packages feed

lex-applicative (empty) → 0.0.0.0

raw patch · 9 files changed

+318/−0 lines, 9 filesdep +basedep +gaugedep +hs-functors

Dependencies added: base, gauge, hs-functors, lex-applicative, parser-combinators, regex-applicative, text, ucd, unicode-transforms, util

Files

+ CHANGELOG.md view
@@ -0,0 +1,11 @@+# Changelog++`lex-regex-applicative.hs` uses [PVP Versioning][1].+The changelog is available [on GitHub][2].++## 0.0.0.0++* Initially created.++[1]: https://pvp.haskell.org+[2]: https://github.com/strake/lex-regex-applicative.hs/releases
+ LICENSE view
@@ -0,0 +1,29 @@+BSD 3-Clause License++Copyright (c) 2019, M Farkas-Dyck+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.++3. Neither the name of the copyright holder nor the names of its+   contributors may be used to endorse or promote products derived from+   this software without specific prior written permission.++THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT HOLDER 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.
+ README.md view
@@ -0,0 +1,7 @@+# lex-regex-applicative.hs++[![Build status](https://img.shields.io/travis/strake/lex-regex-applicative.hs.svg?logo=travis)](https://travis-ci.org/strake/lex-regex-applicative.hs)+[![Hackage](https://img.shields.io/hackage/v/lex-regex-applicative.hs.svg?logo=haskell)](https://hackage.haskell.org/package/lex-regex-applicative.hs)+[![BSD3 license](https://img.shields.io/badge/license-BSD3-blue.svg)](LICENSE)++See README for more info
+ bench/Main.hs view
@@ -0,0 +1,7 @@+module Main (main) where++import Gauge.Main+++main :: IO ()+main = defaultMain [bench "const" (whnf const ())]
+ lex-applicative.cabal view
@@ -0,0 +1,85 @@+cabal-version:       2.2+name:                lex-applicative+version:             0.0.0.0+synopsis:            See README for more info+description:         See README for more info+homepage:            https://github.com/strake/lex-applicative.hs+bug-reports:         https://github.com/strake/lex-applicative.hs/issues+license:             BSD-3-Clause+license-file:        LICENSE+author:              M Farkas-Dyck+maintainer:          strake888@gmail.com+copyright:           2019 M Farkas-Dyck+category:            Parsing,Text+build-type:          Simple+extra-doc-files:     README.md+                   , CHANGELOG.md+tested-with:         GHC == 8.6.5++common c+  build-depends:       base ^>= 4.12 || ^>= 4.13+                     , util ^>= 0.1.15+  ghc-options:         -Wall+                       -Wcompat+                       -Wredundant-constraints+                       -Wno-name-shadowing+                       -Wincomplete-uni-patterns+                       -Wincomplete-record-updates+                       -Werror=incomplete-patterns+                       -Werror=incomplete-uni-patterns+                       -Werror=incomplete-record-updates+                       -Werror=missing-fields+                       -Werror=missing-methods+  default-language:    Haskell2010+  default-extensions:  UnicodeSyntax+                       LambdaCase+                       EmptyCase+                       InstanceSigs+                       PartialTypeSignatures+                       PolyKinds+                       ConstraintKinds+                       FlexibleContexts+                       FlexibleInstances+                       MonadComprehensions+                       StandaloneDeriving+                       DeriveFunctor+                       DeriveFoldable+                       DeriveTraversable++library+  import:              c+  hs-source-dirs:      src+  exposed-modules:     Data.TextPos+                     , Text.Lexer+                     , Text.Regex.Applicative.Lex+  build-depends:       hs-functors ^>= 0.1.4+                     , parser-combinators ^>= 1.2+                     , regex-applicative ^>= 0.3.3+                     , text ^>= 1.2.3+                     , ucd ^>= 0.0.1.3+                     , unicode-transforms ^>= 0.3.6++test-suite test+  import:              c+  type:                exitcode-stdio-1.0+  hs-source-dirs:      test+  main-is:             Spec.hs+  build-depends:       lex-applicative+  ghc-options:         -threaded+                       -rtsopts+                       -with-rtsopts=-N++benchmark bench+  import:              c+  type:                exitcode-stdio-1.0+  hs-source-dirs:      bench+  main-is:             Main.hs+  build-depends:       gauge+                     , lex-applicative+  ghc-options:         -threaded+                       -rtsopts+                       -with-rtsopts=-N++source-repository head+  type:                git+  location:            https://github.com/strake/lex-applicative.hs.git
+ src/Data/TextPos.hs view
@@ -0,0 +1,15 @@+{-# LANGUAGE StrictData #-}+module Data.TextPos where++data Pos = Pos+  { char :: Word+  , line :: Word+  , col  :: Word+  } deriving (Eq, Ord, Read, Show)++move :: Char -> Pos -> Pos+move x = \ (Pos k m n) -> Pos (k+1) `uncurry` case x of+    '\n' -> (m+1, 0)+    '\r' -> (m,   0)+    '\b' -> (m, case n of 0 -> 0; _ -> n-1)+    _    -> (m, n+1)
+ src/Text/Lexer.hs view
@@ -0,0 +1,65 @@+{-# LANGUAGE StrictData #-}+{-# LANGUAGE RecordWildCards #-}+module Text.Lexer (Error (..), LexerSpec (token, space, blockComment, move, init), defaultLexerSpec, lex) where++import           Prelude hiding (lex)+import           Control.Applicative+import           Control.Monad.Free (Free (..))+import qualified Data.Char as Char+import           Data.Semigroup (Min (..), Max (..))+import qualified Data.TextPos as Text+import           Text.Regex.Applicative (RE, findLongestPrefix')+import qualified Text.Regex.Applicative as RE+import           Util++data LexerSpec p x t = LexerSpec+  { token :: RE x t+  , space :: RE x ()+  , blockComment :: RE x (RE x ())+  , move :: x -> p -> p+  , init :: p+  }++defaultLexerSpec :: LexerSpec Text.Pos Char t+defaultLexerSpec = LexerSpec+  { token = empty+  , space = () <$ many (RE.psym Char.isSpace)+  , blockComment = empty+  , move = Text.move+  , init = Text.Pos 0 1 0+  }++lex :: LexerSpec p x t -> [x] -> Free ((,,) (Min p, Max p) t) (Maybe (Error p))+lex LexerSpec {..} = go' [] . annotate move init+  where+    go bs = stripLongestPrefix' stripAnnotation (many space) & go' bs+    go' bs' xs@(AList p l) = case (bs', l) of+        ([], Nothing) -> Pure Nothing+        (_,  Nothing) -> Pure (Just (Error p))+        (b:bs, Just (_, xs')) -> case findLongestPrefix' stripAnnotation (Nothing <$ b <|> Just <$> blockComment) xs of+            Just (Nothing, xs) -> (case bs of [] -> go; _ -> go') bs xs+            Just (Just b', xs) -> go' (b':bs') xs+            Nothing -> go' bs' xs'+        ([], Just _) -> case findLongestPrefix' stripAnnotation' (Left <$> blockComment <|> Right <$> token) (xs, p) of+            Just (Left b, (xs, _)) -> go' [b] xs+            Just (Right t, (xs, q)) -> Free ((Min p, Max q), t, go [] xs)+            Nothing -> Pure (Just (Error p))++data AList a b = AList { annotation :: a, stripAnnotation :: Maybe (b, AList a b) }+  deriving (Eq, Show)++stripAnnotation' :: (AList a b, a) -> Maybe (b, (AList a b, a))+stripAnnotation' = fst & \ (AList a l) -> fmap (flip (,) a) <$> l++annotate :: (a -> b -> b) -> b -> [a] -> AList b a+annotate f = go+  where+    go b = AList b . \ case+        [] -> Nothing+        a:as -> let b' = f a b in b' `seq` Just (a, go b' as)++newtype Error p = Error { errorPos :: p }+  deriving (Eq, Ord, Read, Show)++stripLongestPrefix' :: (xs -> Maybe (x, xs)) -> RE x a -> xs -> xs+stripLongestPrefix' uncons re = flip maybe snd <*> findLongestPrefix' uncons re
+ src/Text/Regex/Applicative/Lex.hs view
@@ -0,0 +1,95 @@+{-# LANGUAGE StrictData #-}+{-# LANGUAGE RecordWildCards #-}+module Text.Regex.Applicative.Lex (natural', natural, ident', ident, IdentSpec (..), defaultIdentSpec, string, esc, unicodepoint) where++import           Control.Applicative.Combinators (between, count')+import           Control.Monad ((>=>), guard, replicateM)+import qualified Data.Char.Properties.DerivedCore as UC+import           Data.Foldable+import           Data.Text (Text)+import qualified Data.Text as T+import qualified Data.Text.Lazy as TL+import qualified Data.Text.Normalize as T+import           Numeric.Natural+import           Text.Regex.Applicative hiding (string)+import qualified Text.Regex.Applicative as RE+import           Util hiding (some)++natural' :: RE Char Natural+natural' = asum+  [ natural 10+  , traverse sym "0b" *> natural  2+  , traverse sym "0o" *> natural  8+  , traverse sym "0d" *> natural 10+  , traverse sym "0x" *> natural 16+  ]++natural :: Word -> RE Char Natural+natural = naturalWith some++naturalWith :: (RE Char Word -> RE Char [Word]) -> Word -> RE Char Natural+naturalWith f r = fromDigits r <$> f (digit' r)++fromDigits :: Integral a => Word -> [a] -> Natural+fromDigits r = foldl' (\ n w -> fromIntegral r*n + fromIntegral w) 0++digit' :: Word -> RE Char Word+digit' r = msym (digit >=> \ n -> n <$ guard (n < r))++ident' :: RE Char Text+ident' = ident defaultIdentSpec++ident :: IdentSpec -> RE Char Text+ident IdentSpec {..} = normalize . T.pack <$> start <:> many cont <++> (fmap asum . many) (med <:> some cont)+  where+    start = psym isStart+    cont = psym isContinue+    med = psym isMedial+    infixr 5 <:>, <++>+    (<:>) = liftA2 (:)+    (<++>) = liftA2 (++)++data IdentSpec = IdentSpec+  { isStart, isContinue, isMedial :: Char -> Bool+  , normalize :: Text -> Text }++defaultIdentSpec :: IdentSpec+defaultIdentSpec = IdentSpec+  { isStart = UC.isXIDStart <||> (∈ "_")+  , isContinue = UC.isXIDContinue <&&> (∉ "·\x0387") <||> (∈ "_\x05F3")+  , isMedial = (∈ "'-·\x0387\x058A\x05F4\x0F0B\x2010\x2027\x30A0\x30FB")+  , normalize = T.map normalizeIDMedial . T.normalize T.NFC+  } where+    normalizeIDMedial = \ case+        '\x058A' -> '-'+        '\x2010' -> '-'+        '\x30A0' -> '-'+        '\x0F0B' -> '·'+        '\x2027' -> '·'+        '\x30FB' -> '·'+        x       -> x++string :: RE Char TL.Text+string = TL.pack <$> between (sym '"') (sym '"') (many xre)+  where xre = psym (∉ "\"\\") <|> sym '\\' *> (psym (∈ "\"\\") <|> esc)++esc :: RE Char Char+esc = asum+    [toEnum . fromIntegral <$ sym 'x' <*> naturalWith (replicateM 2) 16+    , sym 'u' *> between (sym '{') (sym '}') unicodepoint+    , '\x00' <$ sym '0'+    , '\x07' <$ sym 'a'+    , '\x08' <$ sym 'b'+    , '\x09' <$ sym 't'+    , '\x0A' <$ sym 'n'+    , '\x0B' <$ sym 'v'+    , '\x0C' <$ sym 'f'+    , '\x0D' <$ sym 'r'+    , '\x1B' <$ sym 'e'+    ]++unicodepoint :: RE Char Char+unicodepoint = (\ a b -> toEnum . fromIntegral $ 0x10000 * a + b)+    <$> asum [16 <$ RE.string "10", naturalWith (fmap pure) 16]+    <*> naturalWith (replicateM 4) 16+    <|> toEnum . fromIntegral <$> naturalWith (count' 0 4) 16
+ test/Spec.hs view
@@ -0,0 +1,4 @@+module Main (main) where++main :: IO ()+main = putStrLn ("Test suite not yet implemented" :: String)