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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
|
{-# LANGUAGE OverloadedStrings #-}
{-# LANGUAGE ViewPatterns #-}
{- |
Module : Text.Pandoc.Readers.CommonMark
Copyright : Copyright (C) 2015-2020 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 Control.Monad.State
import qualified Data.Set as Set
import Data.Text (Text)
import qualified Data.Text as T
import Text.Pandoc.Class.PandocMonad (PandocMonad)
import Text.Pandoc.Definition
import Text.Pandoc.Emoji (emojiToInline)
import Text.Pandoc.Options
import Text.Pandoc.Shared (uniqueIdent, taskListItemFromAscii)
import Text.Pandoc.Walk (walkM)
-- | Parse a CommonMark formatted string into a 'Pandoc' structure.
readCommonMark :: PandocMonad m => ReaderOptions -> Text -> m Pandoc
readCommonMark opts s = return $
(if isEnabled Ext_auto_identifiers opts
then addHeaderIdentifiers opts
else id) $
nodeToPandoc opts $ commonmarkToNode opts' exts s
where opts' = [ optSmart | isEnabled Ext_smart opts ]
exts = [ extStrikethrough | isEnabled Ext_strikeout opts ] ++
[ extTable | isEnabled Ext_pipe_tables opts ] ++
[ extAutolink | isEnabled Ext_autolink_bare_uris opts ]
convertEmojis :: Text -> [Inline]
convertEmojis s@(T.uncons -> Just (':',xs)) =
case T.break (==':') xs of
(ys, T.uncons -> Just (':',zs)) ->
case emojiToInline ys of
Just em -> em : convertEmojis zs
Nothing -> Str (":" <> ys) : convertEmojis (":" <> zs)
_ -> [Str s]
convertEmojis s =
case T.break (==':') s of
("","") -> []
(_,"") -> [Str s]
(xs,ys) -> Str xs : convertEmojis ys
addHeaderIdentifiers :: ReaderOptions -> Pandoc -> Pandoc
addHeaderIdentifiers opts doc = evalState (walkM (addHeaderId opts) doc) mempty
addHeaderId :: ReaderOptions -> Block -> State (Set.Set Text) Block
addHeaderId opts (Header lev (_,classes,kvs) ils) = do
ids <- get
let ident = uniqueIdent (readerExtensions opts) ils ids
modify (Set.insert ident)
return $ Header lev (ident,classes,kvs) ils
addHeaderId _ x = return x
nodeToPandoc :: ReaderOptions -> Node -> Pandoc
nodeToPandoc opts (Node _ DOCUMENT nodes) =
Pandoc nullMeta $ foldr (addBlock opts) [] nodes
nodeToPandoc opts n = -- shouldn't happen
Pandoc nullMeta $ foldr (addBlock opts) [] [n]
addBlocks :: ReaderOptions -> [Node] -> [Block]
addBlocks opts = foldr (addBlock opts) []
addBlock :: ReaderOptions -> Node -> [Block] -> [Block]
addBlock opts (Node _ PARAGRAPH nodes) =
(Para (addInlines opts nodes) :)
addBlock _ (Node _ THEMATIC_BREAK _) =
(HorizontalRule :)
addBlock opts (Node _ BLOCK_QUOTE nodes) =
(BlockQuote (addBlocks opts nodes) :)
addBlock opts (Node _ (HTML_BLOCK t) _)
| isEnabled Ext_raw_html opts = (RawBlock (Format "html") t :)
| otherwise = id
-- 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 (T.words info), []) t :)
addBlock opts (Node _ (HEADING lev) nodes) =
(Header lev ("",[],[]) (addInlines opts nodes) :)
addBlock opts (Node _ (LIST listAttrs) nodes) =
(constructor (map listItem nodes) :)
where constructor = case listType listAttrs of
BULLET_LIST -> BulletList
ORDERED_LIST -> OrderedList
(start, DefaultStyle, delim)
start = listStart listAttrs
listItem = taskListItemFromAscii exts . setTightness
. addBlocks opts . children
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
exts = readerExtensions opts
addBlock opts (Node _ (TABLE alignments) nodes) =
(Table
nullAttr
(Caption Nothing [])
(zip aligns widths)
(TableHead nullAttr headers)
[TableBody nullAttr 0 [] rows]
(TableFoot nullAttr []) :)
where aligns = map fromTableCellAlignment alignments
fromTableCellAlignment NoAlignment = AlignDefault
fromTableCellAlignment LeftAligned = AlignLeft
fromTableCellAlignment RightAligned = AlignRight
fromTableCellAlignment CenterAligned = AlignCenter
widths = replicate numcols ColWidthDefault
numcols = if null rows'
then 0
else maximum $ map rowLength 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) = Row nullAttr $ map toCell $ filter isCell ns
toRow (Node _ t _) = error $ "toRow encountered non-row " ++ show t
toCell (Node _ TABLE_CELL []) = fromSimpleCell []
toCell (Node _ TABLE_CELL (n:ns))
| isBlockNode n = fromSimpleCell $ addBlocks opts (n:ns)
| otherwise = fromSimpleCell [Plain (addInlines opts (n:ns))]
toCell (Node _ t _) = error $ "toCell encountered non-cell " ++ show t
fromSimpleCell = Cell nullAttr AlignDefault 1 1
rowLength (Row _ body) = length body -- all cells are 1×1
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 :: ReaderOptions -> [Node] -> [Inline]
addInlines opts = foldr (addInline opts) []
addInline :: ReaderOptions -> Node -> [Inline] -> [Inline]
addInline opts (Node _ (TEXT t) _) = (concatMap toinl clumps ++)
where clumps = T.groupBy samekind t
samekind ' ' ' ' = True
samekind ' ' _ = False
samekind _ ' ' = False
samekind _ _ = True
toinl (T.uncons -> Just (' ', _)) = [Space]
toinl xs = if isEnabled Ext_emoji opts
then convertEmojis xs
else [Str xs]
addInline _ (Node _ LINEBREAK _) = (LineBreak :)
addInline opts (Node _ SOFTBREAK _)
| isEnabled Ext_hard_line_breaks opts = (LineBreak :)
| otherwise = (SoftBreak :)
addInline opts (Node _ (HTML_INLINE t) _)
| isEnabled Ext_raw_html opts = (RawInline (Format "html") t :)
| otherwise = id
-- 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 ("",[],[]) t :)
addInline opts (Node _ EMPH nodes) =
(Emph (addInlines opts nodes) :)
addInline opts (Node _ STRONG nodes) =
(Strong (addInlines opts nodes) :)
addInline opts (Node _ STRIKETHROUGH nodes) =
(Strikeout (addInlines opts nodes) :)
addInline opts (Node _ (LINK url title) nodes) =
(Link nullAttr (addInlines opts nodes) (url, title) :)
addInline opts (Node _ (IMAGE url title) nodes) =
(Image nullAttr (addInlines opts nodes) (url, title) :)
addInline _ _ = id
|
