我部分地从SO中获取了下面的示例并将其更改为我的需要。它几乎适合,但我想做的是始终将 commaSep expr 中的第一个字符串解析为标识符,而所有后续字符串应该只是字符串。
目前它们都被解析为标识符。
*Parser> parse expr "" "rd (isFib, test2, 100.1, ?BOOL)"
Right (FuncCall "rd" [Identifier "isFib",Identifier "test2",Number 100.1,Query "?BOOL"])
我尝试了许多解决方案,最终所有解决方案都会分解为在不使用 commaSep 的情况下解析整个输入。意味着我将不得不忽略结构并做类似的事情
expr_parse = do
name <- resvd_cmd
char '('
skipMany space
worker <- ident
char ','
skipMany1 space
args <- commaSep expr --not fully worked this out yet
query <- theQuery
skipMany space
char ')'
return (name, worker, args, query)
这对我来说看起来不太理想而且非常笨重。有没有办法重构expr
下面的代码,实现我需要的并保持简单?
module Parser where
import Control.Monad (liftM)
import Text.Parsec
import Text.Parsec.String (Parser)
import Lexer
import AST
expr = ident <|> astring <|> number <|> theQuery <|> callOrIdent
astring = liftM String stringLiteral <?> "String"
number = liftM Number float <?> "Number"
ident = liftM Identifier identifier <?> "WorkerName"
questionm :: Parser Char
questionm = oneOf "?"
theQuery :: Parser AST
theQuery = do first <- questionm
rest <- many1 letter
let query = first:rest
return ( Query query )
resvd_cmd = do { reserved "rd"; return ("rd") }
<|> do { reserved "eval"; return ("eval") }
<|> do { reserved "read"; return ("read") }
<|> do { reserved "in"; return ("in") }
<|> do { reserved "out"; return ("out") }
<?> "LINDA-like Tuple"
callOrIdent = do
name <- resvd_cmd
liftM (FuncCall name)(parens $ commaSep expr) <|> return (Identifier name)
AST.hs
{-# LANGUAGE DeriveDataTypeable #-}
module AST where
import Data.Typeable
data AST
= Number Double
| Identifier String
| String String
| FuncCall String [AST]
| Query String
deriving (Show, Eq, Typeable)
词法分析器
module Lexer (
identifier, reserved, operator, reservedOp, charLiteral, stringLiteral,
natural, integer, float, naturalOrFloat, decimal, hexadecimal, octal,
symbol, lexeme, whiteSpace, parens, braces, angles, brackets, semi,
comma, colon, dot, semiSep, semiSep1, commaSep, commaSep1
)where
import Text.Parsec
import qualified Text.Parsec.Token as P
import Text.Parsec.Language (haskellStyle)
lexer = P.makeTokenParser ( haskellStyle
{P.reservedNames = ["rd", "in", "out", "eval", "take"]}
)
identifier = P.identifier lexer
reserved = P.reserved lexer
operator = P.operator lexer
reservedOp = P.reservedOp lexer
charLiteral = P.charLiteral lexer
stringLiteral = P.stringLiteral lexer
natural = P.natural lexer
integer = P.integer lexer
float = P.float lexer
naturalOrFloat = P.naturalOrFloat lexer
decimal = P.decimal lexer
hexadecimal = P.hexadecimal lexer
octal = P.octal lexer
symbol = P.symbol lexer
lexeme = P.lexeme lexer
whiteSpace = P.whiteSpace lexer
parens = P.parens lexer
braces = P.braces lexer
angles = P.angles lexer
brackets = P.brackets lexer
semi = P.semi lexer
comma = P.comma lexer
colon = P.colon lexer
dot = P.dot lexer
semiSep = P.semiSep lexer
semiSep1 = P.semiSep1 lexer
commaSep = P.commaSep lexer
commaSep1 = P.commaSep1 lexer