purebred-email 0.5 → 0.5.1

raw patch · 6 files changed

+58/−16 lines, 6 filesdep −semigroupsdep ~attoparsecdep ~bytestringPVP ok

version bump matches the API change (PVP)

Dependencies removed: semigroups

Dependency ranges changed: attoparsec, bytestring

API changes (from Hackage documentation)

Files

• purebred-email.cabal +4/−5
• src/Data/IMF.hs +30/−1
• src/Data/IMF/Syntax.hs +19/−8
• src/Data/MIME.hs +1/−1
• src/Data/MIME/EncodedWord.hs +2/−0
• tests/Parser.hs +2/−1

@@ -1,6 +1,6 @@ cabal-version:       2.2 name:                purebred-email-version:             0.5+version:             0.5.1 synopsis:            types and parser for email messages (including MIME) description:   The purebred email library.  RFC 5322, MIME, etc.@@ -36,7 +36,7 @@   test-vectors/*.eml   tests/golden/*.golden tested-with:-  GHC ==8.8.4 || ==8.10.4 || ==9.0.1+  GHC ==8.8.4 || ==8.10.7 || ==9.0.2 || ==9.2.3 || ==9.4.1  homepage:            https://github.com/purebred-mua/purebred-email bug-reports:         https://github.com/purebred-mua/purebred-email/issues@@ -54,11 +54,10 @@    build-depends:     base >= 4.11 && < 5-    , attoparsec >= 0.13 && < 0.14-    , bytestring >= 0.10 && < 0.11+    , attoparsec >= 0.13 && < 0.15+    , bytestring >= 0.10 && < 0.12     , case-insensitive >= 1.2 && < 1.3     , lens >= 4 && < 6-    , semigroups >= 0.16     , text >= 1.2     , time >= 1.9 

@@ -387,7 +387,36 @@  phrase :: CharsetLookup -> Parser T.Text phrase charsets = foldMany1Sep " " $-  fmap (decodeEncodedWord charsets) ("=?" *> encodedWord)+  -- RFC 2047 §2: if it is desirable to encode more text than will+  -- fit in an 'encoded-word' of 75 characters, multiple+  -- 'encoded-word's (separated by CRLF SPACE) may be used.+  --+  -- The initial header parsing unfolds the header, so such+  -- "continuation" encoded-words are now separated by SPACE.  The+  -- CRLFs have been erased.  Naïvely, this seems to make this case+  -- indistinguishable from "consecutive" encoded-words that were+  -- actually separated by SPACE.  However, a careful examination of+  -- the grammar shows that encoded-words in a 'phrase' cannot be+  -- separated by whitespace:+  --+  -- @+  -- phrase         = 1*( encoded-word / word )+  -- encoded-word   = "=?" charset "?" encoding "?" encoded-text "?="+  -- word           = atom / quoted-string+  -- atom           = [CFWS] 1*atext [CFWS]+  -- quoted-string  = [CFWS]+  --                  DQUOTE *([FWS] qcontent) [FWS] DQUOTE+  --                  [CFWS]+  -- @+  --+  -- The only place whitespace is allowed is within 'atom' and+  -- 'quoted-string'.  Therefore two encoded-words separated by+  -- SPACE must be the result of folding a long encoded-word.  So+  -- consume as many SPACE separated encoded-words as possible,+  -- decode them, and concatenate the result.+  fmap+    ( foldMap (decodeEncodedWord charsets) )+    ( ("=?" *> encodedWord) `sepBy1` char8 ' ' )   <|> fmap decodeLenient word  displayName :: CharsetLookup -> Parser T.Text

@@ -14,7 +14,6 @@ -- You should have received a copy of the GNU Affero General Public License -- along with this program.  If not, see <http://www.gnu.org/licenses/>. -{-# LANGUAGE CPP #-} {-# LANGUAGE ConstraintKinds #-} {-# LANGUAGE FlexibleInstances #-} {-# LANGUAGE FunctionalDependencies #-}@@ -77,7 +76,7 @@   ) where  import Prelude hiding (takeWhile)-import Control.Applicative ((<|>), Alternative, liftA2, many, optional)+import Control.Applicative ((<|>), Alternative, liftA2, many, optional, some) import Control.Monad (void) import qualified Data.Attoparsec.ByteString as A import qualified Data.Attoparsec.Internal as A@@ -98,11 +97,7 @@  -- | Constraint synonym to handle the Semigroup Monoid Proposal -- transition gracefully.-#if MIN_VERSION_base(4,11,0) type SM a = Monoid a-#else-type SM a = (Semigroup a, Monoid a)-#endif  class IsChar a where   toChar :: a -> Char@@ -196,8 +191,24 @@ -- | Folding white space (FWS).  A run of one or more whitespace -- characters.  Returns a single SPACE character. fws :: (Alternative (f s), CharParsing f s a) => (f s) s-fws = ( optional (takeWhile isWsp *> crlf) *> takeWhile1 isWsp )-      $> singleton ' '+fws =+  -- obs-FWS is more permissive, so must come first.  This means+  -- that the second branch is unused, but keep it anyway for+  -- completeness.+  obsFWS+  <|>+  --    FWS             =   ([*WSP CRLF] 1*WSP) /  obs-FWS+  optional (takeWhile isWsp *> crlf) *> takeWhile1 isWsp $> singleton ' '++-- | Obsolete Folding White Space:+-- https://www.rfc-editor.org/errata/eid1908+--+-- @+-- obs-FWS         =   1*([CRLF] WSP)+-- @+--+obsFWS :: (Alternative (f s), CharParsing f s a) => (f s) s+obsFWS = some (optional crlf *> wsp) $> singleton ' '  -- | FWS collapsed to a single SPACE character, or empty string --

@@ -486,7 +486,7 @@     (\(Message h' b') -> Message h' (Part b')) <$> f (Message h b)   Encapsulated msg -> Message h . Encapsulated <$> entities f msg   Multipart sub b bs ->-    Message h . Multipart sub b <$> sequenceA (entities f <$> bs)+    Message h . Multipart sub b <$> traverse (entities f) bs   FailedParse _ _ -> pure (Message h a)  -- | Leaf entities with @Content-Disposition: attachment@

@@ -56,6 +56,8 @@ import Data.MIME.QuotedPrintable import Data.IMF.Syntax (ci, takeTillString) +{-# ANN module ("HLint: ignore Eta reduce" :: String) #-}+ data EncodedWord = EncodedWord   { _encodedWordCharset :: CI.CI B.ByteString   , _encodedWordLanguage :: Maybe (CI.CI B.ByteString)

@@ -20,7 +20,8 @@  import Data.Either (isLeft) -import Data.Attoparsec.ByteString.Lazy as AL+import Data.Attoparsec.ByteString.Lazy as AL hiding (parseOnly)+import Data.Attoparsec.ByteString (parseOnly) import qualified Data.ByteString as B import qualified Data.ByteString.Char8 as Char8 import qualified Data.ByteString.Lazy as L