firefox-main/testing/web-platform/tests/svg/struct/systemLanguage-parsing.html

Source code

Revision control

Copy as Markdown

Other Tools

Test Info:

<!DOCTYPE html>
<title>systemLanguage attribute is parsed as comma-separated tokens</title>
<meta name="assert" content="The systemLanguage attribute value is a set of comma-separated tokens per SVG2. Each token is trimmed of surrounding ASCII whitespace.">
<script src="/resources/testharness.js"></script>
<script src="/resources/testharnessreport.js"></script>
<script>
function parsesAs(input, expected, description) {
test(() => {
const el = document.createElementNS("http://www.w3.org/2000/svg", "text");
el.setAttribute("systemLanguage", input);
const list = el.systemLanguage;
assert_equals(list.length, expected.length, "token count");
for (let i = 0; i < expected.length; i++)
assert_equals(list.getItem(i), expected[i], `token ${i}`);
}, description);
}
// SVG2: "The value is a set of comma-separated tokens, each of which must be
// a Language-Tag value, as defined in BCP 47."
//
// HTML: "A set of comma-separated tokens is a string containing zero or more
// tokens each separated from the next by a single U+002C COMMA character (,),
// where tokens consist of any string of zero or more characters, neither
// beginning nor ending with ASCII whitespace, nor containing any U+002C COMMA
// characters (,), and optionally surrounded by ASCII whitespace."
parsesAs("en,fr,de", ["en", "fr", "de"],
"Comma-separated tokens are split into individual items");
parsesAs("en, fr, de", ["en", "fr", "de"],
"Whitespace after comma is stripped");
parsesAs("en ,fr ,de", ["en", "fr", "de"],
"Whitespace before comma is stripped");
parsesAs("en , fr , de", ["en", "fr", "de"],
"Whitespace around commas is stripped");
parsesAs(" en, fr ", ["en", "fr"],
"Leading and trailing whitespace on the value is stripped");
parsesAs(" \t\nen, fr\t\n ", ["en", "fr"],
"Tabs and newlines as leading/trailing whitespace are stripped");
parsesAs("en", ["en"],
"Single token without commas");
// "each of which must be a Language-Tag value, as defined in BCP 47"
// BCP 47 tags use hyphens for subtags (e.g. "en-US", "zh-Hans").
// Hyphens are not separators — only commas are.
parsesAs("en-US, zh-Hans, pt-BR", ["en-US", "zh-Hans", "pt-BR"],
"BCP 47 subtags are preserved within tokens");
// Edge cases: the parser does not validate token content.
// Invalid BCP 47 tags are stored as-is. They simply won't match
// any user language, so the element won't render.
// Double comma — per the HTML comma-separated token spec, the empty
// string between consecutive commas is a valid token.
// Example from spec: " a ,b,,d d " → ["a", "b", "", "d d"]
parsesAs("en,,fr", ["en", "", "fr"],
"Double comma produces an empty token between the two commas");
// "zero or more tokens" — an empty string yields an empty list.
// SVG2: "If a null string or empty string value is given to attribute
// 'systemLanguage', the attribute evaluates to 'false'."
parsesAs("", [""],
"Empty string results in a single empty token");
// A lone comma separates two empty tokens per the HTML spec.
parsesAs(",", ["", ""],
"A single comma separates two empty tokens");
// Numeric strings are not valid BCP 47 tags but are stored as tokens.
parsesAs("123, 456", ["123", "456"],
"Numeric tokens are parsed without validation");
// Arbitrary invalid strings are stored as tokens without validation.
parsesAs("not-a-lang, ???, @#$", ["not-a-lang", "???", "@#$"],
"Invalid language tags are stored as tokens without validation");
</script>