diff --git a/Changelog.md b/Changelog.md --- a/Changelog.md +++ b/Changelog.md @@ -1,5 +1,9 @@ # Changelog +## 0.5.0 (September 2025) + +- Updated to [Unicode 16.0.0](https://www.unicode.org/versions/Unicode16.0.0/). + ## 0.4.0 (July 2024) - Updated to [Unicode 15.1.0](https://www.unicode.org/versions/Unicode15.1.0/). diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ The Haskell data structures are generated programmatically from the Unicode character database (UCD) files. The latest Unicode version supported by this library is -[`15.1.0`](https://www.unicode.org/versions/Unicode15.1.0/). +[`16.0.0`](https://www.unicode.org/versions/Unicode16.0.0/). Please see the [Haddock documentation](https://hackage.haskell.org/package/unicode-data-names) diff --git a/lib/Unicode/Char/General/Names.hs b/lib/Unicode/Char/General/Names.hs --- a/lib/Unicode/Char/General/Names.hs +++ b/lib/Unicode/Char/General/Names.hs @@ -80,6 +80,18 @@ where !hex = showHex c# !n = 'T':'A':'N':'G':'U':'T':' ':'I':'D':'E':'O':'G':'R':'A':'P':'H':'-':hex + DerivedName.EgyptianHieroglyph -> Just n + where + !hex = showHex c# + !n = 'E':'G':'Y':'P':'T':'I':'A':'N':' ':'H':'I':'E':'R':'O':'G':'L':'Y':'P':'H':'-':hex + DerivedName.KhitanSmallScript -> Just n + where + !hex = showHex c# + !n = 'K':'H':'I':'T':'A':'N':' ':'S':'M':'A':'L':'L':' ':'S':'C':'R':'I':'P':'T':' ':'C':'H':'A':'R':'A':'C':'T':'E':'R':'-':hex + DerivedName.NushuCharacter -> Just n + where + !hex = showHex c# + !n = 'N':'U':'S':'H':'U':' ':'C':'H':'A':'R':'A':'C':'T':'E':'R':'-':hex _ | isTrue# (len# <# DerivedName.HangulSyllable) -> let !n = unpack name# [] len# in Just n | otherwise -> diff --git a/lib/Unicode/Char/General/Names/ByteString.hs b/lib/Unicode/Char/General/Names/ByteString.hs --- a/lib/Unicode/Char/General/Names/ByteString.hs +++ b/lib/Unicode/Char/General/Names/ByteString.hs @@ -62,6 +62,15 @@ DerivedName.TangutIdeograph -> Just n where !n = mkNameFromTemplate# "TANGUT IDEOGRAPH-"# 17# (ord# c#) + DerivedName.EgyptianHieroglyph -> Just n + where + !n = mkNameFromTemplate# "EGYPTIAN HIEROGLYPH-"# 20# (ord# c#) + DerivedName.KhitanSmallScript -> Just n + where + !n = mkNameFromTemplate# "KHITAN SMALL SCRIPT CHARACTER-"# 30# (ord# c#) + DerivedName.NushuCharacter -> Just n + where + !n = mkNameFromTemplate# "NUSHU CHARACTER-"# 16# (ord# c#) _ | isTrue# (len# <# DerivedName.HangulSyllable) -> let !n = unpackAddr# name# len# diff --git a/lib/Unicode/Char/General/Names/Text.hs b/lib/Unicode/Char/General/Names/Text.hs --- a/lib/Unicode/Char/General/Names/Text.hs +++ b/lib/Unicode/Char/General/Names/Text.hs @@ -54,6 +54,15 @@ DerivedName.TangutIdeograph -> Just n where !n = mkNameFromTemplate "TANGUT IDEOGRAPH-"# 17# (ord# c#) + DerivedName.EgyptianHieroglyph -> Just n + where + !n = mkNameFromTemplate "EGYPTIAN HIEROGLYPH-"# 20# (ord# c#) + DerivedName.KhitanSmallScript -> Just n + where + !n = mkNameFromTemplate "KHITAN SMALL SCRIPT CHARACTER-"# 30# (ord# c#) + DerivedName.NushuCharacter -> Just n + where + !n = mkNameFromTemplate "NUSHU CHARACTER-"# 16# (ord# c#) _ | isTrue# (len# <# DerivedName.HangulSyllable) -> let !n = unpackAddr# name# len# diff --git a/lib/Unicode/Internal/Char/Names/Version.hs b/lib/Unicode/Internal/Char/Names/Version.hs --- a/lib/Unicode/Internal/Char/Names/Version.hs +++ b/lib/Unicode/Internal/Char/Names/Version.hs @@ -13,8 +13,8 @@ import Data.Version (Version, makeVersion) -- | Version of the Unicode standard used by this package: --- [15.1.0](https://www.unicode.org/versions/Unicode15.1.0/). +-- [16.0.0](https://www.unicode.org/versions/Unicode16.0.0/). -- -- @since 0.3.0 unicodeVersion :: Version -unicodeVersion = makeVersion [15,1,0] +unicodeVersion = makeVersion [16,0,0] diff --git a/lib/Unicode/Internal/Char/UnicodeData/DerivedName.hs b/lib/Unicode/Internal/Char/UnicodeData/DerivedName.hs # file too large to diff: lib/Unicode/Internal/Char/UnicodeData/DerivedName.hs diff --git a/lib/Unicode/Internal/Char/UnicodeData/NameAliases.hs b/lib/Unicode/Internal/Char/UnicodeData/NameAliases.hs --- a/lib/Unicode/Internal/Char/UnicodeData/NameAliases.hs +++ b/lib/Unicode/Internal/Char/UnicodeData/NameAliases.hs @@ -1,4 +1,4 @@ --- autogenerated from https://www.unicode.org/Public/15.1.0/ucd/NameAliases.txt +-- autogenerated from https://www.unicode.org/Public/16.0.0/ucd/NameAliases.txt -- | -- Module : Unicode.Internal.Char.UnicodeData.NameAliases -- Copyright : (c) 2022 Composewell Technologies and Contributors @@ -197,12 +197,16 @@ '\xFEFF'# -> "\0\0\5\0\22\15BYTE ORDER MARK\0\3BOM\6ZWNBSP\0\0"# '\x122D4'# -> "\5\0\0\0\0\24CUNEIFORM SIGN NU11 TENU\0\0"# '\x122D5'# -> "\5\0\0\0\0\42CUNEIFORM SIGN NU11 OVER NU11 BUR OVER BUR\0\0"# + '\x12327'# -> "\5\0\0\0\0\20CUNEIFORM SIGN KALAM\0\0"# + '\x1680B'# -> "\5\0\0\0\0\30BAMUM LETTER PHASE-A MAEMGBIEE\0\0"# '\x16E56'# -> "\5\0\0\0\0\28MEDEFAIDRIN CAPITAL LETTER H\0\0"# '\x16E57'# -> "\5\0\0\0\0\29MEDEFAIDRIN CAPITAL LETTER NG\0\0"# '\x16E76'# -> "\5\0\0\0\0\26MEDEFAIDRIN SMALL LETTER H\0\0"# '\x16E77'# -> "\5\0\0\0\0\27MEDEFAIDRIN SMALL LETTER NG\0\0"# '\x1B001'# -> "\5\0\0\0\0\21HENTAIGANA LETTER E-1\0\0"# '\x1D0C5'# -> "\5\0\0\0\0\52BYZANTINE MUSICAL SYMBOL FTHORA SKLIRON CHROMA VASIS\0\0"# + '\x1E899'# -> "\5\0\0\0\0\31MENDE KIKAKUI SYLLABLE M172 MBO\0\0"# + '\x1E89A'# -> "\5\0\0\0\0\32MENDE KIKAKUI SYLLABLE M174 MBOO\0\0"# '\xE0100'# -> "\0\0\0\0\5\4VS17\0\0"# '\xE0101'# -> "\0\0\0\0\5\4VS18\0\0"# '\xE0102'# -> "\0\0\0\0\5\4VS19\0\0"# diff --git a/test/ICU/NamesSpec.hs b/test/ICU/NamesSpec.hs --- a/test/ICU/NamesSpec.hs +++ b/test/ICU/NamesSpec.hs @@ -57,6 +57,8 @@ #endif where ourUnicodeVersion = versionBranch U.unicodeVersion + theirUnicodeVersion = take 3 (versionBranch ICU.unicodeVersion) + versionMismatch = ourUnicodeVersion /= theirUnicodeVersion showCodePoint c = ("U+" ++) . fmap U.toUpper . showHex (U.ord c) -- There is no feature to display warnings other than `trace`, so @@ -85,6 +87,8 @@ -- Unicode version mismatch: char is not mapped in one of the libs: -- add warning. | ageMismatch c = acc{warnings=c : warnings acc} + -- Unicode version mismatch + | versionMismatch = acc{warnings=c : warnings acc} -- Error | otherwise = let !msg = mconcat diff --git a/test/Unicode/Char/General/NamesSpec.hs b/test/Unicode/Char/General/NamesSpec.hs --- a/test/Unicode/Char/General/NamesSpec.hs +++ b/test/Unicode/Char/General/NamesSpec.hs @@ -50,9 +50,12 @@ -- Name with correction name '\x1D0C5' `shouldBe` Just "BYZANTINE MUSICAL SYMBOL FHTORA SKLIRON CHROMA VASIS" name '\x1f41d' `shouldBe` Just "HONEYBEE" - -- Name generated using pattern (example from UCD file) + -- Names generated using pattern (example from UCD file) + name '\x13460' `shouldBe` Just "EGYPTIAN HIEROGLYPH-13460" + name '\x18B00' `shouldBe` Just "KHITAN SMALL SCRIPT CHARACTER-18B00" + name '\x18CFF' `shouldBe` Just "KHITAN SMALL SCRIPT CHARACTER-18CFF" name '\x2f89f' `shouldBe` Just "CJK COMPATIBILITY IDEOGRAPH-2F89F" - -- Last name defined, as of Unicode 15.0.0 + -- Last name defined, as of Unicode 16.0.0 name '\xe01ef' `shouldBe` Just "VARIATION SELECTOR-256" name maxBound `shouldBe` Nothing it "correctedName: Test some characters" do diff --git a/unicode-data-names.cabal b/unicode-data-names.cabal --- a/unicode-data-names.cabal +++ b/unicode-data-names.cabal @@ -1,6 +1,6 @@ cabal-version: 2.2 name: unicode-data-names -version: 0.4.0 +version: 0.5.0 synopsis: Unicode characters names and aliases description: @unicode-data-names@ provides Haskell APIs to access the Unicode @@ -9,7 +9,7 @@ . The Haskell data structures are generated programmatically from the UCD files. The latest Unicode version supported by this library is - @@. + @@. homepage: http://github.com/composewell/unicode-data bug-reports: https://github.com/composewell/unicode-data/issues license: Apache-2.0 @@ -20,8 +20,7 @@ category: Data,Text,Unicode stability: Experimental build-type: Simple -tested-with: GHC==8.0.2 - , GHC==8.2.2 +tested-with: GHC==8.2.2 , GHC==8.4.4 , GHC==8.6.5 , GHC==8.8.4 @@ -30,8 +29,9 @@ , GHC==9.2.8 , GHC==9.4.8 , GHC==9.6.5 - , GHC==9.8.2 - , GHC==9.10.1 + , GHC==9.8.4 + , GHC==9.10.2 + , GHC==9.12.2 extra-doc-files: Changelog.md @@ -104,8 +104,8 @@ hs-source-dirs: lib build-depends: - base >= 4.7 && < 4.21, - unicode-data >= 0.6 && < 0.7 + base >= 4.7 && < 4.23, + unicode-data >= 0.7 && < 0.8 -- Support for raw string literals unpacking is included in base ≥ 4.15 if impl(ghc < 9.0.0) build-depends: @@ -130,9 +130,9 @@ other-modules: Unicode.Char.General.NamesSpec build-depends: - base >= 4.7 && < 4.21 + base >= 4.7 && < 4.23 , hspec >= 2.0 && < 2.12 - , unicode-data >= 0.6 && < 0.7 + , unicode-data >= 0.7 && < 0.8 , unicode-data-names if flag(has-text) cpp-options: -DHAS_TEXT @@ -173,11 +173,11 @@ hs-source-dirs: bench main-is: Main.hs build-depends: - base >= 4.7 && < 4.21, + base >= 4.7 && < 4.23, deepseq >= 1.1 && < 1.6, - tasty-bench >= 0.2.5 && < 0.4, + tasty-bench >= 0.2.5 && < 0.5, tasty >= 1.4.1 && < 1.6, - unicode-data >= 0.6 && < 0.7, + unicode-data >= 0.7 && < 0.8, unicode-data-names if flag(has-text) cpp-options: -DHAS_TEXT