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
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
|
{-# LANGUAGE OverloadedStrings, PatternGuards #-}
{-
Copyright (C) 2006-2015 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.Writers.Docbook
Copyright : Copyright (C) 2006-2015 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Conversion of 'Pandoc' documents to Docbook XML.
-}
module Text.Pandoc.Writers.Docbook ( writeDocbook) where
import Text.Pandoc.Definition
import Text.Pandoc.XML
import Text.Pandoc.Shared
import Text.Pandoc.Walk
import Text.Pandoc.Writers.Shared
import Text.Pandoc.Options
import Text.Pandoc.Templates (renderTemplate')
import Text.Pandoc.Readers.TeXMath
import Data.List ( stripPrefix, isPrefixOf, intercalate, isSuffixOf )
import Data.Char ( toLower )
import Data.Monoid ( Any(..) )
import Text.Pandoc.Highlighting ( languages, languagesByExtension )
import Text.Pandoc.Pretty
import Text.Pandoc.ImageSize
import qualified Text.Pandoc.Builder as B
import Text.TeXMath
import qualified Text.XML.Light as Xml
import Data.Generics (everywhere, mkT)
-- | Convert list of authors to a docbook <author> section
authorToDocbook :: WriterOptions -> [Inline] -> B.Inlines
authorToDocbook opts name' =
let name = render Nothing $ inlinesToDocbook opts name'
colwidth = if writerWrapText opts == WrapAuto
then Just $ writerColumns opts
else Nothing
in B.rawInline "docbook" $ render colwidth $
if ',' `elem` name
then -- last name first
let (lastname, rest) = break (==',') name
firstname = triml rest in
inTagsSimple "firstname" (text $ escapeStringForXML firstname) <>
inTagsSimple "surname" (text $ escapeStringForXML lastname)
else -- last name last
let namewords = words name
lengthname = length namewords
(firstname, lastname) = case lengthname of
0 -> ("","")
1 -> ("", name)
n -> (intercalate " " (take (n-1) namewords), last namewords)
in inTagsSimple "firstname" (text $ escapeStringForXML firstname) $$
inTagsSimple "surname" (text $ escapeStringForXML lastname)
-- | Convert Pandoc document to string in Docbook format.
writeDocbook :: WriterOptions -> Pandoc -> String
writeDocbook opts (Pandoc meta blocks) =
let elements = hierarchicalize blocks
colwidth = if writerWrapText opts == WrapAuto
then Just $ writerColumns opts
else Nothing
render' = render colwidth
opts' = if (maybe False (("/book>" `isSuffixOf`) . trimr)
(writerTemplate opts) &&
TopLevelDefault == writerTopLevelDivision opts)
then opts{ writerTopLevelDivision = TopLevelChapter }
else opts
-- The numbering here follows LaTeX's internal numbering
startLvl = case writerTopLevelDivision opts' of
TopLevelPart -> -1
TopLevelChapter -> 0
TopLevelSection -> 1
TopLevelDefault -> 1
auths' = map (authorToDocbook opts) $ docAuthors meta
meta' = B.setMeta "author" auths' meta
Just metadata = metaToJSON opts
(Just . render colwidth . (vcat .
(map (elementToDocbook opts' startLvl)) . hierarchicalize))
(Just . render colwidth . inlinesToDocbook opts')
meta'
main = render' $ vcat (map (elementToDocbook opts' startLvl) elements)
context = defField "body" main
$ defField "mathml" (case writerHTMLMathMethod opts of
MathML _ -> True
_ -> False)
$ metadata
in case writerTemplate opts of
Nothing -> main
Just tpl -> renderTemplate' tpl context
-- | Convert an Element to Docbook.
elementToDocbook :: WriterOptions -> Int -> Element -> Doc
elementToDocbook opts _ (Blk block) = blockToDocbook opts block
elementToDocbook opts lvl (Sec _ _num (id',_,_) title elements) =
-- Docbook doesn't allow sections with no content, so insert some if needed
let elements' = if null elements
then [Blk (Para [])]
else elements
tag = case lvl of
-1 -> "part"
0 -> "chapter"
n | n >= 1 && n <= 5 -> if writerDocbook5 opts
then "section"
else "sect" ++ show n
_ -> "simplesect"
idAttr = [("id", writerIdentifierPrefix opts ++ id') | not (null id')]
nsAttr = if writerDocbook5 opts && lvl == 0 then [("xmlns", "http://docbook.org/ns/docbook"),("xmlns:xlink", "http://www.w3.org/1999/xlink")]
else []
attribs = nsAttr ++ idAttr
in inTags True tag attribs $
inTagsSimple "title" (inlinesToDocbook opts title) $$
vcat (map (elementToDocbook opts (lvl + 1)) elements')
-- | Convert a list of Pandoc blocks to Docbook.
blocksToDocbook :: WriterOptions -> [Block] -> Doc
blocksToDocbook opts = vcat . map (blockToDocbook opts)
-- | Auxiliary function to convert Plain block to Para.
plainToPara :: Block -> Block
plainToPara (Plain x) = Para x
plainToPara x = x
-- | Convert a list of pairs of terms and definitions into a list of
-- Docbook varlistentrys.
deflistItemsToDocbook :: WriterOptions -> [([Inline],[[Block]])] -> Doc
deflistItemsToDocbook opts items =
vcat $ map (\(term, defs) -> deflistItemToDocbook opts term defs) items
-- | Convert a term and a list of blocks into a Docbook varlistentry.
deflistItemToDocbook :: WriterOptions -> [Inline] -> [[Block]] -> Doc
deflistItemToDocbook opts term defs =
let def' = concatMap (map plainToPara) defs
in inTagsIndented "varlistentry" $
inTagsIndented "term" (inlinesToDocbook opts term) $$
inTagsIndented "listitem" (blocksToDocbook opts def')
-- | Convert a list of lists of blocks to a list of Docbook list items.
listItemsToDocbook :: WriterOptions -> [[Block]] -> Doc
listItemsToDocbook opts items = vcat $ map (listItemToDocbook opts) items
-- | Convert a list of blocks into a Docbook list item.
listItemToDocbook :: WriterOptions -> [Block] -> Doc
listItemToDocbook opts item =
inTagsIndented "listitem" $ blocksToDocbook opts $ map plainToPara item
imageToDocbook :: WriterOptions -> Attr -> String -> Doc
imageToDocbook _ attr src = selfClosingTag "imagedata" $
("fileref", src) : idAndRole attr ++ dims
where
dims = go Width "width" ++ go Height "depth"
go dir dstr = case (dimension dir attr) of
Just a -> [(dstr, show a)]
Nothing -> []
-- | Convert a Pandoc block element to Docbook.
blockToDocbook :: WriterOptions -> Block -> Doc
blockToDocbook _ Null = empty
-- Add ids to paragraphs in divs with ids - this is needed for
-- pandoc-citeproc to get link anchors in bibliographies:
blockToDocbook opts (Div (ident,_,_) [Para lst]) =
let attribs = [("id", ident) | not (null ident)] in
if hasLineBreaks lst
then flush $ nowrap $ inTags False "literallayout" attribs
$ inlinesToDocbook opts lst
else inTags True "para" attribs $ inlinesToDocbook opts lst
blockToDocbook opts (Div (ident,_,_) bs) =
(if null ident
then mempty
else selfClosingTag "anchor" [("id", ident)]) $$
blocksToDocbook opts (map plainToPara bs)
blockToDocbook _ (Header _ _ _) = empty -- should not occur after hierarchicalize
blockToDocbook opts (Plain lst) = inlinesToDocbook opts lst
-- title beginning with fig: indicates that the image is a figure
blockToDocbook opts (Para [Image attr txt (src,'f':'i':'g':':':_)]) =
let alt = inlinesToDocbook opts txt
capt = if null txt
then empty
else inTagsSimple "title" alt
in inTagsIndented "figure" $
capt $$
(inTagsIndented "mediaobject" $
(inTagsIndented "imageobject"
(imageToDocbook opts attr src)) $$
inTagsSimple "textobject" (inTagsSimple "phrase" alt))
blockToDocbook opts (Para lst)
| hasLineBreaks lst = flush $ nowrap $ inTagsSimple "literallayout" $ inlinesToDocbook opts lst
| otherwise = inTagsIndented "para" $ inlinesToDocbook opts lst
blockToDocbook opts (LineBlock lns) =
blockToDocbook opts $ linesToPara lns
blockToDocbook opts (BlockQuote blocks) =
inTagsIndented "blockquote" $ blocksToDocbook opts blocks
blockToDocbook _ (CodeBlock (_,classes,_) str) =
text ("<programlisting" ++ lang ++ ">") <> cr <>
flush (text (escapeStringForXML str) <> cr <> text "</programlisting>")
where lang = if null langs
then ""
else " language=\"" ++ escapeStringForXML (head langs) ++
"\""
isLang l = map toLower l `elem` map (map toLower) languages
langsFrom s = if isLang s
then [s]
else languagesByExtension . map toLower $ s
langs = concatMap langsFrom classes
blockToDocbook opts (BulletList lst) =
let attribs = [("spacing", "compact") | isTightList lst]
in inTags True "itemizedlist" attribs $ listItemsToDocbook opts lst
blockToDocbook _ (OrderedList _ []) = empty
blockToDocbook opts (OrderedList (start, numstyle, _) (first:rest)) =
let numeration = case numstyle of
DefaultStyle -> []
Decimal -> [("numeration", "arabic")]
Example -> [("numeration", "arabic")]
UpperAlpha -> [("numeration", "upperalpha")]
LowerAlpha -> [("numeration", "loweralpha")]
UpperRoman -> [("numeration", "upperroman")]
LowerRoman -> [("numeration", "lowerroman")]
spacing = [("spacing", "compact") | isTightList (first:rest)]
attribs = numeration ++ spacing
items = if start == 1
then listItemsToDocbook opts (first:rest)
else (inTags True "listitem" [("override",show start)]
(blocksToDocbook opts $ map plainToPara first)) $$
listItemsToDocbook opts rest
in inTags True "orderedlist" attribs items
blockToDocbook opts (DefinitionList lst) =
let attribs = [("spacing", "compact") | isTightList $ concatMap snd lst]
in inTags True "variablelist" attribs $ deflistItemsToDocbook opts lst
blockToDocbook opts (RawBlock f str)
| f == "docbook" = text str -- raw XML block
| f == "html" = if writerDocbook5 opts
then empty -- No html in Docbook5
else text str -- allow html for backwards compatibility
| otherwise = empty
blockToDocbook _ HorizontalRule = empty -- not semantic
blockToDocbook opts (Table caption aligns widths headers rows) =
let captionDoc = if null caption
then empty
else inTagsIndented "title"
(inlinesToDocbook opts caption)
tableType = if isEmpty captionDoc then "informaltable" else "table"
percent w = show (truncate (100*w) :: Integer) ++ "*"
coltags = vcat $ zipWith (\w al -> selfClosingTag "colspec"
([("colwidth", percent w) | w > 0] ++
[("align", alignmentToString al)])) widths aligns
head' = if all null headers
then empty
else inTagsIndented "thead" $
tableRowToDocbook opts headers
body' = inTagsIndented "tbody" $
vcat $ map (tableRowToDocbook opts) rows
in inTagsIndented tableType $ captionDoc $$
(inTags True "tgroup" [("cols", show (length headers))] $
coltags $$ head' $$ body')
hasLineBreaks :: [Inline] -> Bool
hasLineBreaks = getAny . query isLineBreak . walk removeNote
where
removeNote :: Inline -> Inline
removeNote (Note _) = Str ""
removeNote x = x
isLineBreak :: Inline -> Any
isLineBreak LineBreak = Any True
isLineBreak _ = Any False
alignmentToString :: Alignment -> [Char]
alignmentToString alignment = case alignment of
AlignLeft -> "left"
AlignRight -> "right"
AlignCenter -> "center"
AlignDefault -> "left"
tableRowToDocbook :: WriterOptions
-> [[Block]]
-> Doc
tableRowToDocbook opts cols =
inTagsIndented "row" $ vcat $ map (tableItemToDocbook opts) cols
tableItemToDocbook :: WriterOptions
-> [Block]
-> Doc
tableItemToDocbook opts item =
inTags True "entry" [] $ vcat $ map (blockToDocbook opts) item
-- | Convert a list of inline elements to Docbook.
inlinesToDocbook :: WriterOptions -> [Inline] -> Doc
inlinesToDocbook opts lst = hcat $ map (inlineToDocbook opts) lst
-- | Convert an inline element to Docbook.
inlineToDocbook :: WriterOptions -> Inline -> Doc
inlineToDocbook _ (Str str) = text $ escapeStringForXML str
inlineToDocbook opts (Emph lst) =
inTagsSimple "emphasis" $ inlinesToDocbook opts lst
inlineToDocbook opts (Strong lst) =
inTags False "emphasis" [("role", "strong")] $ inlinesToDocbook opts lst
inlineToDocbook opts (Strikeout lst) =
inTags False "emphasis" [("role", "strikethrough")] $
inlinesToDocbook opts lst
inlineToDocbook opts (Superscript lst) =
inTagsSimple "superscript" $ inlinesToDocbook opts lst
inlineToDocbook opts (Subscript lst) =
inTagsSimple "subscript" $ inlinesToDocbook opts lst
inlineToDocbook opts (SmallCaps lst) =
inTags False "emphasis" [("role", "smallcaps")] $
inlinesToDocbook opts lst
inlineToDocbook opts (Quoted _ lst) =
inTagsSimple "quote" $ inlinesToDocbook opts lst
inlineToDocbook opts (Cite _ lst) =
inlinesToDocbook opts lst
inlineToDocbook opts (Span (ident,_,_) ils) =
(if null ident
then mempty
else selfClosingTag "anchor" [("id", ident)]) <>
inlinesToDocbook opts ils
inlineToDocbook _ (Code _ str) =
inTagsSimple "literal" $ text (escapeStringForXML str)
inlineToDocbook opts (Math t str)
| isMathML (writerHTMLMathMethod opts) =
case writeMathML dt <$> readTeX str of
Right r -> inTagsSimple tagtype
$ text $ Xml.ppcElement conf
$ fixNS
$ removeAttr r
Left _ -> inlinesToDocbook opts
$ texMathToInlines t str
| otherwise = inlinesToDocbook opts $ texMathToInlines t str
where (dt, tagtype) = case t of
InlineMath -> (DisplayInline,"inlineequation")
DisplayMath -> (DisplayBlock,"informalequation")
conf = Xml.useShortEmptyTags (const False) Xml.defaultConfigPP
removeAttr e = e{ Xml.elAttribs = [] }
fixNS' qname = qname{ Xml.qPrefix = Just "mml" }
fixNS = everywhere (mkT fixNS')
inlineToDocbook _ (RawInline f x) | f == "html" || f == "docbook" = text x
| otherwise = empty
inlineToDocbook _ LineBreak = text "\n"
inlineToDocbook _ Space = space
-- because we use \n for LineBreak, we can't do soft breaks:
inlineToDocbook _ SoftBreak = space
inlineToDocbook opts (Link attr txt (src, _))
| Just email <- stripPrefix "mailto:" src =
let emailLink = inTagsSimple "email" $ text $
escapeStringForXML $ email
in case txt of
[Str s] | escapeURI s == email -> emailLink
_ -> inlinesToDocbook opts txt <+>
char '(' <> emailLink <> char ')'
| otherwise =
(if isPrefixOf "#" src
then inTags False "link" $ ("linkend", drop 1 src) : idAndRole attr
else if writerDocbook5 opts
then inTags False "link" $ ("xlink:href", src) : idAndRole attr
else inTags False "ulink" $ ("url", src) : idAndRole attr ) $
inlinesToDocbook opts txt
inlineToDocbook opts (Image attr _ (src, tit)) =
let titleDoc = if null tit
then empty
else inTagsIndented "objectinfo" $
inTagsIndented "title" (text $ escapeStringForXML tit)
in inTagsIndented "inlinemediaobject" $ inTagsIndented "imageobject" $
titleDoc $$ imageToDocbook opts attr src
inlineToDocbook opts (Note contents) =
inTagsIndented "footnote" $ blocksToDocbook opts contents
isMathML :: HTMLMathMethod -> Bool
isMathML (MathML _) = True
isMathML _ = False
idAndRole :: Attr -> [(String, String)]
idAndRole (id',cls,_) = ident ++ role
where
ident = if null id'
then []
else [("id", id')]
role = if null cls
then []
else [("role", unwords cls)]
|