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

sub processor accepts parameters

Browse Source
This commit is contained in:
Nitsud Yarg 2026-05-15 18:51:41 -07:00
parent e2d0e08346
commit 3cd4e9279b
2 changed files with 45 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
process_markdown.py
View File

@ -38,7 +38,7 @@ def main():
file_changed = False
while i < len(lines):
## Skip lines that start with certain elements
if lines[i][0:6] == '<span>' or lines[i][0] in ('#','>'):
if lines[i][0:6] == '<span>' or lines[i][0] in ('#','>','['):
i+=1
continue
## If the line has japanese
@ -57,24 +57,6 @@ def main():
## Lookup vocab
for word in vocab:
write_word_note(word, destination_path)
# if Path(destination_path.joinpath('/' + word + '.md')).exists() == False:
# definitions = anki_fields_term(word)
# if definitions.get("fields"):
# with open(destination_path.as_posix() + '/' + 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)
# print(entry['furigana'], file=vocab_note)
# if entry['expression'] != entry['reading']:
# print(entry['reading'], file=vocab_note)
# print("> ",re.sub(r'<.*?>', '', entry['glossary-plain-no-dictionary']), "\n", 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("\n", file=vocab_note)
## Output file with changes if changes
with open(args.markdown_file, "w", encoding="utf-8") as f:

82
subtitle_processor.py
View File

@ -6,33 +6,48 @@ 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)
# 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]'
# dictionary_name = 'Jitendex.org [2026-04-04]'
#print(annotate_phrase("私は学校へ行きます"))
# #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)
# ## 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()
parser = argparse.ArgumentParser()
#parser.add_argument("--vocab-file", required=True)
parser.add_argument("--subtitle-file", required=True)
parser.add_argument("--vocab-folder", required=False)
args = parser.parse_args()
vocab = load_vocab('foo.json')
if args.vocab_folder:
destination_path = Path(args.vocab_folder)
if destination_path.is_dir() == False:
raise ValueError("Vocab Folder is not a directory.")
return
else:
destination_path = Path(args.subtitle_file).parent
if not destination_path.joinpath('vocab').exists():
destination_path.joinpath('vocab').mkdir(parents=True, exist_ok=True)
destination_path = destination_path.joinpath('vocab')
with open("/run/media/deck/YF8SD/Video/Yu-Gi-Oh! Duel Monsters - 001.vtt", "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()
vocab = {} #load_vocab('foo.json')
## Currently just doing this line by line
with open(args.subtitle_file, "r", encoding="utf-8") as f:
lines = f.readlines()
@ -64,32 +79,21 @@ def main():
i+=1
## Lookup vocab
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)
write_word_note(word, destination_path)
with open("/run/media/deck/YF8SD/Video/Yu-Gi-Oh! Duel Monsters - 001.vtt", "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)
## Output file with changes if changes
out_dir = Path(args.subtitle_file).parent
changed_file = out_dir.joinpath(Path(args.subtitle_file).stem + '.txt')
with open(changed_file, "w", encoding="utf-8") as f:
f.writelines(lines)
# with open("notestest-newchunks.md", "w", encoding="utf-8") as f:
# f.writelines(notes_lines)
note_file = out_dir.joinpath(Path(args.subtitle_file).stem + '.md')
with open(note_file, "w", encoding="utf-8") as f:
f.writelines(notes_lines)
#vocab = load_vocab(args.vocab_file)
#result = analyze(text, vocab)