Skip to content

[stdlib] Unicode 16 #78664

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Jan 21, 2025
Merged

[stdlib] Unicode 16 #78664

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
c6bcb03
Update Unicode generator data files to 16
Azoy Jan 14, 2025
b49466d
Update Unicode generators to support 16
Azoy Jan 14, 2025
4e08765
Update Unicode data files in stdlib
Azoy Jan 15, 2025
1f74aa1
Update grapheme breaking logic to support Unicode 16
Azoy Jan 15, 2025
d3146e3
Update Scalar names for Unicode 16
Azoy Jan 15, 2025
708d72d
Update tests for 6.1 Unicode 16 stdlib
Azoy Jan 15, 2025
6d5acec
Update embedded dead strip tests
Azoy Jan 16, 2025
29378d3
Update embedded unicode dead strip test v2
Azoy Jan 17, 2025
69f6df0
Remove consonant check
Azoy Jan 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion stdlib/private/StdlibUnicodeUnittest/StdlibUnicodeUnittest.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,7 +118,7 @@ func readInputNormalizationTest(index: Int) -> [NormalizationTest] {
public let normalizationTests = readInputNormalizationTest(index: 2)

// Native normalization in stdlib supporting Unicode 14
public let normalizationTests14 = readInputNormalizationTest(index: 3)
public let normalizationTestsNew = readInputNormalizationTest(index: 3)
#endif

public struct UTFTest {
Expand Down
28 changes: 21 additions & 7 deletions stdlib/private/StdlibUnicodeUnittest/UnicodeScalarProperties.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -691,13 +691,13 @@ public let caseFolding: [Unicode.Scalar: String] = {
//===----------------------------------------------------------------------===//

extension Unicode {
// Note: The `Script` enum includes the "meta" script type "Katakana_Or_Hiragana", which
// isn't defined by https://www.unicode.org/Public/UCD/latest/ucd/Scripts.txt,
// but is defined by https://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt.
// We may want to split it out, as it's the only case that is a union of
// other script types.

/// Character script types.
///
/// Note this includes the "meta" script type "Katakana_Or_Hiragana", which
/// isn't defined by https://www.unicode.org/Public/UCD/latest/ucd/Scripts.txt,
/// but is defined by https://www.unicode.org/Public/UCD/latest/ucd/PropertyValueAliases.txt.
/// We may want to split it out, as it's the only case that is a union of
/// other script types.
public enum Script: String, Hashable {
case adlam = "Adlam"
case ahom = "Ahom"
Expand Down Expand Up @@ -738,6 +738,7 @@ extension Unicode {
case elbasan = "Elbasan"
case elymaic = "Elymaic"
case ethiopic = "Ethiopic"
case garay = "Garay"
case georgian = "Georgian"
case glagolitic = "Glagolitic"
case gothic = "Gothic"
Expand All @@ -746,6 +747,7 @@ extension Unicode {
case gujarati = "Gujarati"
case gunjalaGondi = "Gunjala_Gondi"
case gurmukhi = "Gurmukhi"
case gurungKhema = "Gurung_Khema"
case han = "Han"
case hangul = "Hangul"
case hanifiRohingya = "Hanifi_Rohingya"
Expand Down Expand Up @@ -778,6 +780,7 @@ extension Unicode {
case lisu = "Lisu"
case lycian = "Lycian"
case lydian = "Lydian"
case kiratRai = "Kirat_Rai"
case mahajani = "Mahajani"
case makasar = "Makasar"
case malayalam = "Malayalam"
Expand Down Expand Up @@ -815,6 +818,7 @@ extension Unicode {
case oldSouthArabian = "Old_South_Arabian"
case oldTurkic = "Old_Turkic"
case oldUyghur = "Old_Uyghur"
case olOnal = "Ol_Onal"
case oriya = "Oriya"
case osage = "Osage"
case osmanya = "Osmanya"
Expand All @@ -837,6 +841,7 @@ extension Unicode {
case soraSompeng = "Sora_Sompeng"
case soyombo = "Soyombo"
case sundanese = "Sundanese"
case sunuwar = "Sunuwar"
case sylotiNagri = "Syloti_Nagri"
case syriac = "Syriac"
case tagalog = "Tagalog"
Expand All @@ -854,7 +859,9 @@ extension Unicode {
case tibetan = "Tibetan"
case tifinagh = "Tifinagh"
case tirhuta = "Tirhuta"
case todhri = "Todhri"
case toto = "Toto"
case tuluTigalari = "Tulu_Tigalari"
case ugaritic = "Ugaritic"
case unknown = "Unknown"
case vai = "Vai"
Expand Down Expand Up @@ -940,6 +947,7 @@ func classifyScriptProperty(
case "elba", "elbasan": return .elbasan
case "elym", "elymaic": return .elymaic
case "ethi", "ethiopic": return .ethiopic
case "gara", "garay": return .garay
case "geor", "georgian": return .georgian
case "glag", "glagolitic": return .glagolitic
case "gong", "gunjalagondi": return .gunjalaGondi
Expand All @@ -948,6 +956,7 @@ func classifyScriptProperty(
case "gran", "grantha": return .grantha
case "grek", "greek": return .greek
case "gujr", "gujarati": return .gujarati
case "gukh", "gurungkhema": return .gurungKhema
case "guru", "gurmukhi": return .gurmukhi
case "hang", "hangul": return .hangul
case "hani", "han": return .han
Expand All @@ -970,6 +979,7 @@ func classifyScriptProperty(
case "khoj", "khojki": return .khojki
case "kits", "khitansmallscript": return .khitanSmallScript
case "knda", "kannada": return .kannada
case "krai", "kiratrai": return .kiratRai
case "kthi", "kaithi": return .kaithi
case "lana", "taitham": return .taiTham
case "laoo", "lao": return .lao
Expand Down Expand Up @@ -997,7 +1007,7 @@ func classifyScriptProperty(
case "mtei", "meeteimayek": return .meeteiMayek
case "mult", "multani": return .multani
case "mymr", "myanmar": return .myanmar
case "nagm", "nagmundari": return .nagMundari
case "nagm", "nagmundari": return .nagMundari
case "nand", "nandinagari": return .nandinagari
case "narb", "oldnortharabian": return .oldNorthArabian
case "nbat", "nabataean": return .nabataean
Expand All @@ -1006,6 +1016,7 @@ func classifyScriptProperty(
case "nshu", "nushu": return .nushu
case "ogam", "ogham": return .ogham
case "olck", "olchiki": return .olChiki
case "onao", "olonal": return .olOnal
case "orkh", "oldturkic": return .oldTurkic
case "orya", "oriya": return .oriya
case "osge", "osage": return .osage
Expand Down Expand Up @@ -1037,6 +1048,7 @@ func classifyScriptProperty(
case "sora", "sorasompeng": return .soraSompeng
case "soyo", "soyombo": return .soyombo
case "sund", "sundanese": return .sundanese
case "sunu", "sunuwar": return .sunuwar
case "sylo", "sylotinagri": return .sylotiNagri
case "syrc", "syriac": return .syriac
case "tagb", "tagbanwa": return .tagbanwa
Expand All @@ -1054,7 +1066,9 @@ func classifyScriptProperty(
case "tibt", "tibetan": return .tibetan
case "tirh", "tirhuta": return .tirhuta
case "tnsa", "tangsa": return .tangsa
case "todr", "todhri": return .todhri
case "toto": return .toto
case "tutg", "tulutigalari": return .tuluTigalari
case "ugar", "ugaritic": return .ugaritic
case "vaii", "vai": return .vai
case "vith", "vithkuqi": return .vithkuqi
Expand Down
2 changes: 1 addition & 1 deletion stdlib/public/SwiftShims/swift/shims/UnicodeData.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ SWIFT_RUNTIME_STDLIB_INTERNAL
__swift_uint8_t _swift_stdlib_getGraphemeBreakProperty(__swift_uint32_t scalar);

SWIFT_RUNTIME_STDLIB_INTERNAL
__swift_bool _swift_stdlib_isLinkingConsonant(__swift_uint32_t scalar);
__swift_bool _swift_stdlib_isInCB_Consonant(__swift_uint32_t scalar);

//===----------------------------------------------------------------------===//
// Word Breaking
Expand Down
Loading