Update to Unicode 15.0.0 (#92)

* Update ucd.sh

* Regenerate files

* Update references to Unicode version

* Bump packages versions

* Restrict comparison to base to compatible GHC

* Fix bounds of unicode-data

* Add missing packages to stack.yaml

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
-[`14.0.0`](https://www.unicode.org/versions/Unicode14.0.0/).
+[`15.0.0`](https://www.unicode.org/versions/Unicode15.0.0/).
 
 ### `unicode-data`
 

experimental/unicode-data-text/test/Unicode/Text/CaseSpec.hs

@@ -22,6 +22,7 @@ does not match the version of this package.
 | 9.0.[1-2]   | 4.15.0         | 12.1            |
 | 9.2.[1-4]   | 4.16.0         | 14.0            |
 | 9.4.[1-2]   | 4.17.0         | 14.0            |
+| 9.6.1       | 4.18.0         | 15.0            |
 +-------------+----------------+-----------------+
 -}
 

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

@@ -68,7 +68,7 @@ library
   build-depends:
     base             >= 4.7   && < 4.18,
     text             >= 1.2.4 && < 2.1,
-    unicode-data     >= 0.3   && < 0.4
+    unicode-data     >= 0.3   && < 0.5
 
 test-suite test
   import: default-extensions, compile-options
@@ -85,7 +85,7 @@ test-suite test
     unicode-data-text
   build-tool-depends:
     hspec-discover:hspec-discover >= 2.0 && < 2.11
-  if impl(ghc >= 9.2.1)
+  if impl(ghc >= 9.5.1)
     cpp-options: -DCOMPATIBLE_GHC_UNICODE
   default-language: Haskell2010
 
@@ -100,6 +100,6 @@ benchmark bench
     tasty-bench      >= 0.2.5 && < 0.4,
     tasty            >= 1.4.1,
     text             >= 1.2.4 && < 2.1,
-    unicode-data     >= 0.3   && < 0.4,
+    unicode-data     >= 0.3   && < 0.5,
     unicode-data-text
   ghc-options: -O2 -fdicts-strict -rtsopts

stack.yaml

@@ -2,6 +2,9 @@ resolver: lts-18.18
 packages:
 - './unicode-data'
 - './unicode-data-names'
+- './unicode-data-scripts'
+- './unicode-data-security'
+- './experimental/unicode-data-text'
 extra-deps:
 - streamly-0.8.0
 flags:

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=14.0.0
+VERSION=15.0.0
 
 # When downloading fresh new version comment this out
 VERIFY_CHECKSUM=y
@@ -14,29 +14,29 @@ VERIFY_CHECKSUM=y
 UCD_URL="https://www.unicode.org/Public/$VERSION/ucd"
 # Filename:checksum
 UCD_FILES="\
-  Blocks.txt:598870dddef7b34b5a972916528c456aff2765b79cd4f9647fb58ceb767e7f17 \
-  CaseFolding.txt:a566cd48687b2cd897e02501118b2413c14ae86d318f9abbbba97feb84189f0f \
-  DerivedCoreProperties.txt:e3eddd7d469cd1b0feed7528defad1a1cc7c6a9ceb0ae4446a6d10921ed2e7bc \
-  DerivedNormalizationProps.txt:b2c444c20730b097787fdf50bd7d6dd3fc5256ab8084f5b35b11c8776eca674c \
-  NameAliases.txt:14b3b677d33f95c51423dce6eef4a6a28b4b160451ecedee4b91edb6745cf4a3 \
-  PropertyValueAliases.txt:eb755757e20b72b330b2948df3cf2ff7adb0e31bb060140dc09dafb132ace2cd \
-  PropList.txt:6bddfdb850417a5bee6deff19290fd1b138589909afb50f5a049f343bf2c6722 \
-  Scripts.txt:52db475c4ec445e73b0b16915448c357614946ad7062843c563e00d7535c6510 \
-  ScriptExtensions.txt:d37eedf63ff9c48bac863d5f76862373d6cf5269fd21253d499e2430d638c01d \
-  SpecialCasing.txt:c667b45908fd269af25fd55d2fc5bbc157fb1b77675936e25c513ce32e080334 \
-  UnicodeData.txt:36018e68657fdcb3485f636630ffe8c8532e01c977703d2803f5b89d6c5feafb \
-  extracted/DerivedCombiningClass.txt:12b0c3af9b600b49488d66545a3e7844ea980809627201bf9afeebe1c9f16f4e \
-  extracted/DerivedName.txt:fef3e11514ba152f0d38a09f8018c03a825f846dbb912334c1e5c9fb29392a02 \
-  extracted/DerivedNumericValues.txt:11075771b112e8e7ccf6ffa637c4c91eadc3ef3db0517b24e605df8fd3624239"
+  Blocks.txt:529dc5d0f6386d52f2f56e004bbfab48ce2d587eea9d38ba546c4052491bd820 \
+  CaseFolding.txt:cdd49e55eae3bbf1f0a3f6580c974a0263cb86a6a08daa10fbf705b4808a56f7 \
+  DerivedCoreProperties.txt:d367290bc0867e6b484c68370530bdd1a08b6b32404601b8c7accaf83e05628d \
+  DerivedNormalizationProps.txt:d5687a48c95c7d6e1ec59cb29c0f2e8b052018eb069a4371b7368d0561e12a29 \
+  NameAliases.txt:3e39509e8fae3e5d50ba73759d0b97194501d14a9c63107a6372a46b38be18e8 \
+  PropertyValueAliases.txt:13a7666843abea5c6b7eb8c057c57ab9bb2ba96cfc936e204224dd67d71cafad \
+  PropList.txt:e05c0a2811d113dae4abd832884199a3ea8d187ee1b872d8240a788a96540bfd \
+  Scripts.txt:cca85d830f46aece2e7c1459ef1249993dca8f2e46d51e869255be140d7ea4b0 \
+  ScriptExtensions.txt:7e07313d9d0bee42220c476b64485995130ae30917bbcf7780b602d677d7e33f \
+  SpecialCasing.txt:78b29c64b5840d25c11a9f31b665ee551b8a499eca6c70d770fcad7dd710f494 \
+  UnicodeData.txt:806e9aed65037197f1ec85e12be6e8cd870fc5608b4de0fffd990f689f376a73 \
+  extracted/DerivedCombiningClass.txt:ca54f6360cd288ad92113415bf1f77749015abe11cbd6798d21f7fa81f04205d \
+  extracted/DerivedName.txt:f76288153e20de185a40f7ee6e0e365f3c6c80e9e3019b5aa0afc8ac2c1b15f2 \
+  extracted/DerivedNumericValues.txt:6bd30f385f3baf3ab5d5308c111a81de87bea5f494ba0ba69e8ab45263b8c34d"
 
 # Security files (https://www.unicode.org/Public/security/$VERSION/$file)
 SECURITY_URL="https://www.unicode.org/Public/security/$VERSION"
 # Filename:checksum
 SECURITY_FILES="\
-    IdentifierStatus.txt:3f3f368fccdb37f350ecedc20b37fa71ab31c04e847884c77780d34283539f73 \
-    IdentifierType.txt:45a150c23961b58d7784704af6c4daccd6517d97b6489e53d13bbdbf9e4f065f \
-    confusables.txt:f901938af166c3afa471bd10c224b0979cd024340f290649e16b29f779d48bfe \
-    intentional.txt:42243c12a2e20546e836576e3091a5a5db2c1fc506899b1d8b56f7b6eab77cb3"
+    IdentifierStatus.txt:fd5c5e510914a2018e092bc51ea653bd2bfcf7daa116a346f09179a0f74704b0 \
+    IdentifierType.txt:71e95d5811999776a39c33a9149e5bf3c3311217a36b89005c678f34f08debc0 \
+    confusables.txt:2b10130885c3370b101c52d7baedc452ab7f0e257b86c1e52ee657ecfc29ce64 \
+    intentional.txt:4550bcc406b5ce3b1a40ff857a3f8b703ea0c868c35f2f7c93d86bfb733215f9"
 
 # Download the files
 

unicode-data-names/Changelog.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.2.0 (September 2022)
+
+- Update to [Unicode 15.0.0](https://www.unicode.org/versions/Unicode15.0.0/).
+
 ## 0.1.0 (June 2022)
 
 - Initial release

unicode-data-names/README.md

@@ -7,7 +7,7 @@ character names and aliases from the
 The Haskell data structures are generated programmatically from the
 Unicode character database (UCD) files. The latest Unicode version
 supported by this library is
-[`14.0.0`](https://www.unicode.org/versions/Unicode14.0.0/).
+[`15.0.0`](https://www.unicode.org/versions/Unicode15.0.0/).
 
 Please see the
 [Haddock documentation](https://hackage.haskell.org/package/unicode-data-names)

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

@@ -6,7 +6,7 @@
 -- Stability   : experimental
 --
 -- Unicode character names and name aliases.
--- See Unicode standard 14.0.0, section 4.8.
+-- See Unicode standard 15.0.0, section 4.8.
 --
 -- @since 0.1.0
 
@@ -84,7 +84,7 @@ nameAliasesWithTypes
   = fmap (fmap (fmap unpack))
   . NameAliases.nameAliasesWithTypes
 
--- Note: names are ASCII. See Unicode Standard 14.0.0, section 4.8.
+-- Note: names are ASCII. See Unicode Standard 15.0.0, section 4.8.
 {-# INLINE unpack #-}
 unpack :: CString -> String
 unpack = unsafePerformIO . peekCAString

unicode-data-names/lib/Unicode/Internal/Char/UnicodeData/NameAliases.hs

@@ -1,4 +1,4 @@
--- autogenerated from https://www.unicode.org/Public/14.0.0/ucd/NameAliases.txt
+-- autogenerated from https://www.unicode.org/Public/15.0.0/ucd/NameAliases.txt
 -- |
 -- Module      : Unicode.Internal.Char.UnicodeData.NameAliases
 -- Copyright   : (c) 2022 Composewell Technologies and Contributors
@@ -17,7 +17,7 @@ import Data.Maybe (fromMaybe)
 import Foreign.C.String (CString)
 import GHC.Exts (Ptr(..))
 
--- | Type of name alias. See Unicode Standard 14.0.0, section 4.8.
+-- | Type of name alias. See Unicode Standard 15.0.0, section 4.8.
 --
 -- @since 0.1.0
 data NameAliasType
@@ -86,7 +86,7 @@ nameAliasesWithTypes = \case
   '\x0016' -> [(Control,[Ptr "SYNCHRONOUS IDLE\0"#]),(Abbreviation,[Ptr "SYN\0"#])]
   '\x0017' -> [(Control,[Ptr "END OF TRANSMISSION BLOCK\0"#]),(Abbreviation,[Ptr "ETB\0"#])]
   '\x0018' -> [(Control,[Ptr "CANCEL\0"#]),(Abbreviation,[Ptr "CAN\0"#])]
-  '\x0019' -> [(Control,[Ptr "END OF MEDIUM\0"#]),(Abbreviation,[Ptr "EOM\0"#])]
+  '\x0019' -> [(Control,[Ptr "END OF MEDIUM\0"#]),(Abbreviation,[Ptr "EOM\0"#,Ptr "EM\0"#])]
   '\x001a' -> [(Control,[Ptr "SUBSTITUTE\0"#]),(Abbreviation,[Ptr "SUB\0"#])]
   '\x001b' -> [(Control,[Ptr "ESCAPE\0"#]),(Abbreviation,[Ptr "ESC\0"#])]
   '\x001c' -> [(Control,[Ptr "INFORMATION SEPARATOR FOUR\0"#,Ptr "FILE SEPARATOR\0"#]),(Abbreviation,[Ptr "FS\0"#])]
@@ -132,6 +132,7 @@ nameAliasesWithTypes = \case
   '\x01a2' -> [(Correction,[Ptr "LATIN CAPITAL LETTER GHA\0"#])]
   '\x01a3' -> [(Correction,[Ptr "LATIN SMALL LETTER GHA\0"#])]
   '\x034f' -> [(Abbreviation,[Ptr "CGJ\0"#])]
+  '\x0616' -> [(Correction,[Ptr "ARABIC SMALL HIGH LIGATURE ALEF WITH YEH BARREE\0"#])]
   '\x061c' -> [(Abbreviation,[Ptr "ALM\0"#])]
   '\x0709' -> [(Correction,[Ptr "SYRIAC SUBLINEAR COLON SKEWED LEFT\0"#])]
   '\x0cde' -> [(Correction,[Ptr "KANNADA LETTER LLLA\0"#])]
@@ -149,6 +150,7 @@ nameAliasesWithTypes = \case
   '\x180d' -> [(Abbreviation,[Ptr "FVS3\0"#])]
   '\x180e' -> [(Abbreviation,[Ptr "MVS\0"#])]
   '\x180f' -> [(Abbreviation,[Ptr "FVS4\0"#])]
+  '\x1bbd' -> [(Correction,[Ptr "SUNDANESE LETTER ARCHAIC I\0"#])]
   '\x200b' -> [(Abbreviation,[Ptr "ZWSP\0"#])]
   '\x200c' -> [(Abbreviation,[Ptr "ZWNJ\0"#])]
   '\x200d' -> [(Abbreviation,[Ptr "ZWJ\0"#])]

unicode-data-names/test/Unicode/Char/General/NamesSpec.hs

@@ -28,7 +28,7 @@ spec = do
         name '\x1f41d' `shouldBe` Just "HONEYBEE"
         -- Name generated using pattern (example from UCD file)
         name '\x2f89f' `shouldBe` Just "CJK COMPATIBILITY IDEOGRAPH-2F89F"
-        -- Last name defined, as of Unicode 14.0.0
+        -- Last name defined, as of Unicode 15.0.0
         name '\xe01ef' `shouldBe` Just "VARIATION SELECTOR-256"
         name maxBound  `shouldBe` Nothing
     it "correctedName: Test some characters" do
@@ -48,7 +48,7 @@ spec = do
         correctedName '\x1f41d' `shouldBe` Just "HONEYBEE"
         -- Name generated using pattern (example from UCD file)
         correctedName '\x2f89f' `shouldBe` Just "CJK COMPATIBILITY IDEOGRAPH-2F89F"
-        -- Last name defined, as of Unicode 14.0.0
+        -- Last name defined, as of Unicode 15.0.0
         correctedName '\xe01ef' `shouldBe` Just "VARIATION SELECTOR-256"
         correctedName maxBound  `shouldBe` Nothing
     it "nameOrAlias: Test some characters" do
@@ -68,7 +68,7 @@ spec = do
         nameOrAlias '\x1f41d' `shouldBe` Just "HONEYBEE"
         -- Name generated using pattern (example from UCD file)
         nameOrAlias '\x2f89f' `shouldBe` Just "CJK COMPATIBILITY IDEOGRAPH-2F89F"
-        -- Last name defined, as of Unicode 14.0.0
+        -- Last name defined, as of Unicode 15.0.0
         nameOrAlias '\xe01ef' `shouldBe` Just "VARIATION SELECTOR-256"
         nameOrAlias maxBound  `shouldBe` Nothing
     it "Every defined character has at least a name or an alias" do

unicode-data-names/unicode-data-names.cabal

@@ -1,6 +1,6 @@
 cabal-version:       2.2
 name:                unicode-data-names
-version:             0.1.0
+version:             0.2.0
 synopsis:            Unicode characters names and aliases
 description:
   @unicode-data-names@ provides Haskell APIs to access the Unicode
@@ -9,7 +9,7 @@ description:
   .
   The Haskell data structures are generated programmatically from the UCD files.
   The latest Unicode version supported by this library is
-  @<https://www.unicode.org/versions/Unicode14.0.0/ 14.0.0>@.
+  @<https://www.unicode.org/versions/Unicode15.0.0/ 15.0.0>@.
 homepage:            http://github.com/composewell/unicode-data
 bug-reports:         https://github.com/composewell/unicode-data/issues
 license:             Apache-2.0
@@ -96,7 +96,7 @@ test-suite test
   build-depends:
       base             >= 4.7   && < 4.18
     , hspec            >= 2.0   && < 2.11
-    , unicode-data
+    , unicode-data     >= 0.4   && < 0.5
     , unicode-data-names
   build-tool-depends:
       hspec-discover:hspec-discover >= 2.0 && < 2.11

unicode-data-scripts/Changelog.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## 0.2.0 (September 2022)
+
+- Update to [Unicode 15.0.0](https://www.unicode.org/versions/Unicode15.0.0/).
+
 ## 0.1.0 (September 2022)
 
 Initial release

unicode-data-scripts/README.md

@@ -7,7 +7,7 @@ character [scripts](https://www.unicode.org/reports/tr24/) from the
 The Haskell data structures are generated programmatically from the
 Unicode character database (UCD) files. The latest Unicode version
 supported by this library is
-[`14.0.0`](https://www.unicode.org/versions/Unicode14.0.0/).
+[`15.0.0`](https://www.unicode.org/versions/Unicode15.0.0/).
 
 Please see the
 [Haddock documentation](https://hackage.haskell.org/package/unicode-data-scripts)