diff options
author | Joey Hess <joeyh@joeyh.name> | 2017-06-17 16:17:09 -0400 |
---|---|---|
committer | Joey Hess <joeyh@joeyh.name> | 2017-06-17 16:48:00 -0400 |
commit | 3adf1ea63d9b5feccd4e6cb457fbbb52fdfc9fe0 (patch) | |
tree | bb68382446f50f6687dde96de1816d881bac655a | |
parent | 9f375315d220169240e0e99a667601136b3e06e9 (diff) |
fix failing quickcheck properties
QuickCheck 2.10 found a counterexample eg "\929184" broke the property.
As far as I can tell, Git.Filename is matching how git handles encoding
of strange high unicode characters in filenames for display. Git does
not display high unicode characters, and instead displays the C-style
escaped form of each byte. This is ambiguous, but since git is not
unicode aware, it doesn't need to roundtrip parse it.
So, making Git.FileName's roundtrip test only chars < 256 seems fine.
Utility.Format.format uses encode_c, in order to mimic git, so that's
ok.
Utility.Format.gen uses decode_c, but only so that stuff like "\n"
in the format string is handled. If the format string contains C-style
octal escapes, they will be converted to ascii characters, and not
combined into unicode characters, but that should not be a problem.
If the user wants unicode characters, they can include them in the
format string, without escaping them.
Finally, decode_c is used by Utility.Gpg.secretKeys, because gpg
--with-colons hex-escapes some characters in particular ':' and '\\'.
gpg passes unicode through, so this use of decode_c is not a problem.
This commit was sponsored by Henrik Riomar on Patreon.
-rw-r--r-- | Git/Filename.hs | 14 | ||||
-rw-r--r-- | Test.hs | 4 | ||||
-rw-r--r-- | Utility/Format.hs | 21 | ||||
-rw-r--r-- | Utility/Gpg.hs | 3 |
4 files changed, 30 insertions, 12 deletions
diff --git a/Git/Filename.hs b/Git/Filename.hs index ee84d4883..355e75f45 100644 --- a/Git/Filename.hs +++ b/Git/Filename.hs @@ -8,9 +8,10 @@ module Git.Filename where +import Common import Utility.Format (decode_c, encode_c) -import Common +import Data.Char decode :: String -> FilePath decode [] = [] @@ -23,6 +24,11 @@ decode f@(c:s) encode :: FilePath -> String encode s = "\"" ++ encode_c s ++ "\"" -{- for quickcheck -} -prop_isomorphic_deencode :: String -> Bool -prop_isomorphic_deencode s = s == decode (encode s) +{- For quickcheck. + - + - See comment on Utility.Format.prop_encode_c_decode_c_roundtrip for + - why this only tests chars < 256 -} +prop_encode_decode_roundtrip :: String -> Bool +prop_encode_decode_roundtrip s = s' == decode (encode s') + where + s' = filter (\c -> ord c < 256) s @@ -161,8 +161,8 @@ tests crippledfilesystem opts = testGroup "Tests" $ properties : properties :: TestTree properties = localOption (QuickCheckTests 1000) $ testGroup "QuickCheck" - [ testProperty "prop_isomorphic_deencode_git" Git.Filename.prop_isomorphic_deencode - , testProperty "prop_isomorphic_deencode" Utility.Format.prop_isomorphic_deencode + [ testProperty "prop_encode_decode_roundtrip" Git.Filename.prop_encode_decode_roundtrip + , testProperty "prop_encode_c_decode_c_roundtrip" Utility.Format.prop_encode_c_decode_c_roundtrip , testProperty "prop_isomorphic_fileKey" Annex.Locations.prop_isomorphic_fileKey , testProperty "prop_isomorphic_key_encode" Key.prop_isomorphic_key_encode , testProperty "prop_isomorphic_key_decode" Key.prop_isomorphic_key_decode diff --git a/Utility/Format.hs b/Utility/Format.hs index 1ebf68d6c..3670cd717 100644 --- a/Utility/Format.hs +++ b/Utility/Format.hs @@ -11,7 +11,7 @@ module Utility.Format ( format, decode_c, encode_c, - prop_isomorphic_deencode + prop_encode_c_decode_c_roundtrip ) where import Text.Printf (printf) @@ -100,8 +100,8 @@ empty :: Frag -> Bool empty (Const "") = True empty _ = False -{- Decodes a C-style encoding, where \n is a newline, \NNN is an octal - - encoded character, and \xNN is a hex encoded character. +{- Decodes a C-style encoding, where \n is a newline (etc), + - \NNN is an octal encoded character, and \xNN is a hex encoded character. -} decode_c :: FormatString -> String decode_c [] = [] @@ -173,6 +173,15 @@ encode_c' p = concatMap echar e_asc c = showoctal $ ord c showoctal i = '\\' : printf "%03o" i -{- for quickcheck -} -prop_isomorphic_deencode :: String -> Bool -prop_isomorphic_deencode s = s == decode_c (encode_c s) +{- For quickcheck. + - + - Encoding and then decoding roundtrips only when + - the string does not contain high unicode, because eg, + - both "\12345" and "\227\128\185" are encoded to "\343\200\271". + - + - This property papers over the problem, by only testing chars < 256. + -} +prop_encode_c_decode_c_roundtrip :: String -> Bool +prop_encode_c_decode_c_roundtrip s = s' == decode_c (encode_c s') + where + s' = filter (\c -> ord c < 256) s diff --git a/Utility/Gpg.hs b/Utility/Gpg.hs index dae254854..94d588cd7 100644 --- a/Utility/Gpg.hs +++ b/Utility/Gpg.hs @@ -184,6 +184,9 @@ secretKeys cmd = catchDefaultIO M.empty makemap params = [Param "--with-colons", Param "--list-secret-keys", Param "--fixed-list-mode"] parse = extract [] Nothing . map (splitc ':') extract c (Just keyid) (("uid":_:_:_:_:_:_:_:_:userid:_):rest) = + -- If the userid contains a ":" or a few other special + -- characters, gpg will hex-escape it. Use decode_c to + -- undo. extract ((keyid, decode_c userid):c) Nothing rest extract c (Just keyid) rest@(("sec":_):_) = extract ((keyid, ""):c) Nothing rest |