Merge pull request #27 from cdepillabout/token

Add Text.Parsing.Parser.Language and Token modules.

Author: paf31

LICENSE

@@ -18,3 +18,31 @@ FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
 COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
 IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+-------------------------------------------------------------------------------
+
+The `Text.Parsing.Parser.Token` and `Text.Parsing.Parser.Language` modules have
+large amounts of code adopted from the Haskell library parsec.  parsec's
+license is reproduced below:
+
+Copyright 1999-2000, Daan Leijen; 2007, Paolo Martini. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice,
+  this list of conditions and the following disclaimer.
+* 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.
+
+This software is provided by the copyright holders "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 holders 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.

bower.json

@@ -29,7 +29,9 @@
     "purescript-lists": "^0.7.0",
     "purescript-maybe": "^0.3.0",
     "purescript-strings": "~0.7.0",
-    "purescript-transformers": "^0.8.1"
+    "purescript-transformers": "^0.8.1",
+    "purescript-unicode": "^0.0.1",
+    "purescript-integers": "^0.2.0"
   },
   "devDependencies": {
     "purescript-console": "^0.1.0",

src/Text/Parsing/Parser/Combinators.purs

@@ -38,6 +38,10 @@ import Text.Parsing.Parser
 (<?>) :: forall m s a. (Monad m) => ParserT s m a -> String -> ParserT s m a
 (<?>) p msg = p <|> fail ("Expected " ++ msg)
 
+-- | Flipped `(<?>)`.
+(<??>) :: forall m s a. (Monad m) => String -> ParserT s m a -> ParserT s m a
+(<??>) = flip (<?>)
+
 -- | Wrap a parser with opening and closing markers.
 -- |
 -- | For example:
@@ -196,4 +200,3 @@ many1Till p end = do
   x <- p
   xs <- manyTill p end
   return (x:xs)
-

src/Text/Parsing/Parser/Language.purs

@@ -0,0 +1,119 @@
+
+module Text.Parsing.Parser.Language
+    ( haskellDef
+    , haskell
+    , emptyDef
+    , haskellStyle
+    , javaStyle
+    )
+      where
+
+import Prelude
+
+import Control.Alt
+
+import Text.Parsing.Parser
+import Text.Parsing.Parser.String
+import Text.Parsing.Parser.Token
+
+-----------------------------------------------------------
+-- Styles: haskellStyle, javaStyle
+-----------------------------------------------------------
+
+-- | This is a minimal token definition for Haskell style languages. It
+-- | defines the style of comments, valid identifiers and case
+-- | sensitivity. It does not define any reserved words or operators.
+haskellStyle :: LanguageDef
+haskellStyle = LanguageDef (unGenLanguageDef emptyDef)
+                { commentStart    = "{-"
+                , commentEnd      = "-}"
+                , commentLine     = "--"
+                , nestedComments  = true
+                , identStart      = letter
+                , identLetter     = alphaNum <|> oneOf ['_', '\'']
+                , opStart         = op'
+                , opLetter        = op'
+                , reservedOpNames = []
+                , reservedNames   = []
+                , caseSensitive   = true
+                }
+  where
+    op' :: forall m . (Monad m) => ParserT String m Char
+    op' = oneOf [':', '!', '#', '$', '%', '&', '*', '+', '.', '/', '<', '=', '>', '?', '@', '\\', '^', '|', '-', '~']
+
+-- | This is a minimal token definition for Java style languages. It
+-- | defines the style of comments, valid identifiers and case
+-- | sensitivity. It does not define any reserved words or operators.
+javaStyle  :: LanguageDef
+javaStyle   = LanguageDef (unGenLanguageDef emptyDef)
+                { commentStart    = "/*"
+                , commentEnd      = "*/"
+                , commentLine     = "//"
+                , nestedComments  = true
+                , identStart      = letter
+                , identLetter     = alphaNum <|> oneOf ['_', '\'']
+                , reservedNames   = []
+                , reservedOpNames = []
+                , caseSensitive   = false
+                }
+
+-----------------------------------------------------------
+-- minimal language definition
+--------------------------------------------------------
+
+-- | This is the most minimal token definition. It is recommended to use
+-- | this definition as the basis for other definitions. `emptyDef` has
+-- | no reserved names or operators, is case sensitive and doesn't accept
+-- | comments, identifiers or operators.
+emptyDef :: LanguageDef
+emptyDef = LanguageDef
+            { commentStart:    ""
+            , commentEnd:      ""
+            , commentLine:     ""
+            , nestedComments:  true
+            , identStart:      letter <|> char '_'
+            , identLetter:     alphaNum <|> oneOf ['_', '\'']
+            , opStart:         op'
+            , opLetter:        op'
+            , reservedOpNames: []
+            , reservedNames:   []
+            , caseSensitive:   true
+            }
+  where
+    op' :: forall m . (Monad m) => ParserT String m Char
+    op' = oneOf [':', '!', '#', '$', '%', '&', '*', '+', '.', '/', '<', '=', '>', '?', '@', '\\', '^', '|', '-', '~']
+
+-- -----------------------------------------------------------
+-- -- Haskell
+-- -----------------------------------------------------------
+
+-- | A lexer for the haskell language.
+haskell :: TokenParser
+haskell = makeTokenParser haskellDef
+
+-- | The language definition for the Haskell language.
+haskellDef  :: LanguageDef
+haskellDef   =
+    case haskell98Def of
+        (LanguageDef def) -> LanguageDef def
+                { identLetter    = def.identLetter <|> char '#'
+                , reservedNames  = def.reservedNames <>
+                                   ["foreign","import","export","primitive"
+                                   ,"_ccall_","_casm_"
+                                   ,"forall"
+                                   ]
+                }
+
+-- | The language definition for the language Haskell98.
+haskell98Def :: LanguageDef
+haskell98Def = LanguageDef (unGenLanguageDef haskellStyle)
+                { reservedOpNames = ["::","..","=","\\","|","<-","->","@","~","=>"]
+                , reservedNames   = [ "let","in","case","of","if","then","else"
+                                    , "data","type"
+                                    , "class","default","deriving","do","import"
+                                    , "infix","infixl","infixr","instance","module"
+                                    , "newtype","where"
+                                    , "primitive"
+                                    -- "as","qualified","hiding"
+                                    ]
+                }