2023-10-25 18:44:57 +00:00
|
|
|
For a long time (since 2019) git-annex has been progressively converting from
|
|
|
|
FilePath to RawFilePath (aka ByteString).
|
|
|
|
|
|
|
|
The reason is mostly performance, also a simpler representation of
|
|
|
|
filepaths that doesn't need encoding hacks to support non-UTF8 values.
|
|
|
|
|
|
|
|
Some commands like `git-annex find` use RawFilePath end-to-end.
|
|
|
|
But this conversion is not yet complete. This is a todo to keep track of the
|
|
|
|
status.
|
|
|
|
|
|
|
|
* The Abstract FilePath proposal (AFPP) has been implemented, and so a number of
|
|
|
|
libraries like unix and directory now have versions that operate on
|
|
|
|
OSPath. That could be used in git-annex eg for things like
|
|
|
|
getDirectoryContents, when built against those versions.
|
|
|
|
(But OSPath uses ShortByteString, while RawFilePath is ByteString, so
|
|
|
|
conversion still entails a copy.)
|
|
|
|
* withFile remains to be converted, and is used in several important code
|
|
|
|
paths, including Annex.Journal and Annex.Link.
|
2023-10-31 18:06:46 +00:00
|
|
|
There is a RawFilePath version in file-io library, but that is
|
2023-10-25 18:44:57 +00:00
|
|
|
not currently a git-annex dependency. (withFile is in base, and base is
|
|
|
|
unlikely to convert to AFPP soon)
|
|
|
|
|
|
|
|
[[!tag confirmed]]
|
|
|
|
|
|
|
|
----
|
|
|
|
|
|
|
|
The following patch can be useful to find points where conversions are
|
|
|
|
done. Especially useful to identify cases where a value is converted
|
|
|
|
`FilePath -> RawFilePath -> FilePath`.
|
|
|
|
|
|
|
|
diff --git a/Utility/FileSystemEncoding.hs b/Utility/FileSystemEncoding.hs
|
|
|
|
index 2a1dc81bc1..03e6986f6e 100644
|
|
|
|
--- a/Utility/FileSystemEncoding.hs
|
|
|
|
+++ b/Utility/FileSystemEncoding.hs
|
|
|
|
@@ -84,6 +84,9 @@ encodeBL = L.fromStrict . encodeBS
|
|
|
|
encodeBL = L8.fromString
|
|
|
|
#endif
|
|
|
|
|
|
|
|
+debugConversions :: String -> IO ()
|
|
|
|
+debugConversions s = hPutStrLn stderr ("conversion: " ++ s)
|
|
|
|
+
|
|
|
|
decodeBS :: S.ByteString -> FilePath
|
|
|
|
#ifndef mingw32_HOST_OS
|
|
|
|
-- This does the same thing as System.FilePath.ByteString.decodeFilePath,
|
|
|
|
@@ -92,6 +95,7 @@ decodeBS :: S.ByteString -> FilePath
|
|
|
|
-- something other than a unix filepath.
|
|
|
|
{-# NOINLINE decodeBS #-}
|
|
|
|
decodeBS b = unsafePerformIO $ do
|
|
|
|
+ debugConversions (show b)
|
|
|
|
enc <- Encoding.getFileSystemEncoding
|
|
|
|
S.useAsCStringLen b (GHC.peekCStringLen enc)
|
|
|
|
#else
|
|
|
|
@@ -106,17 +110,19 @@ encodeBS :: FilePath -> S.ByteString
|
|
|
|
-- something other than a unix filepath.
|
|
|
|
{-# NOINLINE encodeBS #-}
|
|
|
|
encodeBS f = unsafePerformIO $ do
|
|
|
|
+ debugConversions f
|
|
|
|
enc <- Encoding.getFileSystemEncoding
|
|
|
|
- GHC.newCStringLen enc f >>= unsafePackMallocCStringLen
|
|
|
|
+ b <- GHC.newCStringLen enc f >>= unsafePackMallocCStringLen
|
|
|
|
+ return b
|
|
|
|
#else
|
|
|
|
encodeBS = S8.fromString
|
|
|
|
#endif
|
|
|
|
|
|
|
|
fromRawFilePath :: RawFilePath -> FilePath
|
|
|
|
-fromRawFilePath = decodeFilePath
|
|
|
|
+fromRawFilePath = decodeBS -- decodeFilePath
|
|
|
|
|
|
|
|
toRawFilePath :: FilePath -> RawFilePath
|
|
|
|
-toRawFilePath = encodeFilePath
|
|
|
|
+toRawFilePath = encodeBS -- encodeFilePath
|
|
|
|
|
|
|
|
{- Truncates a FilePath to the given number of bytes (or less),
|
|
|
|
- as represented on disk.
|