From 0c1eebd071c1e1adfb41838f7ac2054bd0c4464f Mon Sep 17 00:00:00 2001 From: Nitsud Yarg Date: Wed, 29 Apr 2026 11:53:14 -0700 Subject: [PATCH] making notes out of json data. First attempt. --- add-readings.py | 12 ++++- create-notes.py | 118 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 129 insertions(+), 1 deletion(-) create mode 100644 create-notes.py diff --git a/add-readings.py b/add-readings.py index acb960c..d8fe8fe 100644 --- a/add-readings.py +++ b/add-readings.py @@ -76,7 +76,7 @@ def anki_fields_term(term : str) -> dict: return json.loads(response.text) def term_entries(term :str) -> dict: - print("Requesting termEntries:") + #print("Requesting termEntries:") params = { "term": term, "maxEntries": 1, @@ -144,12 +144,15 @@ for cd in dump: print(anottated['reading']) dump[cd]['kana'] = anottated['reading'] cd_nm = dump[cd]['name_J'] + if (anottated.get('vocab')): + dump[cd]['glossary_Name_J'] = list() for word in anottated['vocab']: # Skip punctuation words hopefully if len(word) == 1 and has_kanji(word) == False: continue if vocab_dict.get(word) is None: vocab_dict[word] = { + 'Def.': "; ".join(get_glossary(word)), 'count': 0, 'Examples': (cd_nm,) } @@ -157,17 +160,22 @@ for cd in dump: vocab_dict[word]['count'] = vocab_dict[word]['count'] + 1 if cd_nm not in vocab_dict[word]['Examples']: vocab_dict[word]['Examples'] += (cd_nm,) + if vocab_dict.get(word): + dump[cd]['glossary_Name_J'].append(f"{word}: {vocab_dict[word]['Def.']}") print() phrase = dump[cd]['desc_J'] anottated = annotate_phrase(phrase) if anottated['reading'] != phrase: #print(anottated['reading']) dump[cd]['desc_Furi'] = anottated['reading'] + if (anottated.get('vocab')): + dump[cd]['glossary_Desc_J'] = list() for word in anottated['vocab']: if len(word) == 1 and has_kanji(word) == False: continue if vocab_dict.get(word) is None: vocab_dict[word] = { + 'Def.': "; ".join(get_glossary(word)), 'count': 0, 'Examples': (cd_nm,) } @@ -176,6 +184,8 @@ for cd in dump: if len(vocab_dict[word]['Examples']) < 5: if cd_nm not in vocab_dict[word]['Examples']: vocab_dict[word]['Examples'] += (cd_nm,) + if vocab_dict.get(word): + dump[cd]['glossary_Desc_J'].append(f"{word}: {vocab_dict[word]['Def.']}") vocab_dict = sorted(vocab_dict.items(), key= lambda x: x[1]['count'], reverse=True) diff --git a/create-notes.py b/create-notes.py new file mode 100644 index 0000000..20e9032 --- /dev/null +++ b/create-notes.py @@ -0,0 +1,118 @@ +import json +import MeCab +import re + +import requests + +import os +from pathlib import Path +import shutil + +request_url = "http://127.0.0.1:19633" +request_timeout = 10 + +destination_directory_name = '/run/media/deck/YF8SD/Sync/Notebooks/Obsidian/Japanese/Yu-Gi-Oh/Cards/' +destination_path = Path(destination_directory_name) + +# Generate Hiragana and Katakana characters +hiragana = tuple(chr(i) for i in range(12353, 12436)) # \u3041 - \u3094 +katakana = tuple(chr(i) for i in range(12450, 12532)) # \u30A2 - \u30F4 +punctuation = tuple(chr(i) for i in range(65281, 65382)) + +# Combine both into one tuple +all_kana = hiragana + katakana + punctuation + ('　', 'ー', '・') + +KANJI_RE = re.compile(r"[\u4E00-\u9FFF]") + +def katakana_to_hiragana(text: str) -> str: + return "".join( + chr(ord(ch) - 0x60) if 0x30A1 <= ord(ch) <= 0x30F6 else ch + for ch in text + ) + +# def get_node_reading(node) -> str: +# features = node.feature.split(",") +# print() +# if len(features) >= 8 and features[7] != "*": +# return katakana_to_hiragana(features[7]) +# return node.surface + +def has_kanji(text: str) -> bool: + return bool(KANJI_RE.search(text)) + +def anki_fields_term(term : str) -> dict: + params = { + "text": term, + "type": "term", + "markers": ["audio", "cloze-body-kana", "conjugation", "expression", "furigana", "furigana-plain", "glossary", "glossary-brief", "glossary-no-dictionary", "glossary-first", "glossary-first-brief", "glossary-first-no-dictionary", "part-of-speech", "phonetic-transcriptions", "pitch-accents", "pitch-accent-graphs", "pitch-accent-graphs-jj", "pitch-accent-positions", "pitch-accent-categories", "reading", "tags", "clipboard-image", "clipboard-text", "cloze-body", "cloze-prefix", "cloze-suffix", "dictionary", "dictionary-alias", "document-title", "frequencies", "frequency-harmonic-rank", "frequency-harmonic-occurrence", "frequency-average-rank", "frequency-average-occurrence", "screenshot", "search-query", "popup-selection-text", "sentence", "sentence-furigana", "sentence-furigana-plain", "url"], + "maxEntries": 1, + "includeMedia": False, + } + response = requests.post(request_url + "/ankiFields", json = params, timeout = request_timeout) + return json.loads(response.text) + +def term_entries(term :str) -> dict: + #print("Requesting termEntries:") + params = { + "term": term, + "maxEntries": 1, + "includeMedia": False, + } + response = requests.post(request_url + "/termEntries", json = params, timeout = request_timeout) + return json.loads(response.text) + +def get_glossary(word :str) -> list: + glossary = list() + dict_items = term_entries(word) + + entry = next(iter(dict_items.get("dictionaryEntries",[])),None) + if entry: + definition = next(iter(entry.get("definitions",[])),None) + if definition: + def_entry = next(iter(definition.get("entries", [])),None) + if def_entry: + glossary.extend( list(extract_text_by_type(def_entry, "glossary")) ) + return glossary[:2] + +#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) + +with open("dump2.json", "r", encoding="utf-16") as f: + dump = json.load(f) + +for cd in dump: + print(dump[cd]['name_J']) + if Path('YGO_2020/2020.full.illust_j.jpg.zib/' + cd + '.jpg').exists(): + ##TODO: Ew + if Path(destination_path.joinpath('_attachments/' + cd + '.jpg')).exists() == False: + shutil.copy2(Path('YGO_2020/2020.full.illust_j.jpg.zib/' + cd + '.jpg'), destination_path.joinpath('_attachments')) + with open(destination_path.as_posix() + '/' + cd + '.md', 'w') as card_note: + card_note.write("---\n") + card_note.write(f"aliases: [{dump[cd]['name_J']},{dump[cd]['name_E']}]\n") + card_note.write("---\n") + ## Name at the top + card_note.write(f"![[{cd}.jpg]]") + card_note.write("\n
\n") + card_note.write(dump[cd]['name_J']) + card_note.write("\n\n") + card_note.write(dump[cd]['name_E']) + card_note.write("\n
\n") + if(dump[cd].get("kana")): + card_note.write(f"{dump[cd]['kana']}\n") + ## the description + card_note.write(dump[cd]['desc_J']) + card_note.write("
\n") + card_note.write("Translation") + card_note.write("\n\n") + card_note.write(dump[cd]['desc_E']) + card_note.write("\n
\n") + # desc_Furi + if(dump[cd].get("desc_Furi")): + card_note.write(f"{dump[cd]['desc_Furi']}\n") + for vocab in dump[cd]["glossary_Desc_J"]: + print(vocab, file=card_note)