tor-browser

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

big5-encoder.html (1887B)


      1 <!doctype html>
      2 <meta charset=big5> <!-- test breaks if the server overrides this -->
      3 <script src=/resources/testharness.js></script>
      4 <script src=/resources/testharnessreport.js></script>
      5 <div id=log></div>
      6 <script>
      7 function encode(input, output, desc) {
      8   test(function() {
      9     var a = document.createElement("a"); // <a> uses document encoding for URL's query
     10     // Append and prepend X to test for off-by-one errors
     11     a.href = "https://example.com/?X" + input + "X";
     12     assert_equals(a.search.substr(1), "X" + output + "X"); // remove leading "?"
     13   }, "big5 encoder: " + desc);
     14 }
     15 
     16 encode("ab", "ab", "very basic")
     17 // edge cases
     18 encode("\u9EA6", "%26%2340614%3B", "Highest-pointer BMP character excluded from encoder");
     19 encode("\uD858\uDE6B", "%26%23156267%3B", "Highest-pointer character excluded from encoder");
     20 encode("\u3000", "%A1@", "Lowest-pointer character included in encoder");
     21 encode("\u20AC", "%A3%E1", "Euro; the highest-pointer character before a range of 30 unmapped pointers");
     22 encode("\u4E00", "%A4@", "The lowest-pointer character after the range of 30 unmapped pointers");
     23 encode("\uD85D\uDE07", "%C8%A4", "The highest-pointer character before a range of 41 unmapped pointers");
     24 encode("\uFFE2", "%C8%CD", "The lowest-pointer character after the range of 41 unmapped pointers");
     25 encode("\u79D4", "%FE%FE", "The last character in the index");
     26 // not in index
     27 encode("\u2603", "%26%239731%3B", "The canonical BMP test character that is not in the index");
     28 encode("\uD83D\uDCA9", "%26%23128169%3B", "The canonical astral test character that is not in the index");
     29 // duplicate low bits
     30 encode("\uD840\uDFB5", "%FDj", "A Plane 2 character whose low 16 bits match a BMP character that has a lower pointer");
     31 // prefer last
     32 encode("\u2550", "%F9%F9", "A duplicate-mapped code point that prefers the highest pointer in the encoder");
     33 </script>