vadimkantorov

// based on simplified version of Python snippet: https://gist.github.com/vadimkantorov/b26eda3645edb13feaa62b874a3e7f6f

function yaml_loads(frontamtter_str)
{
  const procval = s => (s.length >= 2 && s[0] == '"' && s[s.length - 1] == '"') ? s.slice(1, s.length - 1) : (s.length >= 2 && s[0] == "'" && s[s.length - 1] == "'") ? s.slice(1, s.length - 1) : s;

  for(const line of frontmatter_str.split('\n'))
  {
      const line_strip = line.trim();
      const is_list_item = line_strip.startsWith('- ');

vadimkantorov

// based on https://github.com/tigt/mini-svg-data-uri/issues/24
// Usage: cat myicon.svg | node svgdataurify.js

let svg = "";
process.stdin.on("data", (chunk) => {  svg += chunk; });
process.stdin.on("end", async () => 
{
    const reWhitespace = /\s+/g, reUrlHexPairs = /%[\dA-F]{2}/g, hexDecode = {'%20': ' ', '%3D': '=', '%3A': ':', '%2F': '/'}, specialHexDecode = match => hexDecode[match] || match.toLowerCase();
    if(svg.charCodeAt(0) === 0xfeff) svg = svg.slice(1);
    svg = svg.trim().replace(reWhitespace, ' ').replaceAll('"', '\'');

vadimkantorov

# from https://github.com/microsoft/WSL/issues/8151#issuecomment-2276363014

curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs

vadimkantorov

# prependfrontmatter ./index.html
alias prependfrontmatter="sed -i '1i---\n---'"

# https://unix.stackexchange.com/questions/99350/how-to-insert-text-before-the-first-line-of-a-file

vadimkantorov

# python citygeocoder.py > '~citygeocoder.json'
# https://www.wikidata.org/wiki/Wikidata:SPARQL_tutorial/en
# https://github.com/OSMNames/OSMNames, http://github.com/OSMNames/OSMNames/issues/208
# https://osmnames.org/download/
# https://stackoverflow.com/questions/74261733/how-to-fetch-gps-coordinates-of-worlds-largest-cities-from-wikidata-via-sparql
# FIXME: for some reason misses Helsinki

import sys
import json
import urllib.parse

vadimkantorov

# Usage: to extract all eml files in current directory into the current directory: python uneml.py *.eml

import os
import sys
import email
import email.policy
for input_path in sys.argv[1:]:
    print('eml', repr(input_path))
    eml = email.message_from_file(open(input_path), policy = email.policy.default)
    for part in eml.walk():

vadimkantorov

# https://github.com/wp-cli/entity-command/issues/512
# https://developer.wordpress.org/cli/commands/option/list/
# https://developer.wordpress.org/cli/commands/option/update/

# export options to a pretty-formatted JSON file
wp option list --format=json | jq '.' > wpoptionimpex.json
# [
#   {
#     "option_name": "name1",
#     "option_value": "value1"

vadimkantorov

// https://en.cppreference.com/w/c/string/byte/strrchr

#include <stdio.h>
#include <string.h>

int main(int argc, char* argv[])
{
    if(argc < 2)
        return -1;

vadimkantorov

# works only with a single, non-batched tensor of token ids

import torch

def bpedetokenize_loop(token_ids, token_utf8bytes, token_lens):
    inds = torch.cat((torch.zeros_like(token_lens[:1]), token_lens.cumsum(-1)))
    return torch.cat([token_utf8bytes[inds[i]:inds[i_p_1]] for i, i_p_1 in zip(token_ids, token_ids + 1)])

def bpedetokenize_vec(token_ids, token_utf8bytes, token_lens):
    inds_begin = torch.cat((torch.zeros_like(token_lens[:1]), token_lens[:-1].cumsum(-1)))

vadimkantorov

# before running download captcha.onnx from https://huggingface.co/spaces/docparser/Text_Captcha_breaker
# python -m pip install numpy pillow onnxruntime --user --break-system-packages

import argparse
import PIL.Image
import numpy
import onnxruntime

parser = argparse.ArgumentParser()
parser.add_argument('--model-path', default = 'captcha.onnx')