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
|
{-# 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 Data.Char (isSpace)
import Control.Applicative
import Control.Monad (liftM2)
import Data.Monoid
import Prelude hiding (takeWhile)
-- | Our lexicographical unit
data BBToken = BBOpen Text [(Text, Text)] -- ^ Tag open with attributes
| BBContained Text [(Text, Text)] -- ^ Tag open & immediate close with attributes
| BBClose Text -- ^ Tag close
| BBStr Text -- ^ Content of a tag
| BBNewPar
deriving (Eq, Show)
token :: Parser BBToken
-- ^ Tokenizer
token = BBClose <$> ("[/" *> escapedText' [']'] <* "]")
<|> uncurry BBContained <$ "[" <*> openTag <* "/]"
<|> uncurry BBOpen <$ "[" <*> openTag <* "]"
<|> BBNewPar <$ endOfLine <* many1 endOfLine
<|> BBStr <$> paragraph
where
paragraph = (\a b c -> a <> b <> c) <$> option "" endOfLine' <*> escapedText ['['] <*> option "" paragraph
endOfLine' = "\n" <$ endOfLine
openTag :: Parser (Text, [(Text, Text)])
openTag = (,) <$> escapedText' [']', ' ', '=', '/'] <*> attrs'
attrs :: Parser [(Text, Text)]
attrs = (:) <$> (namedAttr <|> plainValue) <* takeWhile isSpace <*> attrs'
where
namedAttr = (,) <$ takeWhile isSpace <*> escapedText ['=', ']', ' ', '/'] <*> option "" ("=" *> attrArg)
plainValue = (,) <$> pure "" <* "=" <*> attrArg
attrArg = "\"" *> escapedText ['"'] <* "\""
<|> escapedText [']', ' ', '/']
attrs' :: Parser [(Text, Text)]
attrs' = option [] attrs
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 @\\@
--
-- Does not consume characters used to indicate linebreaks as determined by `isEndOfLine`
--
-- 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 . liftM2 (||) special isEndOfLine
, 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
|
