diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -1,5 +1,9 @@ # Changelog and Acknowledgements +## 2.3.1 +* Fixed [#52](https://github.com/sjshuck/hs-pcre2/issues/52) where the caret + appeared in the wrong place. + ## 2.3.0 * Disabled building JIT by default. * Removed various JIT-related functions and constants from diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -7,11 +7,14 @@ ## Teasers ```haskell -licensePlate :: Text -> Maybe Text -licensePlate = match "[A-Z]{3}[0-9]{3,4}" +licensePlateRegex :: (Alternative f) => Text -> f Text +licensePlateRegex = match "[A-Z]{3}[0-9]{3,4}" -licensePlates :: Text -> [Text] -licensePlates = match "[A-Z]{3}[0-9]{3,4}" +firstLicensePlate :: Text -> Maybe Text +firstLicensePlate = licensePlateRegex + +allLicensePlates :: Text -> [Text] +allLicensePlates = licensePlateRegex ``` ```haskell case "The quick brown fox" of @@ -31,16 +34,21 @@ \s*$ # Ignore trailing whitespace |] -forMOf kv'd file $ execStateT $ do - k <- gets $ capture @1 - v <- gets $ capture @2 - liftIO $ Text.putStrLn $ "found " <> k <> " set to " <> v +forOf kv'd file $ \kv -> do + let k = capture @1 kv + v = capture @2 kv - case myMap ^. at k of + Text.putStrLn $ "found " <> k <> " set to " <> v + + kv' <- case Map.lookup k replacements of Just v' | v /= v' -> do - liftIO $ Text.putStrLn $ "setting " <> k <> " to " <> v' - _capture @2 .= v' - _ -> liftIO $ Text.putStrLn $ "no change for " <> k + Text.putStrLn $ "setting " <> k <> " to " <> v' + return $ set (_capture @2) v' kv + _ -> do + Text.putStrLn $ "no change for " <> k + return kv + + ... ``` ## Features @@ -49,7 +57,6 @@ `-> result`. * No [custom typeclasses](https://hackage.haskell.org/package/regex-base/docs/Text-Regex-Base-RegexLike.html#t:RegexContext). * A single datatype for both compile and match options, the `Option` monoid. -* UTF-8 `Text` everywhere. * Match success expressed via `Alternative`. * Opt-in Template Haskell facilities for compile-time verification of patterns, indexing captures, and memoizing inline regexes. @@ -66,14 +73,9 @@ complete, exposed Haskell binding. ## Performance -Currently we are slower than other libraries. The difference is less pronounced -for `Text` where no conversions are necessary to use this library. +Currently (2026-05-02) we are much slower than other libraries. -| Operation | `pcre2` | `regex-pcre-builtin` | `pcre-light` | -| :-- | --: | --: | --: | -| Matching a `String` | 1.22 μs | 0.34 μs | 0.23 μs | -| Matching a `Text` (shorter) | 1.22 μs | 0.93 μs | 0.29 μs | -| Matching a `Text` (longer) | 1.89 μs | 1.52 μs | 11.12 μs | +![Benchmarks graph](https://raw.githubusercontent.com/sjshuck/hs-pcre2/master/bench/bench.svg) If it's really regex processing that's causing a bottleneck, [pcre-light](https://hackage.haskell.org/package/pcre-light)/[-heavy](https://hackage.haskell.org/package/pcre-heavy)/[lens-regex-pcre](https://hackage.haskell.org/package/lens-regex-pcre) @@ -85,6 +87,7 @@ some upstream changes as well but in theory it's possible. * Improve compile time. * Support external `libpcre2` maybe. +* Support more types than just `Text`. ## License [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html). diff --git a/bench/Bench.hs b/bench/Bench.hs --- a/bench/Bench.hs +++ b/bench/Bench.hs @@ -1,21 +1,20 @@ {-# LANGUAGE DataKinds #-} {-# LANGUAGE LambdaCase #-} {-# LANGUAGE QuasiQuotes #-} -{-# LANGUAGE TypeApplications #-} {-# LANGUAGE ViewPatterns #-} module Main where -import Criterion.Main -import Data.List.NonEmpty (NonEmpty(..)) -import qualified Data.Text as Text -import Lens.Micro.Platform -import System.IO.Unsafe (unsafePerformIO) -import qualified Text.Regex.PCRE -import qualified Text.Regex.PCRE.Light.Char8 -import qualified Text.Regex.PCRE.String -import qualified Text.Regex.PCRE.Text -import Text.Regex.Pcre2 +import Data.List.NonEmpty (NonEmpty(..)) +import Data.Text qualified as Text +import Lens.Micro.Platform +import System.IO.Unsafe (unsafePerformIO) +import Test.Tasty.Bench +import Text.Regex.PCRE qualified +import Text.Regex.PCRE.Light.Char8 qualified +import Text.Regex.PCRE.String qualified +import Text.Regex.PCRE.Text qualified +import Text.Regex.Pcre2 main :: IO () main = defaultMain [ @@ -52,9 +51,9 @@ in bar], bgroup "texts" [ - bgroupTexts "short" strings, + bgroupTexts "shorter" strings, - bgroupTexts "long" ( + bgroupTexts "longer" ( "foo (ba*r) baz", "foo b" ++ replicate 1000 'a' ++ "r baz")], diff --git a/pcre2.cabal b/pcre2.cabal --- a/pcre2.cabal +++ b/pcre2.cabal @@ -1,11 +1,11 @@ cabal-version: 1.12 --- This file has been generated from package.yaml by hpack version 0.38.1. +-- This file has been generated from package.yaml by hpack version 0.39.1. -- -- see: https://github.com/sol/hpack name: pcre2 -version: 2.3.0 +version: 2.3.1 synopsis: Regular expressions via the PCRE2 C library (included) description: Please see the README on GitHub at category: Text @@ -203,7 +203,7 @@ , mtl , template-haskell , text >=2 - default-language: Haskell2010 + default-language: GHC2021 if os(darwin) ghc-options: -optc=-Wno-ignored-qualifiers else @@ -231,7 +231,7 @@ , tasty-hunit , template-haskell , text >=2 - default-language: Haskell2010 + default-language: GHC2021 benchmark pcre2-benchmarks type: exitcode-stdio-1.0 @@ -240,17 +240,17 @@ Paths_pcre2 hs-source-dirs: bench - ghc-options: -threaded -rtsopts -with-rtsopts=-N + ghc-options: -rtsopts build-depends: base >=4.9 && <5 , containers - , criterion , microlens , microlens-platform , mtl , pcre-light , pcre2 , regex-pcre-builtin + , tasty-bench , template-haskell , text >=2 - default-language: Haskell2010 + default-language: GHC2021 diff --git a/src/hs/Text/Regex/Pcre2.hs b/src/hs/Text/Regex/Pcre2.hs --- a/src/hs/Text/Regex/Pcre2.hs +++ b/src/hs/Text/Regex/Pcre2.hs @@ -290,8 +290,8 @@ -- * User errors SomePcre2Exception(), Pcre2Exception(), - Pcre2CompileException()) -where + Pcre2CompileException(), +) where import Text.Regex.Pcre2.Internal import Text.Regex.Pcre2.TH diff --git a/src/hs/Text/Regex/Pcre2/Internal.hs b/src/hs/Text/Regex/Pcre2/Internal.hs --- a/src/hs/Text/Regex/Pcre2/Internal.hs +++ b/src/hs/Text/Regex/Pcre2/Internal.hs @@ -1,35 +1,32 @@ -{-# LANGUAGE DeriveFunctor #-} -{-# LANGUAGE ExistentialQuantification #-} {-# LANGUAGE LambdaCase #-} {-# LANGUAGE MultiWayIf #-} -{-# LANGUAGE RankNTypes #-} {-# LANGUAGE RecordWildCards #-} module Text.Regex.Pcre2.Internal where -import Control.Applicative (Alternative(..)) -import Control.Exception -import Control.Monad -import Control.Monad.Cont -import Control.Monad.State.Strict -import Data.Either (partitionEithers) -import Data.Foldable (foldl', toList) -import Data.Functor.Identity (Identity(..)) -import Data.IORef -import Data.List.NonEmpty (NonEmpty(..)) -import Data.Maybe (fromMaybe) -import Data.Monoid (Alt(..), First) -import Data.Proxy (Proxy(..)) -import Data.Text (Text) -import qualified Data.Text as Text -import qualified Data.Text.Foreign as Text -import Data.Typeable (cast) -import Foreign -import Foreign.C.Types (CInt(..), CUChar, CUInt(..)) -import Lens.Micro -import Lens.Micro.Extras (preview, view) -import System.IO.Unsafe (unsafePerformIO) -import Text.Regex.Pcre2.Foreign +import Control.Applicative (Alternative(..)) +import Control.Exception +import Control.Monad +import Control.Monad.Cont +import Control.Monad.State.Strict +import Data.Either (partitionEithers) +import Data.Foldable (foldl', toList) +import Data.Functor.Identity (Identity(..)) +import Data.IORef +import Data.List.NonEmpty (NonEmpty(..)) +import Data.Maybe (fromMaybe) +import Data.Monoid (Alt(..), First) +import Data.Proxy (Proxy(..)) +import Data.Text (Text) +import Data.Text qualified as Text +import Data.Text.Foreign qualified as Text +import Data.Typeable (cast) +import Foreign +import Foreign.C.Types (CInt(..), CUChar, CUInt(..)) +import Lens.Micro +import Lens.Micro.Extras (preview, view) +import System.IO.Unsafe (unsafePerformIO) +import Text.Regex.Pcre2.Foreign -- * General utilities @@ -1156,7 +1153,8 @@ -- FIXME Do not use Text.length since offsets are in code units | offset' == Text.length patt = pattLines | otherwise = insertCaretLine numberedPattLines - offset' = fromIntegral offset + -- See https://github.com/PCRE2Project/pcre2/issues/906 + offset' = max (fromIntegral offset - 1) 0 pattLines = unchompedLines $ Text.unpack patt numberedPattLines = zip [0 :: Int ..] pattLines (caretRow, caretCol) = (!! offset') $ do diff --git a/src/hs/Text/Regex/Pcre2/TH.hs b/src/hs/Text/Regex/Pcre2/TH.hs --- a/src/hs/Text/Regex/Pcre2/TH.hs +++ b/src/hs/Text/Regex/Pcre2/TH.hs @@ -1,43 +1,38 @@ {-# LANGUAGE AllowAmbiguousTypes #-} {-# LANGUAGE DataKinds #-} {-# LANGUAGE LambdaCase #-} -{-# LANGUAGE PolyKinds #-} -{-# LANGUAGE RankNTypes #-} -{-# LANGUAGE ScopedTypeVariables #-} {-# LANGUAGE TemplateHaskell #-} -{-# LANGUAGE TypeApplications #-} {-# LANGUAGE TypeFamilies #-} -{-# LANGUAGE TypeOperators #-} {-# LANGUAGE UndecidableInstances #-} module Text.Regex.Pcre2.TH where -import Control.Applicative (Alternative(..)) -import Control.Monad (forM) -import Control.Monad.State.Strict (evalStateT) -import Data.IORef -import Data.List (sortBy) -import Data.List.NonEmpty (NonEmpty) -import Data.Map.Lazy (Map) -import qualified Data.Map.Lazy as Map -import Data.Ord (comparing) -import Data.Proxy (Proxy(..)) -import Data.Text (Text) -import qualified Data.Text as Text -import qualified Data.Text.Foreign as Text -import Data.Type.Bool (If) -import Foreign -import Foreign.C (CUChar, CUInt) -import GHC.TypeLits hiding (Text) -import qualified GHC.TypeLits as TypeLits -import Language.Haskell.TH -import Language.Haskell.TH.Quote -import Language.Haskell.TH.Syntax (liftData) -import Lens.Micro -import Lens.Micro.Extras (view) -import System.IO.Unsafe (unsafePerformIO) -import Text.Regex.Pcre2.Foreign -import Text.Regex.Pcre2.Internal +import Control.Applicative (Alternative(..)) +import Control.Monad (forM) +import Control.Monad.State.Strict (evalStateT) +import Data.IORef +import Data.List (sortBy) +import Data.List.NonEmpty (NonEmpty) +import Data.Map.Lazy (Map) +import Data.Map.Lazy qualified as Map +import Data.Ord (comparing) +import Data.Proxy (Proxy(..)) +import Data.Text (Text) +import Data.Text qualified as Text +import Data.Text.Foreign qualified as Text +import Data.Type.Bool (If) +import Foreign +import Foreign.C (CUChar, CUInt) +import GHC.TypeLits hiding (Text) +import GHC.TypeLits qualified as TypeLits +import Language.Haskell.TH +import Language.Haskell.TH.Quote (QuasiQuoter(..)) +import Language.Haskell.TH.Syntax (liftData) +import Lens.Micro +import Lens.Micro.Extras (view) +import System.IO.Unsafe (unsafePerformIO) +import Text.Regex.Pcre2.Foreign +import Text.Regex.Pcre2.Internal -- | A wrapper around a list of captures that carries additional type-level -- information about the number and names of those captures. @@ -59,7 +54,8 @@ -- | Look up the number of a capture at compile time, either by number or by -- name. Throw a helpful 'TypeError' if the index doesn't exist. -type family CaptNum (i :: k) (info :: CapturesInfo) :: Nat where +type CaptNum :: k -> CapturesInfo -> Nat +type family CaptNum i info where CaptNum (i :: Nat) '(hi, _) = If (i <=? hi) {- then -} i {- else -} (TypeError diff --git a/src/hs/Text/Regex/Pcre2/Unsafe.hs b/src/hs/Text/Regex/Pcre2/Unsafe.hs --- a/src/hs/Text/Regex/Pcre2/Unsafe.hs +++ b/src/hs/Text/Regex/Pcre2/Unsafe.hs @@ -28,8 +28,8 @@ CalloutIndex(..), CalloutResult(..), SubCalloutInfo(..), - SubCalloutResult(..)) -where + SubCalloutResult(..), +) where import Text.Regex.Pcre2.Internal import Text.Regex.Pcre2.TH diff --git a/test/Spec.hs b/test/Spec.hs --- a/test/Spec.hs +++ b/test/Spec.hs @@ -2,26 +2,24 @@ {-# LANGUAGE DataKinds #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE QuasiQuotes #-} -{-# LANGUAGE ScopedTypeVariables #-} -{-# LANGUAGE TypeApplications #-} {-# LANGUAGE ViewPatterns #-} module Main where -import Control.Applicative (Alternative) -import Control.Exception -import Control.Monad (forM_, void) -import Control.Monad.RWS.Lazy (RWS, ask, evalRWS, tell) -import Data.IORef (modifyIORef', newIORef, readIORef) -import Data.List.NonEmpty (NonEmpty(..)) -import Data.Text (Text) -import qualified Data.Text as Text -import Lens.Micro.Platform -import Test.Tasty (defaultMain, testGroup) -import Test.Tasty.HUnit -import Text.Printf (printf) -import Text.Regex.Pcre2 -import Text.Regex.Pcre2.Unsafe +import Control.Applicative (Alternative) +import Control.Exception +import Control.Monad (forM_, unless, void) +import Control.Monad.RWS.Lazy (RWS, ask, evalRWS, tell) +import Data.IORef (modifyIORef', newIORef, readIORef) +import Data.List.NonEmpty (NonEmpty(..)) +import Data.Text (Text) +import Data.Text qualified as Text +import Lens.Micro.Platform +import Test.Tasty (defaultMain, testGroup) +import Test.Tasty.HUnit +import Text.Printf (printf) +import Text.Regex.Pcre2 +import Text.Regex.Pcre2.Unsafe main :: IO () main = defaultMain $ testGroup "tests" [ @@ -139,7 +137,20 @@ testCase "are catchable using instance Alternative IO" $ do let example = handle @SomePcre2Exception (\_ -> return "broken") $ broken "foo" - example >>= (@?= "broken")], + example >>= (@?= "broken"), + + testCase ("show the caret in the right place" `issue` 52) $ do + infoOrE <- try @Pcre2CompileException $ + predictCapturesInfo mempty "abc)def" + msg <- case infoOrE of + Right _ -> assertFailure "regex compiled" + Left e -> return $ displayException e + case lines msg of + [_, pattLine, caretLine] -> + assertBool ("caret doesn't line up:\n" ++ msg) $ + (')', '^') `elem` zip pattLine caretLine + _ -> assertFailure $ + "didn't get 3-line message, got:\n" ++ msg], testGroup "native substitution" [ testCase "works using sub" $ do