Skip to content

Instantly share code, notes, and snippets.

@mkyt
mkyt / fix-pages-metadata-conflicts.py
Last active December 6, 2022 15:36
Fix merge conflicts for `pages-metadata.edn` of LogSeq data directory
#!/usr/bin/env python3
from pathlib import Path
from typing import Union, Tuple, List, NamedTuple, Dict
import sys
class Block(NamedTuple):
name: str
created: int
updated: int
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
set_pdf_dir.py
Set direction and/or page layout properties of PDF files.
Usage:
$ ./set_pdf_dir.py -l r2l -d book -o my_pdf_1.pdf my_pdf_2.pdf
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""HCP Downloader
This script fetches preprocessed BOLD timeseries in grayordinate space
for all subjects from Human Connectome Project S3 repository
"""
import sys
import os
import os.path
@mkyt
mkyt / kansuji2roman.py
Created May 18, 2020 07:32
法令漢数字→ローマ数字
from kanjize import kanji2int
import re
exprs = [
(r'月([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)日', 1), # 三月二十八日
(r'年([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)月', 1), # 昭和四十二年三月
(r'(明治|大正|昭和|平成|令和)([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)年', 2), # 昭和四十二年
(r'第([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)(章|節|条|項|号)', 1), # 第二十三条
(r'[〇一二三四五六七八九十壱弐参拾百千万萬億兆]+の([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)', 1), # 第十九条の六の十五
(r'条の([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)', 1), # 第十九条の六
(r'^([〇一二三四五六七八九十壱弐参拾百千万萬億兆]+)', 1), # <行頭>二
@mkyt
mkyt / eijiro.py
Created January 16, 2020 16:08
convert EIJIRO text data into JSON format
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""eijiro.py - convert EIJIRO text data into JSON format
Input: Raw EIJIRO text data (can be purchased from https://booth.pm/ja/items/777563 )
Output: Dictionary data in JSON format
< Data Schema >
@mkyt
mkyt / cook4me_recipe.py
Last active May 13, 2018 13:26
Extract recipes for cook4me express
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from urllib.request import urlopen
import re
import json
from pprint import pprint
from bs4 import BeautifulSoup
BASE_URL = 'http://www.club.t-fal.co.jp'
LIST_URL = BASE_URL + '/recipe/category/c4m-express/{:d}/'
@mkyt
mkyt / lyrics_offset.py
Created February 16, 2017 12:58
Lyrics offset
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys
import re
import os.path
timecode_pat = re.compile(r'\[(\d{2}:\d{2}:\d{2})\]')
timecode_parser = re.compile(r'(\d{2}):(\d{2}):(\d{2})')
@mkyt
mkyt / concat_seqs.py
Last active August 29, 2015 14:01
change indentation "\t" -> " "
#!/usr/bin/env python
from Bio import SeqIO
from Bio.SeqRecord import SeqRecord
from Bio.Seq import Seq
from Bio.Blast.Applications import NcbiblastpCommandline
from Bio.Blast import NCBIXML
import sys
if sys.hexversion >= 0x3000000:
from io import StringIO
else: