## First lien has some unicode bom bs
|
|
i = 0
|
|
while i < len(lines):
|
|
if re.fullmatch(r'\d+', lines[i].strip()) or i == 0:
|
|
notes_lines.append('##### ' + lines[i].strip() + " `" + lines[i+1].strip() + "`" + "\n")
|
|
i+=2
|
|
continue
|
|
if has_japanese(lines[i]):
|
|
print(lines[i])
|
|
result = analyze(lines[i],vocab)
|
|
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
|
|
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)
|
|
|
|
with open("subtitle.srt", "w", encoding="utf-8") as f:
|
|
f.writelines(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)
|
|
#save_vocab('foo.json', vocab)
|
|
|
|
#result["vocab_file"] = args.vocab_file
|
|
#print(json.dumps(result, ensure_ascii=False, indent=2))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |