unicode-input-toolconverter 0.2.0

package/browser_action/encodingBehaviors.js

@@ -0,0 +1,72 @@
+import {$} from '../vendor/jamilih/dist/jml-es.js';
+
+import {classChange as charrefClassChange} from './charrefConverters.js';
+
+// UI Bridges
+export const convertEncoding = (out) => {
+  const from = $('#encoding_from').value,
+    to = $('#encoding_to').value,
+    toconvert = out;
+
+  if (!from || !to) {
+    return;
+  }
+
+  const Components = 'todo';
+  const Cc = Components.classes,
+    Ci = Components.interfaces;
+  const cnv = Cc[
+    '@mozilla.org/intl/scriptableunicodeconverter'
+  ].createInstance(Ci.nsIScriptableUnicodeConverter);
+  cnv.charset = from; // The charset to use
+  const os = cnv.convertToInputStream(toconvert);
+
+  // Fix: could customize
+  const replacementChar = Ci.
+    nsIConverterInputStream.DEFAULT_REPLACEMENT_CHARACTER;
+
+  const is = Cc[
+    '@mozilla.org/intl/converter-input-stream;1'
+  ].createInstance(Ci.nsIConverterInputStream);
+  is.init(os, to, 1024, replacementChar);
+  const str = {};
+  let output = '';
+  while (is.readString(4096, str) !== 0) {
+    output += str.value;
+  }
+  os.close();
+  $('#converted').value = output;
+  /*
+  const cv = Cc[
+    '@mozilla.org/intl/scriptableunicodeconverter'
+  ].getService(Ci.nsIScriptableUnicodeConverter);
+  cv.charset = to;
+  const unicode_str = cv.ConvertToUnicode(toconvert);
+  cv.charset = from;
+  $('#converted').value = cv.ConvertFromUnicode(unicode_str);
+  */
+};
+
+/**
+* @param {PlainObject} cfg
+* @param {import('intl-dom').I18NCallback} cfg._
+* @returns {void}
+*/
+function setupEncodingEvents ({_}) {
+  /**
+   * @returns {void}
+   */
+  function encodingListener () {
+    charrefClassChange(this);
+    try {
+      convertEncoding($('#toconvert').value);
+    } catch {
+      alert(_('chars_could_not_be_converted'));
+    }
+  }
+
+  $('#encoding_from').addEventListener('click', encodingListener);
+  $('#encoding_to').addEventListener('click', encodingListener);
+}
+
+export {setupEncodingEvents};

package/browser_action/encodings.js

@@ -0,0 +1,97 @@
+// Todo: Autogenerate if updating
+const encodings = [
+  // eslint-disable-next-line unicorn/text-encoding-identifier-case -- Required
+  'UTF-8',
+  'ISO-8859-1',
+  'Big5',
+  'Big5-HKSCS',
+  'EUC-JP',
+  'EUC-KR',
+  'GB2312',
+  'GEOSTD8',
+  'HZ-GB-2312',
+  'IBM850',
+  'IBM852',
+  'IBM855',
+  'IBM857',
+  'IBM862',
+  'IBM864',
+  'IBM864i',
+  'IBM866',
+  'ISO-2022-CN',
+  'ISO-2022-JP',
+  'ISO-2022-KR',
+  'ISO-8859-1',
+  'ISO-8859-10',
+  'ISO-8859-11',
+  'ISO-8859-13',
+  'ISO-8859-14',
+  'ISO-8859-15',
+  'ISO-8859-16',
+  'ISO-8859-2',
+  'ISO-8859-3',
+  'ISO-8859-4',
+  'ISO-8859-5',
+  'ISO-8859-6',
+  'ISO-8859-6-E',
+  'ISO-8859-6-I',
+  'ISO-8859-7',
+  'ISO-8859-8',
+  'ISO-8859-8-E',
+  'ISO-8859-8-I',
+  'ISO-8859-9',
+  'ISO-IR-111',
+  'KOI8-R',
+  'KOI8-U',
+  'Shift_JIS',
+  'T.61-8bit',
+  'TIS-620',
+  'UTF-16',
+  'UTF-16BE',
+  'UTF-16LE',
+  'UTF-32',
+  'UTF-32BE',
+  'UTF-32LE',
+  'UTF-7',
+  // eslint-disable-next-line unicorn/text-encoding-identifier-case -- Required
+  'UTF-8',
+  'VISCII',
+  'armscii-8',
+  'gb18030',
+  'us-ascii',
+  'windows-1250',
+  'windows-1251',
+  'windows-1252',
+  'windows-1253',
+  'windows-1254',
+  'windows-1255',
+  'windows-1256',
+  'windows-1257',
+  'windows-1258',
+  'windows-874',
+  'windows-936',
+  'x-euc-tw',
+  'x-gbk',
+  'x-imap4-modified-utf7',
+  'x-johab',
+  'x-mac-arabic',
+  'x-mac-ce',
+  'x-mac-croatian',
+  'x-mac-cyrillic',
+  'x-mac-devanagari',
+  'x-mac-farsi',
+  'x-mac-greek',
+  'x-mac-gujarati',
+  'x-mac-gurmukhi',
+  'x-mac-hebrew',
+  'x-mac-icelandic',
+  'x-mac-roman',
+  'x-mac-romanian',
+  'x-mac-turkish',
+  'x-user-defined',
+  'x-viet-tcvn5712',
+  'x-viet-vps',
+  'x-windows-949'
+];
+
+export default encodings;

package/browser_action/entities.js

@@ -0,0 +1,12 @@
+/* eslint-disable @stylistic/comma-spacing, @stylistic/max-len -- Lot of data */
+const entities = ['nbsp','iexcl','cent','pound','curren','yen','brvbar','sect','uml','copy','ordf','laquo','not','shy','reg','macr','deg','plusmn','sup2','sup3','acute','micro','para','middot','cedil','sup1','ordm','raquo','frac14','frac12','frac34','iquest','Agrave','Aacute','Acirc','Atilde','Auml','Aring','AElig','Ccedil','Egrave','Eacute','Ecirc','Euml','Igrave','Iacute','Icirc','Iuml','ETH','Ntilde','Ograve','Oacute','Ocirc','Otilde','Ouml','times','Oslash','Ugrave','Uacute','Ucirc','Uuml','Yacute','THORN','szlig','agrave','aacute','acirc','atilde','auml','aring','aelig','ccedil','egrave','eacute','ecirc','euml','igrave','iacute','icirc','iuml','eth','ntilde','ograve','oacute','ocirc','otilde','ouml','divide','oslash','ugrave','uacute','ucirc','uuml','yacute','thorn','yuml','quot','gt','apos','amp','lt','OElig','oelig','Scaron','scaron','Yuml','circ','tilde','ensp','emsp','thinsp','zwnj','zwj','lrm','rlm','ndash','mdash','lsquo','rsquo','sbquo','ldquo','rdquo','bdquo','dagger','Dagger','permil','lsaquo','rsaquo','euro','fnof','Alpha','Beta','Gamma','Delta','Epsilon','Zeta','Eta','Theta','Iota','Kappa','Lambda','Mu','Nu','Xi','Omicron','Pi','Rho','Sigma','Tau','Upsilon','Phi','Chi','Psi','Omega','alpha','beta','gamma','delta','epsilon','zeta','eta','theta','iota','kappa','lambda','mu','nu','xi','omicron','pi','rho','sigmaf','sigma','tau','upsilon','phi','chi','psi','omega','thetasym','upsih','piv','bull','hellip','prime','Prime','oline','frasl','weierp','image','real','trade','alefsym','larr','uarr','rarr','darr','harr','crarr','lArr','uArr','rArr','dArr','hArr','forall','part','exist','empty','nabla','isin','notin','ni','prod','sum','minus','lowast','radic','prop','infin','ang','and','or','cap','cup','int','there4','sim','cong','asymp','ne','equiv','le','ge','sub','sup','nsub','sube','supe','oplus','otimes','perp','sdot','lceil','rceil','lfloor','rfloor','lang','rang','loz','spades','clubs','hearts','diams'];
+/* eslint-enable @stylistic/comma-spacing, @stylistic/max-len -- Lot of data */
+
+const numericCharacterReferences =
+  // This should be kept in sync with the entities array
+  /* eslint-disable @stylistic/max-len -- Long */
+  /* eslint-disable @stylistic/comma-spacing -- Lot of data */
+  [160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,34,62,39,38,60,338,339,352,353,376,710,732,8194,8195,8201,8204,8205,8206,8207,8211,8212,8216,8217,8218,8220,8221,8222,8224,8225,8240,8249,8250,8364,402,913,914,915,916,917,918,919,920,921,922,923,924,925,926,927,928,929,931,932,933,934,935,936,937,945,946,947,948,949,950,951,952,953,954,955,956,957,958,959,960,961,962,963,964,965,966,967,968,969,977,978,982,8226,8230,8242,8243,8254,8260,8472,8465,8476,8482,8501,8592,8593,8594,8595,8596,8629,8656,8657,8658,8659,8660,8704,8706,8707,8709,8711,8712,8713,8715,8719,8721,8722,8727,8730,8733,8734,8736,8743,8744,8745,8746,8747,8756,8764,8773,8776,8800,8801,8804,8805,8834,8835,8836,8838,8839,8853,8855,8869,8901,8968,8969,8970,8971,9001,9002,9674,9824,9827,9829,9830];
+/* eslint-enable @stylistic/comma-spacing -- Lot of data */
+/* eslint-enable @stylistic/max-len -- Long */
+export {entities, numericCharacterReferences};

package/browser_action/entityBehaviors.js

@@ -0,0 +1,96 @@
+import {$} from '../vendor/jamilih/dist/jml-es.js';
+import {getUnicodeDefaults} from './preferences/prefDefaults.js';
+import unicodecharref from './unicodecharref.js';
+
+let charrefunicodeConverter, getPref, setPref;
+export const shareVars = ({charrefunicodeConverter: _uc}) => {
+  charrefunicodeConverter = _uc;
+  ({getPref, setPref} = getUnicodeDefaults());
+};
+
+/**
+ * @param {Event} e
+ * @returns {Promise<void>}
+ */
+async function insertEntityFile (e) {
+  const entFile = await fetch(
+    '../download/entities/' + e.target.value + '.ent'
+  );
+  const data = await entFile.text();
+
+  $('#DTDtextbox').value += '\n' + data;
+  await registerDTD();
+}
+
+/**
+ * @returns {Promise<{void}>}
+ */
+async function registerDTD () {
+  // Cannot use back-reference inside char. class, so need to do twice
+  const pattern = /<!ENTITY\s+([^'"\s]*)\s+(["'])(.*)\2\s*>/gu;
+
+  const text = $('#DTDtextbox').value;
+  await setPref('DTDtextbox', text);
+
+  let result;
+
+  // Reset in case charrefs or ents array deleted before and now want to
+  //  go back to their original values.
+  if (await getPref('appendtohtmldtd')) {
+    charrefunicodeConverter.entities = [...unicodecharref.origents];
+    charrefunicodeConverter.numericCharacterReferences = [
+      ...unicodecharref.origcharrefs
+    ];
+  } else {
+    charrefunicodeConverter.entities = [];
+    charrefunicodeConverter.numericCharacterReferences = [];
+  }
+
+  // Start off blank in case items erased
+  charrefunicodeConverter.newents = [...unicodecharref.orignewents];
+  // Start off blank in case items erased
+  charrefunicodeConverter.newcharrefs = [...unicodecharref.orignewcharrefs];
+
+  const decreg = /^(?:&#|#)?(\d\d+);?$/u;
+  // const decreg2 = /^(&#|#)([0-9]);?$/u;
+  const hexreg = /^(?:&#|#|0|U|u)?(?:[xX+])([\da-fA-F]+);?$/u;
+
+  while ((result = pattern.exec(text)) !== null) {
+    let m = result[3];
+    let addreg = true;
+    if (decreg.test(m)) { // Dec
+      m = m.replace(decreg, '$1');
+      m = Number.parseInt(m);
+    } else if (hexreg.test(m)) { // Hex
+      m = m.replace(hexreg, '$1');
+      m = Number.parseInt(m, 16);
+    // Todo: Fix this so it can handle surrogate pairs
+    // If replacing with Unicode sequence longer than one character, assume
+    //  only wish to convert from entity (not from Unicode)
+    } else if (m.length > 1) {
+      addreg = false;
+    } else {
+      m = m.charCodeAt();
+    }
+    if (addreg) {
+      // Used to ensure apos or amp is detected in same position
+      charrefunicodeConverter.entities.unshift(result[1]);
+      charrefunicodeConverter.numericCharacterReferences.unshift(m);
+    // For translating entities into two-char+ Unicode, or hex or dec
+    } else {
+      charrefunicodeConverter.newents.push(result[1]);
+      charrefunicodeConverter.newcharrefs.push(m); // Can be a string, etc.
+    }
+  }
+}
+
+/**
+* @returns {void}
+*/
+function setupEntityEvents () {
+  $('#insertEntityFile').addEventListener('change', async function (e) {
+    await insertEntityFile(e);
+  });
+}
+
+export {registerDTD, setupEntityEvents};

package/browser_action/index-es.html

@@ -0,0 +1,15 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>-</title>
+    <!-- Temporary favicon no-op -->
+    <link rel="shortcut icon" href="data:image/x-icon;," type="image/x-icon">
+
+    <script src="/vendor/jquery/dist/jquery.js"></script>
+    <!-- <script src="/polyfills/browser-polyfill.min.js"></script> -->
+    <script type="module" src="/browser_action/index.js"></script>
+  </head>
+  <body>
+  </body>
+</html>

package/browser_action/index-instrumented.html

@@ -0,0 +1,16 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>-</title>
+    <!-- Temporary favicon no-op -->
+    <link rel="shortcut icon" href="data:image/x-icon;," type="image/x-icon">
+
+    <script src="/vendor/jquery/dist/jquery.js"></script>
+    <!-- <script src="/polyfills/browser-polyfill.min.js"></script> -->
+    <!-- <script type="module" src="/browser_action/index.js"></script> -->
+  </head>
+  <body>
+    <script src="/browser_action/index.instrumented.iife.min.js"></script>
+  </body>
+</html>

package/browser_action/index-pages.html

@@ -0,0 +1,16 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>-</title>
+    <!-- Temporary favicon no-op -->
+    <link rel="shortcut icon" href="data:image/x-icon;," type="image/x-icon">
+
+    <script src="../vendor/jquery/dist/jquery.js"></script>
+    <!-- <script src="/polyfills/browser-polyfill.min.js"></script> -->
+    <!-- <script type="module" src="/browser_action/index.js"></script> -->
+  </head>
+  <body>
+    <script src="index.iife.min.js"></script>
+  </body>
+</html>

package/browser_action/index.html

@@ -0,0 +1,16 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <title>-</title>
+    <!-- Temporary favicon no-op -->
+    <link rel="shortcut icon" href="data:image/x-icon;," type="image/x-icon">
+
+    <script src="/vendor/jquery/dist/jquery.js"></script>
+    <!-- <script src="/polyfills/browser-polyfill.min.js"></script> -->
+    <!-- <script type="module" src="/browser_action/index.js"></script> -->
+  </head>
+  <body>
+    <script src="/browser_action/index.iife.min.js"></script>
+  </body>
+</html>