8ca1916 · typeable/pandoc

MANUAL.txt+1

compare with master

unifiedsplit

@@ -1464,6 +1464,7 @@ Nonzero exit codes have the following meanings:

1464 24 PandocCiteprocError

1465 31 PandocEpubSubdirectoryError

1466 43 PandocPDFError

1467+ 44 PandocXMLError

1467 47 PandocPDFProgramNotFoundError

1468 47 PandocPDFProgramNotFoundError

1468 61 PandocHttpError

1469 61 PandocHttpError

1469 62 PandocShouldNeverHappenError

1470 62 PandocShouldNeverHappenError

pandoc.cabal+2

@@ -493,6 +493,7 @@ library

493 unicode-transforms >= 0.3 && < 0.4,

494 unordered-containers >= 0.2 && < 0.3,

495 xml >= 1.3.12 && < 1.4,

496+ xml-conduit >= 1.7 && < 1.10,

496 zip-archive >= 0.2.3.4 && < 0.5,

497 zip-archive >= 0.2.3.4 && < 0.5,

497 zlib >= 0.5 && < 0.7

498 zlib >= 0.5 && < 0.7

498 if os(windows) && arch(i386)

499 if os(windows) && arch(i386)

@@ -686,6 +687,7 @@ library

686 Text.Pandoc.Lua.PandocLua,

687 Text.Pandoc.Lua.PandocLua,

687 Text.Pandoc.Lua.Util,

688 Text.Pandoc.Lua.Util,

688 Text.Pandoc.Lua.Walk,

689 Text.Pandoc.Lua.Walk,

690+ Text.Pandoc.XMLParser,

689 Text.Pandoc.CSS,

691 Text.Pandoc.CSS,

690 Text.Pandoc.CSV,

692 Text.Pandoc.CSV,

691 Text.Pandoc.RoffChar,

693 Text.Pandoc.RoffChar,

src/Text/Pandoc/Error.hs+3

@@ -48,6 +48,7 @@ data PandocError = PandocIOError Text IOError

48 | PandocFailOnWarningError

49 | PandocPDFProgramNotFoundError Text

50 | PandocPDFError Text

51+ | PandocXMLError Text Text

51 | PandocFilterError Text Text

52 | PandocFilterError Text Text

52 | PandocLuaError Text

53 | PandocLuaError Text

53 | PandocCouldNotFindDataFileError Text

54 | PandocCouldNotFindDataFileError Text

@@ -103,6 +104,8 @@ handleError (Left e) =

103 PandocPDFProgramNotFoundError pdfprog -> err 47 $

104 PandocPDFProgramNotFoundError pdfprog -> err 47 $

104 pdfprog <> " not found. Please select a different --pdf-engine or install " <> pdfprog

105 pdfprog <> " not found. Please select a different --pdf-engine or install " <> pdfprog

105 PandocPDFError logmsg -> err 43 $ "Error producing PDF.\n" <> logmsg

106 PandocPDFError logmsg -> err 43 $ "Error producing PDF.\n" <> logmsg

107+ PandocXMLError fp logmsg -> err 44 $ "Invalid XML" <>

108+ (if T.null fp then "" else " in " <> fp) <> ":\n" <> logmsg

106 PandocFilterError filtername msg -> err 83 $ "Error running filter " <>

109 PandocFilterError filtername msg -> err 83 $ "Error running filter " <>

107 filtername <> ":\n" <> msg

110 filtername <> ":\n" <> msg

108 PandocLuaError msg -> err 84 $ "Error running Lua:\n" <> msg

111 PandocLuaError msg -> err 84 $ "Error running Lua:\n" <> msg

src/Text/Pandoc/ImageSize.hs+4−1

@@ -45,7 +45,9 @@ import Text.Pandoc.Definition

45import Text.Pandoc.Options

46import qualified Text.Pandoc.UTF8 as UTF8

47import qualified Text.XML.Light as Xml

48+import Text.Pandoc.XMLParser (parseXMLElement)

48import qualified Data.Text as T

49import qualified Data.Text as T

50+import qualified Data.Text.Lazy as TL

49import qualified Data.Text.Encoding as TE

51import qualified Data.Text.Encoding as TE

50import Control.Applicative

52import Control.Applicative

51import qualified Data.Attoparsec.ByteString.Char8 as A

53import qualified Data.Attoparsec.ByteString.Char8 as A

@@ -327,7 +329,8 @@ getSize img =

327

329

328svgSize :: WriterOptions -> ByteString -> Maybe ImageSize

330svgSize :: WriterOptions -> ByteString -> Maybe ImageSize

329svgSize opts img = do

331svgSize opts img = do

330− doc <- Xml.parseXMLDoc $ UTF8.toString img

332+ doc <- either (const mzero) return $ parseXMLElement

333+ $ TL.fromStrict $ UTF8.toText img

331 let viewboxSize = do

334 let viewboxSize = do

332 vb <- Xml.findAttrBy (== Xml.QName "viewBox" Nothing Nothing) doc

335 vb <- Xml.findAttrBy (== Xml.QName "viewBox" Nothing Nothing) doc

333 [_,_,w,h] <- mapM safeRead (T.words (T.pack vb))

336 [_,_,w,h] <- mapM safeRead (T.words (T.pack vb))

src/Text/Pandoc/Readers/DocBook.hs+33−19

@@ -12,7 +12,7 @@ Conversion of DocBook XML to 'Pandoc' document.

12-}

13module Text.Pandoc.Readers.DocBook ( readDocBook ) where

14import Control.Monad.State.Strict

15−import Data.Char (isSpace, toUpper)

15+import Data.Char (isSpace, toUpper, isLetter)

16import Data.Default

17import Data.Either (rights)

18import Data.Foldable (asum)

@@ -21,7 +21,10 @@ import Data.List (intersperse,elemIndex)

21import Data.Maybe (fromMaybe,mapMaybe)

22import Data.Text (Text)

23import qualified Data.Text as T

24+import qualified Data.Text.Lazy as TL

25+import Control.Monad.Except (throwError)

24import Text.HTML.TagSoup.Entity (lookupEntity)

26import Text.HTML.TagSoup.Entity (lookupEntity)

27+import Text.Pandoc.Error (PandocError(..))

25import Text.Pandoc.Builder

28import Text.Pandoc.Builder

26import Text.Pandoc.Class.PandocMonad (PandocMonad, report)

29import Text.Pandoc.Class.PandocMonad (PandocMonad, report)

27import Text.Pandoc.Options

30import Text.Pandoc.Options

@@ -29,6 +32,7 @@ import Text.Pandoc.Logging (LogMessage(..))

29import Text.Pandoc.Shared (crFilter, safeRead, extractSpaces)

32import Text.Pandoc.Shared (crFilter, safeRead, extractSpaces)

30import Text.TeXMath (readMathML, writeTeX)

33import Text.TeXMath (readMathML, writeTeX)

31import Text.XML.Light

34import Text.XML.Light

35+import Text.Pandoc.XMLParser (parseXMLContents)

32

36

33{-

37{-

34

38

@@ -537,22 +541,25 @@ instance Default DBState where

537

541

538readDocBook :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

542readDocBook :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

539readDocBook _ inp = do

543readDocBook _ inp = do

544+ tree <- either (throwError . PandocXMLError "") (return . normalizeTree) $

540− let tree = normalizeTree . parseXML . handleInstructions $ crFilter inp

545+ parseXMLContents (TL.fromStrict . handleInstructions $ crFilter inp)

541 (bs, st') <- flip runStateT (def{ dbContent = tree }) $ mapM parseBlock tree

546 (bs, st') <- flip runStateT (def{ dbContent = tree }) $ mapM parseBlock tree

542 return $ Pandoc (dbMeta st') (toList . mconcat $ bs)

547 return $ Pandoc (dbMeta st') (toList . mconcat $ bs)

543

548

544−-- We treat <?asciidoc-br?> specially (issue #1236), converting it

549+-- We treat certain processing instructions by converting them to tags

545−-- to <br/>, since xml-light doesn't parse the instruction correctly.

550+-- beginning "pi-".

546−-- Other xml instructions are simply removed from the input stream.

547handleInstructions :: Text -> Text

551handleInstructions :: Text -> Text

548−handleInstructions = T.pack . handleInstructions' . T.unpack

552+handleInstructions t =

549−

553+ let (x,y) = T.breakOn "<?" t

550−handleInstructions' :: String -> String

554+ in if T.null y

551−handleInstructions' ('<':'?':'a':'s':'c':'i':'i':'d':'o':'c':'-':'b':'r':'?':'>':xs) = '<':'b':'r':'/':'>': handleInstructions' xs

555+ then x

552−handleInstructions' xs = case break (=='<') xs of

556+ else

553− (ys, []) -> ys

557+ let (w,z) = T.breakOn "?>" y

554− ([], '<':zs) -> '<' : handleInstructions' zs

558+ in (if T.takeWhile (\c -> isLetter c || c == '-')

559+ (T.drop 2 w) `elem` ["asciidoc-br", "dbfo"]

560+ then x <> "<pi-" <> T.drop 2 w <> "/>"

561+ else x <> w <> T.take 2 z) <>

555− (ys, zs) -> ys ++ handleInstructions' zs

562+ handleInstructions (T.drop 2 z)

556

563

557getFigure :: PandocMonad m => Element -> DB m Blocks

564getFigure :: PandocMonad m => Element -> DB m Blocks

558getFigure e = do

565getFigure e = do

@@ -892,7 +899,11 @@ parseBlock (Elem e) =

892 "subtitle" -> return mempty -- handled in parent element

899 "subtitle" -> return mempty -- handled in parent element

893 _ -> skip >> getBlocks e

900 _ -> skip >> getBlocks e

894 where skip = do

901 where skip = do

895− lift $ report $ IgnoredElement $ T.pack $ qName (elName e)

902+ let qn = T.pack $ qName $ elName e

903+ let name = if "pi-" `T.isPrefixOf` qn

904+ then "<?" <> qn <> "?>"

905+ else qn

906+ lift $ report $ IgnoredElement name

896 return mempty

907 return mempty

897

908

898 codeBlockWithLang = do

909 codeBlockWithLang = do

@@ -964,7 +975,7 @@ parseBlock (Elem e) =

964 cs -> map toAlignment cs

975 cs -> map toAlignment cs

965 let parseWidth s = safeRead (T.filter (\x -> (x >= '0' && x <= '9')

976 let parseWidth s = safeRead (T.filter (\x -> (x >= '0' && x <= '9')

966 || x == '.') s)

977 || x == '.') s)

967− let textWidth = case filterChild (named "?dbfo") e of

978+ let textWidth = case filterChild (named "pi-dbfo") e of

968 Just d -> case attrValue "table-width" d of

979 Just d -> case attrValue "table-width" d of

969 "" -> 1.0

980 "" -> 1.0

970 w -> fromMaybe 100.0 (parseWidth w) / 100.0

981 w -> fromMaybe 100.0 (parseWidth w) / 100.0

@@ -1165,12 +1176,15 @@ parseInline (Elem e) =

1165 "title" -> return mempty

1176 "title" -> return mempty

1166 "affiliation" -> skip

1177 "affiliation" -> skip

1167 -- Note: this isn't a real docbook tag; it's what we convert

1178 -- Note: this isn't a real docbook tag; it's what we convert

1168− -- <?asciidor-br?> to in handleInstructions, above. A kludge to

1179+ -- <?asciidor-br?> to in handleInstructions, above.

1169− -- work around xml-light's inability to parse an instruction.

1170− "br" -> return linebreak

1180+ "pi-asciidoc-br" -> return linebreak

1171 _ -> skip >> innerInlines id

1181 _ -> skip >> innerInlines id

1172 where skip = do

1182 where skip = do

1173− lift $ report $ IgnoredElement $ T.pack $ qName (elName e)

1183+ let qn = T.pack $ qName $ elName e

1184+ let name = if "pi-" `T.isPrefixOf` qn

1185+ then "<?" <> qn <> "?>"

1186+ else qn

1187+ lift $ report $ IgnoredElement name

1174 return mempty

1188 return mempty

1175

1189

1176 innerInlines f = extractSpaces f . mconcat <$>

1190 innerInlines f = extractSpaces f . mconcat <$>

src/Text/Pandoc/Readers/Docx/Parse.hs+14−7

@@ -74,6 +74,7 @@ import Text.TeXMath.Readers.OMML (readOMML)

74import Text.TeXMath.Unicode.Fonts (Font (..), getUnicode, textToFont)

75import Text.XML.Light

76import qualified Text.XML.Light.Cursor as XMLC

77+import Text.Pandoc.XMLParser (parseXMLElement)

77

78

78data ReaderEnv = ReaderEnv { envNotes :: Notes

79data ReaderEnv = ReaderEnv { envNotes :: Notes

79 , envComments :: Comments

80 , envComments :: Comments

@@ -343,10 +344,16 @@ archiveToDocxWithWarnings archive = do

343 Right doc -> Right (Docx doc, stateWarnings st)

344 Right doc -> Right (Docx doc, stateWarnings st)

344 Left e -> Left e

345 Left e -> Left e

345

346

347+parseXMLFromEntry :: Entry -> Maybe Element

348+parseXMLFromEntry entry =

349+ case parseXMLElement (UTF8.toTextLazy (fromEntry entry)) of

350+ Left _ -> Nothing

351+ Right el -> Just el

352+

346getDocumentXmlPath :: Archive -> Maybe FilePath

353getDocumentXmlPath :: Archive -> Maybe FilePath

347getDocumentXmlPath zf = do

354getDocumentXmlPath zf = do

348 entry <- findEntryByPath "_rels/.rels" zf

355 entry <- findEntryByPath "_rels/.rels" zf

349− relsElem <- (parseXMLDoc . UTF8.toStringLazy . fromEntry) entry

356+ relsElem <- parseXMLFromEntry entry

350 let rels = filterChildrenName (\n -> qName n == "Relationship") relsElem

357 let rels = filterChildrenName (\n -> qName n == "Relationship") relsElem

351 rel <- find (\e -> findAttr (QName "Type" Nothing Nothing) e ==

358 rel <- find (\e -> findAttr (QName "Type" Nothing Nothing) e ==

352 Just "http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument")

359 Just "http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument")

@@ -362,7 +369,7 @@ archiveToDocument :: Archive -> D Document

362archiveToDocument zf = do

369archiveToDocument zf = do

363 docPath <- asks envDocXmlPath

370 docPath <- asks envDocXmlPath

364 entry <- maybeToD $ findEntryByPath docPath zf

371 entry <- maybeToD $ findEntryByPath docPath zf

365− docElem <- maybeToD $ (parseXMLDoc . UTF8.toStringLazy . fromEntry) entry

372+ docElem <- maybeToD $ parseXMLFromEntry entry

366 let namespaces = elemToNameSpaces docElem

373 let namespaces = elemToNameSpaces docElem

367 bodyElem <- maybeToD $ findChildByName namespaces "w" "body" docElem

374 bodyElem <- maybeToD $ findChildByName namespaces "w" "body" docElem

368 let bodyElem' = fromMaybe bodyElem (walkDocument namespaces bodyElem)

375 let bodyElem' = fromMaybe bodyElem (walkDocument namespaces bodyElem)

@@ -401,9 +408,9 @@ constructBogusParStyleData stName = ParStyle

401archiveToNotes :: Archive -> Notes

408archiveToNotes :: Archive -> Notes

402archiveToNotes zf =

409archiveToNotes zf =

403 let fnElem = findEntryByPath "word/footnotes.xml" zf

410 let fnElem = findEntryByPath "word/footnotes.xml" zf

404− >>= (parseXMLDoc . UTF8.toStringLazy . fromEntry)

411+ >>= parseXMLFromEntry

405 enElem = findEntryByPath "word/endnotes.xml" zf

412 enElem = findEntryByPath "word/endnotes.xml" zf

406− >>= (parseXMLDoc . UTF8.toStringLazy . fromEntry)

413+ >>= parseXMLFromEntry

407 fn_namespaces = maybe [] elemToNameSpaces fnElem

414 fn_namespaces = maybe [] elemToNameSpaces fnElem

408 en_namespaces = maybe [] elemToNameSpaces enElem

415 en_namespaces = maybe [] elemToNameSpaces enElem

409 ns = unionBy (\x y -> fst x == fst y) fn_namespaces en_namespaces

416 ns = unionBy (\x y -> fst x == fst y) fn_namespaces en_namespaces

@@ -415,7 +422,7 @@ archiveToNotes zf =

415archiveToComments :: Archive -> Comments

422archiveToComments :: Archive -> Comments

416archiveToComments zf =

423archiveToComments zf =

417 let cmtsElem = findEntryByPath "word/comments.xml" zf

424 let cmtsElem = findEntryByPath "word/comments.xml" zf

418− >>= (parseXMLDoc . UTF8.toStringLazy . fromEntry)

425+ >>= parseXMLFromEntry

419 cmts_namespaces = maybe [] elemToNameSpaces cmtsElem

426 cmts_namespaces = maybe [] elemToNameSpaces cmtsElem

420 cmts = elemToComments cmts_namespaces <$> (cmtsElem >>= walkDocument cmts_namespaces)

427 cmts = elemToComments cmts_namespaces <$> (cmtsElem >>= walkDocument cmts_namespaces)

421 in

428 in

@@ -445,7 +452,7 @@ filePathToRelationships :: Archive -> FilePath -> FilePath -> [Relationship]

445filePathToRelationships ar docXmlPath fp

452filePathToRelationships ar docXmlPath fp

446 | Just relType <- filePathToRelType fp docXmlPath

453 | Just relType <- filePathToRelType fp docXmlPath

447 , Just entry <- findEntryByPath fp ar

454 , Just entry <- findEntryByPath fp ar

448− , Just relElems <- (parseXMLDoc . UTF8.toStringLazy . fromEntry) entry =

455+ , Just relElems <- parseXMLFromEntry entry =

449 mapMaybe (relElemToRelationship relType) $ elChildren relElems

456 mapMaybe (relElemToRelationship relType) $ elChildren relElems

450filePathToRelationships _ _ _ = []

457filePathToRelationships _ _ _ = []

451

458

@@ -527,7 +534,7 @@ archiveToNumbering' zf =

527 case findEntryByPath "word/numbering.xml" zf of

534 case findEntryByPath "word/numbering.xml" zf of

528 Nothing -> Just $ Numbering [] [] []

535 Nothing -> Just $ Numbering [] [] []

529 Just entry -> do

536 Just entry -> do

530− numberingElem <- (parseXMLDoc . UTF8.toStringLazy . fromEntry) entry

537+ numberingElem <- parseXMLFromEntry entry

531 let namespaces = elemToNameSpaces numberingElem

538 let namespaces = elemToNameSpaces numberingElem

532 numElems = findChildrenByName namespaces "w" "num" numberingElem

539 numElems = findChildrenByName namespaces "w" "num" numberingElem

533 absNumElems = findChildrenByName namespaces "w" "abstractNum" numberingElem

540 absNumElems = findChildrenByName namespaces "w" "abstractNum" numberingElem

src/Text/Pandoc/Readers/Docx/Parse/Styles.hs+16−12

@@ -53,6 +53,7 @@ import Data.Coerce

53import Text.Pandoc.Readers.Docx.Util

54import qualified Text.Pandoc.UTF8 as UTF8

55import Text.XML.Light

56+import Text.Pandoc.XMLParser (parseXMLElement)

56

57

57newtype CharStyleId = CharStyleId T.Text

58newtype CharStyleId = CharStyleId T.Text

58 deriving (Show, Eq, Ord, IsString, FromStyleId)

59 deriving (Show, Eq, Ord, IsString, FromStyleId)

@@ -135,19 +136,22 @@ defaultRunStyle = RunStyle { isBold = Nothing

135 , rParentStyle = Nothing

136 , rParentStyle = Nothing

136 }

137 }

137

138

139+archiveToStyles'

138−archiveToStyles' :: (Ord k1, Ord k2, ElemToStyle a1, ElemToStyle a2) =>

140+ :: (Ord k1, Ord k2, ElemToStyle a1, ElemToStyle a2)

139− (a1 -> k1) -> (a2 -> k2) -> Archive -> (M.Map k1 a1, M.Map k2 a2)

141+ => (a1 -> k1) -> (a2 -> k2) -> Archive -> (M.Map k1 a1, M.Map k2 a2)

140archiveToStyles' conv1 conv2 zf =

142archiveToStyles' conv1 conv2 zf =

141− let stylesElem = findEntryByPath "word/styles.xml" zf >>=

143+ case findEntryByPath "word/styles.xml" zf of

142− (parseXMLDoc . UTF8.toStringLazy . fromEntry)

144+ Nothing -> (M.empty, M.empty)

143− in

145+ Just entry ->

144− case stylesElem of

146+ case parseXMLElement . UTF8.toTextLazy . fromEntry $ entry of

145− Nothing -> (M.empty, M.empty)

147+ Left _ -> (M.empty, M.empty)

146− Just styElem ->

148+ Right styElem ->

147− let namespaces = elemToNameSpaces styElem

149+ let namespaces = elemToNameSpaces styElem

148− in

150+ in

151+ ( M.fromList $ map (\r -> (conv1 r, r)) $

149− ( M.fromList $ map (\r -> (conv1 r, r)) $ buildBasedOnList namespaces styElem Nothing,

152+ buildBasedOnList namespaces styElem Nothing,

153+ M.fromList $ map (\p -> (conv2 p, p)) $

150− M.fromList $ map (\p -> (conv2 p, p)) $ buildBasedOnList namespaces styElem Nothing)

154+ buildBasedOnList namespaces styElem Nothing)

151

155

152isBasedOnStyle :: (ElemToStyle a, FromStyleId (StyleId a)) => NameSpaces -> Element -> Maybe a -> Bool

156isBasedOnStyle :: (ElemToStyle a, FromStyleId (StyleId a)) => NameSpaces -> Element -> Maybe a -> Bool

153isBasedOnStyle ns element parentStyle

157isBasedOnStyle ns element parentStyle

src/Text/Pandoc/Readers/EPUB.hs+11−6

@@ -17,7 +17,7 @@ module Text.Pandoc.Readers.EPUB

17 (readEPUB)

18 where

19

20−import Codec.Archive.Zip (Archive (..), Entry, findEntryByPath, fromEntry,

20+import Codec.Archive.Zip (Archive (..), Entry(..), findEntryByPath, fromEntry,

21 toArchiveOrFail)

22import Control.DeepSeq (NFData, deepseq)

23import Control.Monad (guard, liftM, liftM2, mplus)

@@ -41,9 +41,10 @@ import Text.Pandoc.MIME (MimeType)

41import Text.Pandoc.Options (ReaderOptions (..))

42import Text.Pandoc.Readers.HTML (readHtml)

43import Text.Pandoc.Shared (addMetaField, collapseFilePath, escapeURI)

44−import qualified Text.Pandoc.UTF8 as UTF8 (toStringLazy)

44+import qualified Text.Pandoc.UTF8 as UTF8 (toTextLazy)

45import Text.Pandoc.Walk (query, walk)

46import Text.XML.Light

47+import Text.Pandoc.XMLParser (parseXMLElement)

47

48

48type Items = M.Map String (FilePath, MimeType)

49type Items = M.Map String (FilePath, MimeType)

49

50

@@ -181,7 +182,7 @@ renameMeta s = T.pack s

181getManifest :: PandocMonad m => Archive -> m (String, Element)

182getManifest :: PandocMonad m => Archive -> m (String, Element)

182getManifest archive = do

183getManifest archive = do

183 metaEntry <- findEntryByPathE ("META-INF" </> "container.xml") archive

184 metaEntry <- findEntryByPathE ("META-INF" </> "container.xml") archive

184− docElem <- (parseXMLDocE . UTF8.toStringLazy . fromEntry) metaEntry

185+ docElem <- parseXMLDocE metaEntry

185 let namespaces = mapMaybe attrToNSPair (elAttribs docElem)

186 let namespaces = mapMaybe attrToNSPair (elAttribs docElem)

186 ns <- mkE "xmlns not in namespaces" (lookup "xmlns" namespaces)

187 ns <- mkE "xmlns not in namespaces" (lookup "xmlns" namespaces)

187 as <- fmap (map attrToPair . elAttribs)

188 as <- fmap (map attrToPair . elAttribs)

@@ -190,7 +191,7 @@ getManifest archive = do

190 let rootdir = dropFileName manifestFile

191 let rootdir = dropFileName manifestFile

191 --mime <- lookup "media-type" as

192 --mime <- lookup "media-type" as

192 manifest <- findEntryByPathE manifestFile archive

193 manifest <- findEntryByPathE manifestFile archive

193− (rootdir,) <$> (parseXMLDocE . UTF8.toStringLazy . fromEntry $ manifest)

194+ (rootdir,) <$> parseXMLDocE manifest

194

195

195-- Fixup

196-- Fixup

196

197

@@ -284,8 +285,12 @@ findEntryByPathE :: PandocMonad m => FilePath -> Archive -> m Entry

284findEntryByPathE (normalise . unEscapeString -> path) a =

285findEntryByPathE (normalise . unEscapeString -> path) a =

285 mkE ("No entry on path: " ++ path) $ findEntryByPath path a

286 mkE ("No entry on path: " ++ path) $ findEntryByPath path a

286

287

287−parseXMLDocE :: PandocMonad m => String -> m Element

288+parseXMLDocE :: PandocMonad m => Entry -> m Element

288−parseXMLDocE doc = mkE "Unable to parse XML doc" $ parseXMLDoc doc

289+parseXMLDocE entry =

290+ either (throwError . PandocXMLError fp) return $ parseXMLElement doc

291+ where

292+ doc = UTF8.toTextLazy . fromEntry $ entry

293+ fp = T.pack $ eRelativePath entry

289

294

290findElementE :: PandocMonad m => QName -> Element -> m Element

295findElementE :: PandocMonad m => QName -> Element -> m Element

291findElementE e x = mkE ("Unable to find element: " ++ show e) $ findElement e x

296findElementE e x = mkE ("Unable to find element: " ++ show e) $ findElement e x

src/Text/Pandoc/Readers/FB2.hs+6−4

@@ -32,6 +32,7 @@ import Data.List (intersperse)

32import qualified Data.Map as M

33import Data.Text (Text)

34import qualified Data.Text as T

35+import qualified Data.Text.Lazy as TL

35import Data.Default

36import Data.Default

36import Data.Maybe

37import Data.Maybe

37import Text.HTML.TagSoup.Entity (lookupEntity)

38import Text.HTML.TagSoup.Entity (lookupEntity)

@@ -42,6 +43,7 @@ import Text.Pandoc.Logging

42import Text.Pandoc.Options

43import Text.Pandoc.Options

43import Text.Pandoc.Shared (crFilter)

44import Text.Pandoc.Shared (crFilter)

44import Text.XML.Light

45import Text.XML.Light

46+import Text.Pandoc.XMLParser (parseXMLElement)

45

47

46type FB2 m = StateT FB2State m

48type FB2 m = StateT FB2State m

47

49

@@ -64,10 +66,10 @@ instance HasMeta FB2State where

64

66

65readFB2 :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

67readFB2 :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

66readFB2 _ inp =

68readFB2 _ inp =

67− case parseXMLDoc $ crFilter inp of

69+ case parseXMLElement $ TL.fromStrict $ crFilter inp of

68− Nothing -> throwError $ PandocParseError "Not an XML document"

70+ Left msg -> throwError $ PandocXMLError "" msg

69− Just e -> do

71+ Right el -> do

70− (bs, st) <- runStateT (parseRootElement e) def

72+ (bs, st) <- runStateT (parseRootElement el) def

71 let authors = if null $ fb2Authors st

73 let authors = if null $ fb2Authors st

72 then id

74 then id

73 else setMeta "author" (map text $ reverse $ fb2Authors st)

75 else setMeta "author" (map text $ reverse $ fb2Authors st)

src/Text/Pandoc/Readers/JATS.hs+7−2

@@ -14,6 +14,8 @@ Conversion of JATS XML to 'Pandoc' document.

14

15module Text.Pandoc.Readers.JATS ( readJATS ) where

16import Control.Monad.State.Strict

17+import Control.Monad.Except (throwError)

18+import Text.Pandoc.Error (PandocError(..))

17import Data.Char (isDigit, isSpace, toUpper)

19import Data.Char (isDigit, isSpace, toUpper)

18import Data.Default

20import Data.Default

19import Data.Generics

21import Data.Generics

@@ -22,6 +24,7 @@ import qualified Data.Map as Map

22import Data.Maybe (maybeToList, fromMaybe)

24import Data.Maybe (maybeToList, fromMaybe)

23import Data.Text (Text)

25import Data.Text (Text)

24import qualified Data.Text as T

26import qualified Data.Text as T

27+import qualified Data.Text.Lazy as TL

25import Text.HTML.TagSoup.Entity (lookupEntity)

28import Text.HTML.TagSoup.Entity (lookupEntity)

26import Text.Pandoc.Builder

29import Text.Pandoc.Builder

27import Text.Pandoc.Class.PandocMonad (PandocMonad)

30import Text.Pandoc.Class.PandocMonad (PandocMonad)

@@ -29,6 +32,7 @@ import Text.Pandoc.Options

29import Text.Pandoc.Shared (crFilter, safeRead, extractSpaces)

32import Text.Pandoc.Shared (crFilter, safeRead, extractSpaces)

30import Text.TeXMath (readMathML, writeTeX)

33import Text.TeXMath (readMathML, writeTeX)

31import Text.XML.Light

34import Text.XML.Light

35+import Text.Pandoc.XMLParser (parseXMLContents)

32import qualified Data.Set as S (fromList, member)

36import qualified Data.Set as S (fromList, member)

33import Data.Set ((\\))

37import Data.Set ((\\))

34

38

@@ -51,8 +55,9 @@ instance Default JATSState where

51

55

52readJATS :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

56readJATS :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

53readJATS _ inp = do

57readJATS _ inp = do

58+ tree <- either (throwError . PandocXMLError "")

54− let tree = normalizeTree . parseXML

59+ (return . normalizeTree) $

55− $ T.unpack $ crFilter inp

60+ parseXMLContents (TL.fromStrict $ crFilter inp)

56 (bs, st') <- flip runStateT (def{ jatsContent = tree }) $ mapM parseBlock tree

61 (bs, st') <- flip runStateT (def{ jatsContent = tree }) $ mapM parseBlock tree

57 return $ Pandoc (jatsMeta st') (toList . mconcat $ bs)

62 return $ Pandoc (jatsMeta st') (toList . mconcat $ bs)

58

63

src/Text/Pandoc/Readers/OPML.hs+8−2

@@ -19,14 +19,18 @@ import Data.Generics

19import Data.Maybe (fromMaybe)

20import Data.Text (Text)

21import qualified Data.Text as T

22+import qualified Data.Text.Lazy as TL

22import Text.HTML.TagSoup.Entity (lookupEntity)

23import Text.HTML.TagSoup.Entity (lookupEntity)

23import Text.Pandoc.Builder

24import Text.Pandoc.Builder

24import Text.Pandoc.Class.PandocMonad (PandocMonad)

25import Text.Pandoc.Class.PandocMonad (PandocMonad)

25import Text.Pandoc.Options

26import Text.Pandoc.Options

27+import Text.Pandoc.Error (PandocError(..))

26import Text.Pandoc.Readers.HTML (readHtml)

28import Text.Pandoc.Readers.HTML (readHtml)

27import Text.Pandoc.Readers.Markdown (readMarkdown)

29import Text.Pandoc.Readers.Markdown (readMarkdown)

28import Text.Pandoc.Shared (crFilter, blocksToInlines')

30import Text.Pandoc.Shared (crFilter, blocksToInlines')

29import Text.XML.Light

31import Text.XML.Light

32+import Text.Pandoc.XMLParser (parseXMLContents)

33+import Control.Monad.Except (throwError)

30

34

31type OPML m = StateT OPMLState m

35type OPML m = StateT OPMLState m

32

36

@@ -49,8 +53,10 @@ instance Default OPMLState where

49readOPML :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

53readOPML :: PandocMonad m => ReaderOptions -> Text -> m Pandoc

50readOPML opts inp = do

54readOPML opts inp = do

51 (bs, st') <- runStateT

55 (bs, st') <- runStateT

52− (mapM parseBlock $ normalizeTree $

56+ (case parseXMLContents (TL.fromStrict (crFilter inp)) of

57+ Left msg -> throwError $ PandocXMLError "" msg

58+ Right ns -> mapM parseBlock $ normalizeTree ns)

53− parseXML (T.unpack (crFilter inp))) def{ opmlOptions = opts }

59+ def{ opmlOptions = opts }

54 return $

60 return $

55 setTitle (opmlDocTitle st') $

61 setTitle (opmlDocTitle st') $

56 setAuthors (opmlDocAuthors st') $

62 setAuthors (opmlDocAuthors st') $

src/Text/Pandoc/Readers/Odt.hs+14−10

@@ -15,6 +15,7 @@ module Text.Pandoc.Readers.Odt ( readOdt ) where

15

16import Codec.Archive.Zip

17import qualified Text.XML.Light as XML

18+import Text.Pandoc.XMLParser (parseXMLElement)

18

19

19import qualified Data.ByteString.Lazy as B

20import qualified Data.ByteString.Lazy as B

20

21

@@ -66,18 +67,18 @@ bytesToOdt bytes = case toArchiveOrFail bytes of

66

67

67--

68--

68archiveToOdt :: Archive -> Either PandocError (Pandoc, MediaBag)

69archiveToOdt :: Archive -> Either PandocError (Pandoc, MediaBag)

69−archiveToOdt archive = either (Left. PandocParseError) Right $ do

70+archiveToOdt archive = do

70− let onFailure msg Nothing = Left msg

71+ let onFailure msg Nothing = Left $ PandocParseError msg

71 onFailure _ (Just x) = Right x

72 onFailure _ (Just x) = Right x

72 contentEntry <- onFailure "Could not find content.xml"

73 contentEntry <- onFailure "Could not find content.xml"

73 (findEntryByPath "content.xml" archive)

74 (findEntryByPath "content.xml" archive)

74 stylesEntry <- onFailure "Could not find styles.xml"

75 stylesEntry <- onFailure "Could not find styles.xml"

75 (findEntryByPath "styles.xml" archive)

76 (findEntryByPath "styles.xml" archive)

76− contentElem <- onFailure "Could not find content element"

77− (entryToXmlElem contentEntry)

77+ contentElem <- entryToXmlElem contentEntry

78− stylesElem <- onFailure "Could not find styles element"

79− (entryToXmlElem stylesEntry)

78+ stylesElem <- entryToXmlElem stylesEntry

79+ styles <- either

80− styles <- either (\_ -> Left "Could not read styles") Right

80+ (\_ -> Left $ PandocParseError "Could not read styles")

81+ Right

81 (chooseMax (readStylesAt stylesElem ) (readStylesAt contentElem))

82 (chooseMax (readStylesAt stylesElem ) (readStylesAt contentElem))

82 let filePathIsOdtMedia :: FilePath -> Bool

83 let filePathIsOdtMedia :: FilePath -> Bool

83 filePathIsOdtMedia fp =

84 filePathIsOdtMedia fp =

@@ -85,10 +86,13 @@ archiveToOdt archive = either (Left. PandocParseError) Right $ do

85 in (dir == "Pictures/") || (dir /= "./" && name == "content.xml")

86 in (dir == "Pictures/") || (dir /= "./" && name == "content.xml")

86 let media = filteredFilesFromArchive archive filePathIsOdtMedia

87 let media = filteredFilesFromArchive archive filePathIsOdtMedia

87 let startState = readerState styles media

88 let startState = readerState styles media

88− either (\_ -> Left "Could not convert opendocument") Right

89+ either (\_ -> Left $ PandocParseError "Could not convert opendocument") Right

89 (runConverter' read_body startState contentElem)

90 (runConverter' read_body startState contentElem)

90

91

92

92--

93--

93−entryToXmlElem :: Entry -> Maybe XML.Element

94+entryToXmlElem :: Entry -> Either PandocError XML.Element

94−entryToXmlElem = XML.parseXMLDoc . UTF8.toStringLazy . fromEntry

95+entryToXmlElem entry =

96+ case parseXMLElement . UTF8.toTextLazy . fromEntry $ entry of

97+ Right x -> Right x

98+ Left msg -> Left $ PandocXMLError (T.pack $ eRelativePath entry) msg

src/Text/Pandoc/Writers/EPUB.hs+10−3

@@ -55,8 +55,9 @@ import Text.Pandoc.Walk (query, walk, walkM)

55import Text.Pandoc.Writers.HTML (writeHtmlStringForEPUB)

56import Text.Printf (printf)

57import Text.XML.Light (Attr (..), Element (..), Node (..), QName (..),

58− add_attrs, lookupAttr, node, onlyElems, parseXML,

58+ add_attrs, lookupAttr, node, onlyElems,

59 ppElement, showElement, strContent, unode, unqual)

60+import Text.Pandoc.XMLParser (parseXMLContents)

60import Text.Pandoc.XML (escapeStringForXML)

61import Text.Pandoc.XML (escapeStringForXML)

61import Text.DocTemplates (FromContext(lookupContext), Context(..),

62import Text.DocTemplates (FromContext(lookupContext), Context(..),

62 ToContext(toVal), Val(..))

63 ToContext(toVal), Val(..))

@@ -160,7 +161,12 @@ mkEntry path content = do

160getEPUBMetadata :: PandocMonad m => WriterOptions -> Meta -> E m EPUBMetadata

161getEPUBMetadata :: PandocMonad m => WriterOptions -> Meta -> E m EPUBMetadata

161getEPUBMetadata opts meta = do

162getEPUBMetadata opts meta = do

162 let md = metadataFromMeta opts meta

163 let md = metadataFromMeta opts meta

163− let elts = maybe [] (onlyElems . parseXML) $ writerEpubMetadata opts

164+ elts <- case writerEpubMetadata opts of

165+ Nothing -> return []

166+ Just t -> case parseXMLContents (TL.fromStrict t) of

167+ Left msg -> throwError $

168+ PandocXMLError "epub metadata" msg

169+ Right ns -> return (onlyElems ns)

164 let md' = foldr addMetadataFromXML md elts

170 let md' = foldr addMetadataFromXML md elts

165 let addIdentifier m =

171 let addIdentifier m =

166 if null (epubIdentifier m)

172 if null (epubIdentifier m)

@@ -836,7 +842,8 @@ pandocToEPUB version opts doc = do

836 : case subs of

842 : case subs of

837 [] -> []

843 [] -> []

838 (_:_) -> [unode "ol" ! [("class","toc")] $ subs]

844 (_:_) -> [unode "ol" ! [("class","toc")] $ subs]

839− where titElements = parseXML titRendered

845+ where titElements = either (const []) id $

846+ parseXMLContents (TL.fromStrict titRendered)

840 titRendered = case P.runPure

847 titRendered = case P.runPure

841 (writeHtmlStringForEPUB version

848 (writeHtmlStringForEPUB version

842 opts{ writerTemplate = Nothing

849 opts{ writerTemplate = Nothing

src/Text/Pandoc/Writers/FB2.hs+8−3

@@ -19,7 +19,7 @@ FictionBook is an XML-based e-book format. For more information see:

19module Text.Pandoc.Writers.FB2 (writeFB2) where

20

21import Control.Monad (zipWithM)

22−import Control.Monad.Except (catchError)

22+import Control.Monad.Except (catchError, throwError)

23import Control.Monad.State.Strict (StateT, evalStateT, get, gets, lift, liftM, modify)

24import Data.ByteString.Base64 (encode)

25import Data.Char (isAscii, isControl, isSpace)

@@ -27,16 +27,18 @@ import Data.Either (lefts, rights)

27import Data.List (intercalate)

28import Data.Text (Text, pack)

29import qualified Data.Text as T

30+import qualified Data.Text.Lazy as TL

30import qualified Data.Text.Encoding as TE

31import qualified Data.Text.Encoding as TE

31import Network.HTTP (urlEncode)

32import Network.HTTP (urlEncode)

32import Text.XML.Light

33import Text.XML.Light

33import qualified Text.XML.Light as X

34import qualified Text.XML.Light as X

34import qualified Text.XML.Light.Cursor as XC

35import qualified Text.XML.Light.Cursor as XC

35−import qualified Text.XML.Light.Input as XI

36+import Text.Pandoc.XMLParser (parseXMLContents)

36

37

37import Text.Pandoc.Class.PandocMonad (PandocMonad, report)

38import Text.Pandoc.Class.PandocMonad (PandocMonad, report)

38import qualified Text.Pandoc.Class.PandocMonad as P

39import qualified Text.Pandoc.Class.PandocMonad as P

39import Text.Pandoc.Definition

40import Text.Pandoc.Definition

41+import Text.Pandoc.Error (PandocError(..))

40import Text.Pandoc.Logging

42import Text.Pandoc.Logging

41import Text.Pandoc.Options (HTMLMathMethod (..), WriterOptions (..), def)

43import Text.Pandoc.Options (HTMLMathMethod (..), WriterOptions (..), def)

42import Text.Pandoc.Shared (capitalize, isURI, orderedListMarkers,

44import Text.Pandoc.Shared (capitalize, isURI, orderedListMarkers,

@@ -307,7 +309,10 @@ blockToXml (CodeBlock _ s) = return . spaceBeforeAfter .

307 map (el "p" . el "code" . T.unpack) . T.lines $ s

309 map (el "p" . el "code" . T.unpack) . T.lines $ s

308blockToXml (RawBlock f str) =

310blockToXml (RawBlock f str) =

309 if f == Format "fb2"

311 if f == Format "fb2"

310− then return $ XI.parseXML str

312+ then

313+ case parseXMLContents (TL.fromStrict str) of

314+ Left msg -> throwError $ PandocXMLError "" msg

315+ Right nds -> return nds

311 else return []

316 else return []

312blockToXml (Div _ bs) = cMapM blockToXml bs

317blockToXml (Div _ bs) = cMapM blockToXml bs

313blockToXml (BlockQuote bs) = list . el "cite" <$> cMapM blockToXml bs

318blockToXml (BlockQuote bs) = list . el "cite" <$> cMapM blockToXml bs

src/Text/Pandoc/Writers/ODT.hs+16−13

@@ -13,7 +13,7 @@ Conversion of 'Pandoc' documents to ODT.

13-}

14module Text.Pandoc.Writers.ODT ( writeODT ) where

15import Codec.Archive.Zip

16−import Control.Monad.Except (catchError)

16+import Control.Monad.Except (catchError, throwError)

17import Control.Monad.State.Strict

18import qualified Data.ByteString.Lazy as B

19import Data.Generics (everywhere', mkT)

@@ -27,6 +27,7 @@ import Text.Pandoc.BCP47 (Lang (..), getLang, renderLang)

27import Text.Pandoc.Class.PandocMonad (PandocMonad, report, toLang)

28import qualified Text.Pandoc.Class.PandocMonad as P

29import Text.Pandoc.Definition

30+import Text.Pandoc.Error (PandocError(..))

30import Text.Pandoc.ImageSize

31import Text.Pandoc.ImageSize

31import Text.Pandoc.Logging

32import Text.Pandoc.Logging

32import Text.Pandoc.MIME (extensionFromMimeType, getMimeType)

33import Text.Pandoc.MIME (extensionFromMimeType, getMimeType)

@@ -35,10 +36,11 @@ import Text.DocLayout

35import Text.Pandoc.Shared (stringify, pandocVersion, tshow)

36import Text.Pandoc.Shared (stringify, pandocVersion, tshow)

36import Text.Pandoc.Writers.Shared (lookupMetaString, lookupMetaBlocks,

37import Text.Pandoc.Writers.Shared (lookupMetaString, lookupMetaBlocks,

37 fixDisplayMath)

38 fixDisplayMath)

38−import Text.Pandoc.UTF8 (fromStringLazy, fromTextLazy, toStringLazy)

39+import Text.Pandoc.UTF8 (fromStringLazy, fromTextLazy, toTextLazy)

39import Text.Pandoc.Walk

40import Text.Pandoc.Walk

40import Text.Pandoc.Writers.OpenDocument (writeOpenDocument)

41import Text.Pandoc.Writers.OpenDocument (writeOpenDocument)

41import Text.Pandoc.XML

42import Text.Pandoc.XML

43+import Text.Pandoc.XMLParser (parseXMLElement)

42import Text.TeXMath

44import Text.TeXMath

43import Text.XML.Light

45import Text.XML.Light

44

46

@@ -172,17 +174,18 @@ updateStyleWithLang :: PandocMonad m => Maybe Lang -> Archive -> O m Archive

172updateStyleWithLang Nothing arch = return arch

174updateStyleWithLang Nothing arch = return arch

173updateStyleWithLang (Just lang) arch = do

175updateStyleWithLang (Just lang) arch = do

174 epochtime <- floor `fmap` lift P.getPOSIXTime

176 epochtime <- floor `fmap` lift P.getPOSIXTime

175− return arch{ zEntries = [if eRelativePath e == "styles.xml"

177+ entries <- mapM (\e -> if eRelativePath e == "styles.xml"

176− then case parseXMLDoc

178+ then case parseXMLElement

177− (toStringLazy (fromEntry e)) of

179+ (toTextLazy (fromEntry e)) of

178− Nothing -> e

180+ Left msg -> throwError $

179− Just d ->

181+ PandocXMLError "styles.xml" msg

182+ Right d -> return $

180− toEntry "styles.xml" epochtime

183+ toEntry "styles.xml" epochtime

181− ( fromStringLazy

184+ ( fromStringLazy

182− . ppTopElement

185+ . ppTopElement

183− . addLang lang $ d )

186+ . addLang lang $ d )

184− else e

185− | e <- zEntries arch] }

187+ else return e) (zEntries arch)

188+ return arch{ zEntries = entries }

186

189

187addLang :: Lang -> Element -> Element

190addLang :: Lang -> Element -> Element

188addLang lang = everywhere' (mkT updateLangAttr)

191addLang lang = everywhere' (mkT updateLangAttr)

src/Text/Pandoc/Writers/OOXML.hs+5−4

@@ -35,6 +35,7 @@ import qualified Data.Text as T

35import Text.Pandoc.Class.PandocMonad (PandocMonad)

36import qualified Text.Pandoc.UTF8 as UTF8

37import Text.XML.Light as XML

38+import Text.Pandoc.XMLParser (parseXMLElement)

38

39

39mknode :: Node t => String -> [(String,String)] -> t -> Element

40mknode :: Node t => String -> [(String,String)] -> t -> Element

40mknode s attrs =

41mknode s attrs =

@@ -62,10 +63,10 @@ parseXml refArchive distArchive relpath =

62 findEntryByPath relpath distArchive of

63 findEntryByPath relpath distArchive of

63 Nothing -> throwError $ PandocSomeError $

64 Nothing -> throwError $ PandocSomeError $

64 T.pack relpath <> " missing in reference file"

65 T.pack relpath <> " missing in reference file"

65− Just e -> case parseXMLDoc . UTF8.toStringLazy . fromEntry $ e of

66+ Just e -> case parseXMLElement . UTF8.toTextLazy . fromEntry $ e of

66− Nothing -> throwError $ PandocSomeError $

67+ Left msg ->

67− T.pack relpath <> " corrupt in reference file"

68+ throwError $ PandocXMLError (T.pack relpath) msg

68− Just d -> return d

69+ Right d -> return d

69

70

70-- Copied from Util

71-- Copied from Util

71

72

src/Text/Pandoc/Writers/Powerpoint/Output.hs+3−1

@@ -29,6 +29,7 @@ import Data.Time.Clock (UTCTime)

29import Data.Time.Clock.POSIX (utcTimeToPOSIXSeconds, posixSecondsToUTCTime)

30import System.FilePath.Posix (splitDirectories, splitExtension, takeExtension)

31import Text.XML.Light

32+import Text.Pandoc.XMLParser (parseXMLElement)

32import Text.Pandoc.Definition

33import Text.Pandoc.Definition

33import qualified Text.Pandoc.UTF8 as UTF8

34import qualified Text.Pandoc.UTF8 as UTF8

34import Text.Pandoc.Class.PandocMonad (PandocMonad)

35import Text.Pandoc.Class.PandocMonad (PandocMonad)

@@ -77,7 +78,8 @@ getPresentationSize :: Archive -> Archive -> Maybe (Integer, Integer)

77getPresentationSize refArchive distArchive = do

78getPresentationSize refArchive distArchive = do

78 entry <- findEntryByPath "ppt/presentation.xml" refArchive `mplus`

79 entry <- findEntryByPath "ppt/presentation.xml" refArchive `mplus`

79 findEntryByPath "ppt/presentation.xml" distArchive

80 findEntryByPath "ppt/presentation.xml" distArchive

80− presElement <- parseXMLDoc $ UTF8.toStringLazy $ fromEntry entry

81+ presElement <- either (const Nothing) return $

82+ parseXMLElement $ UTF8.toTextLazy $ fromEntry entry

81 let ns = elemToNameSpaces presElement

83 let ns = elemToNameSpaces presElement

82 sldSize <- findChild (elemName ns "p" "sldSz") presElement

84 sldSize <- findChild (elemName ns "p" "sldSz") presElement

83 cxS <- findAttr (QName "cx" Nothing Nothing) sldSize

85 cxS <- findAttr (QName "cx" Nothing Nothing) sldSize

src/Text/Pandoc/XMLParser.hsnew file+66

@@ -0,0 +1,66 @@

1+{-# LANGUAGE OverloadedStrings #-}

2+{- |

3+ Module : Text.Pandoc.XMLParser

5+ License : GNU GPL, version 2 or above

6+

7+ Maintainer : John MacFarlane <jgm@berkeley.edu>

8+ Stability : alpha

9+ Portability : portable

10+

11+Bridge to allow using xml-conduit's parser with xml-light's types.

12+-}

13+module Text.Pandoc.XMLParser

14+ ( parseXMLElement

15+ , parseXMLContents

16+ , module Text.XML.Light.Types

17+ ) where

18+

19+import qualified Control.Exception as E

20+import qualified Text.XML as Conduit

21+import Text.XML.Unresolved (InvalidEventStream(..))

22+import qualified Text.XML.Light as Light

23+import Text.XML.Light.Types

24+import qualified Data.Text as T

25+import qualified Data.Text.Lazy as TL

26+import qualified Data.Map as M

27+import Data.Maybe (mapMaybe)

28+

29+-- Drop in replacement for parseXMLDoc in xml-light.

30+parseXMLElement :: TL.Text -> Either T.Text Light.Element

31+parseXMLElement t =

32+ elementToElement . Conduit.documentRoot <$>

33+ either (Left . T.pack . E.displayException) Right

34+ (Conduit.parseText Conduit.def{ Conduit.psRetainNamespaces = True } t)

35+

36+parseXMLContents :: TL.Text -> Either T.Text [Light.Content]

37+parseXMLContents t =

38+ case Conduit.parseText Conduit.def{ Conduit.psRetainNamespaces = True } t of

39+ Left e ->

40+ case E.fromException e of

41+ Just (ContentAfterRoot _) ->

42+ elContent <$> parseXMLElement ("<wrapper>" <> t <> "</wrapper>")

43+ _ -> Left . T.pack . E.displayException $ e

44+ Right x -> Right [Light.Elem . elementToElement . Conduit.documentRoot $ x]

45+

46+elementToElement :: Conduit.Element -> Light.Element

47+elementToElement (Conduit.Element name attribMap nodes) =

48+ Light.Element (nameToQname name) attrs (mapMaybe nodeToContent nodes) Nothing

49+ where

50+ attrs = map (\(n,v) -> Light.Attr (nameToQname n) (T.unpack v)) $

51+ M.toList attribMap

52+ nameToQname (Conduit.Name localName mbns mbpref) =

53+ case mbpref of

54+ Nothing | "xmlns:" `T.isPrefixOf` localName ->

55+ Light.QName (T.unpack $ T.drop 6 localName) (T.unpack <$> mbns)

56+ (Just "xmlns")

57+ _ -> Light.QName (T.unpack localName) (T.unpack <$> mbns)

58+ (T.unpack <$> mbpref)

59+

60+nodeToContent :: Conduit.Node -> Maybe Light.Content

61+nodeToContent (Conduit.NodeElement el) =

62+ Just (Light.Elem (elementToElement el))

63+nodeToContent (Conduit.NodeContent t) =

64+ Just (Light.Text (Light.CData Light.CDataText (T.unpack t) Nothing))

65+nodeToContent _ = Nothing

66+

test/Tests/Readers/JATS.hs+1

@@ -88,6 +88,7 @@ tests = [ testGroup "inline code"

88 "<p>\n\

89 \ <inline-formula><alternatives>\n\

90 \ <tex-math><![CDATA[\\sigma|_{\\{x\\}}]]></tex-math>\n\

91+ \ </alternatives></inline-formula>\n\

91 \</p>"

92 \</p>"

92 =?> para (math "\\sigma|_{\\{x\\}}")

93 =?> para (math "\\sigma|_{\\{x\\}}")

93 , test jats "math ml only" $

94 , test jats "math ml only" $

test/command/5321.md+2−2

@@ -4,7 +4,7 @@

4 <caption>

5 <p>bar</p>

6 </caption>

7− <graphic xlink:href="foo.png" xlink:alt-text="baz">

7+ <graphic xlink:href="foo.png" xlink:alt-text="baz" />

8</fig>

9^D

10[Para [Image ("fig-1",[],[]) [Str "bar"] ("foo.png","fig:")]]

@@ -17,7 +17,7 @@

17 <title>foo</title>

18 <p>bar</p>

19 </caption>

20− <graphic xlink:href="foo.png" xlink:alt-text="baz">

20+ <graphic xlink:href="foo.png" xlink:alt-text="baz" />

21</fig>

22^D

23[Para [Image ("fig-1",[],[]) [Str "foo",LineBreak,Str "bar"] ("foo.png","fig:")]]

test/docbook-reader.docbook+6−1

@@ -1,6 +1,11 @@

1<?xml version="1.0" encoding="utf-8" ?>

2<!DOCTYPE article PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"

3− "http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd">

3+"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd"

4+[

5+<!ENTITY GHC "GHC" >

6+<!ENTITY let "LET" >

7+<!ENTITY case "CASE" >

8+]>

4<article>

9<article>

5 <articleinfo>

10 <articleinfo>

6 <title>Pandoc Test Suite</title>

11 <title>Pandoc Test Suite</title>

test/docx/golden/block_quotes.docx

Binary file not shown.

test/docx/golden/codeblock.docx

Binary file not shown.

test/docx/golden/comments.docx

Binary file not shown.

test/docx/golden/custom_style_no_reference.docx

Binary file not shown.

test/docx/golden/custom_style_preserve.docx

Binary file not shown.

test/docx/golden/custom_style_reference.docx

Binary file not shown.

test/docx/golden/definition_list.docx

Binary file not shown.

test/docx/golden/document-properties-short-desc.docx

Binary file not shown.

test/docx/golden/document-properties.docx

Binary file not shown.

test/docx/golden/headers.docx

Binary file not shown.

test/docx/golden/image.docx

Binary file not shown.

test/docx/golden/inline_code.docx

Binary file not shown.

test/docx/golden/inline_formatting.docx

Binary file not shown.

test/docx/golden/inline_images.docx

Binary file not shown.

test/docx/golden/link_in_notes.docx

Binary file not shown.

test/docx/golden/links.docx

Binary file not shown.

test/docx/golden/lists.docx

Binary file not shown.

test/docx/golden/lists_continuing.docx

Binary file not shown.

test/docx/golden/lists_multiple_initial.docx

Binary file not shown.

test/docx/golden/lists_restarting.docx

Binary file not shown.

test/docx/golden/nested_anchors_in_header.docx

Binary file not shown.

test/docx/golden/notes.docx

Binary file not shown.

test/docx/golden/raw-blocks.docx

Binary file not shown.

test/docx/golden/raw-bookmarks.docx

Binary file not shown.

test/docx/golden/table_one_row.docx

Binary file not shown.

test/docx/golden/table_with_list_cell.docx

Binary file not shown.

test/docx/golden/tables.docx

Binary file not shown.

test/docx/golden/track_changes_deletion.docx

Binary file not shown.

test/docx/golden/track_changes_insertion.docx

Binary file not shown.

test/docx/golden/track_changes_move.docx

Binary file not shown.

test/docx/golden/track_changes_scrubbed_metadata.docx

Binary file not shown.

test/docx/golden/unicode.docx

Binary file not shown.

test/docx/golden/verbatim_subsuper.docx

Binary file not shown.

test/jats-reader.native+1−1

@@ -1,4 +1,4 @@

1−Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"]]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]})

1+Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"],MetaInlines [Str "Anonymous"]]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]})

2[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."]

3,Header 1 ("headers",[],[]) [Str "Headers"]

4,Header 2 ("level-2-with-an-embedded-link",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",SoftBreak,Link ("",[],[]) [Str "embedded",SoftBreak,Str "link"] ("/url","")]

test/jats-reader.xml+1

@@ -20,6 +20,7 @@

20 <surname>MacFarlane</surname>

21 <given-names>John</given-names>

22 </name>

23+ </contrib>

23 <contrib contrib-type="author">

24 <contrib contrib-type="author">

24 <name>

25 <name>

25 <surname>Anonymous</surname>

26 <surname>Anonymous</surname>

test/pptx/code-custom.pptx

Binary file not shown.

test/pptx/code-custom_templated.pptx

Binary file not shown.

test/pptx/code.pptx

Binary file not shown.

test/pptx/code_templated.pptx

Binary file not shown.

test/pptx/document-properties-short-desc.pptx

Binary file not shown.

test/pptx/document-properties-short-desc_templated.pptx

Binary file not shown.

test/pptx/document-properties.pptx

Binary file not shown.

test/pptx/document-properties_templated.pptx

Binary file not shown.

test/pptx/endnotes.pptx

Binary file not shown.

test/pptx/endnotes_templated.pptx

Binary file not shown.

test/pptx/endnotes_toc.pptx

Binary file not shown.

test/pptx/endnotes_toc_templated.pptx

Binary file not shown.

test/pptx/images.pptx

Binary file not shown.

test/pptx/images_templated.pptx

Binary file not shown.

test/pptx/inline_formatting.pptx

Binary file not shown.

test/pptx/inline_formatting_templated.pptx

Binary file not shown.

test/pptx/lists.pptx

Binary file not shown.

test/pptx/lists_templated.pptx

Binary file not shown.

test/pptx/raw_ooxml.pptx

Binary file not shown.

test/pptx/raw_ooxml_templated.pptx

Binary file not shown.

test/pptx/remove_empty_slides.pptx

Binary file not shown.

test/pptx/remove_empty_slides_templated.pptx

Binary file not shown.

test/pptx/slide_breaks.pptx

Binary file not shown.

test/pptx/slide_breaks_slide_level_1.pptx

Binary file not shown.

test/pptx/slide_breaks_slide_level_1_templated.pptx

Binary file not shown.

test/pptx/slide_breaks_templated.pptx

Binary file not shown.

test/pptx/slide_breaks_toc.pptx

Binary file not shown.

test/pptx/slide_breaks_toc_templated.pptx

Binary file not shown.

test/pptx/speaker_notes.pptx

Binary file not shown.

test/pptx/speaker_notes_after_metadata.pptx

Binary file not shown.

test/pptx/speaker_notes_after_metadata_templated.pptx

Binary file not shown.

test/pptx/speaker_notes_afterheader.pptx

Binary file not shown.

test/pptx/speaker_notes_afterheader_templated.pptx

Binary file not shown.

test/pptx/speaker_notes_afterseps.pptx

Binary file not shown.

test/pptx/speaker_notes_afterseps_templated.pptx

Binary file not shown.

test/pptx/speaker_notes_templated.pptx

Binary file not shown.

test/pptx/start_numbering_at.pptx

Binary file not shown.

test/pptx/start_numbering_at_templated.pptx

Binary file not shown.

test/pptx/tables.pptx

Binary file not shown.

test/pptx/tables_templated.pptx

Binary file not shown.

test/pptx/two_column.pptx

Binary file not shown.

test/pptx/two_column_templated.pptx

Binary file not shown.