Update to Unicode 18.0.0

.github/workflows/haskell.yml

@@ -58,9 +58,10 @@ jobs:
           - 9.4.8+macOS
           - 9.6.5
           - 9.8.4
-          - 9.10.2+ucd2haskell
-          - 9.12.2
-          - 9.14.1-alpha
+          - 9.10.3+ucd2haskell
+          - 9.12.4
+          - 9.14.1
+          # - 9.16.1-alpha
           - hlint
         include:
 
@@ -135,32 +136,39 @@ jobs:
             runner: ubuntu-latest
             ignore_error: false
 
-          - name: 9.10.2+ucd2haskell
-            ghc_version: 9.10.2
+          - name: 9.10.3+ucd2haskell
+            ghc_version: 9.10.3
             cabal_version: 3.12.1.0
             pack_options: CABAL_BUILD_OPTIONS="-f ucd2haskell"
             runner: ubuntu-latest
             ignore_error: false
 
-          - name: 9.12.2
-            ghc_version: 9.12.2
+          - name: 9.12.4
+            ghc_version: 9.12.4
             cabal_version: 3.14.2.0
             runner: ubuntu-latest
             ignore_error: false
 
-          - name: 9.14.1-alpha
-            ghc_version: head
-            cabal_version: 3.16.0.0
-            pack_options: >
-                GHCUP_GHC_OPTIONS="-u https://downloads.haskell.org/ghc/9.14.1-alpha1/ghc-9.14.0.20250819-x86_64-deb12-linux.tar.xz"
-                DISABLE_TEST=y
-                CABAL_BUILD_OPTIONS="--allow-newer=base,template-haskell"
+          - name: 9.14.1
+            ghc_version: 9.14.1
+            cabal_version: 3.16.1.0
             runner: ubuntu-latest
             ignore_error: false
 
+          # TODO: update to 9.16.1-alpha when available
+          # - name: 9.16.1-alpha
+          #   ghc_version: head
+          #   cabal_version: 3.16.1.0
+          #   pack_options: >
+          #       GHCUP_GHC_OPTIONS="-u https://downloads.haskell.org/ghc/9.16.1-alpha1/ghc-9.16.0.XXXXX-x86_64-deb12-linux.tar.xz"
+          #       DISABLE_TEST=y
+          #       CABAL_BUILD_OPTIONS="--allow-newer=base,template-haskell"
+          #   runner: ubuntu-latest
+          #   ignore_error: false
+
           # Template for release candidates
-          # - name: 9.10.0
-          #   ghc_version: 9.8.0.XXXXX
+          # - name: 9.16.0
+          #   ghc_version: 9.16.0.XXXXX
           #   ghcup_release_channel: "https://raw.githubusercontent.com/haskell/ghcup-metadata/master/ghcup-prereleases-0.0.7.yaml"
           #   runner: ubuntu-latest
           #   cabal_version: latest

README.md

@@ -12,7 +12,7 @@ This repository provides packages to use the
 
 The Haskell data structures are generated programmatically from the UCD files.
 The latest Unicode version supported by these libraries is
-[`17.0.0`](https://www.unicode.org/versions/Unicode17.0.0/).
+[`18.0.0`](https://www.unicode.org/versions/Unicode18.0.0/).
 
 ### `unicode-data`
 

experimental/icu/icu.cabal

@@ -14,6 +14,9 @@ copyright:           2023 Composewell Technologies and Contributors
 category:            Data,Text,Unicode
 stability:           Experimental
 build-type:          Simple
+extra-source-files:
+  cbits/icu.c
+  cbits/icu.h
 
 source-repository head
   type: git
@@ -48,9 +51,6 @@ common compile-options
                -fwarn-tabs
   default-language: Haskell2010
 
-extra-source-files:
-  cbits/icu.h
-
 library
   import: default-extensions, compile-options
   if flag(has-icu)

experimental/unicode-data-text/unicode-data-text.cabal

@@ -26,8 +26,9 @@ tested-with:         GHC==8.2.2
                    , GHC==9.4.8
                    , GHC==9.6.5
                    , GHC==9.8.4
-                   , GHC==9.10.2
-                   , GHC==9.12.2
+                   , GHC==9.10.3
+                   , GHC==9.12.4
+                   , GHC==9.14.1
 
 extra-doc-files:
     Changelog.md
@@ -68,7 +69,7 @@ library
   build-depends:
     base             >= 4.7   && < 4.23,
     text             >= 1.2.4 && < 2.2,
-    unicode-data     >= 0.8   && < 0.9
+    unicode-data     >= 0.9   && < 0.10
 
 test-suite test
   import: default-extensions, compile-options
@@ -82,7 +83,7 @@ test-suite test
     base             >= 4.7   && < 4.23,
     hspec            >= 2.0   && < 2.12,
     text             >= 1.2.4 && < 2.2,
-    unicode-data     >= 0.8   && < 0.9,
+    unicode-data     >= 0.9   && < 0.10,
     unicode-data-text
   build-tool-depends:
     hspec-discover:hspec-discover >= 2.0 && < 2.12
@@ -98,7 +99,7 @@ benchmark bench
     tasty-bench      >= 0.2.5 && < 0.6,
     tasty            >= 1.4.1 && < 1.6,
     text             >= 1.2.4 && < 2.2,
-    unicode-data     >= 0.8   && < 0.9,
+    unicode-data     >= 0.9   && < 0.10,
     unicode-data-text
   -- [NOTE] Recommendation of tasty-bench to reduce garbage collection noisiness
   ghc-options: -O2 -fdicts-strict -rtsopts -with-rtsopts=-A32m

ucd.sh

@@ -5,7 +5,7 @@
 # we used to generate them earlier are exactly the same as the ones we are
 # downloading. To ensure that verfication of the checksum is necessary.
 
-VERSION=17.0.0
+VERSION=18.0.0
 
 # When downloading fresh new version comment this out
 VERIFY_CHECKSUM=y
@@ -16,31 +16,31 @@ UCD_URL="https://www.unicode.org/Public/$VERSION/ucd"
 # $ find data/$VERSION/ -type f -print0 | xargs -0 sha256sum
 # Format: filename:checksum
 UCD_FILES="\
-    Blocks.txt:c0edefaf1a19771e830a82735472716af6bf3c3975f6c2a23ffbe2580fbbcb15\
-    CaseFolding.txt:ff8d8fefbf123574205085d6714c36149eb946d717a0c585c27f0f4ef58c4183\
-    DerivedCoreProperties.txt:24c7fed1195c482faaefd5c1e7eb821c5ee1fb6de07ecdbaa64b56a99da22c08\
-    DerivedNormalizationProps.txt:71fd6a206a2c0cdd41feb6b7f656aa31091db45e9cedc926985d718397f9e488\
-    NameAliases.txt:793f6f1e4d15fd90f05ae66460191dc4d75d1fea90136a25f30dd6a4cb950eac\
-    PropertyValueAliases.txt:64e9a5f76f7a1e8b5a47d6a1f9a26522a251208f5276bdfa1559dac7cf2e827a\
-    PropList.txt:130dcddcaadaf071008bdfce1e7743e04fdfbc910886f017d9f9ac931d8c64dd\
-    Scripts.txt:9f5e50d3abaee7d6ce09480f325c706f485ae3240912527e651954d2d6b035bf\
-    ScriptExtensions.txt:ec2107e58825a1586acee8e0911ce18260394ac8b87e535ca325f1ccbeb06bc6\
-    SpecialCasing.txt:efc25faf19de21b92c1194c111c932e03d2a5eaf18194e33f1156e96de4c9588\
-    UnicodeData.txt:2e1efc1dcb59c575eedf5ccae60f95229f706ee6d031835247d843c11d96470c\
-    extracted/DerivedCombiningClass.txt:191463abfbd202703c6fd6776a92a23ac44ec65e0476a7f95aa91ca492cef29b\
-    extracted/DerivedName.txt:019758bbe6c756c40fca6d505187ea660c5e195533e2ff2c841963a212c9d369\
-    extracted/DerivedNumericValues.txt:139b976bdc288be01c80f018523da769cf2845109b5a7f0f8a432db64bfedcfa"
+    Blocks.txt:2ba23579ee38e0b62b00a1a448f094eb54a823fb96109da685ad261b9bd493f2\
+    CaseFolding.txt:a004797658a457bec4dc11683e39f69249ea3b595b752dbea6721c4c9f587b0d\
+    DerivedCoreProperties.txt:b040c9b05cd49ca9ecced4066e667abf7513488fa726cc01bbd54948319bdea6\
+    DerivedNormalizationProps.txt:98ac7f67d985fe781e317f6182e885e94cabb0c314769e6dd73e48b226931ccd\
+    NameAliases.txt:3d5cf5e468901b080cd99adf2230061b748083705fe633db43ac8b73ec7a13da\
+    PropertyValueAliases.txt:19a6c4ab639d09a42881507ff1a1055286768f24e9b96d1e810b354a759ec030\
+    PropList.txt:ff65a2e6a57992504dad1251281eb9de7f0b223f73c7af9108466b5769141721\
+    Scripts.txt:66b1d21a528a1eb8bbfd48e05c2c0808435e90d1787cf5a69752dc88f6e941a0\
+    ScriptExtensions.txt:a5dfefc6660af2e34f47269915ca321f58574aa276de2acea9760cd94af96968\
+    SpecialCasing.txt:8538dea57c184f1ef3783885ea79677b10f6efa06423717157e63712f14d1ad2\
+    UnicodeData.txt:3a30a86cb25ccd95a63baffeabce026ccf59a19d2f7e705acc0a44c1326a5764\
+    extracted/DerivedCombiningClass.txt:10048c71ff6860cb707ee21cb7d401a1e50b1169e8e5613018ebca616ed8f5b1\
+    extracted/DerivedName.txt:fa05755dfa75395823ce0d8cc0508f645b6bbcf8f59a9468b80586d458b3cd5f\
+    extracted/DerivedNumericValues.txt:94e6c8a73e460c4196ab198aec2219cf3bbfd5aae6595f5d048311d41d20c9fb"
 
 # Security files:
 # - < 17.0.0: https://www.unicode.org/Public/security/$VERSION/$file)
 # - ≥ 17.0.0: https://www.unicode.org/Public/$VERSION/security/$file)
 SECURITY_URL="https://www.unicode.org/Public/$VERSION/security"
 # Format: filename:checksum
 SECURITY_FILES="\
-    IdentifierStatus.txt:617228a16da13850bf8af28b6cd08f5e9b6595d2eb60404fe6eee2c85b4e4a35\
-    IdentifierType.txt:924ac63faa97ed73420d6ac48d08279d90968c7da0502ab701e08bfbb9683c22\
-    confusables.txt:091c7f82fc39ef208faf8f94d29c244de99254675e09de163160c810d13ef22a\
-    intentional.txt:33738217c15c1a0df0b7a2cc0a0b50b27ebdca119ca11253440ec0102f05626b"
+    IdentifierStatus.txt:5863c7d99ca18f213c41c7318aa5528bebfb6d32ec0f1d5944e37192c119aebd\
+    IdentifierType.txt:16cd9c65392945904890bb2b64c686397438bcf29b1a47a0fc478a24c17d433a\
+    confusables.txt:fa913a52e5ee1106631b0c5489198e36970596fa2d2b3a36e9ed5dfb8f66e4c6\
+    intentional.txt:5b69cdfd7be6be45d51b9cf7ec799df91c1acc47c557d66c92a8d6623df78b0e"
 
 # Download the files
 

ucd2haskell/exe/UCD2Haskell/Modules/UnicodeData/DerivedNames.hs

@@ -99,6 +99,8 @@ genNamesModule moduleName = Fold step initial done
     egyptianHieroglyph = 0xf3
     khitan = 0xf4
     nushu = 0xf5
+    jurchen = 0xf6
+    seal = 0xf7
     hangul = 0x80
 
     rangePrefixes =
@@ -107,7 +109,9 @@ genNamesModule moduleName = Fold step initial done
         , "TANGUT IDEOGRAPH-"
         , "EGYPTIAN HIEROGLYPH-"
         , "KHITAN SMALL SCRIPT CHARACTER-"
-        , "NUSHU CHARACTER-" ]
+        , "NUSHU CHARACTER-"
+        , "JURCHEN CHARACTER-"
+        , "SEAL CHARACTER-" ]
 
     encodeName name
         | BS.take 28 name == "CJK COMPATIBILITY IDEOGRAPH-"   = ("", cjkCompat, 0, True)
@@ -116,13 +120,14 @@ genNamesModule moduleName = Fold step initial done
         | BS.take 20 name == "EGYPTIAN HIEROGLYPH-"           = ("", egyptianHieroglyph, 0, True)
         | BS.take 30 name == "KHITAN SMALL SCRIPT CHARACTER-" = ("", khitan, 0, True)
         | BS.take 16 name == "NUSHU CHARACTER-"               = ("", nushu, 0, True)
+        | BS.take 18 name == "JURCHEN CHARACTER-"             = ("", jurchen, 0, True)
+        | BS.take 15 name == "SEAL CHARACTER-"                = ("", seal, 0, True)
         | BS.take 16 name == "HANGUL SYLLABLE "               =
             let !name' = BS.drop 16 name; !len = BS.length name'
             in if len <= 12
                 then (name', hangul + len, len, True)
                 else error ("genNamesModule: cannot encode Hangul: " <> show len)
         | otherwise = let !len = BS.length name in (name, len, len, False)
-
     encodeOffset offset len = encode32LE offset' mempty
         where !offset' = len .|. (offset `shiftL` 8)
     encode32LE v acc
@@ -146,6 +151,8 @@ genNamesModule moduleName = Fold step initial done
         , "    , pattern EgyptianHieroglyph"
         , "    , pattern KhitanSmallScript"
         , "    , pattern NushuCharacter"
+        , "    , pattern JurchenCharacter"
+        , "    , pattern SealCharacter"
         , "    , pattern HangulSyllable"
         , "    ) where"
         , ""
@@ -200,6 +207,18 @@ genNamesModule moduleName = Fold step initial done
         , "pattern NushuCharacter :: Int#"
         , "pattern NushuCharacter = 0x" <> intHex nushu <> "#"
         , ""
+        , "-- | Jurchen Character. Used to test the length returned by 'name'."
+        , "--"
+        , "-- @since 0.8.0"
+        , "pattern JurchenCharacter :: Int#"
+        , "pattern JurchenCharacter = 0x" <> intHex jurchen <> "#"
+        , ""
+        , "-- | Seal Character. Used to test the length returned by 'name'."
+        , "--"
+        , "-- @since 0.8.0"
+        , "pattern SealCharacter :: Int#"
+        , "pattern SealCharacter = 0x" <> intHex seal <> "#"
+        , ""
         , "-- | Hangul syllable. Used to test the length returned by 'name'."
         , "--"
         , "-- @since 0.3.0"
@@ -230,6 +249,12 @@ genNamesModule moduleName = Fold step initial done
         , "-- * If length = @'NushuCharacter'@,"
         , "--   then the name is generated from the pattern “NUSHU CHARACTER-*”,"
         , "--   where * is the hexadecimal codepoint."
+        , "-- * If length = @'JurchenCharacter'@,"
+        , "--   then the name is generated from the pattern “JURCHEN CHARACTER-*”,"
+        , "--   where * is the hexadecimal codepoint."
+        , "-- * If length = @'SealCharacter'@,"
+        , "--   then the name is generated from the pattern “SEAL CHARACTER-*”,"
+        , "--   where * is the hexadecimal codepoint."
         , "-- * If length ≥ @'HangulSyllable'@,"
         , "--   then the name is generated by prepending “HANGUL SYLLABLE ”"
         , "--   to the returned string."

ucd2haskell/ucd2haskell.cabal

@@ -1,6 +1,6 @@
 cabal-version:       2.2
 name:                ucd2haskell
-version:             0.7.0
+version:             0.8.0
 synopsis:            Generate the code of the unicode-data* packages
 description:
     Internal package for the generation of @unicode-data*@ packages.
@@ -18,8 +18,9 @@ tested-with:         GHC==9.2.8
                    , GHC==9.4.8
                    , GHC==9.6.5
                    , GHC==9.8.4
-                   , GHC==9.10.2
-                   , GHC==9.12.2
+                   , GHC==9.10.3
+                   , GHC==9.12.4
+                   , GHC==9.14.1
 
 extra-doc-files:
     README.md

unicode-data-names/Changelog.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.7.0 (September 2026)
+
+- Updated to [Unicode 18.0.0](https://www.unicode.org/versions/Unicode18.0.0/).
+
 ## 0.6.0 (September 2025)
 
 - Updated to [Unicode 17.0.0](https://www.unicode.org/versions/Unicode17.0.0/).

unicode-data-names/README.md

@@ -12,7 +12,7 @@ There are 3 APIs:
 The Haskell data structures are generated programmatically from the
 Unicode character database (UCD) files. The latest Unicode version
 supported by this library is
-[`17.0.0`](https://www.unicode.org/versions/Unicode17.0.0/).
+[`18.0.0`](https://www.unicode.org/versions/Unicode18.0.0/).
 
 Please see the
 [Haddock documentation](https://hackage.haskell.org/package/unicode-data-names)

unicode-data-names/lib/Unicode/Char/General/Names.hs

@@ -92,6 +92,14 @@ name (C# c#) = case DerivedName.name c# of
             where
             !hex = showHex c#
             !n = 'N':'U':'S':'H':'U':' ':'C':'H':'A':'R':'A':'C':'T':'E':'R':'-':hex
+        DerivedName.JurchenCharacter -> Just n
+            where
+            !hex = showHex c#
+            !n = 'J':'U':'R':'C':'H':'E':'N':' ':'C':'H':'A':'R':'A':'C':'T':'E':'R':'-':hex
+        DerivedName.SealCharacter -> Just n
+            where
+            !hex = showHex c#
+            !n = 'S':'E':'A':'L':' ':'C':'H':'A':'R':'A':'C':'T':'E':'R':'-':hex
         _
             | isTrue# (len# <# DerivedName.HangulSyllable) -> let !n = unpack name# [] len# in Just n
             | otherwise ->

unicode-data-names/lib/Unicode/Char/General/Names/ByteString.hs

@@ -71,6 +71,12 @@ name (C# c#) = case DerivedName.name c# of
         DerivedName.NushuCharacter -> Just n
             where
             !n = mkNameFromTemplate# "NUSHU CHARACTER-"# 16# (ord# c#)
+        DerivedName.JurchenCharacter -> Just n
+            where
+            !n = mkNameFromTemplate# "JURCHEN CHARACTER-"# 18# (ord# c#)
+        DerivedName.SealCharacter -> Just n
+            where
+            !n = mkNameFromTemplate# "SEAL CHARACTER-"# 15# (ord# c#)
         _
             | isTrue# (len# <# DerivedName.HangulSyllable) ->
                 let !n = unpackAddr# name# len#

unicode-data-names/lib/Unicode/Char/General/Names/Text.hs

@@ -63,6 +63,12 @@ name (C# c#) = case DerivedName.name c# of
         DerivedName.NushuCharacter -> Just n
             where
             !n = mkNameFromTemplate "NUSHU CHARACTER-"# 16# (ord# c#)
+        DerivedName.JurchenCharacter -> Just n
+            where
+            !n = mkNameFromTemplate "JURCHEN CHARACTER-"# 18# (ord# c#)
+        DerivedName.SealCharacter -> Just n
+            where
+            !n = mkNameFromTemplate "SEAL CHARACTER-"# 15# (ord# c#)
         _
             | isTrue# (len# <# DerivedName.HangulSyllable) ->
                 let !n = unpackAddr# name# len#

unicode-data-names/lib/Unicode/Internal/Char/Names/Version.hs

@@ -13,8 +13,8 @@ module Unicode.Internal.Char.Names.Version (unicodeVersion) where
 import Data.Version (Version, makeVersion)
 
 -- | Version of the Unicode standard used by this package:
--- [17.0.0](https://www.unicode.org/versions/Unicode17.0.0/).
+-- [18.0.0](https://www.unicode.org/versions/Unicode18.0.0/).
 --
 -- @since 0.3.0
 unicodeVersion :: Version
-unicodeVersion = makeVersion [17,0,0]
+unicodeVersion = makeVersion [18,0,0]