Skip to content

Add specializations for Text, makes maching 2 times faster #72

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 29, 2025
Merged

Add specializations for Text, makes maching 2 times faster #72

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions lib/Text/Regex/TDFA/NewDFA/Engine.hs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,8 @@ import Data.Sequence(Seq,ViewL(..),viewl)
import qualified Data.Sequence as Seq(null)
import qualified Data.ByteString.Char8 as SBS(ByteString)
import qualified Data.ByteString.Lazy.Char8 as LBS(ByteString)
import qualified Data.Text as T
import qualified Data.Text.Lazy as TL
import Foreign.Ptr(Ptr)

import Text.Regex.Base(MatchArray,MatchOffset,MatchLength)
Expand Down Expand Up @@ -82,6 +84,8 @@ set = unsafeWrite
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> (Seq Char) -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> SBS.ByteString -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> LBS.ByteString -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> T.Text -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> TL.Text -> [MatchArray] #-}
execMatch :: Uncons text => Regex -> Position -> Char -> text -> [MatchArray]
execMatch r@(Regex { regex_dfa = DFA {d_id=didIn,d_dt=dtIn}
, regex_init = startState
Expand Down
4 changes: 4 additions & 0 deletions lib/Text/Regex/TDFA/NewDFA/Engine_NC.hs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@ import qualified Control.Monad.ST.Strict as S(ST)
import Data.Sequence(Seq)
import qualified Data.ByteString.Char8 as SBS(ByteString)
import qualified Data.ByteString.Lazy.Char8 as LBS(ByteString)
import qualified Data.Text as T
import qualified Data.Text.Lazy as TL

import Text.Regex.Base(MatchArray,MatchOffset,MatchLength)
import qualified Text.Regex.TDFA.IntArrTrieSet as Trie(lookupAsc)
Expand All @@ -44,6 +46,8 @@ set = unsafeWrite
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> (Seq Char) -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> SBS.ByteString -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> LBS.ByteString -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> T.Text -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> TL.Text -> [MatchArray] #-}
execMatch :: Uncons text => Regex -> Position -> Char -> text -> [MatchArray]
execMatch (Regex { regex_dfa = (DFA {d_id=didIn,d_dt=dtIn})
, regex_init = startState
Expand Down
4 changes: 4 additions & 0 deletions lib/Text/Regex/TDFA/NewDFA/Engine_NC_FA.hs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@ import qualified Control.Monad.ST.Strict as S(ST,runST)
import Data.Sequence(Seq)
import qualified Data.ByteString.Char8 as SBS(ByteString)
import qualified Data.ByteString.Lazy.Char8 as LBS(ByteString)
import qualified Data.Text as T
import qualified Data.Text.Lazy as TL

import Text.Regex.Base(MatchArray,MatchOffset,MatchLength)
import Text.Regex.TDFA.Common hiding (indent)
Expand All @@ -31,6 +33,8 @@ import Text.Regex.TDFA.NewDFA.MakeTest(test_singleline)
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> (Seq Char) -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> SBS.ByteString -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> LBS.ByteString -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> T.Text -> [MatchArray] #-}
{-# SPECIALIZE execMatch :: Regex -> Position -> Char -> TL.Text -> [MatchArray] #-}
execMatch :: Uncons text => Regex -> Position -> Char -> text -> [MatchArray]
execMatch (Regex { regex_dfa = DFA {d_dt=dtIn} })
offsetIn _prevIn inputIn = S.runST goNext where
Expand Down
4 changes: 4 additions & 0 deletions lib/Text/Regex/TDFA/NewDFA/Tester.hs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ import qualified Data.IntSet as ISet(null)
import Data.Sequence(Seq)
import qualified Data.ByteString.Char8 as SBS(ByteString)
import qualified Data.ByteString.Lazy.Char8 as LBS(ByteString)
import qualified Data.Text as T
import qualified Data.Text.Lazy as TL

import Text.Regex.Base()
import Text.Regex.TDFA.Common hiding (indent)
Expand All @@ -19,6 +21,8 @@ import Text.Regex.TDFA.NewDFA.MakeTest(test_singleline,test_multiline)
{-# SPECIALIZE matchTest :: Regex -> (Seq Char) -> Bool #-}
{-# SPECIALIZE matchTest :: Regex -> SBS.ByteString -> Bool #-}
{-# SPECIALIZE matchTest :: Regex -> LBS.ByteString -> Bool #-}
{-# SPECIALIZE matchTest :: Regex -> T.Text -> Bool #-}
{-# SPECIALIZE matchTest :: Regex -> TL.Text -> Bool #-}
matchTest :: Uncons text => Regex -> text -> Bool
matchTest (Regex { regex_dfa = dfaIn
, regex_isFrontAnchored = ifa } )
Expand Down