anki-connect.py

@@ -1,103 +0,0 @@
-import json
-import requests
-
-ANKI_URL = "http://127.0.0.1:8765"
-
-def request_anki(action, params=None):
-    """Sends a payload to AnkiConnect."""
-    payload = {"action": action, "version": 6, "params": params or {}}
-    response = requests.post(ANKI_URL, json=payload)
-    response.raise_for_status()
-    return response.json().get("result")
-
-def get_card_proficiency(query="deck:current"):
-    """
-    Finds cards by query, retrieves scheduling data, 
-    and prints proficiency stats for each card.
-    """
-    card_ids = request_anki("findCards", {"query": query})
-    if not card_ids:
-        print("No cards found.")
-        return
-
-    card_info = request_anki("cardsInfo", {"cards": card_ids})
-
-    card_proficiency = {}
-    
-    for card in card_info:
-        card_id = card["cardId"]
-        # In Anki: 0=new, 1=learning, 2=review, 3=relearning
-        queue_state = card["queue"] 
-        interval = card["interval"]
-        reps = card["reps"]
-        lapses = card["lapses"]
-
-        # Anki queue mappings: 
-        # 0 = New, 1 = Learning, 2 = Review, 3 = Relearning
-        if queue_state == 0:
-            status = "New"
-            color = ''
-        elif queue_state == 1:
-            status = "Learning"
-            color = 'orangered'
-        elif queue_state == 3:
-            status = "Relearning"
-            color = 'yellow'
-        elif queue_state == 2:
-            # Review card split by 21-day threshold
-            if interval >= 21:
-                status = "Mature" 
-                color = 'cyan'
-            else: 
-                status = "Young"
-                color = 'lime'
-        elif queue_state < 0:
-            status = "Suspended"
-            color = ''
-        else:
-            status = f"Unknown (Queue {queue})"
-            color = ''
-
-        word = ''
-        if (card['fields'].get('Word')):
-            print(card['fields']['Word'])
-            word = card['fields']['Word']['value']
-        else:
-            #print(card['fields'])
-            continue
-
-        if (card_proficiency.get(word)):
-            print("Multiple matches for word")
-        else:
-            card_proficiency[word] = {'Status' : status,'State' : status, 'Color' : color}
-
-        print(f"Card ID {card_id} (State: {queue_state}):")
-        print(f"  Reps: {reps} | Lapses: {lapses} | Interval: {interval} days | Ease: {status} \n")
-
-    return card_proficiency
-
-# Example usage: Evaluate proficiency for all cards in a specific deck
-# get_card_proficiency(query='deck:"Your Deck Name Here"')
-proficiency_stats = get_card_proficiency(query='deck:"Japanese Vocab" card:0')
-if proficiency_stats.get('休み'):
-    proficiency_stats['休み']['Status']
-
-#Anki determines a card's maturity, learning, or relearning state based on its queue type and interval value.
-# Mature: Review card with an interval of 21 days or more.
-# Young: Review card with an interval of less than 21 days.
-# Relearning: Card currently failing review, placed back into a learning queue.
-"""
-    # Anki queue mappings: 
-    # 0 = New, 1 = Learning, 2 = Review, 3 = Relearning
-    if queue == 0:
-        status = "New"
-    elif queue == 1:
-        status = "Learning"
-    elif queue == 3:
-        status = "Relearning"
-    elif queue == 2:
-        # Review card split by 21-day threshold
-        status = "Mature (Review)" if ivl >= 21 else "Young (Review)"
-    else:
-        status = f"Unknown (Queue {queue})"
-"""

ass_furigana.py

@@ -1,138 +0,0 @@
-import re
-from pathlib import Path
-from math import ceil
-#import tkinter as tk
-#from tkinter.filedialog import askopenfilename
-from pykakasi import kakasi
-
-KANJI_RE = r"[㐀-䶵一-鿋豈-頻]"
-NOT_KANJI_RE = r"[^㐀-䶵一-鿋豈-頻]"
-K_TIME_RE = r"(\{\\k\d+})"
-
-
-# open a window for choosing file
-def choose_file():
-    #root = tk.Tk()
-    #root.withdraw()
-    #file_path = askopenfilename()
-    file_path = '/run/media/deck/YF8SD/Video/Yu-Gi-Oh! Duel Monsters/test.ass'
-    if not file_path:
-        print("No file is chosen. Exit.")
-        exit()
-    return Path(file_path)
-
-
-# create a dictionary mapping kanji to hiragana
-def get_furi(word):
-    print(word['orig'])
-    # simple deletion of the following hiraganas
-    for i in range(-1, (-1*len(word["orig"]) - 1), -1):
-        if word["orig"][i] != word["hira"][i]:
-            i += 1
-            if i != 0:
-                word["hira"] = word["hira"][:i]
-            break
-    
-    # create kanji - hiragana mapping
-    # initialize
-    furi_dict = {}
-    word_kanjis = re.findall(KANJI_RE, word["orig"])
-    if not word_kanjis:
-        return furi_dict
-    
-    # evenly assign hiraganas to each kanji
-    furi_length = ceil(len(word["hira"]) / len(word_kanjis))
-    for i, kanji in enumerate(word_kanjis):
-        start = i * furi_length
-        end = start + furi_length
-        furi_dict[kanji] = word["hira"][start:end]
-    return furi_dict
-
-def has_japanese(text: str) -> bool:
-    return any(
-        0x3040 <= ord(ch) <= 0x30FF or
-        0x3400 <= ord(ch) <= 0x9FFF
-        for ch in text
-    )
-
-
-# process a line in ass file
-def process_line(ass_line, kks_obj):
-    ass_line_items = ass_line.split(",")
-    text = ass_line_items[-1]
-    text_items = re.split(K_TIME_RE, text)
-
-    lyric = re.sub(K_TIME_RE, "", text)
-    kks_res = kks_obj.convert(lyric)
-    cur_word = kks_res.pop(0)
-    cur_word_end = len(cur_word["orig"])
-    cur_pos = 0
-    processed_items = []
-    for item in text_items:
-        # if current position reach the end of current word, then get next word
-        while cur_pos >= cur_word_end:
-            cur_word = kks_res.pop(0)
-            cur_word_end += len(cur_word["orig"])
-        
-        # is japanese?
-        # if has_japanese(item) == False:
-        #     processed_items.append(item)
-        #     continue
-
-        # item is not in the lyric, which means item is k_time
-        if item not in lyric:
-            processed_items.append(item)
-            continue
-
-        # item is in the lyric, but it does not contain any kanji
-        if not re.search(KANJI_RE, item):
-            processed_items.append(item)
-            cur_pos += len(item)
-            continue
-
-        # item contains kanji
-        char_add_furi = []
-        cur_furi = get_furi(cur_word)
-        for char in item:
-            if cur_pos >= cur_word_end:
-                cur_word = kks_res.pop(0)
-                cur_furi = get_furi(cur_word)
-                cur_word_end += len(cur_word["orig"])
-            if re.match(KANJI_RE, char):
-                char_add_furi.append(f"{char}|<{cur_furi[char]}")
-            else:
-                char_add_furi.append(char)
-            cur_pos += 1
-
-        # calculate and add k_time for each character
-        item_k_time = re.search(r"\d+", processed_items[-1])
-        item_k_time = int(item_k_time.group(0))
-        time_each, time_mod = divmod(item_k_time, len(item))
-        processed_items[-1] = r"{\k%s}" % (time_each + time_mod)
-        char_k_time = r"{\k%s}" % time_each
-        item_add_furi = char_k_time.join(char_add_furi)
-        processed_items.append(item_add_furi)
-
-    processed_text = "".join(processed_items)
-    ass_line = ass_line_items[:-1]
-    ass_line.append(processed_text)
-    return ",".join(ass_line)
-
-
-if __name__ == "__main__":
-    # chooose the input file
-    input_path = choose_file()
-    ass = open(input_path, "r", encoding="utf-8")
-    output_path = input_path.with_stem(input_path.stem + "_furigana")
-    ass_furi = open(output_path, "w", encoding="utf-8")
-    
-    # process each line
-    kks = kakasi()
-    for line in ass:
-        if not line.startswith("Dialogue: "):
-            ass_furi.write(line)
-        else:
-            ass_furi.write(process_line(line, kks))
-
-    ass.close()
-    ass_furi.close()

build_jp101_reading.py

@@ -1,33 +0,0 @@
-from fugashi_parser import *
-
-import os
-from pathlib import Path
-import shutil
-import hashlib
-
-season_path = Path('/run/media/deck/YF8SD/Sync/Notebooks/Obsidian/Japanese/JPod101/3N_Absolute Beginner Season 2/')
-
-pos_list = list()
-with open(season_path.parent.joinpath(season_path.stem + '.md'), 'w') as out_file:
-    for file_path in sorted(season_path.iterdir()):
-        if file_path.is_file() and file_path.suffix == '.md':  # Ensure it's a file, not a subdirectory
-            #out_file = file_path.parent.parent.joinpath(file_path.parent.stem + '_READ.md')
-            with open(file_path, "r") as file:
-                #file.write("This text will be added to the end.")
-                print(f"###### [[{file_path.name}]]", file=out_file)
-                file.seek(0)
-                kanji_block = re.search(r'·+\s*KANJI(.*?)·+\s*[KANA|ROMANIZATION]', file.read(), re.DOTALL)
-                if (kanji_block):
-                    kanji_block.group(1)
-                    print( kanji_block.group(1).strip().replace('····','') , file=out_file)
-                else:
-                    print(file_path.stem, 'No Kanji block found')
-            # else:
-            #     print(pos, ' - no tag')
-
-            # with file_path.open('r') as file:
-            #     content = file.read()
-            #     print(f"Content of {file_path.name}: {content}")
-
-unique_values = list(set(pos_list))
-print(unique_values)

fugashi_parser.py

@@ -34,19 +34,19 @@ KATAKANA_TO_HIRAGANA_OFFSET = ord("ぁ") - ord("ァ")
 
 CONTENT_POS1 = {"名詞", "動詞", "形容詞", "形状詞", "副詞", "代名詞"}
 
-# def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
+def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
-#     pos1, pos2, pos3, pos4 = pos
+    pos1, pos2, pos3, pos4 = pos
 
-#     if pos1 not in CONTENT_POS1:
+    if pos1 not in CONTENT_POS1:
-#         return False
+        return False
 
-#     if pos1 == "代名詞" and not keep_pronouns:
+    if pos1 == "代名詞" and not keep_pronouns:
-#         return False
+        return False
 
-#     if pos1 == "名詞" and pos2 == "数詞" and not keep_numbers:
+    if pos1 == "名詞" and pos2 == "数詞" and not keep_numbers:
-#         return False
+        return False
 
-#     return True
+    return True
 
 
 
@@ -98,94 +98,6 @@ def term_entries(term :str) -> dict:
     response = requests.post(request_url + "/termEntries", json = params, timeout = request_timeout)
     return json.loads(response.text)
 
-ANKI_URL = "http://127.0.0.1:8765"
-
-def request_anki(action, params=None):
-    """Sends a payload to AnkiConnect."""
-    payload = {"action": action, "version": 6, "params": params or {}}
-    response = requests.post(ANKI_URL, json=payload)
-    response.raise_for_status()
-    return response.json().get("result")
-
-def get_card_proficiency(query="deck:current"):
-    """
-    Finds cards by query, retrieves scheduling data, 
-    and prints proficiency stats for each card.
-    """
-    card_ids = request_anki("findCards", {"query": query})
-    if not card_ids:
-        print("No cards found.")
-        return
-
-    card_info = request_anki("cardsInfo", {"cards": card_ids})
-
-    card_proficiency = {}
-    
-    for card in card_info:
-        card_id = card["cardId"]
-        # In Anki: 0=new, 1=learning, 2=review, 3=relearning
-        queue_state = card["queue"] 
-        interval = card["interval"]
-        reps = card["reps"]
-        lapses = card["lapses"]
-
-        # Anki queue mappings: 
-        # 0 = New, 1 = Learning, 2 = Review, 3 = Relearning
-        # https://www.w3.org/TR/webvtt1/#default-text-color
-        if queue_state == 0:
-            status = "New"
-            color = 'red'
-        elif queue_state == 1:
-            status = "Learning"
-            color = 'yellow'
-        elif queue_state == 3:
-            status = "Relearning"
-            color = 'lime'
-        elif queue_state == 2 or queue_state == -2:
-            # Review card split by 21-day threshold
-            if interval >= 21:
-                status = "Mature" 
-                color = 'magenta'
-            else: 
-                status = "Young"
-                color = 'cyan'
-        elif queue_state == -1:
-            status = "Suspended"
-            color = ''
-        else:
-            status = f"Unknown (Queue {queue_state})"
-            color = ''
-
-        word = ''
-        if (card['fields'].get('Word')):
-            print(card['fields']['Word'])
-            word = card['fields']['Word']['value']
-        else:
-            #print(card['fields'])
-            continue
-
-        if (card_proficiency.get(word)):
-            print("Multiple matches for word")
-            if (card_proficiency[word]['State'] < queue_state):
-                card_proficiency[word] = {'Status' : status,'State' : queue_state, 'Color' : color}
-        else:
-            card_proficiency[word] = {'Status' : status,'State' : queue_state, 'Color' : color }
-
-        print(f"Card ID {card_id} (State: {queue_state}):")
-        print(f"  Reps: {reps} | Lapses: {lapses} | Interval: {interval} days | Ease: {status} \n")
-
-    return card_proficiency
-
-# Example usage: Evaluate proficiency for all cards in a specific deck
-# get_card_proficiency(query='deck:"Your Deck Name Here"')
-try:
-    proficiency_stats = get_card_proficiency(query='deck:"Japanese Vocab" card:0')
-    with open('vocab-cache.json', "w", encoding="utf-8") as f:
-        json.dump(proficiency_stats, f, ensure_ascii=False, indent=2)
-except:
-    with open("vocab-cache.json", "r", encoding="utf-8") as f:
-        proficiency_stats = json.load(f)
-
 CONTENT_LINK_TAG = {
     '名詞': 'meishi', # noun
     '動詞': 'doshi', # verb
@@ -224,38 +136,10 @@ def should_ruby(surface, reading_hiragana):
 
     return True
 
-def build_ruby(token :TokenReading) -> str:
+def build_ruby(surface: str, reading: str) -> str:
-    if not token.reading_hiragana or not has_japanese(token.surface):
+    if not reading or surface == reading or not has_japanese(surface):
-        return html.escape(token.surface)
+        return html.escape(surface)
-    style_attr = ''
+    return f"<ruby>{html.escape(surface)}<rt>{html.escape(reading)}</rt></ruby>"
-    # First try lemma then try surface
-    if proficiency_stats.get(token.lemma):
-        if proficiency_stats[token.lemma]['Color'] != '':
-            style_attr = f"style=\"color:{proficiency_stats[token.lemma]['Color']}\""
-    elif proficiency_stats.get(token.surface):
-        if proficiency_stats[token.surface]['Color'] != '':
-            style_attr = f"style=\"color:{proficiency_stats[token.surface]['Color']}\""
-    if token.surface == token.reading_hiragana:
-        return f"<span {style_attr}>{html.escape(token.surface)}</span>"
-    return f"<ruby {style_attr}>{html.escape(token.surface)}<rt>{html.escape(token.reading_hiragana)}</rt></ruby>"
-
-def build_sub_cue(token :TokenReading) -> str:
-    if not token.reading_hiragana or not has_japanese(token.surface):
-        return html.escape(token.surface)
-    # Check if color
-    color_prefix = ''
-    color_suffix = ''
-    if proficiency_stats.get(token.lemma):
-        if proficiency_stats[token.lemma]['Color'] != '':
-            color_prefix = f"<c.{proficiency_stats[token.lemma]['Color']}>"
-            color_suffix = f"</c>"
-    elif proficiency_stats.get(token.surface):
-        if proficiency_stats[token.surface]['Color'] != '':
-            color_prefix = f"<c.{proficiency_stats[token.surface]['Color']}>"
-            color_suffix = f"</c>"
-    if token.surface == token.reading_hiragana:
-        return f"{color_prefix}{html.escape(token.surface)}{color_suffix}"
-    return f"{color_prefix}<ruby>{html.escape(token.surface)}<rt>{html.escape(token.reading_hiragana)}</rt></ruby>{color_suffix}"
 
 def build_kana(surface: str, reading: str) -> str:
     if not reading or surface == reading or not has_japanese(surface):
@@ -264,7 +148,7 @@ def build_kana(surface: str, reading: str) -> str:
 
 def build_vocab_link(surface: str, reading: str, pos) -> str:
     pos1, pos2, pos3, pos4 = pos
-    if not is_vocab_token(surface, pos, keep_pronouns=True,keep_numbers=False):
+    if not is_vocab_token(pos, keep_pronouns=True,keep_numbers=False):
         return surface
     # if surface == reading:
     #     return f"[[{surface}]]"
@@ -348,7 +232,7 @@ def chunk_predicates(tokens):
     return chunks
 
 ## Vocab Filtering
-def is_vocab_token(surface, pos, keep_pronouns=False, keep_numbers=False):
+def is_vocab_token(pos, keep_pronouns=False, keep_numbers=False):
     pos1, pos2, pos3, pos4 = pos
 
     if pos1 not in {"名詞", "動詞", "形容詞", "形状詞", "副詞", "代名詞", "感動詞"}:
@@ -357,7 +241,7 @@ def is_vocab_token(surface, pos, keep_pronouns=False, keep_numbers=False):
     if pos1 == "代名詞" and not keep_pronouns:
         return False
 
-    if pos1 == "名詞" and pos2 == "数詞" and not has_kanji(surface) and not keep_numbers:
+    if pos1 == "名詞" and pos2 == "数詞" and not keep_numbers:
         return False
 
     return True
@@ -415,7 +299,7 @@ def update_vocab(vocab: Dict[str, Dict], tokens: List[TokenReading]):
 
         # if should_skip(t.surface, pos1) or not is_content_word(pos1):
         #     continue
-        if not is_vocab_token(t.surface, t.pos, keep_pronouns=True,keep_numbers=False):
+        if not is_vocab_token(t.pos, keep_pronouns=True,keep_numbers=False):
             continue
 
         entry = vocab.get(t.lemma)
@@ -440,7 +324,6 @@ def analyze(text: str, vocab: Dict[str, Dict]):
 
     tokens: List[TokenReading] = []
     ruby_parts = []
-    subtitle_parts = []
     kana_parts = []
     vocab_link_parts = []
 
@@ -475,8 +358,7 @@ def analyze(text: str, vocab: Dict[str, Dict]):
         token = TokenReading(surface, reading, lemma, lemma_reading, pos)
         tokens.append(token)
 
-        ruby_parts.append(build_ruby(token))
+        ruby_parts.append(build_ruby(surface, reading))
-        subtitle_parts.append(build_sub_cue(token))
         kana_parts.append(build_kana(surface, reading))
         predicate_chunks = chunk_predicates(tokens)
 
@@ -486,7 +368,6 @@ def analyze(text: str, vocab: Dict[str, Dict]):
         "original_text": text,
         "kana_reading": "".join(kana_parts),
         "ruby_html": "".join(ruby_parts),
-        "sub_cue": "".join(subtitle_parts),
         "notes_link":"".join(vocab_link_parts),
         "token_readings": [asdict(t) for t in tokens],
         "predicate_chunks" : predicate_chunks,

make_help_notes.py

@@ -1,49 +0,0 @@
-## This is just copied from make_dialog_notes.py 
-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/'
-destination_path = Path(destination_directory_name)
-vocab_destination_path = Path('/run/media/deck/YF8SD/Sync/Notebooks/Obsidian/Japanese/vocab')
-
-with open("helptext_dump.json", "r", encoding="utf-8") as f:
-    dump = json.load(f)
-
-if not destination_path.exists():
-    destination_path.mkdir(parents=True, exist_ok=True)
-if not destination_path.joinpath('YLOTD_help').exists():
-    destination_path.joinpath('YLOTD_help').mkdir(parents=True, exist_ok=True)
-
-counter = 0
-destination_path = destination_path.joinpath('YLOTD_help')
-with open(destination_path.as_posix() + f"/HelpText.md", 'w') as card_note:
-    for title in dump:
-        print(title)
-        counter+=1
-        ## copy the image if it isn't already there
-        print(title)
-        card_note.write(f"\n")
-        #card_note.write(f"\n###### {title}\n\n")
-        #reformatted = re.sub(r'(\d{2})/(\d{2})/(\d{4})', r'\3-\1-\2', date)
-        #re.replace('\$R')
-        text_J = dump[title]['ja']
-        text_J = re.sub(r'\$R(.*?)\((.*?)\)',r'<ruby>\1<rt>\2</rt></ruby>',text_J)
-        if text_J[0] == '●':
-            card_note.write(f"#### {text_J}\n\n")
-        print(f"<details><summary>{text_J}</summary>{dump[title]['en']}</details>",file=card_note)
-        text_J = dump[title]['ja']
-        text_J = re.sub(r'\$R(.*?)\((.*?)\)',r'\1',text_J)
-        text_J = text_J.replace('<br>', '').replace('\n','')
-        ## print raw for vocab lookup
-        print(f"\n{text_J}\n", file=card_note)
-        vocab = {} ## flush the vocab variable each time
-        result = analyze(text_J, vocab)
-        print(f"> [!summary]- Vocab\n>{result['notes_link']}",file=card_note)
-        for word in vocab:
-            write_word_note(word, vocab_destination_path, vocab[word]['pos'][0])
-        # ## add card names as properties
-

process_markdown.py

@@ -45,7 +45,7 @@ def main():
             result = analyze(lines[i],vocab)
             ## If the line changed at all
             if lines[i] != result['ruby_html']:
-                lines[i] = '<span><details><summary>' + result['ruby_html'] + '</summary>' + lines[i]  + '</span>' + "\n> [!summary]- Vocab\n>" + result['notes_link'] + "\n\n" # lost the new line
+                lines[i] = '<span>' + result['ruby_html'] + '</span>' + "\n> [!summary]- Vocab\n>" + result['notes_link'] + "\n\n" # lost the new line
                 file_changed = True
         i+=1
 

subtitle_processor.py

@@ -70,10 +70,11 @@ def main():
         if has_japanese(lines[i]):
             print(lines[i])
             result = analyze(lines[i],vocab)
-            notes_lines.append(result["sub_cue"] + "\n" )
+            print(result['kana_reading'])
+            notes_lines.append(result["ruby_html"] + "\n" )
             notes_lines.append (result['notes_link'] + "\n")
-            if lines[i] != result['sub_cue']:
+            if lines[i] != result['ruby_html']:
-                lines[i] = result['sub_cue'] + "\n" # lost the new line
+                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:
@@ -82,20 +83,16 @@ def main():
         i+=1
 
     ## Lookup vocab
-    try:
     for word in vocab:
         write_word_note(word, destination_path)
-    except:
+    return
-        print("Unable to word lookup")
-    ## Dammit
-    # return
 
     # 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 + '-ruby.vtt')
+    changed_file = out_dir.joinpath(Path(args.subtitle_file).stem + '.txt')
     with open(changed_file, "w", encoding="utf-8") as f:
         f.writelines(lines)