Merge remote-tracking branch 'origin/master' into feature/general_cat…

…egory # Conflicts: # appveyor.yml # lib/Unicode/Internal/Bits.hs
composewell · Nov 22, 2021 · 2ace84e · 2ace84e
2 parents eb03cfa + e3208a4
commit 2ace84e
Show file tree

Hide file tree

Showing 7 changed files with 62 additions and 30 deletions.
diff --git a/.github/workflows/haskell.yml b/.github/workflows/haskell.yml
@@ -28,8 +28,8 @@ jobs:
       # Location of packcheck.sh
       # ------------------------------------------------------------------------
       PACKCHECK_LOCAL_PATH: "./packcheck.sh"
-      PACKCHECK_GITHUB_URL: "https://raw.githubusercontent.com/harendra-kumar/packcheck"
-      PACKCHECK_GITHUB_COMMIT: "37bbe8a79ad5136e654e48e03ec519060a5b11e6"
+      PACKCHECK_GITHUB_URL: "https://raw.githubusercontent.com/composewell/packcheck"
+      PACKCHECK_GITHUB_COMMIT: "v0.6.0"
 
       # ------------------------------------------------------------------------
       # Build options
@@ -42,55 +42,77 @@ jobs:
       fail-fast: false
       matrix:
         name:
-          [ Ubuntu+GHC822, Ubuntu+GHC865, Ubuntu+GHC844
-          , Ubuntu+GHC884, Ubuntu+GHC8102+exe
-          , MacOS+GHC884+exe
-          , Hlint ]
-        cabal_version: [3.2]
+          - 7.10.3
+          - 8.0.2
+          - 8.2.2
+          - 8.4.4
+          - 8.8.4+macOS+exe
+          - 8.6.5
+          - 8.8.4
+          - 8.10.7+exe
+          - 9.0.1+exe
+          - 9.2.1
+          - hlint
+
         include:
 
-          - name: Ubuntu+GHC7103
+          - name: 7.10.3
             ghc_version: 7.10.3
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC802
+          - name: 8.0.2
             ghc_version: 8.0.2
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC822
+          - name: 8.2.2
             ghc_version: 8.2.2
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC844
+          - name: 8.4.4
             ghc_version: 8.4.4
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC865
+          - name: 8.6.5
             ghc_version: 8.6.5
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC884
+          - name: 8.8.4
             ghc_version: 8.8.4
             runner: ubuntu-latest
+            cabal_version: 3.2
+
+          - name: 8.8.4+macOS+exe
+            ghc_version: 8.8.4
+            pack_options: CABAL_BUILD_OPTIONS="-f ucd2haskell"
+            runner: macos-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC8102+exe
-            ghc_version: 8.10.2
+          - name: 8.10.7+exe
+            ghc_version: 8.10.7
             pack_options: CABAL_BUILD_OPTIONS="-f ucd2haskell"
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Ubuntu+GHC901+exe
+          - name: 9.0.1+exe
             ghc_version: 9.0.1
             pack_options: CABAL_BUILD_OPTIONS="-f ucd2haskell"
             runner: ubuntu-latest
+            cabal_version: 3.2
 
-          - name: Hlint
-            pack_options: HLINT_OPTIONS="lint" HLINT_TARGETS="lib exe"
+          - name: 9.2.1
+            ghc_version: 9.2.1
             runner: ubuntu-latest
+            cabal_version: 3.6
 
-          - name: MacOS+GHC884+exe
-            ghc_version: 8.8.4
-            pack_options: CABAL_BUILD_OPTIONS="-f ucd2haskell"
-            runner: macos-latest
+          - name: hlint
+            pack_options: HLINT_OPTIONS="lint" HLINT_TARGETS="lib exe"
+            runner: ubuntu-latest
+            cabal_version: 3.2
 
     steps:
     - uses: actions/checkout@v2

diff --git a/Changelog.md b/Changelog.md
@@ -3,6 +3,8 @@
 ## 0.2.0 (November 2021)
 
 * Update to [Unicode 14.0.0](https://www.unicode.org/versions/Unicode14.0.0/).
+* Add `Unicode.Char.Identifiers` supporting Unicode Identifier and Pattern
+  Syntax.
 
 ## 0.1.0.1 (Jul 2021)
 

diff --git a/README.md b/README.md
@@ -48,6 +48,6 @@ $ cabal-docspec --check-properties --property-variables c
 `unicode-data` is an [open source](https://github.com/composewell/unicode-data)
 project available under a liberal [Apache-2.0 license](LICENSE).
 
-## Contributing to Streamly
+## Contributing
 
 As an open project we welcome contributions.
diff --git a/appveyor.yml b/appveyor.yml
@@ -33,7 +33,7 @@ environment:
     # version.
     #STACKVER: "1.6.5"
     STACK_UPGRADE: "y"
-    RESOLVER: "lts-18.16"
+    RESOLVER: "lts-18.17"
     STACK_ROOT: "c:\\sr"
 
     # ------------------------------------------------------------------------
@@ -60,7 +60,7 @@ environment:
     # If you have not committed packcheck.sh in your repo at PACKCHECK_LOCAL_PATH
     # then it is automatically pulled from this URL.
     PACKCHECK_GITHUB_URL: "https://raw.githubusercontent.com/composewell/packcheck"
-    PACKCHECK_GITHUB_COMMIT: "37bbe8a79ad5136e654e48e03ec519060a5b11e6"
+    PACKCHECK_GITHUB_COMMIT: "v0.6.0"
 
     # Override the temp directory to avoid sed escaping issues
     # See https://github.com/haskell/cabal/issues/5386

diff --git a/lib/Unicode/Char/Identifiers.hs b/lib/Unicode/Char/Identifiers.hs
@@ -46,13 +46,12 @@ isXIDContinue = P.isXID_Continue
 isXIDStart :: Char -> Bool
 isXIDStart = P.isXID_Start
 
--- | Returns 'True' is a pattern syntax character.
+-- | Returns 'True' if a character is a pattern syntax character.
 {-# INLINE isPatternSyntax #-}
 isPatternSyntax :: Char -> Bool
 isPatternSyntax = P.isPattern_Syntax
 
--- | Returns 'True' is a pattern whitespace character.
+-- | Returns 'True' if a character is a pattern whitespace character.
 {-# INLINE isPatternWhitespace #-}
 isPatternWhitespace :: Char -> Bool
 isPatternWhitespace = P.isPattern_White_Space
-
diff --git a/lib/Unicode/Internal/Bits.hs b/lib/Unicode/Internal/Bits.hs
@@ -17,6 +17,8 @@ module Unicode.Internal.Bits
       lookupIntN
     ) where
 
+#include "MachDeps.h"
+
 import Data.Bits (finiteBitSize, popCount)
 import GHC.Exts
        (Addr#, Int(..), Word(..),
@@ -26,6 +28,9 @@ import GHC.Exts
 #if MIN_VERSION_base(4,16,0)
 import GHC.Exts (word8ToWord#)
 #endif
+#ifdef WORDS_BIGENDIAN
+import GHC.Exts (byteSwap#)
+#endif
 
 -- | @lookup64 addr index@ looks up the bit stored at bit index @index@ using a
 -- bitmap starting at the address @addr@. Looks up the 64-bit word containing
@@ -43,7 +48,11 @@ lookupBit64 addr# (I# index#) = W# (word## `and#` bitMask##) /= 0
       _  -> popCount fbs -- this is a really weird architecture
 
     wordIndex# = index# `uncheckedIShiftRL#` logFbs#
+#ifdef WORDS_BIGENDIAN
+    word## = byteSwap# (indexWordOffAddr# addr# wordIndex#)
+#else
     word## = indexWordOffAddr# addr# wordIndex#
+#endif
     bitIndex# = index# `andI#` fbs#
     bitMask## = 1## `uncheckedShiftL#` bitIndex#
 

diff --git a/unicode-data.cabal b/unicode-data.cabal
@@ -25,10 +25,10 @@ tested-with:         GHC==7.10.3
                    , GHC==8.2.2
                    , GHC==8.4.4
                    , GHC==8.6.5
-                   , GHC==8.8.3
                    , GHC==8.8.4
-                   , GHC==8.10.2
+                   , GHC==8.10.7
                    , GHC==9.0.1
+                   , GHC==9.2.1
 
 extra-source-files:
     Changelog.md