diff --git a/CHANGELOG.md b/CHANGELOG.md --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,38 +1,50 @@ +See also http://pvp.haskell.org/faq + +## 1.3.1.0 + +- Merge into `regex-tdfa`; see . +- Don't inject `ghc-options: -O2` by default anymore (see #7 for rationale) and introduce `force-O2` cabal flag to control the injection of `ghc-options: -O2`. + Note that you can conveniently control optimization levels on a per-package granularity via `cabal.project` files; see [cabal's user-guide](https://cabal.readthedocs.io/en/latest/nix-local-build.html#configuring-builds-with-cabal-project) for more details. + # 1.3.0 -Same as 1.2.3.3. +- Same as 1.2.3.3 release; see . +- Compatibility with GHC 8.8 and regex-base-0.9.4 (h/t @asr). +- Turned `regex-tdfa-unittest` into a `regex-tdfa` testsuite. -See . +---- -# 1.2.3.3 (deprecated) +### 1.2.3.3 (deprecated) * Compatibility with GHC 8.8 and regex-base-0.9.4 (h/t @asr). * Turned `regex-tdfa-unittest` into a `regex-tdfa` testsuite. -# 1.2.3.2 +### 1.2.3.2 * Significantly improved documentation (h/t William Yao). -# 1.2.3.1 +### 1.2.3.1 * Compatibility with `containers-0.6`. -# 1.2.3 +## 1.2.3 * Added `Semigroup` instances for some types (h/t Herbert Valerio Riedel). -# 1.2.2 +## 1.2.2 * New maintainer. * Now we don't reexport the problematic `Show` instance for functions. -# 1.2.1 +## 1.2.1 * Updated dependency versions. # 1.2.0 "Almost ghc-7.8" with the array 0.4 changes for `Data.Array.Unsafe` + +---- # 1.1.8 diff --git a/Setup.hs b/Setup.hs deleted file mode 100644 --- a/Setup.hs +++ /dev/null @@ -1,6 +0,0 @@ -#!/usr/bin/env runhaskell - --- I usually compile this with "ghc --make -o setup Setup.hs" - -import Distribution.Simple(defaultMain) -main = defaultMain diff --git a/lib/Data/IntMap/EnumMap2.hs b/lib/Data/IntMap/EnumMap2.hs --- a/lib/Data/IntMap/EnumMap2.hs +++ b/lib/Data/IntMap/EnumMap2.hs @@ -2,7 +2,7 @@ module Data.IntMap.EnumMap2 where -import Data.Foldable(Foldable(..)) +import Data.Foldable as F (Foldable(foldMap)) import qualified Data.IntMap as M #if MIN_VERSION_containers(0,6,0) import qualified Data.IntMap.Internal.Debug as MD @@ -27,8 +27,8 @@ instance Ord k => Functor (EnumMap k) where fmap f (EnumMap m) = EnumMap (fmap f m) -instance Ord k => Foldable (EnumMap k) where - foldMap f (EnumMap m) = foldMap f m +instance Ord k => F.Foldable (EnumMap k) where + foldMap f (EnumMap m) = F.foldMap f m (!) :: (Enum key) => EnumMap key a -> key -> a (!) (EnumMap m) k = (M.!) m (fromEnum k) diff --git a/lib/Text/Regex/TDFA.hs b/lib/Text/Regex/TDFA.hs --- a/lib/Text/Regex/TDFA.hs +++ b/lib/Text/Regex/TDFA.hs @@ -1,4 +1,8 @@ {-| +Module: Text.Regex.TDFA +Copyright: (c) Chris Kuklewicz 2007-2009 +SPDX-License-Identifier: BSD-3-Clause +Maintainer: hvr@gnu.org The "Text.Regex.TDFA" module provides a backend for regular expressions. It provides instances for the classes defined and @@ -7,25 +11,22 @@ qualified imports (with renaming for convenience). This regex-tdfa package implements, correctly, POSIX extended regular -expressions. It is highly unlikely that the regex-posix package on +expressions. It is highly unlikely that the @regex-posix@ package on your operating system is correct, see for examples of your OS's bugs. = Importing and using -Add to your package.yaml/cabal file: - -> dependencies: -> - regex-tdfa + on the @regex-tdfa@ library in your @.cabal@ file: -In modules where you need to use regexes: +> build-depends: regex-tdfa ^>= 1.3.1.0 -> import Text.Regex.TDFA +In Haskell modules where you want to use regexes simply @import@ /this/ module: -Note that regex-tdfa does not provide support for @Text@ by default. -If you need this functionality, add -as a dependency and @import Text.Regex.TDFA.Text ()@. +@ +import "Text.Regex.TDFA" +@ = Basics @@ -115,7 +116,7 @@ This package does provide captured parenthesized subexpressions. Depending on the text being searched this package supports Unicode. -The @[Char]@ and @(Seq Char)@ text types support Unicode. The @ByteString@ +The @[Char]@, @Text@, @Text.Lazy@, and @(Seq Char)@ text types support Unicode. The @ByteString@ and @ByteString.Lazy@ text types only support ASCII. It is possible to support utf8 encoded @ByteString.Lazy@ by using regex-tdfa and @@ -182,6 +183,8 @@ import Text.Regex.TDFA.String() import Text.Regex.TDFA.ByteString() import Text.Regex.TDFA.ByteString.Lazy() +import Text.Regex.TDFA.Text() +import Text.Regex.TDFA.Text.Lazy() import Text.Regex.TDFA.Sequence() import Text.Regex.TDFA.Common(Regex,CompOption(..),ExecOption(..)) --import Text.Regex.TDFA.Wrap(Regex,CompOption(..),ExecOption(..),(=~),(=~~)) diff --git a/lib/Text/Regex/TDFA/NewDFA/Engine.hs b/lib/Text/Regex/TDFA/NewDFA/Engine.hs --- a/lib/Text/Regex/TDFA/NewDFA/Engine.hs +++ b/lib/Text/Regex/TDFA/NewDFA/Engine.hs @@ -10,7 +10,7 @@ -- #ifdef __GLASGOW_HASKELL__ import GHC.Arr(STArray(..)) import GHC.ST(ST(..)) -import GHC.Prim(MutableByteArray#,RealWorld,Int#,sizeofMutableByteArray#,unsafeCoerce#) +import GHC.Exts(MutableByteArray#,RealWorld,Int#,sizeofMutableByteArray#,unsafeCoerce#) {- -- #else import Control.Monad.ST(ST) @@ -26,7 +26,7 @@ import Data.IntMap(IntMap) import qualified Data.IntMap as IMap(null,toList,lookup,insert) import Data.Maybe(catMaybes) -import Data.Monoid(Monoid(..)) +import Data.Monoid as Mon(Monoid(..)) import qualified Data.IntSet as ISet(toAscList) import Data.Array.IArray((!)) import Data.List(partition,sort,foldl',sortBy,groupBy) @@ -523,7 +523,7 @@ newMScratch :: (Index,Index) -> S.ST s (MScratch s) newMScratch b_index = do pos's <- newArray b_index Nothing - orbit's <- newArray b_index mempty + orbit's <- newArray b_index Mon.mempty return (MScratch pos's orbit's) {- COMPOSE A FUNCTION CLOSURE TO COMPARE TAG VALUES -} diff --git a/lib/Text/Regex/TDFA/NewDFA/Engine_FA.hs b/lib/Text/Regex/TDFA/NewDFA/Engine_FA.hs --- a/lib/Text/Regex/TDFA/NewDFA/Engine_FA.hs +++ b/lib/Text/Regex/TDFA/NewDFA/Engine_FA.hs @@ -10,7 +10,7 @@ -- #ifdef __GLASGOW_HASKELL__ import GHC.Arr(STArray(..)) import GHC.ST(ST(..)) -import GHC.Prim(MutableByteArray#,RealWorld,Int#,sizeofMutableByteArray#,unsafeCoerce#) +import GHC.Exts(MutableByteArray#,RealWorld,Int#,sizeofMutableByteArray#,unsafeCoerce#) {- -- #else import Control.Monad.ST(ST) @@ -27,7 +27,7 @@ import Data.IntMap(IntMap) import qualified Data.IntMap as IMap(null,toList,lookup,insert) import Data.Maybe(catMaybes) -import Data.Monoid(Monoid(..)) +import Data.Monoid as Mon(Monoid(..)) import qualified Data.IntSet as ISet(toAscList,null) import Data.Array.IArray((!)) import Data.List(sortBy,groupBy) @@ -382,7 +382,7 @@ newMScratch :: (Index,Index) -> S.ST s (MScratch s) newMScratch b_index = do pos's <- newArray b_index Nothing - orbit's <- newArray b_index mempty + orbit's <- newArray b_index Mon.mempty return (MScratch pos's orbit's) {- COMPOSE A FUNCTION CLOSURE TO COMPARE TAG VALUES -} diff --git a/lib/Text/Regex/TDFA/NewDFA/Uncons.hs b/lib/Text/Regex/TDFA/NewDFA/Uncons.hs --- a/lib/Text/Regex/TDFA/NewDFA/Uncons.hs +++ b/lib/Text/Regex/TDFA/NewDFA/Uncons.hs @@ -3,6 +3,8 @@ import qualified Data.ByteString.Char8 as SBS(ByteString,uncons) import qualified Data.ByteString.Lazy.Char8 as LBS(ByteString,uncons) import Data.Sequence(Seq,viewl,ViewL(EmptyL,(:<))) +import qualified Data.Text as T +import qualified Data.Text.Lazy as TL class Uncons a where {- INLINE uncons #-} @@ -26,3 +28,13 @@ instance Uncons LBS.ByteString where {- INLINE uncons #-} uncons = LBS.uncons + +-- | @since 1.3.1 +instance Uncons T.Text where + {- INLINE uncons #-} + uncons = T.uncons + +-- | @since 1.3.1 +instance Uncons TL.Text where + {- INLINE uncons #-} + uncons = TL.uncons diff --git a/lib/Text/Regex/TDFA/TDFA.hs b/lib/Text/Regex/TDFA/TDFA.hs --- a/lib/Text/Regex/TDFA/TDFA.hs +++ b/lib/Text/Regex/TDFA/TDFA.hs @@ -6,7 +6,7 @@ ,examineDFA,nfaToDFA,dfaMap) where --import Control.Arrow((***)) -import Data.Monoid(Monoid(..)) +import Data.Monoid as Mon(Monoid(..)) import Control.Monad.State(State,MonadState(..),execState) import Data.Array.IArray(Array,(!),bounds,{-assocs-}) import Data.IntMap(IntMap) @@ -424,7 +424,7 @@ newOrbit pos = Orbits { inOrbit = inOrbit' , basePos = pos , ordinal = Nothing - , getOrbits = mempty} + , getOrbits = Mon.mempty} updateOrbit pos _tag new old | inOrbit old = old { inOrbit = inOrbit' , getOrbits = getOrbits old |> pos } | otherwise = new diff --git a/lib/Text/Regex/TDFA/TNFA.hs b/lib/Text/Regex/TDFA/TNFA.hs --- a/lib/Text/Regex/TDFA/TNFA.hs +++ b/lib/Text/Regex/TDFA/TNFA.hs @@ -47,7 +47,7 @@ import Data.IntSet.EnumSet2(EnumSet) import qualified Data.IntSet.EnumSet2 as Set(singleton,toList,insert) import Data.Maybe(catMaybes,isNothing) -import Data.Monoid(mempty,mappend) +import Data.Monoid as Mon(Monoid(..)) import qualified Data.Set as S(Set,insert,toAscList,empty) import Text.Regex.TDFA.Common(QT(..),QNFA(..),QTrans,TagTask(..),TagUpdate(..),DoPa(..) @@ -771,7 +771,7 @@ addNewline | multiline compOpt = S.insert '\n' | otherwise = id dotTrans | multiline compOpt = Map.singleton '\n' mempty - | otherwise = mempty + | otherwise = Mon.mempty {- diff --git a/lib/Text/Regex/TDFA/Text.hs b/lib/Text/Regex/TDFA/Text.hs new file mode 100644 --- /dev/null +++ b/lib/Text/Regex/TDFA/Text.hs @@ -0,0 +1,101 @@ +{-| +Module : Text.Regex.TDFA.Text +Copyright : Chris Kuklewicz 2007-2009, shelarcy 2012 +License : BSD-style (see the file LICENSE) + +This modules provides 'RegexMaker' and 'RegexLike' instances for using +'Text' with the TDFA backend ("Text.Regex.TDFA.NewDFA.Engine" and +"Text.Regex.TDFA.NewDFA.Tester"). + +This exports instances of the high level API and the medium level +API of 'compile','execute', and 'regexec'. + +@since 1.3.1 +-} +module Text.Regex.TDFA.Text( + Regex + ,CompOption + ,ExecOption + ,compile + ,execute + ,regexec + ) where + +import Data.Array((!),elems) +import qualified Data.Text as T(Text,unpack) + +import Text.Regex.Base(RegexLike(..),RegexMaker(..),Extract(..),MatchArray,RegexContext(..)) +import Text.Regex.Base.Impl(polymatch,polymatchM) +import Text.Regex.TDFA.ReadRegex(parseRegex) +import Text.Regex.TDFA.String() -- piggyback on RegexMaker for String +import Text.Regex.TDFA.TDFA(patternToRegex) +import Text.Regex.TDFA.Common(Regex(..),CompOption,ExecOption(captureGroups),Position) + +import Data.Maybe(listToMaybe) +import Text.Regex.TDFA.NewDFA.Uncons(Uncons) +import qualified Text.Regex.TDFA.NewDFA.Engine as Engine(execMatch) +import qualified Text.Regex.TDFA.NewDFA.Tester as Tester(matchTest) + +-- | @since 1.3.1 +instance RegexContext Regex T.Text T.Text where + match = polymatch + matchM = polymatchM + +-- | @since 1.3.1 +instance RegexMaker Regex CompOption ExecOption T.Text where + makeRegexOptsM c e source = makeRegexOptsM c e (T.unpack source) + +-- | @since 1.3.1 +{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> T.Text -> [MatchArray] #-} +execMatch :: Uncons text => Regex -> Position -> Char -> text -> [MatchArray] +execMatch = Engine.execMatch + +-- | @since 1.3.1 +{-# SPECIALIZE myMatchTest :: Regex -> T.Text -> Bool #-} +myMatchTest :: Uncons text => Regex -> text -> Bool +myMatchTest = Tester.matchTest + +-- | @since 1.3.1 +instance RegexLike Regex T.Text where + matchOnce r s = listToMaybe (matchAll r s) + matchAll r s = execMatch r 0 '\n' s + matchCount r s = length (matchAll r' s) + where r' = r { regex_execOptions = (regex_execOptions r) {captureGroups = False} } + matchTest = myMatchTest + matchOnceText regex source = + fmap (\ma -> let (o,l) = ma!0 + in (before o source + ,fmap (\ol -> (extract ol source,ol)) ma + ,after (o+l) source)) + (matchOnce regex source) + matchAllText regex source = + map (fmap (\ol -> (extract ol source,ol))) + (matchAll regex source) + +-- | @since 1.3.1 +compile :: CompOption -- ^ Flags (summed together) + -> ExecOption -- ^ Flags (summed together) + -> T.Text -- ^ The regular expression to compile + -> Either String Regex -- ^ Returns: the compiled regular expression +compile compOpt execOpt txt = + case parseRegex (T.unpack txt) of + Left err -> Left ("parseRegex for Text.Regex.TDFA.Text failed:"++show err) + Right pattern -> Right (patternToRegex pattern compOpt execOpt) + +-- | @since 1.3.1 +execute :: Regex -- ^ Compiled regular expression + -> T.Text -- ^ Text to match against + -> Either String (Maybe MatchArray) +execute r txt = Right (matchOnce r txt) + +-- | @since 1.3.1 +regexec :: Regex -- ^ Compiled regular expression + -> T.Text -- ^ Text to match against + -> Either String (Maybe (T.Text, T.Text, T.Text, [T.Text])) +regexec r txt = + case matchOnceText r txt of + Nothing -> Right (Nothing) + Just (pre,mt,post) -> + let main = fst (mt!0) + rest = map fst (tail (elems mt)) -- will be [] + in Right (Just (pre,main,post,rest)) diff --git a/lib/Text/Regex/TDFA/Text/Lazy.hs b/lib/Text/Regex/TDFA/Text/Lazy.hs new file mode 100644 --- /dev/null +++ b/lib/Text/Regex/TDFA/Text/Lazy.hs @@ -0,0 +1,109 @@ +{-| +Module : Text.Regex.TDFA.Text.Lazy +Copyright : Chris Kuklewicz 2007-2009, shelarcy 2012 +License : BSD-style (see the file LICENSE) + +This modules provides 'RegexMaker' and 'RegexLike' instances for using +'Text' with the TDFA backend ("Text.Regex.TDFA.NewDFA.Engine" and +"Text.Regex.TDFA.NewDFA.Tester"). + +This exports instances of the high level API and the medium level +API of 'compile','execute', and 'regexec'. + +@since 1.3.1 +-} +module Text.Regex.TDFA.Text.Lazy( + Regex + ,CompOption + ,ExecOption + ,compile + ,execute + ,regexec + ) where + +import Data.Array.IArray(Array,(!),elems) +import qualified Data.Text.Lazy as L(Text,unpack) + +import Text.Regex.Base(MatchArray,RegexContext(..),Extract(..),RegexMaker(..),RegexLike(..)) +import Text.Regex.Base.Impl(polymatch,polymatchM) +import Text.Regex.TDFA.ReadRegex(parseRegex) +import Text.Regex.TDFA.String() -- piggyback on RegexMaker for String +import Text.Regex.TDFA.TDFA(patternToRegex) +import Text.Regex.TDFA.Common(Regex(..),CompOption,ExecOption(captureGroups),Position) + +import Data.Maybe(listToMaybe) +import Text.Regex.TDFA.NewDFA.Uncons(Uncons) +import qualified Text.Regex.TDFA.NewDFA.Engine as Engine(execMatch) +import qualified Text.Regex.TDFA.NewDFA.Tester as Tester(matchTest) + +-- | @since 1.3.1 +instance RegexContext Regex L.Text L.Text where + match = polymatch + matchM = polymatchM + +-- | @since 1.3.1 +instance RegexMaker Regex CompOption ExecOption L.Text where + makeRegexOptsM c e source = makeRegexOptsM c e (L.unpack source) + +-- | @since 1.3.1 +{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> L.Text -> [MatchArray] #-} +execMatch :: Uncons text => Regex -> Position -> Char -> text -> [MatchArray] +execMatch = Engine.execMatch + +-- | @since 1.3.1 +{-# SPECIALIZE myMatchTest :: Regex -> L.Text -> Bool #-} +myMatchTest :: Uncons text => Regex -> text -> Bool +myMatchTest = Tester.matchTest + +-- | @since 1.3.1 +instance RegexLike Regex L.Text where + matchOnce r s = listToMaybe (matchAll r s) + matchAll r s = execMatch r 0 '\n' s + matchCount r s = length (matchAll r' s) + where r' = r { regex_execOptions = (regex_execOptions r) {captureGroups = False} } + matchTest = myMatchTest + matchOnceText regex source = + fmap (\ ma -> + let (o,l) = ma!0 + in (before o source + ,fmap (\ ol -> (extract ol source,ol)) ma + ,after (o+l) source)) + (matchOnce regex source) + matchAllText regex source = + let go :: Int -> L.Text -> [Array Int (Int, Int)] -> [Array Int (L.Text, (Int, Int))] + go i _ _ | i `seq` False = undefined + go _i _t [] = [] + go i t (x:xs) = + let (off0,len0) = x!0 + trans pair@(off,len) = (extract (off-i,len) t,pair) + t' = after (off0+(len0-i)) t + in fmap trans x : seq t' (go (off0+len0) t' xs) + in go 0 source (matchAll regex source) + +-- | @since 1.3.1 +compile :: CompOption -- ^ Flags (summed together) + -> ExecOption -- ^ Flags (summed together) + -> L.Text -- ^ The regular expression to compile + -> Either String Regex -- ^ Returns: the compiled regular expression +compile compOpt execOpt txt = + case parseRegex (L.unpack txt) of + Left err -> Left ("parseRegex for Text.Regex.TDFA.Text.Lazy failed:"++show err) + Right pattern -> Right (patternToRegex pattern compOpt execOpt) + +-- | @since 1.3.1 +execute :: Regex -- ^ Compiled regular expression + -> L.Text -- ^ Text to match against + -> Either String (Maybe MatchArray) +execute r txt = Right (matchOnce r txt) + +-- | @since 1.3.1 +regexec :: Regex -- ^ Compiled regular expression + -> L.Text -- ^ Text to match against + -> Either String (Maybe (L.Text, L.Text, L.Text, [L.Text])) +regexec r txt = + case matchOnceText r txt of + Nothing -> Right (Nothing) + Just (pre,mt,post) -> + let main = fst (mt!0) + rest = map fst (tail (elems mt)) -- will be [] + in Right (Just (pre,main,post,rest)) diff --git a/regex-tdfa.cabal b/regex-tdfa.cabal --- a/regex-tdfa.cabal +++ b/regex-tdfa.cabal @@ -1,17 +1,16 @@ -Name: regex-tdfa -Version: 1.3.0 -License: BSD3 -License-File: LICENSE -Copyright: Copyright (c) 2007, Christopher Kuklewicz -Author: Christopher Kuklewicz -Maintainer: Artyom , Christopher Kuklewicz -Stability: Seems to work, but not POSIX yet -Homepage: https://github.com/ChrisKuklewicz/regex-tdfa -Bug-Reports: https://github.com/ChrisKuklewicz/regex-tdfa/issues -Synopsis: Replaces/Enhances Text.Regex -Description: A new all Haskell "tagged" DFA regex engine, inspired by libtre -Category: Text -Tested-With: GHC==7.6.3 +cabal-version: 1.12 +name: regex-tdfa +version: 1.3.1.0 + +build-Type: Simple +license: BSD3 +license-file: LICENSE +copyright: Copyright (c) 2007-2009, Christopher Kuklewicz +author: Christopher Kuklewicz +maintainer: hvr@gnu.org +bug-reports: https://github.com/hvr/regex-tdfa/issues +tested-with: GHC==7.4.2 + , GHC==7.6.3 , GHC==7.8.4 , GHC==7.10.3 , GHC==8.0.2 @@ -19,32 +18,61 @@ , GHC==8.4.4 , GHC==8.6.5 , GHC==8.8.1 -Build-Type: Simple + +category: Text +synopsis: Pure Haskell Tagged DFA Backend for "Text.Regex" (regex-base) +description: + This package provides a pure Haskell \"Tagged\" DFA regex engine for . This implementation was inspired by the algorithm (and Master's thesis) behind the regular expression library known as . + . + Please consult the "Text.Regex.TDFA" module for API documentation including a tutorial with usage examples; + see also for general information about regular expression support in Haskell. + extra-source-files: CHANGELOG.md test/cases/*.txt -Cabal-Version: >= 1.8 source-repository head type: git - location: git://github.com/ChrisKuklewicz/regex-tdfa.git + location: https://github.com/hvr/regex-tdfa.git -flag devel - description: enable flags that are useful for development +flag force-O2 default: False manual: True + description: + Force building @regex-tdfa@ with \"@ghc-options: -O2@\". + . + __NOTE__: This flag is mostly provided for legacy use-cases. Nowadays you can conveniently control optimization levels on a per-package granularity via @cabal.project@ files; see for more details. library hs-source-dirs: lib - Build-Depends: array >= 0.4 && < 0.6 - , base >= 4 && < 5 - , bytestring >= 0.10 && < 0.11 - , containers >= 0.5 && < 0.7 - , ghc-prim - , mtl == 2.* - , parsec == 3.* - , regex-base >= 0.93.1 && < 0.95 + exposed-modules: Data.IntMap.CharMap2 + Data.IntMap.EnumMap2 + Data.IntSet.EnumSet2 + Text.Regex.TDFA + Text.Regex.TDFA.ByteString + Text.Regex.TDFA.ByteString.Lazy + Text.Regex.TDFA.Common + Text.Regex.TDFA.CorePattern + Text.Regex.TDFA.IntArrTrieSet + Text.Regex.TDFA.NewDFA.Engine + Text.Regex.TDFA.NewDFA.Engine_FA + Text.Regex.TDFA.NewDFA.Engine_NC + Text.Regex.TDFA.NewDFA.Engine_NC_FA + Text.Regex.TDFA.NewDFA.Tester + Text.Regex.TDFA.NewDFA.Uncons + Text.Regex.TDFA.NewDFA.MakeTest + Text.Regex.TDFA.Pattern + Text.Regex.TDFA.ReadRegex + Text.Regex.TDFA.Sequence + Text.Regex.TDFA.String + Text.Regex.TDFA.TDFA + Text.Regex.TDFA.TNFA + Text.Regex.TDFA.Text + Text.Regex.TDFA.Text.Lazy + + other-modules: Paths_regex_tdfa + -- Support Semigroup instances uniformly -- -- See also @@ -54,46 +82,75 @@ -- add any new dependency that isn't already incurred by -- `regex-tdfa`'s transitive deps if !impl(ghc >= 8.0) - build-depends: fail - , semigroups == 0.18.* + build-depends: fail == 4.9.* + , semigroups == 0.18.* || == 0.19.* + build-depends: array >= 0.4 && < 0.6 + , base >= 4.5 && < 4.14 + , bytestring >= 0.9.2 && < 0.11 + , containers >= 0.4.2 && < 0.7 + , mtl >= 2.1.3 && < 2.3 + , parsec == 3.1.* + , regex-base == 0.94.* + , text >= 1.2.3 && < 1.3 - other-modules: Paths_regex_tdfa - Exposed-Modules: Data.IntMap.CharMap2 - Data.IntMap.EnumMap2 - Data.IntSet.EnumSet2 - Text.Regex.TDFA - Text.Regex.TDFA.ByteString - Text.Regex.TDFA.ByteString.Lazy - Text.Regex.TDFA.Common - Text.Regex.TDFA.CorePattern - Text.Regex.TDFA.IntArrTrieSet - Text.Regex.TDFA.NewDFA.Engine - Text.Regex.TDFA.NewDFA.Engine_FA - Text.Regex.TDFA.NewDFA.Engine_NC - Text.Regex.TDFA.NewDFA.Engine_NC_FA - Text.Regex.TDFA.NewDFA.Tester - Text.Regex.TDFA.NewDFA.Uncons - Text.Regex.TDFA.NewDFA.MakeTest - Text.Regex.TDFA.Pattern - Text.Regex.TDFA.ReadRegex - Text.Regex.TDFA.Sequence - Text.Regex.TDFA.String - Text.Regex.TDFA.TDFA - Text.Regex.TDFA.TNFA - Buildable: True - Extensions: MultiParamTypeClasses, FunctionalDependencies, BangPatterns, MagicHash, RecursiveDo, NoMonoPatBinds, ForeignFunctionInterface, UnboxedTuples, TypeOperators, FlexibleContexts, ExistentialQuantification, UnliftedFFITypes, TypeSynonymInstances, FlexibleInstances - GHC-Options: -Wall -funbox-strict-fields -fspec-constr-count=10 -O2 -fno-warn-orphans - if flag(devel) - ghc-prof-options: -auto-all + default-language: Haskell2010 + default-extensions: BangPatterns + ExistentialQuantification + FlexibleContexts + FlexibleInstances + ForeignFunctionInterface + FunctionalDependencies + MagicHash + MultiParamTypeClasses + NoMonoPatBinds + NondecreasingIndentation + RecursiveDo + TypeOperators + TypeSynonymInstances + UnboxedTuples + UnliftedFFITypes + other-extensions: CPP + ghc-options: -Wall -funbox-strict-fields -fspec-constr-count=10 -fno-warn-orphans + + if flag(force-O2) + ghc-options: -O2 + + test-suite regex-tdfa-unittest type: exitcode-stdio-1.0 - build-depends: regex-base >= 0.93.1, base >=4 && < 5, regex-tdfa >= 0.92, bytestring, containers, array, mtl, file-embed, filepath, utf8-string + hs-source-dirs: test main-is: Main.hs - extensions: FlexibleInstances, FlexibleContexts,Rank2Types - GHC-Options: -Wall -O2 -funbox-strict-fields - if flag(devel) - ghc-prof-options: -auto-all + + -- intra-package dependency + build-depends: regex-tdfa + + -- dependencies whose version constraints are inherited via intra-package 'regex-tdfa' dependency if !impl(ghc >= 8.0) build-depends: fail + , semigroups + build-depends: array + , base + , bytestring + , containers + , filepath + , mtl + , regex-base + , text + + -- component-specific dependencies not inherited via 'regex-tdfa' + , directory >= 1.1.0 && < 1.4 + , filepath >= 1.3.0 && < 1.5 + , utf8-string >= 1.0.1 && < 1.1 + + default-language: Haskell2010 + default-extensions: FlexibleInstances + FlexibleContexts + Rank2Types + other-extensions: GeneralizedNewtypeDeriving + + ghc-options: -Wall -funbox-strict-fields + + if flag(force-O2) + ghc-options: -O2 diff --git a/test/Main.hs b/test/Main.hs --- a/test/Main.hs +++ b/test/Main.hs @@ -1,28 +1,25 @@ -{-# LANGUAGE TemplateHaskell #-} {-# LANGUAGE GeneralizedNewtypeDeriving #-} +{-# LANGUAGE MonoLocalBinds #-} module Main where -import Control.Monad -import Control.Monad.Error() -import Data.Array -import Data.List -import Control.Applicative ---import Data.Monoid -import Data.Sequence(Seq) -import Data.String -import Data.Typeable -import Data.Version() -import System.Environment -import Text.Regex.Base -import qualified Data.Foldable as F -import Data.FileEmbed +import Control.Applicative as App +import Control.Monad +import qualified Control.Monad.Fail as Fail +import Data.Array +import qualified Data.ByteString as BS import qualified Data.ByteString.UTF8 as UTF8 -import qualified Control.Monad.Fail as Fail -import System.Exit +import Data.List +import Data.String +import Data.Typeable +import Data.Version () +import System.Directory (getDirectoryContents) +import System.Environment +import System.Exit +import System.FilePath (()) +import Text.Regex.Base -import qualified Text.Regex.TDFA.Common as TDFA -import qualified Text.Regex.TDFA as TDFA +import qualified Text.Regex.TDFA as TDFA default(Int) @@ -55,18 +52,18 @@ toTest :: String -> (Int,String,String,String) toTest line = let [n,regex,input,output] = words line - noQ [] = [] + noQ [] = [] noQ ('?':xs) = '-':'1':noQ xs - noQ (x:xs) = x:noQ xs + noQ (x:xs) = x:noQ xs input' = if input == "NULL" then "" else unN input in (read n,regex,input',noQ output) toTest' :: String -> String -> (String,(Int,String,String,String)) toTest' oldRegex line = let [n,regex,input,output] = words line - noQ [] = [] + noQ [] = [] noQ ('?':xs) = '-':'1':noQ xs - noQ (x:xs) = x:noQ xs + noQ (x:xs) = x:noQ xs input' = if input == "NULL" then "" else input regex' = if regex == "SAME" then oldRegex else regex in (regex',(read n,regex',input',noQ output)) @@ -107,22 +104,26 @@ p ("Actual result : "++show output') return (if n<0 then [] else [n]) -checkFile :: (RType -> RSource -> Result A) -> (String, String) -> IO (String,[Int]) +checkFile :: (RType -> RSource -> Result A) -> (FilePath, String) -> IO (FilePath,[Int]) checkFile opM (filepath, contents) = do putStrLn $ "\nUsing Tests from: "++filepath vals <- liftM concat (mapM (checkTest opM) (load' contents)) return (filepath,vals) -checkTests :: (RType -> RSource -> Result A) -> IO [(String, [Int])] -checkTests opM = mapM (checkFile opM) testCases +checkTests :: (RType -> RSource -> Result A) -> [(FilePath,String)] -> IO [(String, [Int])] +checkTests opM testCases = mapM (checkFile opM) testCases -testCases :: [(String, String)] -testCases = - map (\(filename, contents) -> (filename, UTF8.toString contents)) $ - $(embedDir =<< makeRelativeToProject "test/cases") +readTestCases :: FilePath -> IO [(String, String)] +readTestCases folder = do + fns <- filter (isSuffixOf ".txt") <$> getDirectoryContents folder + when (null fns) $ + fail ("readTestCases: No test-cases found in " ++ show folder) + forM (sort fns) $ \fn -> do + bs <- BS.readFile (folder fn) + return (fn, UTF8.toString bs) newtype Result a = Result (Either String a) - deriving (Eq, Show, Functor, Applicative, Monad) + deriving (Eq, Show, Functor, App.Applicative, Monad) instance Fail.MonadFail Result where fail = Result . Left @@ -137,8 +138,8 @@ unN :: String -> String unN ('\\':'n':xs) = '\n':unN xs -unN (x:xs) = x:unN xs -unN [] = [] +unN (x:xs) = x:unN xs +unN [] = [] manual :: [String] -> IO () manual [sIn,rIn] = do @@ -178,7 +179,7 @@ putStrLn $ "With exactly two arguments:" putStrLn $ " The first argument is the text to be searched." putStrLn $ " The second argument is the regular expression pattern to search with." - vals <- checkTests posix + vals <- checkTests posix =<< readTestCases ("test" "cases") if null (concatMap snd vals) then putStrLn "\nWow, all the tests passed!" else do