delimited-text (empty) → 0.0.1

raw patch · 6 files changed

+152/−0 lines, 6 filesdep +arraydep +attoparsecdep +basesetup-changed

Dependencies added: array, attoparsec, base, binary, bytestring, bytestring-show

Files

• LICENSE +24/−0
• Setup.lhs +4/−0
• Text/Delimited.hs +12/−0
• Text/Delimited/ByteString/Lazy.hs +63/−0
• Text/Delimited/Types.hs +20/−0
• delimited-text.cabal +29/−0

@@ -0,0 +1,24 @@+Copyright (c) Stefan Kersten 2008++All rights reserved.++Redistribution and use in source and binary forms, with or without+modification, are permitted provided that the following conditions+are met:+1. Redistributions of source code must retain the above copyright+   notice, this list of conditions and the following disclaimer.+2. Redistributions in binary form must reproduce the above copyright+   notice, this list of conditions and the following disclaimer in the+   documentation and/or other materials provided with the distribution.++THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE+ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHORS OR CONTRIBUTORS BE LIABLE+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS+OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)+HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF+SUCH DAMAGE.

@@ -0,0 +1,4 @@+#!/usr/bin/env runhaskell++> import Distribution.Simple+> main = defaultMain

@@ -0,0 +1,12 @@+-- | Parse text files containing lines with records separated by character+-- delimiters.+--+-- At this time parsing is only supported for lazy 'ByteString's.+--+module Text.Delimited (+	module Text.Delimited.ByteString.Lazy,+	module Text.Delimited.Types+) where++import Text.Delimited.ByteString.Lazy+import Text.Delimited.Types

@@ -0,0 +1,63 @@+module Text.Delimited.ByteString.Lazy (+    encode, decode, interact+) where++import Data.Binary.Put										(Put, putByteString, runPut)+import Data.ByteString.Lazy									(ByteString, toChunks)+import qualified Data.ByteString                			as BS+import Prelude                              				hiding (interact)+import Text.Show.ByteString                					(putAscii, showp, unlinesP)+import qualified Data.ParserCombinators.Attoparsec.Char8 	as P+import Text.Delimited.Types++-- | Intersperse a list of 'Put's with a delimiter.+intersperseP :: Put -> [Put] -> Put+intersperseP _ []     = return ()+intersperseP _ (x:[]) = showp x+intersperseP d (x:xs) = x >> d >> intersperseP d xs++-- | Convert 'Content' delimited by 'delim' to a 'Put'.+putContent :: Char -> Content -> Put+putContent delim = unlinesP . map (intersperseP (putAscii delim) . map putByteString)++-- | Encode records separated by newlines to a ByteString.+-- Record fields are separated by 'delim'.+encode :: Char -> Content -> ByteString+encode delim = runPut . putContent delim++-- | Construct a strict ByteString from a lazy one.+fromLazy :: ByteString -> BS.ByteString+fromLazy = BS.concat . toChunks++-- | Construct a parser from 'a' terminated by 'b'.+endBy :: P.Parser a -> P.Parser b -> P.Parser a+a `endBy` b = do+	r <- a+	b+	return r++-- | A lazy 'ByteString' parser for delimited text.+parser :: [Char] -> P.Parser Content+parser delims = line `P.manyTill` P.eof+	where+		line  = (field `P.sepBy` sep) `endBy` eol+		field = fromLazy `fmap` P.takeWhile (P.notInClass (delims ++ nls))+		sep   = P.skipMany1 (P.satisfy $ P.inClass delims)+		eol   = P.skipMany1 (P.satisfy $ P.inClass nls)+		nls   = "\n\r"++-- | Parse records separated by newlines from a ByteString.+-- Record fields are separated by any of the characters in 'delims'. There is+-- no way of escaping delimiters, so record fields may not contain any of the+-- characters in 'delims'.+decode :: [Char] -> ByteString -> Result Content+decode delims = snd . P.parse (parser delims)++-- | Decode a ByteString, apply a function to each 'Record' and encode the content.+-- Delimiters may contain multiple characters but only the first is used for+-- encoding.+interact :: (Record -> Record) -> [Char] -> ByteString -> Result ByteString+interact f delims s =+    case decode delims s of+		Right c -> Right (encode (head delims) (map f c))+		Left e  -> Left e

@@ -0,0 +1,20 @@+module Text.Delimited.Types (+	Content, Record, Field,+	Result+) where++import Data.ByteString							(ByteString)+import Data.ParserCombinators.Attoparsec.Char8	(ParseError)++-- | A delimited file is a series of variable length records.+type Content = [Record]++-- | A record is a series of fields.+-- Each record is located on a separate line, delimited by a line break (CRLF).+type Record = [Field]++-- | A field is a strict ByteString.+type Field = ByteString++-- | Result type.+type Result a = Either ParseError a

@@ -0,0 +1,29 @@+name:               delimited-text+version:            0.0.1+synopsis:           Parse character delimited textual data+description:        Parse character delimited textual data+license:            BSD3+license-file:       LICENSE+category:           Data+copyright:          Copyright (c) Stefan Kersten 2008+author:             Stefan Kersten+maintainer:         Stefan Kersten+stability:          provisional+homepage:           http://code.haskell.org/~StefanKersten/code/delimited-text+tested-with:        GHC == 6.10.1+build-type:         Simple+cabal-version:      >= 1.2++library+  exposed-modules:  Text.Delimited+  other-modules:    Text.Delimited.ByteString.Lazy+                    Text.Delimited.Types+                    +  build-depends:    array,+                    base >= 3,+                    binary >= 0.4,+                    bytestring,+                    attoparsec >= 0.5,+                    bytestring-show >= 0.2++  ghc-options:      -O2 -funbox-strict-fields