tor-browser

The Tor Browser
git clone https://git.dasho.dev/tor-browser.git
Log | Files | Refs | README | LICENSE

test_serializers_entities.js (2845B)

      1 const encoders = {
      2  xml: doc => {
      3    let enc = Cu.createDocumentEncoder("text/xml");
      4    enc.init(doc, "text/xml", Ci.nsIDocumentEncoder.OutputLFLineBreak);
      5    return enc;
      6  },
      7  html: doc => {
      8    let enc = Cu.createDocumentEncoder("text/html");
      9    enc.init(doc, "text/html", Ci.nsIDocumentEncoder.OutputLFLineBreak);
     10    return enc;
     11  },
     12  htmlBasic: doc => {
     13    let enc = Cu.createDocumentEncoder("text/html");
     14    enc.init(
     15      doc,
     16      "text/html",
     17      Ci.nsIDocumentEncoder.OutputEncodeBasicEntities |
     18        Ci.nsIDocumentEncoder.OutputLFLineBreak
     19    );
     20    return enc;
     21  },
     22  xhtml: doc => {
     23    let enc = Cu.createDocumentEncoder("application/xhtml+xml");
     24    enc.init(
     25      doc,
     26      "application/xhtml+xml",
     27      Ci.nsIDocumentEncoder.OutputLFLineBreak
     28    );
     29    return enc;
     30  },
     31 };
     32 
     33 // Which characters should we encode as entities?  It depends on the serializer.
     34 const encodeAll = { html: true, htmlBasic: true, xhtml: true, xml: true };
     35 const encodeHTMLBasic = {
     36  html: false,
     37  htmlBasic: true,
     38  xhtml: false,
     39  xml: false,
     40 };
     41 const encodeXML = { html: false, htmlBasic: false, xhtml: true, xml: true };
     42 const encodeNone = { html: false, htmlBasic: false, xhtml: false, xml: false };
     43 const encodingInfoMap = new Map([
     44  // Basic sanity chars '<', '>', '"', '&' get encoded in all cases.
     45  ["<", encodeAll],
     46  [">", encodeAll],
     47  ["&", encodeAll],
     48  // nbsp is only encoded with the HTML encoder when encoding basic entities.
     49  ["\xA0", encodeHTMLBasic],
     50 ]);
     51 
     52 const encodingMap = new Map([
     53  ["<", "&lt;"],
     54  [">", "&gt;"],
     55  ["&", "&amp;"],
     56  // nbsp is only encoded with the HTML encoder when encoding basic entities.
     57  ["\xA0", "&nbsp;"],
     58 ]);
     59 
     60 function encodingInfoForChar(c) {
     61  var info = encodingInfoMap.get(c);
     62  if (info) {
     63    return info;
     64  }
     65  return encodeNone;
     66 }
     67 
     68 function encodingForChar(c, type) {
     69  var info = encodingInfoForChar(c);
     70  if (!info[type]) {
     71    return c;
     72  }
     73  return encodingMap.get(c);
     74 }
     75 
     76 const doc = new DOMParser().parseFromString("<root></root>", "text/xml");
     77 const root = doc.documentElement;
     78 for (let i = 0; i < 255; ++i) {
     79  let el = doc.createElement("span");
     80  el.textContent = String.fromCharCode(i);
     81  root.appendChild(el);
     82 }
     83 for (let type of ["xml", "xhtml", "htmlBasic", "html"]) {
     84  let str = encoders[type](doc).encodeToString();
     85  const prefix = "<root><span>";
     86  const suffix = "</span></root>";
     87  Assert.ok(str.startsWith(prefix), `${type} serialization starts correctly`);
     88  Assert.ok(str.endsWith(suffix), `${type} serialization ends correctly`);
     89  str = str.substring(prefix.length, str.length - suffix.length);
     90  let encodings = str.split("</span><span>");
     91  for (let i = 0; i < 255; ++i) {
     92    let c = String.fromCharCode(i);
     93    Assert.equal(
     94      encodingForChar(c, type),
     95      encodings[i],
     96      `${type} encoding of char ${i} is correct`
     97    );
     98  }
     99 }