Source code
Revision control
Copy as Markdown
Other Tools
Test Info:
- This WPT test may be referenced by the following Test IDs:
- /encoding/legacy-mb-schinese/gb18030/gb18030-encoder.html - WPT Dashboard Interop Dashboard
<!doctype html>
<meta charset=gb18030>
<script src=/resources/testharness.js></script>
<script src=/resources/testharnessreport.js></script>
<script src=resources/ranges.js></script>
<script>
const encode = (input, output, desc) => {
test(function() {
const a = document.createElement("a"); // <a> uses document encoding for URL's query
assert_equals(a.search.substr(1), output); // remove leading "?"
}, "gb18030 encoder: " + desc);
}
encode("s", "s", "very basic");
encode("\u20AC", "%A2%E3", "Euro");
encode("\u4E02", "%81@", "character");
encode("\uE4C6", "%A1@", "PUA");
encode("\uE4C5", "%FE%FE", "PUA #2");
encode("\uE5E5", "%26%2358853%3B", "PUA #3");
encode("\ud83d\udca9", "%949%DA3", "poo");
encode("\uE7C7", "%815%F47", "Ranges pointer special case");
encode("\uE7C8", "%836%C80", "legacy ICU special case 1");
encode("\u2026", "%A1%AD", "legacy ICU special case 2");
encode("\uFF5E", "%A1%AB", "legacy ICU special case 3");
// GB18030-2022
encode("\uFE10", "%A6%D9", "GB18030-2022 1");
encode("\uFE12", "%A6%DA", "GB18030-2022 2");
encode("\uFE11", "%A6%DB", "GB18030-2022 3");
encode("\uFE13", "%A6%DC", "GB18030-2022 4");
encode("\uFE14", "%A6%DD", "GB18030-2022 5");
encode("\uFE15", "%A6%DE", "GB18030-2022 6");
encode("\uFE16", "%A6%DF", "GB18030-2022 7");
encode("\uFE17", "%A6%EC", "GB18030-2022 8");
encode("\uFE18", "%A6%ED", "GB18030-2022 9");
encode("\uFE19", "%A6%F3", "GB18030-2022 10");
encode("\u9FB4", "%FEY", "GB18030-2022 11");
encode("\u9FB5", "%FEa", "GB18030-2022 12");
encode("\u9FB6", "%FEf", "GB18030-2022 13");
encode("\u9FB7", "%FEg", "GB18030-2022 14");
encode("\u9FB8", "%FEm", "GB18030-2022 15");
encode("\u9FB9", "%FE~", "GB18030-2022 16");
encode("\u9FBA", "%FE%90", "GB18030-2022 17");
encode("\u9FBB", "%FE%A0", "GB18030-2022 18");
encode("\uE78D", "%A6%D9", "GB18030-2022 19");
encode("\uE78E", "%A6%DA", "GB18030-2022 20");
encode("\uE78F", "%A6%DB", "GB18030-2022 21");
encode("\uE790", "%A6%DC", "GB18030-2022 22");
encode("\uE791", "%A6%DD", "GB18030-2022 23");
encode("\uE792", "%A6%DE", "GB18030-2022 24");
encode("\uE793", "%A6%DF", "GB18030-2022 25");
encode("\uE794", "%A6%EC", "GB18030-2022 26");
encode("\uE795", "%A6%ED", "GB18030-2022 27");
encode("\uE796", "%A6%F3", "GB18030-2022 28");
encode("\uE81E", "%FEY", "GB18030-2022 29");
encode("\uE826", "%FEa", "GB18030-2022 30");
encode("\uE82B", "%FEf", "GB18030-2022 31");
encode("\uE82C", "%FEg", "GB18030-2022 32");
encode("\uE832", "%FEm", "GB18030-2022 33");
encode("\uE843", "%FE~", "GB18030-2022 34");
encode("\uE854", "%FE%90", "GB18030-2022 35");
encode("\uE864", "%FE%A0", "GB18030-2022 36");
const upperCaseNibble = x => {
return Math.floor(x).toString(16).toUpperCase();
}
const encodePointer = pointer => {
const firstByte = Math.floor(pointer / 12600) + 0x81;
const thirdByte = Math.floor((pointer % 1260) / 10) + 0x81;
return "%"
+ upperCaseNibble(firstByte / 16)
+ upperCaseNibble(firstByte % 16)
+ String.fromCharCode(Math.floor((pointer % 12600) / 1260) + 0x30)
+ "%"
+ upperCaseNibble(thirdByte / 16)
+ upperCaseNibble(thirdByte % 16)
+ String.fromCharCode(pointer % 10 + 0x30);
}
let i = 0;
for (const range of ranges) {
encode(range[1], encodePointer(range[0]), "range " + i++);
}
</script>