mirror of https://github.com/tc39/test262.git
Extract list of structurally invalid tags from invalid-tags.js.
This commit is contained in:
Ms2ger
Rick Waldron
parent
3b7a456ddb
commit
190cf5c730
|
|
@ -162,6 +162,66 @@ function getLocaleSupportInfo(Constructor) {
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Returns an array of strings for which IsStructurallyValidLanguageTag() returns false
|
||||||
|
*/
|
||||||
|
function getInvalidLanguageTags() {
|
||||||
|
var invalidLanguageTags = [
|
||||||
|
"", // empty tag
|
||||||
|
"i", // singleton alone
|
||||||
|
"x", // private use without subtag
|
||||||
|
"u", // extension singleton in first place
|
||||||
|
"419", // region code in first place
|
||||||
|
"u-nu-latn-cu-bob", // extension sequence without language
|
||||||
|
"hans-cmn-cn", // "hans" could theoretically be a 4-letter language code,
|
||||||
|
// but those can't be followed by extlang codes.
|
||||||
|
"cmn-hans-cn-u-u", // duplicate singleton
|
||||||
|
"cmn-hans-cn-t-u-ca-u", // duplicate singleton
|
||||||
|
"de-gregory-gregory", // duplicate variant
|
||||||
|
"*", // language range
|
||||||
|
"de-*", // language range
|
||||||
|
"中文", // non-ASCII letters
|
||||||
|
"en-ß", // non-ASCII letters
|
||||||
|
"ıd", // non-ASCII letters
|
||||||
|
|
||||||
|
// underscores in different parts of the language tag
|
||||||
|
"de_DE",
|
||||||
|
"DE_de",
|
||||||
|
"cmn_Hans",
|
||||||
|
"cmn-hans_cn",
|
||||||
|
"es_419",
|
||||||
|
"es-419-u-nu-latn-cu_bob",
|
||||||
|
"i_klingon",
|
||||||
|
"cmn-hans-cn-t-ca-u-ca-x_t-u",
|
||||||
|
"enochian_enochian",
|
||||||
|
"de-gregory_u-ca-gregory",
|
||||||
|
|
||||||
|
"en\u0000", // null-terminator sequence
|
||||||
|
" en", // leading whitespace
|
||||||
|
"en ", // trailing whitespace
|
||||||
|
"it-IT-Latn", // country before script tag
|
||||||
|
"de-u", // incomplete Unicode extension sequences
|
||||||
|
"de-u-",
|
||||||
|
"de-u-ca-",
|
||||||
|
"de-u-ca-gregory-",
|
||||||
|
"si-x", // incomplete private-use tags
|
||||||
|
"x-",
|
||||||
|
"x-y-",
|
||||||
|
];
|
||||||
|
|
||||||
|
// make sure the data above is correct
|
||||||
|
for (var i = 0; i < invalidLanguageTags.length; ++i) {
|
||||||
|
var invalidTag = invalidLanguageTags[i];
|
||||||
|
assert(
|
||||||
|
!isCanonicalizedStructurallyValidLanguageTag(invalidTag),
|
||||||
|
"Test data \"" + invalidTag + "\" is a canonicalized and structurally valid language tag."
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
return invalidLanguageTags;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* @description Tests whether locale is a String value representing a
|
* @description Tests whether locale is a String value representing a
|
||||||
* structurally valid and canonicalized BCP 47 language tag, as defined in
|
* structurally valid and canonicalized BCP 47 language tag, as defined in
|
||||||
|
|
|
||||||
|
|
@ -21,58 +21,7 @@ info: |
|
||||||
includes: [testIntl.js]
|
includes: [testIntl.js]
|
||||||
---*/
|
---*/
|
||||||
|
|
||||||
var invalidLanguageTags = [
|
var invalidLanguageTags = getInvalidLanguageTags();
|
||||||
"", // empty tag
|
|
||||||
"i", // singleton alone
|
|
||||||
"x", // private use without subtag
|
|
||||||
"u", // extension singleton in first place
|
|
||||||
"419", // region code in first place
|
|
||||||
"u-nu-latn-cu-bob", // extension sequence without language
|
|
||||||
"hans-cmn-cn", // "hans" could theoretically be a 4-letter language code,
|
|
||||||
// but those can't be followed by extlang codes.
|
|
||||||
"cmn-hans-cn-u-u", // duplicate singleton
|
|
||||||
"cmn-hans-cn-t-u-ca-u", // duplicate singleton
|
|
||||||
"de-gregory-gregory", // duplicate variant
|
|
||||||
"*", // language range
|
|
||||||
"de-*", // language range
|
|
||||||
"中文", // non-ASCII letters
|
|
||||||
"en-ß", // non-ASCII letters
|
|
||||||
"ıd", // non-ASCII letters
|
|
||||||
|
|
||||||
// underscores in different parts of the language tag
|
|
||||||
"de_DE",
|
|
||||||
"DE_de",
|
|
||||||
"cmn_Hans",
|
|
||||||
"cmn-hans_cn",
|
|
||||||
"es_419",
|
|
||||||
"es-419-u-nu-latn-cu_bob",
|
|
||||||
"i_klingon",
|
|
||||||
"cmn-hans-cn-t-ca-u-ca-x_t-u",
|
|
||||||
"enochian_enochian",
|
|
||||||
"de-gregory_u-ca-gregory",
|
|
||||||
|
|
||||||
"en\u0000", // null-terminator sequence
|
|
||||||
" en", // leading whitespace
|
|
||||||
"en ", // trailing whitespace
|
|
||||||
"it-IT-Latn", // country before script tag
|
|
||||||
"de-u", // incomplete Unicode extension sequences
|
|
||||||
"de-u-",
|
|
||||||
"de-u-ca-",
|
|
||||||
"de-u-ca-gregory-",
|
|
||||||
"si-x", // incomplete private-use tags
|
|
||||||
"x-",
|
|
||||||
"x-y-",
|
|
||||||
];
|
|
||||||
|
|
||||||
// make sure the data above is correct
|
|
||||||
for (var i = 0; i < invalidLanguageTags.length; ++i) {
|
|
||||||
var invalidTag = invalidLanguageTags[i];
|
|
||||||
assert(
|
|
||||||
!isCanonicalizedStructurallyValidLanguageTag(invalidTag),
|
|
||||||
"Test data \"" + invalidTag + "\" is a canonicalized and structurally valid language tag."
|
|
||||||
);
|
|
||||||
}
|
|
||||||
|
|
||||||
for (var i = 0; i < invalidLanguageTags.length; ++i) {
|
for (var i = 0; i < invalidLanguageTags.length; ++i) {
|
||||||
var invalidTag = invalidLanguageTags[i];
|
var invalidTag = invalidLanguageTags[i];
|
||||||
assert.throws(RangeError, function() {
|
assert.throws(RangeError, function() {
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue