1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
{-# LANGUAGE DeriveFunctor #-}
{-# LANGUAGE OverloadedStrings #-}
module Language.Fiddle.Tokenizer where
import Data.Char (isDigit)
import Data.Text (Text)
import qualified Data.Text
import Language.Fiddle.Types
import Text.Parsec
data T
= KWAssertPos
| KWAt
| KWBits
| KWEnum
| KWInstance
| KWLocation
| KWOption
| KWPackage
| KWReg
| KWReserved
| KWRo
| KWRw
| KWStruct
| KWType
| KWUnion
| KWWo
| KWImport
| KWUsing
| TokColon
| TokComma
| TokDot
| TokComment !Text
| TokDocComment !Text
| TokEq
| TokIdent !Text
| TokLBrace
| TokLBracket
| TokLParen
| TokLitNum !Text
| TokRBrace
| TokRBracket
| TokRParen
| TokSemi
| TokString !Text
| TokDirectiveStart -- [[
| TokDirectiveEnd -- ]]
deriving (Eq, Ord, Show, Read)
textOf :: T -> Maybe Text
textOf t = do
case t of
KWAssertPos -> Just "assert_pos"
KWAt -> Just "at"
KWBits -> Just "bits"
KWEnum -> Just "enum"
KWInstance -> Just "instance"
KWLocation -> Just "location"
KWOption -> Just "option"
KWPackage -> Just "package"
KWReg -> Just "reg"
KWReserved -> Just "reserved"
KWRo -> Just "ro"
KWRw -> Just "rw"
KWStruct -> Just "struct"
KWType -> Just "type"
KWUnion -> Just "union"
KWWo -> Just "wo"
KWImport -> Just "import"
KWUsing -> Just "using"
TokIdent i -> Just i
TokLitNum n -> Just n
_ -> Nothing
data Token a = Token !T a
deriving (Eq, Ord, Show, Functor)
parseToken :: (Monad m) => ParsecT Text u m (Token SourceSpan)
parseToken = spaces *> tok parseToken' <* spaces
where
tok tp = do
p1 <- getPosition
t <- tp
Token t . SourceSpan p1 <$> getPosition
parseAlNumTok :: Text -> T
parseAlNumTok str =
case str of
"at" -> KWAt
"bits" -> KWBits
"enum" -> KWEnum
"location" -> KWLocation
"instance" -> KWInstance
"type" -> KWType
"option" -> KWOption
"package" -> KWPackage
"import" -> KWImport
"reg" -> KWReg
"ro" -> KWRo
"wo" -> KWWo
"rw" -> KWRw
"reserved" -> KWReserved
"union" -> KWUnion
"using" -> KWUsing
"struct" -> KWStruct
"assert_pos" -> KWAssertPos
(Data.Text.head -> h) | isDigit h -> TokLitNum str
ident -> TokIdent ident
parseString = fmap (TokString . Data.Text.pack . concat) $ do
_ <- char '"'
manyTill
( do
c <- anyChar
if c == '\\'
then do
c2 <- anyChar
return [c, c2]
else return [c]
)
(char '"')
parseComment =
try
( do
_ <- string "//"
TokComment . Data.Text.pack <$> manyTill anyChar (char '\n')
)
<|> try
( do
_ <- string "/**"
TokDocComment . Data.Text.pack <$> manyTill anyChar (try $ string "*/")
)
parseSymbol =
choice
[ try (string "[[" $> TokDirectiveStart),
try (string "]]" $> TokDirectiveEnd),
char ':' $> TokColon,
char ',' $> TokComma,
char '.' $> TokDot,
char '=' $> TokEq,
char '{' $> TokLBrace,
char '[' $> TokLBracket,
char '(' $> TokLParen,
char '}' $> TokRBrace,
char ']' $> TokRBracket,
char ')' $> TokRParen,
char ';' $> TokSemi
]
where
a $> b = a >> return b
parseToken' =
fmap (parseAlNumTok . Data.Text.pack) (many1 (alphaNum <|> char '_'))
<|> parseString
<|> parseComment
<|> parseSymbol
tokenize :: String -> Text -> Either ParseError [Token SourceSpan]
tokenize = Text.Parsec.runParser (many parseToken <* eof) ()
tokenType :: Token SourceSpan -> T
tokenType (Token t _) = t
|
