From 4e4e11849a0d95389de81461ba2f2a4e0245d3b2 Mon Sep 17 00:00:00 2001
From: Joey Hess <joeyh@joeyh.name>
Date: Wed, 12 Aug 2015 10:36:51 -0400
Subject: [PATCH] fix test suite fail in LANG=C

This was caused by 23e9d3bb777d580931a5b4d7ee57aa604190d8b2

an Arbitrary String is not necessarily encoded using the filesystem
encoding, and in a non-utf8 locale, encodeBS throws an exception on such a
string. All I could think to do is limit test data to ascii.

This shouldn't be a problem in practice, because the all Strings in
git-annex that are not generated by Arbitrary should be loaded in a way
that does apply the filesystem encoding.
---
 Types/MetaData.hs             | 10 ++++++++--
 Utility/Base64.hs             | 10 ++++++++--
 Utility/FileSystemEncoding.hs |  4 ++++
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/Types/MetaData.hs b/Types/MetaData.hs
index 1e8fb4aa2f..cf2811b224 100644
--- a/Types/MetaData.hs
+++ b/Types/MetaData.hs
@@ -270,10 +270,16 @@ instance Arbitrary MetaData where
 		legal k _v = legalField $ fromMetaField k
 
 instance Arbitrary MetaValue where
-	arbitrary = MetaValue <$> arbitrary <*> arbitrary
+	arbitrary = MetaValue 
+		<$> arbitrary
+		-- Avoid non-ascii metavalues because fully arbitrary
+		-- strings may not be encoded using the filesystem
+		-- encoding, which is norally applied to all input.
+		<*> arbitrary `suchThat` all isAscii
 
 instance Arbitrary MetaField where
-	arbitrary = MetaField . CI.mk <$> arbitrary `suchThat` legalField 
+	arbitrary = MetaField . CI.mk 
+		<$> arbitrary `suchThat` legalField 
 
 prop_metadata_sane :: MetaData -> MetaField -> MetaValue -> Bool
 prop_metadata_sane m f v = and
diff --git a/Utility/Base64.hs b/Utility/Base64.hs
index 0e30872763..8b43ecfabd 100644
--- a/Utility/Base64.hs
+++ b/Utility/Base64.hs
@@ -10,11 +10,13 @@
 
 module Utility.Base64 (toB64, fromB64Maybe, fromB64, prop_b64_roundtrips) where
 
+import Utility.FileSystemEncoding
+
 import qualified "sandi" Codec.Binary.Base64 as B64
 import Data.Maybe
 import qualified Data.ByteString.Lazy as L
 import Data.ByteString.UTF8 (fromString, toString)
-import Utility.FileSystemEncoding
+import Data.Char
 
 toB64 :: String -> String	
 toB64 = toString . B64.encode . L.toStrict . encodeBS
@@ -28,5 +30,9 @@ fromB64 = fromMaybe bad . fromB64Maybe
   where
 	bad = error "bad base64 encoded data"
 
+-- Only ascii strings are tested, because an arbitrary string may contain
+-- characters not encoded using the FileSystemEncoding.
 prop_b64_roundtrips :: String -> Bool
-prop_b64_roundtrips s = s == fromB64 (toB64 s)
+prop_b64_roundtrips s
+	| all (isAscii) s = s == fromB64 (toB64 s)
+	| otherwise = True
diff --git a/Utility/FileSystemEncoding.hs b/Utility/FileSystemEncoding.hs
index 25a09ecc0b..5a2fab0e4c 100644
--- a/Utility/FileSystemEncoding.hs
+++ b/Utility/FileSystemEncoding.hs
@@ -68,6 +68,10 @@ withFilePath fp f = Encoding.getFileSystemEncoding
  - only allows doing this conversion with CStrings, and the CString buffer
  - is allocated, used, and deallocated within the call, with no side
  - effects.
+ -
+ - If the FilePath contains a value that is not legal in the filesystem
+ - encoding, this may throw an exception. For example, "\226" is not valid
+ - in the C locale, but is in utf locales.
  -}
 {-# NOINLINE _encodeFilePath #-}
 _encodeFilePath :: FilePath -> String