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
|
{-
Copyright (C) 2015 John MacFarlane <jgm@berkeley.edu>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
-}
{- |
Module : Text.Pandoc.Readers.CommonMark
Copyright : Copyright (C) 2015 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Conversion of CommonMark-formatted plain text to 'Pandoc' document.
CommonMark is a strongly specified variant of Markdown: http://commonmark.org.
-}
module Text.Pandoc.Readers.CommonMark (readCommonMark)
where
import CMarkGFM
import Data.List (groupBy)
import Data.Text (Text, unpack)
import Text.Pandoc.Class (PandocMonad)
import Text.Pandoc.Definition
import Text.Pandoc.Options
-- | Parse a CommonMark formatted string into a 'Pandoc' structure.
readCommonMark :: PandocMonad m => ReaderOptions -> Text -> m Pandoc
readCommonMark opts s = return $
nodeToPandoc $ commonmarkToNode opts' exts s
where opts' = [optSmart | enabled Ext_smart]
exts = [extStrikethrough, extTable, extAutolink]
enabled x = extensionEnabled x (readerExtensions opts)
nodeToPandoc :: Node -> Pandoc
nodeToPandoc (Node _ DOCUMENT nodes) =
Pandoc nullMeta $ foldr addBlock [] nodes
nodeToPandoc n = -- shouldn't happen
Pandoc nullMeta $ foldr addBlock [] [n]
addBlocks :: [Node] -> [Block]
addBlocks = foldr addBlock []
addBlock :: Node -> [Block] -> [Block]
addBlock (Node _ PARAGRAPH nodes) =
(Para (addInlines nodes) :)
addBlock (Node _ THEMATIC_BREAK _) =
(HorizontalRule :)
addBlock (Node _ BLOCK_QUOTE nodes) =
(BlockQuote (addBlocks nodes) :)
addBlock (Node _ (HTML_BLOCK t) _) =
(RawBlock (Format "html") (unpack t) :)
-- Note: the cmark parser will never generate CUSTOM_BLOCK,
-- so we don't need to handle it:
addBlock (Node _ (CUSTOM_BLOCK _onEnter _onExit) _nodes) =
id
addBlock (Node _ (CODE_BLOCK info t) _) =
(CodeBlock ("", take 1 (words (unpack info)), []) (unpack t) :)
addBlock (Node _ (HEADING lev) nodes) =
(Header lev ("",[],[]) (addInlines nodes) :)
addBlock (Node _ (LIST listAttrs) nodes) =
(constructor (map (setTightness . addBlocks . children) nodes) :)
where constructor = case listType listAttrs of
BULLET_LIST -> BulletList
ORDERED_LIST -> OrderedList
(start, DefaultStyle, delim)
start = listStart listAttrs
setTightness = if listTight listAttrs
then map paraToPlain
else id
paraToPlain (Para xs) = Plain (xs)
paraToPlain x = x
delim = case listDelim listAttrs of
PERIOD_DELIM -> Period
PAREN_DELIM -> OneParen
addBlock (Node _ (TABLE alignments) nodes) = do
(Table [] aligns widths headers rows :)
where aligns = map fromTableCellAlignment alignments
fromTableCellAlignment NoAlignment = AlignDefault
fromTableCellAlignment LeftAligned = AlignLeft
fromTableCellAlignment RightAligned = AlignRight
fromTableCellAlignment CenterAligned = AlignCenter
widths = replicate numcols 0.0
numcols = if null rows'
then 0
else maximum $ map length rows'
rows' = map toRow $ filter isRow nodes
(headers, rows) = case rows' of
(h:rs) -> (h, rs)
[] -> ([], [])
isRow (Node _ TABLE_ROW _) = True
isRow _ = False
isCell (Node _ TABLE_CELL _) = True
isCell _ = False
toRow (Node _ TABLE_ROW ns) = map toCell $ filter isCell ns
toRow (Node _ t _) = error $ "toRow encountered non-row " ++ show t
toCell (Node _ TABLE_CELL []) = []
toCell (Node _ TABLE_CELL (n:ns))
| isBlockNode n = addBlocks (n:ns)
| otherwise = [Plain (addInlines (n:ns))]
toCell (Node _ t _) = error $ "toCell encountered non-cell " ++ show t
addBlock (Node _ TABLE_ROW _) = id -- handled in TABLE
addBlock (Node _ TABLE_CELL _) = id -- handled in TABLE
addBlock _ = id
isBlockNode :: Node -> Bool
isBlockNode (Node _ nodetype _) =
case nodetype of
DOCUMENT -> True
THEMATIC_BREAK -> True
PARAGRAPH -> True
BLOCK_QUOTE -> True
HTML_BLOCK _ -> True
CUSTOM_BLOCK _ _ -> True
CODE_BLOCK _ _ -> True
HEADING _ -> True
LIST _ -> True
ITEM -> True
TEXT _ -> False
SOFTBREAK -> False
LINEBREAK -> False
HTML_INLINE _ -> False
CUSTOM_INLINE _ _ -> False
CODE _ -> False
EMPH -> False
STRONG -> False
LINK _ _ -> False
IMAGE _ _ -> False
STRIKETHROUGH -> False
TABLE _ -> False
TABLE_ROW -> False
TABLE_CELL -> False
children :: Node -> [Node]
children (Node _ _ ns) = ns
addInlines :: [Node] -> [Inline]
addInlines = foldr addInline []
addInline :: Node -> [Inline] -> [Inline]
addInline (Node _ (TEXT t) _) = (map toinl clumps ++)
where raw = unpack t
clumps = groupBy samekind raw
samekind ' ' ' ' = True
samekind ' ' _ = False
samekind _ ' ' = False
samekind _ _ = True
toinl (' ':_) = Space
toinl xs = Str xs
addInline (Node _ LINEBREAK _) = (LineBreak :)
addInline (Node _ SOFTBREAK _) = (SoftBreak :)
addInline (Node _ (HTML_INLINE t) _) =
(RawInline (Format "html") (unpack t) :)
-- Note: the cmark parser will never generate CUSTOM_BLOCK,
-- so we don't need to handle it:
addInline (Node _ (CUSTOM_INLINE _onEnter _onExit) _nodes) =
id
addInline (Node _ (CODE t) _) =
(Code ("",[],[]) (unpack t) :)
addInline (Node _ EMPH nodes) =
(Emph (addInlines nodes) :)
addInline (Node _ STRONG nodes) =
(Strong (addInlines nodes) :)
addInline (Node _ STRIKETHROUGH nodes) =
(Strikeout (addInlines nodes) :)
addInline (Node _ (LINK url title) nodes) =
(Link nullAttr (addInlines nodes) (unpack url, unpack title) :)
addInline (Node _ (IMAGE url title) nodes) =
(Image nullAttr (addInlines nodes) (unpack url, unpack title) :)
addInline _ = id
|
