diff --git a/README.markdown b/README.markdown --- a/README.markdown +++ b/README.markdown @@ -74,6 +74,8 @@     ☒  2017-03-31 v0.12.0.0 [Move IsRegex into Text.RE](https://github.com/iconnect/regex/milestone/16) +    ☒  2017-04-02 v0.13.0.0 [Protect findCaptureID and add Find, re-sort-imports, tutorials](https://github.com/iconnect/regex/milestone/17) +     ☐  2017-04-03 v1.0.0.0 [First stable release](https://github.com/iconnect/regex/milestone/3)     ☐  2017-08-31 v2.0.0.0 [Fast text replacement with benchmarks](https://github.com/iconnect/regex/milestone/4) diff --git a/Text/RE/REOptions.lhs b/Text/RE/REOptions.lhs --- a/Text/RE/REOptions.lhs +++ b/Text/RE/REOptions.lhs @@ -23,8 +23,8 @@ , emptyMacros ) where -import Data.Hashable import qualified Data.HashMap.Strict as HM +import Data.Hashable import Data.String import Language.Haskell.TH import Language.Haskell.TH.Syntax diff --git a/Text/RE/TDFA/ByteString.hs b/Text/RE/TDFA/ByteString.hs --- a/Text/RE/TDFA/ByteString.hs +++ b/Text/RE/TDFA/ByteString.hs @@ -59,9 +59,9 @@ , module Text.RE.ZeInternals.SearchReplace.TDFA.ByteString ) where -import Prelude.Compat import qualified Data.ByteString as B import Data.Typeable +import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace import Text.RE.ZeInternals.AddCaptureNames diff --git a/Text/RE/TDFA/ByteString/Lazy.hs b/Text/RE/TDFA/ByteString/Lazy.hs --- a/Text/RE/TDFA/ByteString/Lazy.hs +++ b/Text/RE/TDFA/ByteString/Lazy.hs @@ -59,9 +59,9 @@ , module Text.RE.ZeInternals.SearchReplace.TDFA.ByteString.Lazy ) where -import Prelude.Compat import qualified Data.ByteString.Lazy.Char8 as LBS import Data.Typeable +import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace import Text.RE.ZeInternals.AddCaptureNames diff --git a/Text/RE/TDFA/Sequence.hs b/Text/RE/TDFA/Sequence.hs --- a/Text/RE/TDFA/Sequence.hs +++ b/Text/RE/TDFA/Sequence.hs @@ -59,9 +59,9 @@ , module Text.RE.ZeInternals.SearchReplace.TDFA.Sequence ) where -import Prelude.Compat import qualified Data.Sequence as S import Data.Typeable +import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace import Text.RE.ZeInternals.AddCaptureNames diff --git a/Text/RE/TDFA/String.hs b/Text/RE/TDFA/String.hs --- a/Text/RE/TDFA/String.hs +++ b/Text/RE/TDFA/String.hs @@ -59,9 +59,9 @@ , module Text.RE.ZeInternals.SearchReplace.TDFA.String ) where -import Prelude.Compat import Data.Typeable +import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace import Text.RE.ZeInternals.AddCaptureNames diff --git a/Text/RE/TDFA/Text.hs b/Text/RE/TDFA/Text.hs --- a/Text/RE/TDFA/Text.hs +++ b/Text/RE/TDFA/Text.hs @@ -59,9 +59,9 @@ , module Text.RE.ZeInternals.SearchReplace.TDFA.Text ) where -import Prelude.Compat import qualified Data.Text as T import Data.Typeable +import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace import Text.RE.ZeInternals.AddCaptureNames diff --git a/Text/RE/TDFA/Text/Lazy.hs b/Text/RE/TDFA/Text/Lazy.hs --- a/Text/RE/TDFA/Text/Lazy.hs +++ b/Text/RE/TDFA/Text/Lazy.hs @@ -59,9 +59,9 @@ , module Text.RE.ZeInternals.SearchReplace.TDFA.Text.Lazy ) where -import Prelude.Compat import qualified Data.Text.Lazy as TL import Data.Typeable +import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace import Text.RE.ZeInternals.AddCaptureNames diff --git a/Text/RE/TestBench.hs b/Text/RE/TestBench.hs --- a/Text/RE/TestBench.hs +++ b/Text/RE/TestBench.hs @@ -43,147 +43,10 @@ , Severity(..) , parseSeverity , severityKeywords + -- * Text.RE + , module Text.RE ) where -import Data.Array -import qualified Data.HashMap.Strict as HM -import Data.Maybe -import qualified Data.Text as T -import Data.Time -import qualified Data.Time.Locale.Compat as LC -import Data.Word -import Text.Printf -import Text.Read -import Text.RE.Replace +import Text.RE import Text.RE.ZeInternals.TestBench - - -parseInteger :: Replace a => a -> Maybe Int -parseInteger = readMaybe . unpackR - -parseHex :: Replace a => a -> Maybe Int -parseHex = readMaybe . ("0x"++) . unpackR - -parseDouble :: Replace a => a -> Maybe Double -parseDouble = readMaybe . unpackR - -parseString :: Replace a => a -> Maybe T.Text -parseString = readMaybe . unpackR - -parseSimpleString :: Replace a => a -> Maybe T.Text -parseSimpleString = Just . T.dropEnd 1 . T.drop 1 . textifyR - -date_templates, time_templates, timezone_templates, - date_time_8601_templates, date_time_templates :: [String] -date_templates = ["%F"] -time_templates = ["%H:%M:%S","%H:%M:%S%Q","%H:%M"] -timezone_templates = ["Z","%z"] -date_time_8601_templates = - [ printf "%sT%s%s" dt tm tz - | dt <- date_templates - , tm <- time_templates - , tz <- timezone_templates - ] -date_time_templates = - [ printf "%s%c%s%s" dt sc tm tz - | dt <- date_templates - , sc <- ['T',' '] - , tm <- time_templates - , tz <- timezone_templates ++ [" UTC",""] - ] - -parseDate :: Replace a => a -> Maybe Day -parseDate = parse_time date_templates - -parseSlashesDate :: Replace a => a -> Maybe Day -parseSlashesDate = parse_time ["%Y/%m/%d"] - -parseTimeOfDay :: Replace a => a -> Maybe TimeOfDay -parseTimeOfDay = parse_time time_templates - -parseTimeZone :: Replace a => a -> Maybe TimeZone -parseTimeZone = parse_time timezone_templates - -parseDateTime :: Replace a => a -> Maybe UTCTime -parseDateTime = parse_time date_time_templates - -parseDateTime8601 :: Replace a => a -> Maybe UTCTime -parseDateTime8601 = parse_time date_time_8601_templates - -parseDateTimeCLF :: Replace a => a -> Maybe UTCTime -parseDateTimeCLF = parse_time ["%d/%b/%Y:%H:%M:%S %z"] - -parseShortMonth :: Replace a => a -> Maybe Int -parseShortMonth = flip HM.lookup short_month_hm . unpackR - -parse_time :: (ParseTime t,Replace s) => [String] -> s -> Maybe t -parse_time tpls = prs . unpackR - where - prs s = listToMaybe $ catMaybes - [ parseTime LC.defaultTimeLocale fmt s - | fmt<-tpls - ] - -short_month_hm :: HM.HashMap String Int -short_month_hm = HM.fromList [ (T.unpack $ shortMonthArray!i,i) | i<-[1..12] ] - -shortMonthArray :: Array Int T.Text -shortMonthArray = listArray (1,12) $ - T.words "Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec" - -type IPV4Address = (Word8,Word8,Word8,Word8) - -parseIPv4Address :: Replace a => a -> Maybe IPV4Address -parseIPv4Address = prs . words_by (=='.') . unpackR - where - prs [a_s,b_s,c_s,d_s] = do - a <- readMaybe a_s - b <- readMaybe b_s - c <- readMaybe c_s - d <- readMaybe d_s - case all is_o [a,b,c,d] of - True -> Just (toEnum a,toEnum b,toEnum c,toEnum d) - False -> Nothing - prs _ = Nothing - - is_o x = 0 <= x && x <= 255 - -data Severity - = Emerg - | Alert - | Crit - | Err - | Warning - | Notice - | Info - | Debug - deriving (Bounded,Enum,Ord,Eq,Show) - -parseSeverity :: Replace a => a -> Maybe Severity -parseSeverity = flip HM.lookup severity_hm . textifyR - -severity_hm :: HM.HashMap T.Text Severity -severity_hm = HM.fromList - [ (kw,pri) - | pri<-[minBound..maxBound] - , let (kw0,kws) = severityKeywords pri - , kw <- kw0:kws - ] - -severityKeywords :: Severity -> (T.Text,[T.Text]) -severityKeywords pri = case pri of - Emerg -> (,) "emerg" ["panic"] - Alert -> (,) "alert" [] - Crit -> (,) "crit" [] - Err -> (,) "err" ["error"] - Warning -> (,) "warning" ["warn"] - Notice -> (,) "notice" [] - Info -> (,) "info" [] - Debug -> (,) "debug" [] - -words_by :: (Char->Bool) -> String -> [String] -words_by f s = case dropWhile f s of - "" -> [] - s' -> w : words_by f s'' - where - (w, s'') = break f s' +import Text.RE.ZeInternals.TestBench.Parsers diff --git a/Text/RE/Tools.hs b/Text/RE/Tools.hs --- a/Text/RE/Tools.hs +++ b/Text/RE/Tools.hs @@ -8,13 +8,21 @@ , sed' -- * Grep , grep + , Verbosity(..) + , Line(..) , grepLines + , grepFilter , GrepScript - , grepScript + , grepWithScript + , report , linesMatched -- * Lex , alex , alex' + -- * Find + , FindMethods(..) + , findMatches + , findMatches' -- * IsRegex , IsRegex(..) -- * Edit @@ -35,6 +43,7 @@ import Text.RE import Text.RE.Tools.Edit +import Text.RE.Tools.Find import Text.RE.Tools.Grep import Text.RE.Tools.Lex import Text.RE.Tools.Sed diff --git a/Text/RE/Tools/Find.lhs b/Text/RE/Tools/Find.lhs new file mode 100644 --- /dev/null +++ b/Text/RE/Tools/Find.lhs @@ -0,0 +1,71 @@ +\begin{code} +{-# LANGUAGE NoImplicitPrelude #-} +{-# LANGUAGE RecordWildCards #-} +{-# LANGUAGE CPP #-} +#if __GLASGOW_HASKELL__ >= 800 +{-# OPTIONS_GHC -fno-warn-redundant-constraints #-} +#endif + +module Text.RE.Tools.Find + ( FindMethods(..) + , findMatches + , findMatches' + -- * Text.RE + , module Text.RE + ) where + +import qualified Data.List as L +import Prelude.Compat +import Text.RE +import Text.RE.Replace + + +-- | as we don't want the @directory@ and FilePath dependencies +-- we will abstract the three calls we need into this record type +data FindMethods s = + FindMethods + { doesDirectoryExistDM :: s -> IO Bool -- ^ doesDirectoryExist from + -- System.Directory + , listDirectoryDM :: s -> IO [s] -- ^ either getDirectoryContents + -- or listDirectory from + -- System.Directory + , combineDM :: s -> s -> s -- ^ from System.FilePath + } + + +-- | recursively list all files whose filename matches given RE, +-- sorting the list into ascending order; +-- if the argument path has a trailing '/' then it will be removed +findMatches :: IsRegex re s => FindMethods s -> re -> s -> IO [s] +findMatches fm = findMatches' fm L.sort matched + +-- | recursively list all files whose filename matches given RE, +-- using the given function to determine which matches to accept; +findMatches' :: IsRegex re s + => FindMethods s -- ^ the directory and filepath methods + -> ([s]->[s]) -- ^ result post-processing function + -> (Match s->Bool) -- ^ filtering function + -> re -- ^ re to be matched against the leaf filename + -> s -- ^ root directory of the search + -> IO [s] +findMatches' fm srt tst re fp = srt <$> find_ fm tst re (packR "") fp + +find_ :: IsRegex re s + => FindMethods s + -> (Match s->Bool) + -> re + -> s + -> s + -> IO [s] +find_ fm@FindMethods{..} tst re fn fp = do + is_dir <- doesDirectoryExistDM fp + case is_dir of + True -> do + fns <- filter ordinary <$> listDirectoryDM fp + concat <$> + mapM (uncurry $ find_ fm tst re) [ (fn_,abs_path fn_) | fn_<-fns ] + False -> return [ fp | lengthR fp /= 0 && tst (matchOnce re fn) ] + where + abs_path fn_ = fp `combineDM` fn_ + ordinary fn_ = not $ fn_ `elem` [packR ".",packR ".."] +\end{code} diff --git a/Text/RE/Tools/Grep.lhs b/Text/RE/Tools/Grep.lhs --- a/Text/RE/Tools/Grep.lhs +++ b/Text/RE/Tools/Grep.lhs @@ -6,12 +6,13 @@ module Text.RE.Tools.Grep ( grep + , Verbosity(..) , Line(..) , grepLines + , grepFilter , GrepScript - , grepScript + , grepWithScript , report - , Verbosity(..) , linesMatched -- * IsRegex , IsRegex(..) @@ -28,6 +29,7 @@ import Prelude.Compat import Text.Printf import Text.RE +import Text.RE.ZeInternals.Replace import Text.RE.ZeInternals.Types.LineNo @@ -35,20 +37,33 @@ grep :: IsRegex re LBS.ByteString => Verbosity -> re -> FilePath -> IO () grep v rex fp = grepLines rex fp >>= putStr . report v +-- | specifies whether to return the linss matched or missed +data Verbosity + = LinesMatched + | LinesNotMatched + deriving (Show,Eq,Ord) + -- | 'grepLines' returns a 'Line' for each line in the file, listing all -- of the 'Matches' for that line -data Line = +data Line s = Line - { getLineNumber :: LineNo -- ^ the 'LineNo' for this line - , getLineMatches :: Matches LBS.ByteString -- ^ all the 'Matches' of the RE on this line + { getLineNumber :: LineNo -- ^ the 'LineNo' for this line + , getLineMatches :: Matches s -- ^ all the 'Matches' of the RE on this line } deriving (Show) --- | returns a 'Line' for each line in the file enumerating all of the --- matches for that line. -grepLines :: IsRegex re LBS.ByteString => re -> FilePath -> IO [Line] -grepLines rex fp = - grepScript [(rex,mk)] . LBS.lines <$> LBS.readFile fp +-- | returns a 'Line' for each line in the file, enumerating all of the +-- matches for that line +grepLines :: IsRegex re LBS.ByteString + => re + -> FilePath + -> IO [Line LBS.ByteString] +grepLines rex fp = grepFilter rex <$> LBS.readFile fp + +-- | returns a 'Line' for each line in the argument text, enumerating +-- all of the matches for that line +grepFilter :: IsRegex re s => re -> s -> [Line s] +grepFilter rex = grepWithScript [(rex,mk)] . linesR where mk i mtchs = Just $ Line i mtchs @@ -57,8 +72,8 @@ type GrepScript re s t = [(re,LineNo -> Matches s -> Maybe t)] -- | given a list of lines, apply the 'GrepScript' to each line of the file -grepScript :: IsRegex re s => GrepScript re s t -> [s] -> [t] -grepScript scr = loop firstLine +grepWithScript :: IsRegex re s => GrepScript re s t -> [s] -> [t] +grepWithScript scr = loop firstLine where loop _ [] = [] loop i (ln:lns) = seq i $ choose i ln lns scr @@ -69,22 +84,16 @@ Just t -> t : loop (succ i) lns -- | generate a grep report from a list of 'Line' -report :: Verbosity -> [Line] -> String +report :: Verbosity -> [Line LBS.ByteString] -> String report v = unlines . map fmt . linesMatched v where fmt Line{..} = printf "%05d %s" (getLineNo getLineNumber) $ LBS.unpack $ matchesSource getLineMatches --- | specifies whether to return the linss matched or missed -data Verbosity - = LinesMatched - | LinesNotMatched - deriving (Show,Eq,Ord) - -- | given a 'velocity' flag filter out either the lines matched or not -- matched -linesMatched :: Verbosity -> [Line] -> [Line] +linesMatched :: Verbosity -> [Line s] -> [Line s] linesMatched v = filter $ f . anyMatches . getLineMatches where f = case v of diff --git a/Text/RE/Tools/Lex.hs b/Text/RE/Tools/Lex.hs --- a/Text/RE/Tools/Lex.hs +++ b/Text/RE/Tools/Lex.hs @@ -8,4 +8,4 @@ ) where import Text.RE -import Text.RE.ZeInternals.Lex +import Text.RE.ZeInternals.Tools.Lex diff --git a/Text/RE/Tools/Sed.lhs b/Text/RE/Tools/Sed.lhs --- a/Text/RE/Tools/Sed.lhs +++ b/Text/RE/Tools/Sed.lhs @@ -56,10 +56,10 @@ => Edits m re a -> a -> m a -sed' as lbs = do +sed' as t = do mconcat <$> sequence [ applyEdits lno as s - | (lno,s)<-zip [firstLine..] $ linesR lbs + | (lno,s)<-zip [firstLine..] $ linesR t ] read_file :: FilePath -> IO LBS.ByteString diff --git a/Text/RE/ZeInternals/AddCaptureNames.hs b/Text/RE/ZeInternals/AddCaptureNames.hs --- a/Text/RE/ZeInternals/AddCaptureNames.hs +++ b/Text/RE/ZeInternals/AddCaptureNames.hs @@ -6,8 +6,8 @@ module Text.RE.ZeInternals.AddCaptureNames where -import qualified Data.ByteString.Lazy.Char8 as LBS import qualified Data.ByteString.Char8 as B +import qualified Data.ByteString.Lazy.Char8 as LBS import Data.Dynamic import Data.Maybe import qualified Data.Sequence as S diff --git a/Text/RE/ZeInternals/Lex.lhs b/Text/RE/ZeInternals/Lex.lhs deleted file mode 100644 --- a/Text/RE/ZeInternals/Lex.lhs +++ /dev/null @@ -1,45 +0,0 @@ -\begin{code} -{-# LANGUAGE NoImplicitPrelude #-} - -module Text.RE.ZeInternals.Lex - ( alex - , alex' - ) where - -import Prelude.Compat -import Text.RE.Replace -import Text.RE.ZeInternals.Types.IsRegex - - --- | a simple regex-based scanner interpretter for prototyping --- scanners -alex :: IsRegex re s => [(re,Match s->Maybe t)] -> t -> s -> [t] -alex = alex' matchOnce - --- | a higher order version of 'alex' parameterised over the @matchOnce@ --- function -alex' :: Replace s - => (re->s->Match s) - -> [(re,Match s->Maybe t)] - -> t - -> s - -> [t] -alex' mo al t_err = loop - where - loop s = case lengthR s == 0 of - True -> [] - False -> choose al s - - choose [] _ = [t_err] - choose ((re,f):al') s = case mb_p of - Just (s',t) -> t : loop s' - _ -> choose al' s - where - mb_p = do - cap <- matchCapture mtch - case captureOffset cap == 0 of - True -> (,) (captureSuffix cap) <$> f mtch - False -> Nothing - - mtch = mo re s -\end{code} diff --git a/Text/RE/ZeInternals/NamedCaptures.lhs b/Text/RE/ZeInternals/NamedCaptures.lhs --- a/Text/RE/ZeInternals/NamedCaptures.lhs +++ b/Text/RE/ZeInternals/NamedCaptures.lhs @@ -27,10 +27,10 @@ import GHC.Generics import qualified Language.Haskell.TH as TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.Lex import Text.RE.ZeInternals.PreludeMacros import Text.RE.ZeInternals.QQ import Text.RE.ZeInternals.TestBench +import Text.RE.ZeInternals.Tools.Lex import Text.RE.ZeInternals.Types.CaptureID import Text.RE.ZeInternals.Types.Match import Text.Regex.TDFA diff --git a/Text/RE/ZeInternals/PreludeMacros.hs b/Text/RE/ZeInternals/PreludeMacros.hs --- a/Text/RE/ZeInternals/PreludeMacros.hs +++ b/Text/RE/ZeInternals/PreludeMacros.hs @@ -30,9 +30,9 @@ import qualified Data.Text as T import Data.Time import Prelude.Compat -import Text.RE.TestBench -import Text.RE.ZeInternals.TestBench import Text.RE.REOptions +import Text.RE.ZeInternals.TestBench +import Text.RE.ZeInternals.TestBench.Parsers -- | generate the standard prelude Macros used to parse REs diff --git a/Text/RE/ZeInternals/Replace.lhs b/Text/RE/ZeInternals/Replace.lhs --- a/Text/RE/ZeInternals/Replace.lhs +++ b/Text/RE/ZeInternals/Replace.lhs @@ -48,11 +48,11 @@ import qualified Data.Text.Encoding as TE import qualified Data.Text.Lazy as LT import Prelude.Compat +import Text.RE.REOptions import Text.RE.ZeInternals.Types.Capture import Text.RE.ZeInternals.Types.CaptureID import Text.RE.ZeInternals.Types.Match import Text.RE.ZeInternals.Types.Matches -import Text.RE.REOptions import Text.Read import Text.Regex.TDFA import Text.Regex.TDFA.Text() diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA.hs b/Text/RE/ZeInternals/SearchReplace/TDFA.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA.hs @@ -23,8 +23,8 @@ import Language.Haskell.TH import Language.Haskell.TH.Quote import Prelude.Compat -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime -- | the @[ed| ... /// ... |]@ quasi quoters diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString.hs b/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString.hs @@ -24,9 +24,9 @@ import qualified Data.ByteString.Char8 as B import Language.Haskell.TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.TDFA -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime +import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.SearchReplace diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString/Lazy.hs b/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString/Lazy.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString/Lazy.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA/ByteString/Lazy.hs @@ -24,9 +24,9 @@ import qualified Data.ByteString.Lazy.Char8 as LBS import Language.Haskell.TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.TDFA -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime +import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.SearchReplace diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA/Sequence.hs b/Text/RE/ZeInternals/SearchReplace/TDFA/Sequence.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA/Sequence.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA/Sequence.hs @@ -24,9 +24,9 @@ import qualified Data.Sequence as S import Language.Haskell.TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.TDFA -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime +import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.SearchReplace diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA/String.hs b/Text/RE/ZeInternals/SearchReplace/TDFA/String.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA/String.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA/String.hs @@ -24,9 +24,9 @@ import Language.Haskell.TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.TDFA -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime +import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.SearchReplace diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA/Text.hs b/Text/RE/ZeInternals/SearchReplace/TDFA/Text.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA/Text.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA/Text.hs @@ -24,9 +24,9 @@ import qualified Data.Text as T import Language.Haskell.TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.TDFA -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime +import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.SearchReplace diff --git a/Text/RE/ZeInternals/SearchReplace/TDFA/Text/Lazy.hs b/Text/RE/ZeInternals/SearchReplace/TDFA/Text/Lazy.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFA/Text/Lazy.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFA/Text/Lazy.hs @@ -24,9 +24,9 @@ import qualified Data.Text.Lazy as TL import Language.Haskell.TH import Language.Haskell.TH.Quote -import Text.RE.ZeInternals.TDFA -import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime import Text.RE.REOptions +import Text.RE.ZeInternals.SearchReplace.TDFAEdPrime +import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.SearchReplace diff --git a/Text/RE/ZeInternals/SearchReplace/TDFAEdPrime.hs b/Text/RE/ZeInternals/SearchReplace/TDFAEdPrime.hs --- a/Text/RE/ZeInternals/SearchReplace/TDFAEdPrime.hs +++ b/Text/RE/ZeInternals/SearchReplace/TDFAEdPrime.hs @@ -18,8 +18,8 @@ import Prelude.Compat import Text.RE.REOptions import Text.RE.Replace -import Text.RE.ZeInternals.SearchReplace import Text.RE.ZeInternals.QQ +import Text.RE.ZeInternals.SearchReplace import Text.RE.ZeInternals.TDFA import Text.RE.ZeInternals.Types.IsRegex import Text.Regex.TDFA diff --git a/Text/RE/ZeInternals/TestBench.lhs b/Text/RE/ZeInternals/TestBench.lhs --- a/Text/RE/ZeInternals/TestBench.lhs +++ b/Text/RE/ZeInternals/TestBench.lhs @@ -41,8 +41,8 @@ import Data.Maybe import Data.Ord import Data.String -import Text.Printf import Prelude.Compat +import Text.Printf import Text.RE.REOptions import Text.RE.ZeInternals.Replace import Text.RE.ZeInternals.Types.Capture diff --git a/Text/RE/ZeInternals/TestBench/Parsers.hs b/Text/RE/ZeInternals/TestBench/Parsers.hs new file mode 100644 --- /dev/null +++ b/Text/RE/ZeInternals/TestBench/Parsers.hs @@ -0,0 +1,189 @@ +{-# OPTIONS_GHC -fno-warn-warnings-deprecations #-} +{-# LANGUAGE OverloadedStrings #-} + +module Text.RE.ZeInternals.TestBench.Parsers + ( + -- * The Test Bench + MacroEnv + , MacroDescriptor(..) + , RegexSource(..) + , WithCaptures(..) + , RegexType + , isTDFA + , isPCRE + , presentRegexType + -- ** Constructing a MacrosEnv + , mkMacros + -- ** Formatting Macros + , formatMacroTable + , formatMacroSummary + , formatMacroSources + , formatMacroSource + -- ** Formatting Macros + , testMacroEnv + , runTests + , runTests' + -- * Parsing + , parseInteger + , parseHex + , parseDouble + , parseString + , parseSimpleString + , parseDate + , parseSlashesDate + , parseTimeOfDay + , parseTimeZone + , parseDateTime + , parseDateTime8601 + , parseDateTimeCLF + , parseShortMonth + , shortMonthArray + , IPV4Address + , parseIPv4Address + , Severity(..) + , parseSeverity + , severityKeywords + ) where + +import Data.Array +import qualified Data.HashMap.Strict as HM +import Data.Maybe +import qualified Data.Text as T +import Data.Time +import qualified Data.Time.Locale.Compat as LC +import Data.Word +import Text.Printf +import Text.RE.Replace +import Text.RE.ZeInternals.TestBench +import Text.Read + + +parseInteger :: Replace a => a -> Maybe Int +parseInteger = readMaybe . unpackR + +parseHex :: Replace a => a -> Maybe Int +parseHex = readMaybe . ("0x"++) . unpackR + +parseDouble :: Replace a => a -> Maybe Double +parseDouble = readMaybe . unpackR + +parseString :: Replace a => a -> Maybe T.Text +parseString = readMaybe . unpackR + +parseSimpleString :: Replace a => a -> Maybe T.Text +parseSimpleString = Just . T.dropEnd 1 . T.drop 1 . textifyR + +date_templates, time_templates, timezone_templates, + date_time_8601_templates, date_time_templates :: [String] +date_templates = ["%F"] +time_templates = ["%H:%M:%S","%H:%M:%S%Q","%H:%M"] +timezone_templates = ["Z","%z"] +date_time_8601_templates = + [ printf "%sT%s%s" dt tm tz + | dt <- date_templates + , tm <- time_templates + , tz <- timezone_templates + ] +date_time_templates = + [ printf "%s%c%s%s" dt sc tm tz + | dt <- date_templates + , sc <- ['T',' '] + , tm <- time_templates + , tz <- timezone_templates ++ [" UTC",""] + ] + +parseDate :: Replace a => a -> Maybe Day +parseDate = parse_time date_templates + +parseSlashesDate :: Replace a => a -> Maybe Day +parseSlashesDate = parse_time ["%Y/%m/%d"] + +parseTimeOfDay :: Replace a => a -> Maybe TimeOfDay +parseTimeOfDay = parse_time time_templates + +parseTimeZone :: Replace a => a -> Maybe TimeZone +parseTimeZone = parse_time timezone_templates + +parseDateTime :: Replace a => a -> Maybe UTCTime +parseDateTime = parse_time date_time_templates + +parseDateTime8601 :: Replace a => a -> Maybe UTCTime +parseDateTime8601 = parse_time date_time_8601_templates + +parseDateTimeCLF :: Replace a => a -> Maybe UTCTime +parseDateTimeCLF = parse_time ["%d/%b/%Y:%H:%M:%S %z"] + +parseShortMonth :: Replace a => a -> Maybe Int +parseShortMonth = flip HM.lookup short_month_hm . unpackR + +parse_time :: (ParseTime t,Replace s) => [String] -> s -> Maybe t +parse_time tpls = prs . unpackR + where + prs s = listToMaybe $ catMaybes + [ parseTime LC.defaultTimeLocale fmt s + | fmt<-tpls + ] + +short_month_hm :: HM.HashMap String Int +short_month_hm = HM.fromList [ (T.unpack $ shortMonthArray!i,i) | i<-[1..12] ] + +shortMonthArray :: Array Int T.Text +shortMonthArray = listArray (1,12) $ + T.words "Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec" + +type IPV4Address = (Word8,Word8,Word8,Word8) + +parseIPv4Address :: Replace a => a -> Maybe IPV4Address +parseIPv4Address = prs . words_by (=='.') . unpackR + where + prs [a_s,b_s,c_s,d_s] = do + a <- readMaybe a_s + b <- readMaybe b_s + c <- readMaybe c_s + d <- readMaybe d_s + case all is_o [a,b,c,d] of + True -> Just (toEnum a,toEnum b,toEnum c,toEnum d) + False -> Nothing + prs _ = Nothing + + is_o x = 0 <= x && x <= 255 + +data Severity + = Emerg + | Alert + | Crit + | Err + | Warning + | Notice + | Info + | Debug + deriving (Bounded,Enum,Ord,Eq,Show) + +parseSeverity :: Replace a => a -> Maybe Severity +parseSeverity = flip HM.lookup severity_hm . textifyR + +severity_hm :: HM.HashMap T.Text Severity +severity_hm = HM.fromList + [ (kw,pri) + | pri<-[minBound..maxBound] + , let (kw0,kws) = severityKeywords pri + , kw <- kw0:kws + ] + +severityKeywords :: Severity -> (T.Text,[T.Text]) +severityKeywords pri = case pri of + Emerg -> (,) "emerg" ["panic"] + Alert -> (,) "alert" [] + Crit -> (,) "crit" [] + Err -> (,) "err" ["error"] + Warning -> (,) "warning" ["warn"] + Notice -> (,) "notice" [] + Info -> (,) "info" [] + Debug -> (,) "debug" [] + +words_by :: (Char->Bool) -> String -> [String] +words_by f s = case dropWhile f s of + "" -> [] + s' -> w : words_by f s'' + where + (w, s'') = break f s' diff --git a/Text/RE/ZeInternals/Tools/Lex.lhs b/Text/RE/ZeInternals/Tools/Lex.lhs new file mode 100644 --- /dev/null +++ b/Text/RE/ZeInternals/Tools/Lex.lhs @@ -0,0 +1,45 @@ +\begin{code} +{-# LANGUAGE NoImplicitPrelude #-} + +module Text.RE.ZeInternals.Tools.Lex + ( alex + , alex' + ) where + +import Prelude.Compat +import Text.RE.Replace +import Text.RE.ZeInternals.Types.IsRegex + + +-- | a simple regex-based scanner interpretter for prototyping +-- scanners +alex :: IsRegex re s => [(re,Match s->Maybe t)] -> t -> s -> [t] +alex = alex' matchOnce + +-- | a higher order version of 'alex' parameterised over the @matchOnce@ +-- function +alex' :: Replace s + => (re->s->Match s) + -> [(re,Match s->Maybe t)] + -> t + -> s + -> [t] +alex' mo al t_err = loop + where + loop s = case lengthR s == 0 of + True -> [] + False -> choose al s + + choose [] _ = [t_err] + choose ((re,f):al') s = case mb_p of + Just (s',t) -> t : loop s' + _ -> choose al' s + where + mb_p = do + cap <- matchCapture mtch + case captureOffset cap == 0 of + True -> (,) (captureSuffix cap) <$> f mtch + False -> Nothing + + mtch = mo re s +\end{code} diff --git a/Text/RE/ZeInternals/Types/CaptureID.hs b/Text/RE/ZeInternals/Types/CaptureID.hs --- a/Text/RE/ZeInternals/Types/CaptureID.hs +++ b/Text/RE/ZeInternals/Types/CaptureID.hs @@ -2,10 +2,9 @@ module Text.RE.ZeInternals.Types.CaptureID where -import Data.Ix -import Data.Hashable import qualified Data.HashMap.Strict as HMS -import Data.Maybe +import Data.Hashable +import Data.Ix import qualified Data.Text as T @@ -38,12 +37,16 @@ deriving (Show,Ord,Eq,Enum,Ix,Num) -- | look up a 'CaptureID' in the 'CaptureNames' dictionary -findCaptureID :: CaptureID -> CaptureNames -> Int -findCaptureID (IsCaptureOrdinal o) _ = getCaptureOrdinal o +unsafeFindCaptureID :: CaptureID -> CaptureNames -> Int +unsafeFindCaptureID cid = either error id . findCaptureID cid + +-- | look up a 'CaptureID' in the 'CaptureNames' dictionary +findCaptureID :: CaptureID -> CaptureNames -> Either String Int +findCaptureID (IsCaptureOrdinal o) _ = Right $ getCaptureOrdinal o findCaptureID (IsCaptureName n) hms = - getCaptureOrdinal $ fromMaybe oops $ HMS.lookup n hms + maybe oops (Right . getCaptureOrdinal) $ HMS.lookup n hms where - oops = error $ unlines $ + oops = Left $ unlines $ ("lookupCaptureID: " ++ T.unpack t ++ " not found in:") : [ " "++T.unpack (getCaptureName nm) | nm <- HMS.keys hms ] t = getCaptureName n diff --git a/Text/RE/ZeInternals/Types/Match.lhs b/Text/RE/ZeInternals/Types/Match.lhs --- a/Text/RE/ZeInternals/Types/Match.lhs +++ b/Text/RE/ZeInternals/Types/Match.lhs @@ -31,9 +31,9 @@ import Data.Array import Data.Maybe import Data.Typeable -import Text.Regex.Base import Text.RE.ZeInternals.Types.Capture import Text.RE.ZeInternals.Types.CaptureID +import Text.Regex.Base infixl 9 !$, !$$ \end{code} @@ -142,17 +142,17 @@ -- capture failed to capture anything (being in a failed alternate) captureMaybe :: CaptureID -> Match a -> Maybe (Capture a) captureMaybe cid mtch@Match{..} = do + i <- lookupCaptureID cid mtch cap <- case bounds matchArray `inRange` CaptureOrdinal i of True -> Just $ matchArray ! CaptureOrdinal i False -> Nothing case hasCaptured cap of True -> Just cap False -> Nothing - where - i = lookupCaptureID cid mtch -lookupCaptureID :: CaptureID -> Match a -> Int -lookupCaptureID cid Match{..} = findCaptureID cid captureNames +lookupCaptureID :: CaptureID -> Match a -> Maybe Int +lookupCaptureID cid Match{..} = + either (const Nothing) Just $ findCaptureID cid captureNames \end{code} diff --git a/Text/RE/ZeInternals/Types/Matches.lhs b/Text/RE/ZeInternals/Types/Matches.lhs --- a/Text/RE/ZeInternals/Types/Matches.lhs +++ b/Text/RE/ZeInternals/Types/Matches.lhs @@ -18,10 +18,10 @@ \begin{code} import Data.Typeable -import Text.Regex.Base import Text.RE.ZeInternals.Types.Capture import Text.RE.ZeInternals.Types.CaptureID import Text.RE.ZeInternals.Types.Match +import Text.Regex.Base \end{code} diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,5 +1,14 @@ -*-change-log-*- +0.13.0.0 Chris Dornan 2017-04-03 + * Add a Find Tool (#106) + * TestBench to export Text.RE (#107) + * Consolidate cabal templates (#108) + * Add special tutorials (#109) + * Add sort-imports example (#110) + * Generalise Grep (#111) + * Tighten up findCaptureID (#112) + 0.12.0.0 Chris Dornan 2017-03-31 * Add Text.RE.REOptions to RE.Summa (#103) * Move IsRegex into Text.RE (#104) diff --git a/regex.cabal b/regex.cabal --- a/regex.cabal +++ b/regex.cabal @@ -1,5 +1,5 @@ Name: regex -Version: 0.12.0.0 +Version: 0.13.0.0 Synopsis: Toolkit for regex-base Description: A regular expression toolkit for regex-base with compile-time checking of RE syntax, data types for @@ -32,14 +32,12 @@ Source-Repository this Type: git Location: https://github.com/iconnect/regex.git - Tag: 0.12.0.0 - + Tag: 0.13.0.0 Library Hs-Source-Dirs: . - Exposed-Modules: Text.RE Text.RE.REOptions @@ -55,13 +53,13 @@ Text.RE.TestBench Text.RE.Tools Text.RE.Tools.Edit + Text.RE.Tools.Find Text.RE.Tools.Grep Text.RE.Tools.Lex Text.RE.Tools.Sed Text.RE.ZeInternals Text.RE.ZeInternals.AddCaptureNames Text.RE.ZeInternals.EscapeREString - Text.RE.ZeInternals.Lex Text.RE.ZeInternals.NamedCaptures Text.RE.ZeInternals.PreludeMacros Text.RE.ZeInternals.QQ @@ -77,6 +75,8 @@ Text.RE.ZeInternals.SearchReplace.TDFAEdPrime Text.RE.ZeInternals.TDFA Text.RE.ZeInternals.TestBench + Text.RE.ZeInternals.TestBench.Parsers + Text.RE.ZeInternals.Tools.Lex Text.RE.ZeInternals.Types.Capture Text.RE.ZeInternals.Types.CaptureID Text.RE.ZeInternals.Types.IsRegex @@ -125,6 +125,7 @@ , containers >= 0.4 , hashable >= 1.2.3.3 , regex-base >= 0.93.2 + , regex-pcre-builtin >= 0.94.4.8.8.35 , regex-tdfa >= 1.2.0 , regex-tdfa-text >= 1.0.0.3 , template-haskell >= 2.7