markdown-it/lib/common/utils.mjs

// Utilities
//

import mdurl from 'mdurl';
import ucmicro from 'uc.micro';
import { decodeHTML } from 'entities';
import UNICODE_PUNCT_RE from 'uc.micro/categories/P/regex.js';

function _class(obj) { return Object.prototype.toString.call(obj); }

function isString(obj) { return _class(obj) === '[object String]'; }

var _hasOwnProperty = Object.prototype.hasOwnProperty;

function has(object, key) {
  return _hasOwnProperty.call(object, key);
}

// Merge objects
//
function assign(obj /*from1, from2, from3, ...*/) {
  var sources = Array.prototype.slice.call(arguments, 1);

  sources.forEach(function (source) {
    if (!source) { return; }

    if (typeof source !== 'object') {
      throw new TypeError(source + 'must be object');
    }

    Object.keys(source).forEach(function (key) {
      obj[key] = source[key];
    });
  });

  return obj;
}

// Remove element from array and put another array at those position.
// Useful for some operations with tokens
function arrayReplaceAt(src, pos, newElements) {
  return [].concat(src.slice(0, pos), newElements, src.slice(pos + 1));
}

////////////////////////////////////////////////////////////////////////////////

function isValidEntityCode(c) {
  /*eslint no-bitwise:0*/
  // broken sequence
  if (c >= 0xD800 && c <= 0xDFFF) { return false; }
  // never used
  if (c >= 0xFDD0 && c <= 0xFDEF) { return false; }
  if ((c & 0xFFFF) === 0xFFFF || (c & 0xFFFF) === 0xFFFE) { return false; }
  // control codes
  if (c >= 0x00 && c <= 0x08) { return false; }
  if (c === 0x0B) { return false; }
  if (c >= 0x0E && c <= 0x1F) { return false; }
  if (c >= 0x7F && c <= 0x9F) { return false; }
  // out of range
  if (c > 0x10FFFF) { return false; }
  return true;
}

function fromCodePoint(c) {
  /*eslint no-bitwise:0*/
  if (c > 0xffff) {
    c -= 0x10000;
    var surrogate1 = 0xd800 + (c >> 10),
        surrogate2 = 0xdc00 + (c & 0x3ff);

    return String.fromCharCode(surrogate1, surrogate2);
  }
  return String.fromCharCode(c);
}


var UNESCAPE_MD_RE  = /\\([!"#$%&'()*+,\-.\/:;<=>?@[\\\]^_`{|}~])/g;
var ENTITY_RE       = /&([a-z#][a-z0-9]{1,31});/gi;
var UNESCAPE_ALL_RE = new RegExp(UNESCAPE_MD_RE.source + '|' + ENTITY_RE.source, 'gi');

var DIGITAL_ENTITY_TEST_RE = /^#((?:x[a-f0-9]{1,8}|[0-9]{1,8}))$/i;


function replaceEntityPattern(match, name) {
  var decoded, code;

  if (name.charCodeAt(0) === 0x23/* # */ && DIGITAL_ENTITY_TEST_RE.test(name)) {
    code = name[1].toLowerCase() === 'x' ?
      parseInt(name.slice(2), 16) : parseInt(name.slice(1), 10);

    if (isValidEntityCode(code)) {
      return fromCodePoint(code);
    }

    return match;
  }

  decoded = decodeHTML(match);
  if (decoded !== match) {
    return decoded;
  }

  return match;
}

/*function replaceEntities(str) {
  if (str.indexOf('&') < 0) { return str; }

  return str.replace(ENTITY_RE, replaceEntityPattern);
}*/

function unescapeMd(str) {
  if (str.indexOf('\\') < 0) { return str; }
  return str.replace(UNESCAPE_MD_RE, '$1');
}

function unescapeAll(str) {
  if (str.indexOf('\\') < 0 && str.indexOf('&') < 0) { return str; }

  return str.replace(UNESCAPE_ALL_RE, function (match, escaped, entity) {
    if (escaped) { return escaped; }
    return replaceEntityPattern(match, entity);
  });
}

////////////////////////////////////////////////////////////////////////////////

var HTML_ESCAPE_TEST_RE = /[&<>"]/;
var HTML_ESCAPE_REPLACE_RE = /[&<>"]/g;
var HTML_REPLACEMENTS = {
  '&': '&amp;',
  '<': '&lt;',
  '>': '&gt;',
  '"': '&quot;'
};

function replaceUnsafeChar(ch) {
  return HTML_REPLACEMENTS[ch];
}

function escapeHtml(str) {
  if (HTML_ESCAPE_TEST_RE.test(str)) {
    return str.replace(HTML_ESCAPE_REPLACE_RE, replaceUnsafeChar);
  }
  return str;
}

////////////////////////////////////////////////////////////////////////////////

var REGEXP_ESCAPE_RE = /[.?*+^$[\]\\(){}|-]/g;

function escapeRE(str) {
  return str.replace(REGEXP_ESCAPE_RE, '\\$&');
}

////////////////////////////////////////////////////////////////////////////////

function isSpace(code) {
  switch (code) {
    case 0x09:
    case 0x20:
      return true;
  }
  return false;
}

// Zs (unicode class) || [\t\f\v\r\n]
function isWhiteSpace(code) {
  if (code >= 0x2000 && code <= 0x200A) { return true; }
  switch (code) {
    case 0x09: // \t
    case 0x0A: // \n
    case 0x0B: // \v
    case 0x0C: // \f
    case 0x0D: // \r
    case 0x20:
    case 0xA0:
    case 0x1680:
    case 0x202F:
    case 0x205F:
    case 0x3000:
      return true;
  }
  return false;
}

////////////////////////////////////////////////////////////////////////////////

/*eslint-disable max-len*/

// Currently without astral characters support.
function isPunctChar(ch) {
  return UNICODE_PUNCT_RE.test(ch);
}


// Markdown ASCII punctuation characters.
//
// !, ", #, $, %, &, ', (, ), *, +, ,, -, ., /, :, ;, <, =, >, ?, @, [, \, ], ^, _, `, {, |, }, or ~
// http://spec.commonmark.org/0.15/#ascii-punctuation-character
//
// Don't confuse with unicode punctuation !!! It lacks some chars in ascii range.
//
function isMdAsciiPunct(ch) {
  switch (ch) {
    case 0x21/* ! */:
    case 0x22/* " */:
    case 0x23/* # */:
    case 0x24/* $ */:
    case 0x25/* % */:
    case 0x26/* & */:
    case 0x27/* ' */:
    case 0x28/* ( */:
    case 0x29/* ) */:
    case 0x2A/* * */:
    case 0x2B/* + */:
    case 0x2C/* , */:
    case 0x2D/* - */:
    case 0x2E/* . */:
    case 0x2F/* / */:
    case 0x3A/* : */:
    case 0x3B/* ; */:
    case 0x3C/* < */:
    case 0x3D/* = */:
    case 0x3E/* > */:
    case 0x3F/* ? */:
    case 0x40/* @ */:
    case 0x5B/* [ */:
    case 0x5C/* \ */:
    case 0x5D/* ] */:
    case 0x5E/* ^ */:
    case 0x5F/* _ */:
    case 0x60/* ` */:
    case 0x7B/* { */:
    case 0x7C/* | */:
    case 0x7D/* } */:
    case 0x7E/* ~ */:
      return true;
    default:
      return false;
  }
}

// Hepler to unify [reference labels].
//
function normalizeReference(str) {
  // Trim and collapse whitespace
  //
  str = str.trim().replace(/\s+/g, ' ');

  // In node v10 'ẞ'.toLowerCase() === 'Ṿ', which is presumed to be a bug
  // fixed in v12 (couldn't find any details).
  //
  // So treat this one as a special case
  // (remove this when node v10 is no longer supported).
  //
  if ('ẞ'.toLowerCase() === 'Ṿ') {
    str = str.replace(/ẞ/g, 'ß');
  }

  // .toLowerCase().toUpperCase() should get rid of all differences
  // between letter variants.
  //
  // Simple .toLowerCase() doesn't normalize 125 code points correctly,
  // and .toUpperCase doesn't normalize 6 of them (list of exceptions:
  // İ, ϴ, ẞ, Ω, K, Å - those are already uppercased, but have differently
  // uppercased versions).
  //
  // Here's an example showing how it happens. Lets take greek letter omega:
  // uppercase U+0398 (Θ), U+03f4 (ϴ) and lowercase U+03b8 (θ), U+03d1 (ϑ)
  //
  // Unicode entries:
  // 0398;GREEK CAPITAL LETTER THETA;Lu;0;L;;;;;N;;;;03B8;
  // 03B8;GREEK SMALL LETTER THETA;Ll;0;L;;;;;N;;;0398;;0398
  // 03D1;GREEK THETA SYMBOL;Ll;0;L;<compat> 03B8;;;;N;GREEK SMALL LETTER SCRIPT THETA;;0398;;0398
  // 03F4;GREEK CAPITAL THETA SYMBOL;Lu;0;L;<compat> 0398;;;;N;;;;03B8;
  //
  // Case-insensitive comparison should treat all of them as equivalent.
  //
  // But .toLowerCase() doesn't change ϑ (it's already lowercase),
  // and .toUpperCase() doesn't change ϴ (already uppercase).
  //
  // Applying first lower then upper case normalizes any character:
  // '\u0398\u03f4\u03b8\u03d1'.toLowerCase().toUpperCase() === '\u0398\u0398\u0398\u0398'
  //
  // Note: this is equivalent to unicode case folding; unicode normalization
  // is a different step that is not required here.
  //
  // Final result should be uppercased, because it's later stored in an object
  // (this avoid a conflict with Object.prototype members,
  // most notably, `__proto__`)
  //
  return str.toLowerCase().toUpperCase();
}

////////////////////////////////////////////////////////////////////////////////

// Re-export libraries commonly used in both markdown-it and its plugins,
// so plugins won't have to depend on them explicitly, which reduces their
// bundled size (e.g. a browser build).
//
const lib = { mdurl, ucmicro };

export {
  lib,
  assign,
  isString,
  has,
  unescapeMd,
  unescapeAll,
  isValidEntityCode,
  fromCodePoint,
  escapeHtml,
  arrayReplaceAt,
  isSpace,
  isWhiteSpace,
  isMdAsciiPunct,
  isPunctChar,
  escapeRE,
  normalizeReference
};

export default {
  lib,
  assign,
  isString,
  has,
  unescapeMd,
  unescapeAll,
  isValidEntityCode,
  fromCodePoint,
  escapeHtml,
  arrayReplaceAt,
  isSpace,
  isWhiteSpace,
  isMdAsciiPunct,
  isPunctChar,
  escapeRE,
  normalizeReference
};