summaryrefslogtreecommitdiff
path: root/Utility/FileSystemEncoding.hs
diff options
context:
space:
mode:
authorGravatar Joey Hess <joeyh@joeyh.name>2015-03-04 11:16:03 -0400
committerGravatar Joey Hess <joeyh@joeyh.name>2015-03-04 12:54:30 -0400
commit05697fe62116181511084a2eba28c5220e8a0363 (patch)
tree6965f56f5648d6dfa6c5e7d6e31e32eb3975b073 /Utility/FileSystemEncoding.hs
parent0c3570844cf60428808d01a73c808e4f7232f082 (diff)
metadata: Fix encoding problem that led to mojibake when storing metadata strings that contained both unicode characters and a space (or '!') character.
The fix is to stop using w82s, which does not properly reconstitute unicode strings. Instrad, use utf8 bytestring to get the [Word8] to base64. This passes unicode through perfectly, including any invalid filesystem encoded characters. Note that toB64 / fromB64 are also used for creds and cipher embedding. It would be unfortunate if this change broke those uses. For cipher embedding, note that ciphers can contain arbitrary bytes (should really be using ByteString.Char8 there). Testing indicated it's not safe to use the new fromB64 there; I think that characters were incorrectly combined. For credpair embedding, the username or password could contain unicode. Before, that unicode would fail to round-trip through the b64. So, I guess this is not going to break any embedded creds that worked before. This bug may have affected some creds before, and if so, this change will not fix old ones, but should fix new ones at least.
Diffstat (limited to 'Utility/FileSystemEncoding.hs')
-rw-r--r--Utility/FileSystemEncoding.hs17
1 files changed, 17 insertions, 0 deletions
diff --git a/Utility/FileSystemEncoding.hs b/Utility/FileSystemEncoding.hs
index 844e81e59..139b74fe4 100644
--- a/Utility/FileSystemEncoding.hs
+++ b/Utility/FileSystemEncoding.hs
@@ -14,6 +14,8 @@ module Utility.FileSystemEncoding (
decodeBS,
decodeW8,
encodeW8,
+ encodeW8NUL,
+ decodeW8NUL,
truncateFilePath,
) where
@@ -25,6 +27,7 @@ import System.IO.Unsafe
import qualified Data.Hash.MD5 as MD5
import Data.Word
import Data.Bits.Utils
+import Data.List.Utils
import qualified Data.ByteString.Lazy as L
#ifdef mingw32_HOST_OS
import qualified Data.ByteString.Lazy.UTF8 as L8
@@ -89,6 +92,9 @@ decodeBS = L8.toString
- w82c produces a String, which may contain Chars that are invalid
- unicode. From there, this is really a simple matter of applying the
- file system encoding, only complicated by GHC's interface to doing so.
+ -
+ - Note that the encoding stops at any NUL in the input. FilePaths
+ - do not normally contain embedded NUL, but Haskell Strings may.
-}
{-# NOINLINE encodeW8 #-}
encodeW8 :: [Word8] -> FilePath
@@ -101,6 +107,17 @@ encodeW8 w8 = unsafePerformIO $ do
decodeW8 :: FilePath -> [Word8]
decodeW8 = s2w8 . _encodeFilePath
+{- Like encodeW8 and decodeW8, but NULs are passed through unchanged. -}
+encodeW8NUL :: [Word8] -> FilePath
+encodeW8NUL = join nul . map encodeW8 . split (s2w8 nul)
+ where
+ nul = ['\NUL']
+
+decodeW8NUL :: FilePath -> [Word8]
+decodeW8NUL = join (s2w8 nul) . map decodeW8 . split nul
+ where
+ nul = ['\NUL']
+
{- Truncates a FilePath to the given number of bytes (or less),
- as represented on disk.
-