aboutsummaryrefslogtreecommitdiff
path: root/src/Haddock/Lex.x
blob: fca2bf7f888e55f6de34441d0cb68ea7b06669ab (plain) (blame)
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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
--
-- Haddock - A Haskell Documentation Tool
--
-- (c) Simon Marlow 2002
--
-- This file was modified and integrated into GHC by David Waern 2006.
-- Then moved back into Haddock by Isaac Dupree in 2009 :-)
--

{
{-# OPTIONS -Wwarn -w #-}
-- The above warning supression flag is a temporary kludge.
-- While working on this module you are encouraged to remove it and fix
-- any warnings in the module. See
--     http://hackage.haskell.org/trac/ghc/wiki/Commentary/CodingStyle#Warnings
-- for details

module Haddock.Lex (
	Token(..),
  LToken,
	tokenise
 ) where

import Lexer hiding (Token)
import Parser ( parseIdentifier )
import StringBuffer
import RdrName
import SrcLoc
import DynFlags

import Data.Char
import Numeric
import System.IO.Unsafe
}

%wrapper "posn"

$ws    = $white # \n
$digit = [0-9]
$hexdigit = [0-9a-fA-F]
$special =  [\"\@]
$alphanum = [A-Za-z0-9]
$ident    = [$alphanum \'\_\.\!\#\$\%\&\*\+\/\<\=\>\?\@\\\\\^\|\-\~\:]

:-

-- beginning of a paragraph
<0,para> {
 $ws* \n		;
 $ws* \>		{ begin birdtrack }
 $ws* ghci \>	        { strtoken TokExamplePrompt `andBegin` exampleexpr }
 $ws* [\*\-]		{ token TokBullet `andBegin` string }
 $ws* \[		{ token TokDefStart `andBegin` def }
 $ws* \( $digit+ \) 	{ token TokNumber `andBegin` string }
 $ws*			{ begin string }		
}

-- beginning of a line
<line> {
  $ws* \>		{ begin birdtrack }
  $ws* ghci \>		{ strtoken TokExamplePrompt `andBegin` exampleexpr }
  $ws* \n		{ token TokPara `andBegin` para }
  -- Here, we really want to be able to say
  -- $ws* (\n | <eof>) 	{ token TokPara `andBegin` para}
  -- because otherwise a trailing line of whitespace will result in 
  -- a spurious TokString at the end of a docstring.  We don't have <eof>,
  -- though (NOW I realise what it was for :-).  To get around this, we always
  -- append \n to the end of a docstring.
  () 			{ begin string }
}

<birdtrack> .*	\n?	{ strtokenNL TokBirdTrack `andBegin` line }

<example> {
  $ws*	\n		{ token TokPara `andBegin` para }
  $ws* ghci \>	        { strtoken TokExamplePrompt `andBegin` exampleexpr }
  ()			{ begin exampleresult }
}

<exampleexpr> .* \n	{ strtokenNL TokExampleExpression `andBegin` example }

<exampleresult> .* \n	{ strtokenNL TokExampleResult `andBegin` example }

<string,def> {
  $special			{ strtoken $ \s -> TokSpecial (head s) }
  \<\< [^\>]* \>\>              { strtoken $ \s -> TokPic (init $ init $ tail $ tail s) }
  \< [^\>]* \>			{ strtoken $ \s -> TokURL (init (tail s)) }
  \# [^\#]* \#			{ strtoken $ \s -> TokAName (init (tail s)) }
  \/ [^\/]* \/                  { strtoken $ \s -> TokEmphasis (init (tail s)) }
  [\'\`] $ident+ [\'\`]		{ ident }
  \\ .				{ strtoken (TokString . tail) }
  "&#" $digit+ \;		{ strtoken $ \s -> TokString [chr (read (init (drop 2 s)))] }
  "&#" [xX] $hexdigit+ \;	{ strtoken $ \s -> case readHex (init (drop 3 s)) of [(n,_)] -> TokString [chr n] }
  -- allow special characters through if they don't fit one of the previous
  -- patterns.
  [\/\'\`\<\#\&\\]			{ strtoken TokString }
  [^ $special \/ \< \# \n \'\` \& \\ \]]* \n { strtokenNL TokString `andBegin` line }
  [^ $special \/ \< \# \n \'\` \& \\ \]]+    { strtoken TokString }
}

<def> {
  \]				{ token TokDefEnd `andBegin` string }
}

-- ']' doesn't have any special meaning outside of the [...] at the beginning
-- of a definition paragraph.
<string> {
  \]				{ strtoken TokString }
}

{
-- | A located token
type LToken = (Token, AlexPosn)

data Token
  = TokPara
  | TokNumber
  | TokBullet
  | TokDefStart
  | TokDefEnd
  | TokSpecial Char
  | TokIdent [RdrName]
  | TokString String
  | TokURL String
  | TokPic String
  | TokEmphasis String
  | TokAName String
  | TokBirdTrack String
  | TokExamplePrompt String
  | TokExampleExpression String
  | TokExampleResult String
--  deriving Show

tokenPos :: LToken -> (Int, Int)
tokenPos t = let AlexPn _ line col = snd t in (line, col)

-- -----------------------------------------------------------------------------
-- Alex support stuff

type StartCode = Int
type Action = AlexPosn -> String -> StartCode -> (StartCode -> [LToken]) -> [LToken]

tokenise :: String -> (Int, Int) -> [LToken]
tokenise str (line, col) = let toks = go (posn, '\n', eofHack str) para in {-trace (show toks)-} toks
  where
    posn = AlexPn 0 line col

    go inp@(pos, _, str) sc =
	  case alexScan inp sc of
		AlexEOF -> []
		AlexError _ -> error "lexical error"
		AlexSkip  inp' _       -> go inp' sc
		AlexToken inp'@(pos',_,_) len act -> act pos (take len str) sc (\sc -> go inp' sc)

-- NB. we add a final \n to the string, (see comment in the beginning of line
-- production above).
eofHack str = str++"\n"

andBegin  :: Action -> StartCode -> Action
andBegin act new_sc = \pos str _ cont -> act pos str new_sc cont

token :: Token -> Action
token t = \pos _ sc cont -> (t, pos) : cont sc

strtoken, strtokenNL :: (String -> Token) -> Action
strtoken t = \pos str sc cont -> (t str, pos) : cont sc
strtokenNL t = \pos str sc cont -> (t (filter (/= '\r') str), pos) : cont sc
-- ^ We only want LF line endings in our internal doc string format, so we
-- filter out all CRs.

begin :: StartCode -> Action
begin sc = \_ _ _ cont -> cont sc

-- -----------------------------------------------------------------------------
-- Lex a string as a Haskell identifier

ident :: Action
ident pos str sc cont = 
  case strToHsQNames id of
	Just names -> (TokIdent names, pos) : cont sc
	Nothing -> (TokString str, pos) : cont sc
 where id = init (tail str)

strToHsQNames :: String -> Maybe [RdrName]
strToHsQNames str0 = 
  let buffer = unsafePerformIO (stringToStringBuffer str0)
      pstate = mkPState buffer noSrcLoc defaultDynFlags
      result = unP parseIdentifier pstate 
  in case result of 
       POk _ name -> Just [unLoc name] 
       _ -> Nothing
}