import file for parser is better maybe
This commit is contained in:
parent
26e43ea184
commit
59ce08f6da
141
add-readings.py
141
add-readings.py
|
|
@ -1,138 +1,17 @@
|
|||
import json
|
||||
import MeCab
|
||||
import re
|
||||
|
||||
import requests
|
||||
|
||||
request_url = "http://127.0.0.1:19633"
|
||||
request_timeout = 10
|
||||
|
||||
# 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 get_node_reading(node) -> str:
|
||||
features = node.feature.split(",")
|
||||
## These depend on what dictionary is being used.
|
||||
if len(features) > 6 and features[6] != "*":
|
||||
return katakana_to_hiragana(features[6])
|
||||
return node.surface
|
||||
|
||||
def annotate_phrase(text: str) -> str:
|
||||
tagger = MeCab.Tagger()
|
||||
node = tagger.parseToNode(text)
|
||||
vocab = ()
|
||||
parts = []
|
||||
# <ruby>漢<rt>かん</rt></ruby><ruby>字<rt>じ</rt></ruby>
|
||||
furi = []
|
||||
while node:
|
||||
surface = node.surface
|
||||
if surface:
|
||||
vocab += (surface,)
|
||||
if has_kanji(surface):
|
||||
reading = get_node_reading(node)
|
||||
parts.append(f"{surface}({reading})")
|
||||
furi.append(f"<ruby>{surface}<rt>{reading}</rt></ruby>")
|
||||
else:
|
||||
parts.append(surface)
|
||||
furi.append(surface)
|
||||
node = node.next
|
||||
|
||||
return {'reading':("".join(parts)),'vocab':vocab,"furigana":("".join(furi))}
|
||||
|
||||
def elide(text: str) -> str:
|
||||
elide_max_length = 100
|
||||
if len(text) > elide_max_length:
|
||||
return text[:100] + "..."
|
||||
return 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)
|
||||
|
||||
# perhaps set up a filter parameter.
|
||||
def flatten_string(node):
|
||||
if isinstance(node,str):
|
||||
yield node
|
||||
elif isinstance(node, list):
|
||||
for item in node:
|
||||
yield from flatten_string(item)
|
||||
elif isinstance(node,dict):
|
||||
if isinstance(node.get("content"), str):
|
||||
yield node["content"]
|
||||
else:
|
||||
for v in node.values():
|
||||
yield from flatten_string(v)
|
||||
|
||||
def extract_text_by_type(node, target_type):
|
||||
if isinstance(node,dict):
|
||||
data = node.get("data")
|
||||
if isinstance(data,dict) and data.get("content") == target_type:
|
||||
yield from flatten_string(node.get("content"))
|
||||
#yield from ",".join(node.get("content"))
|
||||
for value in node.values():
|
||||
yield from extract_text_by_type(value, target_type)
|
||||
elif isinstance(node,list):
|
||||
for item in node:
|
||||
yield from extract_text_by_type(item,target_type)
|
||||
|
||||
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]
|
||||
from parser import *
|
||||
|
||||
#print(annotate_phrase("私は学校へ行きます"))
|
||||
|
||||
with open("dump2.json", "r", encoding="utf-16") as f:
|
||||
dump = json.load(f)
|
||||
|
||||
# foo = anki_fields_term(surface)
|
||||
# for entry in foo.get("fields"):
|
||||
# entry['expression']
|
||||
# entry['glossary-first-brief']
|
||||
# entry['glossary-plain-no-dictionary']
|
||||
# entry['frequency-average-rank']
|
||||
|
||||
vocab_dict = {}
|
||||
## A micab phrase based word parser
|
||||
for cd in dump:
|
||||
|
|
@ -196,8 +75,8 @@ for cd in dump:
|
|||
|
||||
vocab_dict = sorted(vocab_dict.items(), key= lambda x: x[1]['count'], reverse=True)
|
||||
|
||||
with open("dump-withFuri.json", "w", encoding="utf-16") as outfile:
|
||||
json.dump(dump, outfile, ensure_ascii=False, indent=2)
|
||||
#with open("dump-withFuri.json", "w", encoding="utf-16") as outfile:
|
||||
# json.dump(dump, outfile, ensure_ascii=False, indent=2)
|
||||
|
||||
#with open("dump-vocab.json", "w", encoding="utf-16") as outfile:
|
||||
# json.dump(vocab_dict, outfile, ensure_ascii=False, indent=2)
|
||||
|
|
|
|||
113
create-notes.py
113
create-notes.py
|
|
@ -1,79 +1,13 @@
|
|||
import json
|
||||
import MeCab
|
||||
import re
|
||||
|
||||
import requests
|
||||
from parser import *
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
import shutil
|
||||
|
||||
request_url = "http://127.0.0.1:19633"
|
||||
request_timeout = 10
|
||||
import hashlib
|
||||
|
||||
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
|
||||
|
|
@ -81,6 +15,8 @@ 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)
|
||||
|
||||
with open("dump-withFuri.json", "r", encoding="utf-16") as f:
|
||||
dump = json.load(f)
|
||||
|
|
@ -97,33 +33,64 @@ for cd in dump:
|
|||
card_note.write("---\n")
|
||||
## Name at the top
|
||||
card_note.write(f"![[{cd}.jpg]]")
|
||||
card_note.write("\n##### Name\n")
|
||||
card_note.write("\n#### Name\n")
|
||||
card_note.write("<details><summary>")
|
||||
card_note.write(dump[cd]['name_J'])
|
||||
card_note.write("</summary>")
|
||||
card_note.write(dump[cd]['name_E'])
|
||||
card_note.write("</details>")
|
||||
## the description
|
||||
card_note.write("\n##### Details\n")
|
||||
card_note.write("\n#### Details\n")
|
||||
card_note.write("<details><summary>")
|
||||
card_note.write(dump[cd]['desc_J'])
|
||||
card_note.write("</summary>")
|
||||
card_note.write(dump[cd]['desc_E'])
|
||||
card_note.write("</details>")
|
||||
# desc_Furi
|
||||
card_note.write("\n##### Reading\n")
|
||||
card_note.write("\n#### Reading\n")
|
||||
if(dump[cd].get("furi")):
|
||||
card_note.write(f"{dump[cd]['furi']}\n")
|
||||
else:
|
||||
card_note.write(dump[cd]['name_J'])
|
||||
card_note.write("\n")
|
||||
card_note.write("##### Glossary\n")
|
||||
for vocab in dump[cd]["glossary_Name_J"]:
|
||||
print(f"{vocab} : {dump[cd]["glossary_Name_J"][vocab]}", file=card_note)
|
||||
card_note.write("\n")
|
||||
if(dump[cd].get("desc_Furi")):
|
||||
card_note.write(f"{dump[cd]['desc_Furi']}\n")
|
||||
else:
|
||||
card_note.write(dump[cd]['desc_J'])
|
||||
card_note.write("\n")
|
||||
card_note.write("\n##### Glossary\n")
|
||||
card_note.write("##### Glossary\n")
|
||||
for vocab in dump[cd]["glossary_Desc_J"]:
|
||||
print(f"{vocab} : {dump[cd]["glossary_Desc_J"][vocab]}", file=card_note)
|
||||
vocab_hash = hashlib.shake_256((vocab + 'Jitendex.org [2026-04-04]').encode()).hexdigest(4)
|
||||
## Only search and create a vocab file if it doesn't exist
|
||||
if Path(destination_path.joinpath('vocab/' + vocab_hash + '.md')).exists() == False:
|
||||
definitions = anki_fields_term(vocab)
|
||||
if definitions.get("fields"):
|
||||
with open(destination_path.as_posix() + '/vocab/' + vocab_hash + '.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)
|
||||
print(f"[[{vocab_hash}|{vocab}]] : {dump[cd]["glossary_Desc_J"][vocab]}", file=card_note)
|
||||
#print('>' + dump[cd]["glossary_Desc_J"][vocab], file=card_note)
|
||||
card_note.write("\n")
|
||||
|
||||
# foo = anki_fields_term(surface)
|
||||
# for entry in foo.get("fields"):
|
||||
# entry['expression']
|
||||
# entry['glossary-first-brief']
|
||||
# entry['glossary-plain-no-dictionary']
|
||||
# entry['frequency-average-rank']
|
||||
|
||||
|
|
|
|||
130
parser.py
Normal file
130
parser.py
Normal file
|
|
@ -0,0 +1,130 @@
|
|||
import json
|
||||
import MeCab
|
||||
import re
|
||||
|
||||
import requests
|
||||
|
||||
request_url = "http://127.0.0.1:19633"
|
||||
request_timeout = 10
|
||||
|
||||
# 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 get_node_reading(node) -> str:
|
||||
features = node.feature.split(",")
|
||||
## These depend on what dictionary is being used.
|
||||
if len(features) > 6 and features[6] != "*":
|
||||
return katakana_to_hiragana(features[6])
|
||||
return node.surface
|
||||
|
||||
def annotate_phrase(text: str) -> str:
|
||||
tagger = MeCab.Tagger()
|
||||
node = tagger.parseToNode(text)
|
||||
vocab = ()
|
||||
parts = []
|
||||
# <ruby>漢<rt>かん</rt></ruby><ruby>字<rt>じ</rt></ruby>
|
||||
furi = []
|
||||
while node:
|
||||
surface = node.surface
|
||||
if surface:
|
||||
vocab += (surface,)
|
||||
if has_kanji(surface):
|
||||
reading = get_node_reading(node)
|
||||
parts.append(f"{surface}({reading})")
|
||||
furi.append(f"<ruby>{surface}<rt>{reading}</rt></ruby>")
|
||||
else:
|
||||
parts.append(surface)
|
||||
furi.append(surface)
|
||||
node = node.next
|
||||
|
||||
return {'reading':("".join(parts)),'vocab':vocab,"furigana":("".join(furi))}
|
||||
|
||||
def elide(text: str) -> str:
|
||||
elide_max_length = 100
|
||||
if len(text) > elide_max_length:
|
||||
return text[:100] + "..."
|
||||
return 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"],
|
||||
"markers": ["audio", "expression", "cloze-body" , "furigana","furigana-plain", "part-of-speech", "reading", "glossary-first", "glossary-plain-no-dictionary" , "glossary-first-no-dictionary" , "dictionary", "frequencies", "frequency-average-rank", "frequency-average-occurrence", "screenshot", "sentence", "sentence-furigana", "sentence-furigana-plain" ],
|
||||
"maxEntries": 2,
|
||||
"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)
|
||||
|
||||
# perhaps set up a filter parameter.
|
||||
def flatten_string(node):
|
||||
if isinstance(node,str):
|
||||
yield node
|
||||
elif isinstance(node, list):
|
||||
for item in node:
|
||||
yield from flatten_string(item)
|
||||
elif isinstance(node,dict):
|
||||
if isinstance(node.get("content"), str):
|
||||
yield node["content"]
|
||||
else:
|
||||
for v in node.values():
|
||||
yield from flatten_string(v)
|
||||
|
||||
def extract_text_by_type(node, target_type):
|
||||
if isinstance(node,dict):
|
||||
data = node.get("data")
|
||||
if isinstance(data,dict) and data.get("content") == target_type:
|
||||
yield from flatten_string(node.get("content"))
|
||||
#yield from ",".join(node.get("content"))
|
||||
for value in node.values():
|
||||
yield from extract_text_by_type(value, target_type)
|
||||
elif isinstance(node,list):
|
||||
for item in node:
|
||||
yield from extract_text_by_type(item,target_type)
|
||||
|
||||
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]
|
||||
Loading…
Reference in New Issue
Block a user