From 7bb75ae7d99445f8660c4f7b68ddca2647aeb5b0 Mon Sep 17 00:00:00 2001
From: Nitsud Yarg <relay01@gmail.com>
Date: Fri, 15 May 2026 11:46:39 -0700
Subject: [PATCH] add ruby to a vtt file

---
 subtitle_processor.py | 53 +++++++++++++++++++++++--------------------
 1 file changed, 28 insertions(+), 25 deletions(-)

diff --git a/subtitle_processor.py b/subtitle_processor.py
index 4ca1f13..d4e0bee 100644
--- a/subtitle_processor.py
+++ b/subtitle_processor.py
@@ -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)