blob: a7294fe8d5b99e6a04d113be885fa8af58bf072b (
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
|
{-# LANGUAGE OverloadedStrings #-}
{-# LANGUAGE DeriveGeneric, DeriveAnyClass #-}
-- | A parser to transform 'Text' into a stream of 'BBToken's
module Text.BBCode.Lexer
( BBToken(..)
, token
, escapedText
, escapedText'
) where
import Data.Attoparsec.Text
import Data.Text (Text)
import qualified Data.Text as T (singleton)
import Control.Applicative
-- | Our lexicographical unit
data BBToken = BBOpen Text -- ^ Tag open
| BBClose Text -- ^ Tag close
| BBStr Text -- ^ Content of a tag
deriving (Eq, Show)
token :: Parser BBToken
-- ^ Tokenizer
token = BBClose <$> (string "[/" *> escapedText' [']'] <* string "]")
<|> BBOpen <$> (string "[" *> escapedText' [']'] <* string "]")
<|> BBStr <$> escapedText ['[']
escapedText :: [Char] -> Parser Text
-- ^ @escapedText cs@ consumes 'Text' up to (not including) the first occurence of a character from @cs@ that is not escaped using @\\@
--
-- Always consumes at least one character
--
-- @\\@ needs to be escaped (prefixed with @\\@) iff it precedes a character from @cs@
escapedText [] = takeText
escapedText cs = recurse $ choice [ takeWhile1 (not . special)
, escapeSeq
, escapeChar'
]
where
escapeChar = '\\'
special = inClass $ escapeChar : cs
escapeChar' = string $ T.singleton escapeChar
escapeSeq = escapeChar' >> (T.singleton <$> satisfy special) -- s/\\([:cs])/\1/
recurse p = mappend <$> p <*> escapedText' cs
escapedText' :: [Char] -> Parser Text
-- ^ @'option' "" $ 'escapedText' cs@
escapedText' cs = option "" $ escapedText cs
|
