aboutsummaryrefslogtreecommitdiff
path: root/src/Text/Pandoc/Writers/EPUB.hs
blob: cf5cad253ac250fab850719185165cb9ead93e56 (plain)
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
{-
Copyright (C) 2010 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.EPUB
   Copyright   : Copyright (C) 2010 John MacFarlane
   License     : GNU GPL, version 2 or above

   Maintainer  : John MacFarlane <jgm@berkeley.edu>
   Stability   : alpha
   Portability : portable

Conversion of 'Pandoc' documents to EPUB.
-}
module Text.Pandoc.Writers.EPUB ( writeEPUB ) where
import Data.IORef
import Data.Maybe ( fromMaybe, isNothing )
import Data.List ( findIndices, isPrefixOf )
import System.Environment ( getEnv )
import System.FilePath ( (</>), takeBaseName, takeExtension )
import qualified Data.ByteString.Lazy as B
import Data.ByteString.Lazy.UTF8 ( fromString )
import Codec.Archive.Zip
import System.Time
import Text.Pandoc.Shared hiding ( Element )
import Text.Pandoc.Definition
import Text.Pandoc.Generic
import Control.Monad (liftM)
import Text.XML.Light hiding (ppTopElement)
import Text.Pandoc.UUID
import Text.Pandoc.Writers.HTML
import Text.Pandoc.Writers.Markdown ( writePlain )
import Data.Char ( toLower )
import Network.URI ( unEscapeString )

-- | Produce an EPUB file from a Pandoc document.
writeEPUB :: Maybe String   -- ^ EPUB stylesheet specified at command line
          -> WriterOptions  -- ^ Writer options
          -> Pandoc         -- ^ Document to convert
          -> IO B.ByteString
writeEPUB mbStylesheet opts doc@(Pandoc meta _) = do
  (TOD epochtime _) <- getClockTime
  let mkEntry path content = toEntry path epochtime content
  let opts' = opts{ writerEmailObfuscation = NoObfuscation
                  , writerStandalone = True
                  , writerWrapText = False }
  let sourceDir = writerSourceDirectory opts'
  let vars = writerVariables opts'
  let mbCoverImage = lookup "epub-cover-image" vars

  -- cover page
  (cpgEntry, cpicEntry) <-
                case mbCoverImage of
                     Nothing   -> return ([],[])
                     Just img  -> do
                       let coverImage = "cover-image" ++ takeExtension img
                       let cpContent = fromString $ writeHtmlString
                             opts'{writerTemplate = pageTemplate
                                  ,writerVariables =
                                    ("coverimage",coverImage):vars}
                               (Pandoc meta [])
                       imgContent <- B.readFile img
                       return ( [mkEntry "cover.xhtml" cpContent]
                              , [mkEntry coverImage imgContent] )

  -- title page
  let tpContent = fromString $ writeHtmlString
                     opts'{writerTemplate = pageTemplate
                          ,writerVariables = ("titlepage","yes"):vars}
                     (Pandoc meta [])
  let tpEntry = mkEntry "title_page.xhtml" tpContent

  -- handle pictures
  picsRef <- newIORef []
  Pandoc _ blocks <- liftM (bottomUp transformBlock) $ bottomUpM
       (transformInlines (writerHTMLMathMethod opts) sourceDir picsRef) doc
  pics <- readIORef picsRef
  let readPicEntry (oldsrc, newsrc) = readEntry [] oldsrc >>= \e ->
                                          return e{ eRelativePath = newsrc }
  picEntries <- mapM readPicEntry pics

  -- body pages
  let isH1 (Header 1 _) = True
      isH1 _            = False
  let h1Indices = dropWhile (== 0) $ findIndices isH1 blocks
  let chunks = splitByIndices h1Indices blocks
  let titleize (Header 1 xs : ys) = Pandoc meta{docTitle = xs} ys
      titleize xs                 = Pandoc meta xs
  let chapToHtml = writeHtmlString opts'{ writerTemplate = pageTemplate }
  let chapters = map titleize chunks
  let chapterToEntry :: Int -> Pandoc -> Entry
      chapterToEntry num chap = mkEntry ("ch" ++ show num ++ ".xhtml") $
                                   fromString $ chapToHtml chap
  let chapterEntries = zipWith chapterToEntry [1..] chapters

  -- contents.opf
  lang <- catch (liftM (takeWhile (/='.')) $ getEnv "lang")
                (\_ -> return "en-US")
  uuid <- getRandomUUID
  let chapterNode ent = unode "item" !
                           [("id", takeBaseName $ eRelativePath ent),
                            ("href", eRelativePath ent),
                            ("media-type", "application/xhtml+xml")] $ ()
  let chapterRefNode ent = unode "itemref" !
                             [("idref", takeBaseName $ eRelativePath ent)] $ ()
  let pictureNode ent = unode "item" !
                           [("id", takeBaseName $ eRelativePath ent),
                            ("href", eRelativePath ent),
                            ("media-type", fromMaybe "application/octet-stream"
                               $ imageTypeOf $ eRelativePath ent)] $ ()
  let plainify t = removeTrailingSpace $
                    writePlain opts'{ writerStandalone = False } $
                    Pandoc meta [Plain t]
  let plainTitle = plainify $ docTitle meta
  let plainAuthors = map plainify $ docAuthors meta
  let plainDate = plainify $ docDate meta
  let contentsData = fromString $ ppTopElement $
        unode "package" ! [("version","2.0")
                          ,("xmlns","http://www.idpf.org/2007/opf")
                          ,("unique-identifier","BookId")] $
          [ metadataElement (writerEPUBMetadata opts')
              uuid lang plainTitle plainAuthors plainDate mbCoverImage
          , unode "manifest" $
             [ unode "item" ! [("id","ncx"), ("href","toc.ncx")
                              ,("media-type","application/x-dtbncx+xml")] $ ()
             , unode "item" ! [("id","style"), ("href","stylesheet.css")
                              ,("media-type","text/css")] $ ()
             ] ++
             map chapterNode (cpgEntry ++ (tpEntry : chapterEntries)) ++
             map pictureNode (cpicEntry ++ picEntries)
          , unode "spine" ! [("toc","ncx")] $
              case mbCoverImage of
                    Nothing -> []
                    Just _ -> [ unode "itemref" !
                                [("idref", "cover"),("linear","no")] $ () ]
              ++ map chapterRefNode (tpEntry : chapterEntries)
          ]
  let contentsEntry = mkEntry "content.opf" contentsData

  -- toc.ncx
  let navPointNode ent n tit = unode "navPoint" !
                                [("id", "navPoint-" ++ show n)
                                ,("playOrder", show n)] $
                                   [ unode "navLabel" $ unode "text" tit
                                   , unode "content" ! [("src",
                                        eRelativePath ent)] $ ()
                                   ]
  let tocData = fromString $ ppTopElement $
        unode "ncx" ! [("version","2005-1")
                       ,("xmlns","http://www.daisy.org/z3986/2005/ncx/")] $
          [ unode "head" $
             [ unode "meta" ! [("name","dtb:uid")
                              ,("content", show uuid)] $ ()
             , unode "meta" ! [("name","dtb:depth")
                              ,("content", "1")] $ ()
             , unode "meta" ! [("name","dtb:totalPageCount")
                              ,("content", "0")] $ ()
             , unode "meta" ! [("name","dtb:maxPageNumber")
                              ,("content", "0")] $ ()
             ] ++ case mbCoverImage of
                        Nothing  -> []
                        Just _   -> [unode "meta" ! [("name","cover"),
                                            ("content","cover-image")] $ ()]
          , unode "docTitle" $ unode "text" $ plainTitle
          , unode "navMap" $ zipWith3 navPointNode (tpEntry : chapterEntries)
                                [1..(length chapterEntries + 1)]
                                ("Title Page" : map (\(Pandoc m _) ->
                                   plainify $ docTitle m) chapters)
          ]
  let tocEntry = mkEntry "toc.ncx" tocData

  -- mimetype
  let mimetypeEntry = mkEntry "mimetype" $ fromString "application/epub+zip"

  -- container.xml
  let containerData = fromString $ ppTopElement $
       unode "container" ! [("version","1.0")
              ,("xmlns","urn:oasis:names:tc:opendocument:xmlns:container")] $
         unode "rootfiles" $
           unode "rootfile" ! [("full-path","content.opf")
               ,("media-type","application/oebps-package+xml")] $ ()
  let containerEntry = mkEntry "META-INF/container.xml" containerData

  -- stylesheet
  stylesheet <- case mbStylesheet of
                   Just s  -> return s
                   Nothing -> readDataFile (writerUserDataDir opts) "epub.css"
  let stylesheetEntry = mkEntry "stylesheet.css" $ fromString stylesheet

  -- construct archive
  let archive = foldr addEntryToArchive emptyArchive
                 (mimetypeEntry : containerEntry : stylesheetEntry : tpEntry :
                  contentsEntry : tocEntry :
                  (picEntries ++ cpicEntry ++ cpgEntry ++ chapterEntries) )
  return $ fromArchive archive

metadataElement :: String -> UUID -> String -> String -> [String] -> String -> Maybe a -> Element
metadataElement metadataXML uuid lang title authors date mbCoverImage =
  let userNodes = parseXML metadataXML
      elt = unode "metadata" ! [("xmlns:dc","http://purl.org/dc/elements/1.1/")
                               ,("xmlns:opf","http://www.idpf.org/2007/opf")] $
            filter isDublinCoreElement $ onlyElems userNodes
      dublinElements = ["contributor","coverage","creator","date",
            "description","format","identifier","language","publisher",
            "relation","rights","source","subject","title","type"]
      isDublinCoreElement e = qPrefix (elName e) == Just "dc" &&
                              qName (elName e) `elem` dublinElements
      contains e n = not (null (findElements (QName n Nothing (Just "dc")) e))
      newNodes = [ unode "dc:title" title | not (elt `contains` "title") ] ++
           [ unode "dc:language" lang | not (elt `contains` "language") ] ++
           [ unode "dc:identifier" ! [("id","BookId")] $ show uuid |
               not (elt `contains` "identifier") ] ++
           [ unode "dc:creator" ! [("opf:role","aut")] $ a | a <- authors ] ++
           [ unode "dc:date" date | not (elt `contains` "date") ] ++
           [ unode "meta" ! [("name","cover"), ("content","cover-image")] $ () |
               not (isNothing mbCoverImage) ]
  in  elt{ elContent = elContent elt ++ map Elem newNodes }

transformInlines :: HTMLMathMethod
                 -> FilePath
                 -> IORef [(FilePath, FilePath)] -- ^ (oldpath, newpath) images
                 -> [Inline]
                 -> IO [Inline]
transformInlines _ _ _ (Image lab (src,_) : xs) | isNothing (imageTypeOf src) =
  return $ Emph lab : xs
transformInlines _ sourceDir picsRef (Image lab (src,tit) : xs) = do
  let src' = unEscapeString src
  pics <- readIORef picsRef
  let oldsrc = sourceDir </> src'
  let ext = takeExtension src'
  newsrc <- case lookup oldsrc pics of
                  Just n  -> return n
                  Nothing -> do
                        let new = "images/img" ++ show (length pics) ++ ext
                        modifyIORef picsRef ( (oldsrc, new): )
                        return new
  return $ Image lab (newsrc, tit) : xs
transformInlines (MathML _) _ _ (x@(Math _ _) : xs) = do
  let writeHtmlInline opts z = removeTrailingSpace $
         writeHtmlString opts $ Pandoc (Meta [] [] []) [Plain [z]]
      mathml = writeHtmlInline defaultWriterOptions{
                 writerHTMLMathMethod = MathML Nothing } x
      fallback = writeHtmlInline defaultWriterOptions{
                 writerHTMLMathMethod = PlainMath } x
      inOps = "<ops:switch xmlns:ops=\"http://www.idpf.org/2007/ops\">" ++
       "<ops:case required-namespace=\"http://www.w3.org/1998/Math/MathML\">" ++
       mathml ++ "</ops:case><ops:default>" ++ fallback ++ "</ops:default>" ++
       "</ops:switch>"
      result = if "<math" `isPrefixOf` mathml then inOps else mathml
  return $ RawInline "html" result : xs
transformInlines _ _ _ (RawInline _ _ : xs) = return $ Str "" : xs
transformInlines _ _ _ (Link lab (_,_) : xs) = return $ lab ++ xs
transformInlines _ _ _ xs = return xs

transformBlock :: Block -> Block
transformBlock (RawBlock _ _) = Null
transformBlock x = x

(!) :: Node t => (t -> Element) -> [(String, String)] -> t -> Element
(!) f attrs n = add_attrs (map (\(k,v) -> Attr (unqual k) v) attrs) (f n)

-- | Version of 'ppTopElement' that specifies UTF-8 encoding.
ppTopElement :: Element -> String
ppTopElement = ("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" ++) . ppElement

imageTypeOf :: FilePath -> Maybe String
imageTypeOf x = case drop 1 (map toLower (takeExtension x)) of
                     "jpg"       -> Just "image/jpeg"
                     "jpeg"      -> Just "image/jpeg"
                     "jfif"      -> Just "image/jpeg"
                     "png"       -> Just "image/png"
                     "gif"       -> Just "image/gif"
                     "svg"       -> Just "image/svg+xml"
                     _           -> Nothing

pageTemplate :: String
pageTemplate = unlines
 [ "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"
 , "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\" \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">"
 , "<html xmlns=\"http://www.w3.org/1999/xhtml\">"
 , "<head>"
 , "<title>$title$</title>"
 , "$if(coverimage)$"
 , "<style type=\"text/css\">img{ max-width: 100%; }</style>"
 , "$endif$"
 , "<link href=\"stylesheet.css\" type=\"text/css\" rel=\"stylesheet\" />"
 , "</head>"
 , "<body>"
 , "$if(coverimage)$"
 , "<div id=\"cover-image\">"
 , "<img src=\"$coverimage$\" alt=\"$title$\" />"
 , "</div>"
 , "$else$"
 , "$if(titlepage)$"
 , "<h1 class=\"title\">$title$</h1>"
 , "$for(author)$"
 , "<h2 class=\"author\">$author$</h2>"
 , "$endfor$"
 , "$if(date)$"
 , "<h3 class=\"date\">$date$</h3>"
 , "$endif$"
 , "$else$"
 , "<h1>$title$</h1>"
 , "$if(toc)$"
 , "<div id=\"$idprefix$TOC\">"
 , "$toc$"
 , "</div>"
 , "$endif$"
 , "$endif$"
 , "$body$"
 , "$endif$"
 , "</body>"
 , "</html>"
 ]