Merge pull request #75 from Bodigrim/s390x

Add big-endian configuration for CI

Author: Bodigrim

.github/workflows/s390x.yml

@@ -0,0 +1,39 @@
+name: s390x
+on:
+  push:
+    branches:
+      - master
+  pull_request: {} # Validate all PRs
+
+defaults:
+  run:
+    shell: bash
+
+jobs:
+  # Emulation on s390x platform is incredibly slow and memory demanding.
+  # It seems that any executable with GHC RTS takes at least 7-8 Gb of RAM, so we can
+  # run `cabal` or `ghc` on their own, but cannot run them both at the same time, striking
+  # out `cabal test`. Instead we rely on system packages and invoke `ghc --make` manually,
+  # and even so `ghc -O` is prohibitively expensive.
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: uraimo/[email protected]
+      timeout-minutes: 60
+      with:
+        arch: s390x
+        distro: ubuntu20.04
+        githubToken: ${{ github.token }}
+        install: |
+          apt-get update -y
+          apt-get install -y ghc libghc-quickcheck2-dev libghc-hspec-dev libghc-getopt-generics-dev libghc-split-dev curl
+        run: |
+          ghc --version
+          curl -s -L https://hackage.haskell.org/package/unicode-data-0.3.0.tar.gz | tar xz
+          ghc --make -XMagicHash -XBangPatterns -XUnboxedTuples -itest:unicode-data-0.3.0/lib -o extras test/Extra.hs
+          ./extras
+          ghc --make -XMagicHash -XBangPatterns -XUnboxedTuples -itest:unicode-data-0.3.0/lib -o quickcheck test/Properties.hs
+          ./quickcheck
+          ghc --make -XMagicHash -XBangPatterns -XUnboxedTuples -itest:unicode-data-0.3.0/lib -o ucd test/NormalizationTest.hs
+          ./ucd

test/NormalizationTest.hs

@@ -12,6 +12,7 @@
 --
 
 import Control.Monad (when)
+import qualified Data.ByteString as B
 import Data.Char (chr, isSpace, ord, toUpper)
 #if MIN_VERSION_base(4,8,0)
 import Data.Function ((&))
@@ -20,6 +21,7 @@ import Data.List (intercalate, isPrefixOf)
 import Data.List.Split (splitOn)
 import Data.Text (Text)
 import qualified Data.Text as T
+import qualified Data.Text.Encoding as T
 import Data.Text.Normalize (NormalizationMode(NFD, NFKD, NFC, NFKC), normalize)
 import Text.Printf (printf)
 
@@ -109,7 +111,7 @@ checkLine (lineno, line) = do
 
 testNormalize :: FilePath -> IO ()
 testNormalize file = do
-    contents <- readFile file
+    contents <- T.unpack . T.decodeUtf8 <$> B.readFile file
     let ls = lines contents                        -- split into lines
          & map (dropWhile isSpace)                 -- trim leading spaces
          & zip [1..]                               -- add numbering

unicode-transforms.cabal

@@ -156,6 +156,7 @@ test-suite ucd
   ghc-options: -Wall -fwarn-identities -fwarn-incomplete-record-updates -fwarn-incomplete-uni-patterns -fwarn-tabs
   build-depends:
       base >=4.7 && <5
+    , bytestring
     , split >=0.1 && <0.3
     , text
     , unicode-transforms