aboutsummaryrefslogtreecommitdiffstats
path: root/src/Tokenizer.hs
blob: 64ba638e01473b9655fa13df71abdeb1bc168475 (plain)
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
module Tokenizer (
    tokenize,
) where

import qualified Data.Bifunctor as B
import Control.Monad.Except
import Utils

data TChar = TChar {
    tChar :: Char,
    tRow :: Int,
    tColumn :: Int
}

_tokenize :: String -> [Token] -> [TChar] -> [TChar] -> LContext [Token]
_tokenize fileName acc current [] =
    let cur = reverse current
        token = Token {
            tokenContent = cur $> map tChar,
            tokenRow = tRow $ head cur,
            tokenColumn = tColumn $ head cur,
            tokenFileName = fileName }
     in return $ token : acc
_tokenize fileName acc current (x:xs)
    | tChar x == ';' =
        let commentDropped = dropWhile (\tc -> tChar tc /= '\n') xs
            cur = reverse current
            token = Token {
                tokenContent = cur $> map tChar,
                tokenRow = tRow $ head cur,
                tokenColumn = tColumn $ head cur,
                tokenFileName = fileName }
         in _tokenize fileName (token : acc) [] commentDropped
    | tChar x == '"' =
        -- String length -1 signals an unbalanced error
        let inc k n = if n == -1 then -1 else n + k
            consume :: String -> (String, Int)
            consume str = case str of
                ('\\':'"':rest) -> B.bimap ('\"' :) (inc 2) (consume rest)
                ('\\':'n':rest) -> B.bimap ('\n' :) (inc 2) (consume rest)
                ('\\':'t':rest) -> B.bimap ('\t' :) (inc 2) (consume rest)
                ('"':_) -> ("", 1)
                (c:rest) -> B.bimap (c :) (inc 1) (consume rest)
                [] -> ("", -1)
            (string, stringLength) = consume (map tChar xs)
            stringDropped = drop (stringLength) xs
            withQuotes = "\"" ++ string ++ "\""
            token = Token {
                tokenContent = withQuotes,
                tokenRow = tRow $ x,
                tokenColumn = tColumn $ x,
                tokenFileName = fileName }
        in do
            when (stringLength == -1) $ throwL "unbalanced string literal"
            _tokenize fileName (token : acc) [] stringDropped
    | tChar x `elem` [' ', '\n', '\t', '\r'] =
        let cur = reverse current
            token = Token {
                tokenContent = cur $> map tChar,
                tokenRow = tRow $ head cur,
                tokenColumn = tColumn $ head cur,
                tokenFileName = fileName }
         in _tokenize fileName (token : acc) [] xs
    | tChar x `elem` ['(', ')', '[', ']', '{', '}', '\\'] =
        let cur = reverse current
            token1 = Token {
                tokenContent = [tChar x],
                tokenRow = tRow x,
                tokenColumn = tColumn x,
                tokenFileName = fileName
            }
            token2 = Token {
                tokenContent = cur $> map tChar,
                tokenRow = tRow $ head cur,
                tokenColumn = tColumn $ head cur,
                tokenFileName = fileName
            }
         in _tokenize fileName (token1 : token2 : acc) [] xs
    | otherwise = _tokenize fileName acc (x : current) xs

tokenize :: String -> String -> LContext [Token]
tokenize fileName src = do
    let tChars = augment 0 0 src
    tokens <- _tokenize fileName [] [] tChars
    return $ tokens
        $> reverse
        .> filter (\t -> length (tokenContent t) > 0)

    where
        augment row col ('\r':'\n':rest) =
            TChar '\n' row col : augment 0 (col + 1) rest
        augment row col ('\n':rest) =
            TChar '\n' row col : augment 0 (col + 1) rest
        augment row col (c:rest) =
            TChar c (row + 1) col : augment 0 (col + 1) rest
        augment _ _ [] = []