From 1fde92053fb1763c6af913aa9628827dff9ef899 Mon Sep 17 00:00:00 2001
From: mb21 <mb21@users.noreply.github.com>
Date: Sun, 10 Jan 2016 13:30:32 +0100
Subject: LaTeX writer: figure label

---
 src/Text/Pandoc/Writers/LaTeX.hs | 43 ++++++++++++++++++++++------------------
 1 file changed, 24 insertions(+), 19 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 2dcbf62bf..7b2911bcf 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -408,7 +408,7 @@ blockToLaTeX (Div (identifier,classes,kvs) bs) = do
 blockToLaTeX (Plain lst) =
   inlineListToLaTeX $ dropWhile isLineBreakOrSpace lst
 -- title beginning with fig: indicates that the image is a figure
-blockToLaTeX (Para [Image attr txt (src,'f':'i':'g':':':tit)]) = do
+blockToLaTeX (Para [Image attr@(ident, _, _) txt (src,'f':'i':'g':':':tit)]) = do
   inNote <- gets stInNote
   modify $ \st -> st{ stInMinipage = True, stNotes = [] }
   capt <- inlineListToLaTeX txt
@@ -420,13 +420,14 @@ blockToLaTeX (Para [Image attr txt (src,'f':'i':'g':':':tit)]) = do
                    else brackets <$> inlineListToLaTeX (walk deNote txt)
   img <- inlineToLaTeX (Image attr txt (src,tit))
   let footnotes = notesToLaTeX notes
+  figure <- refLabel ident $ cr <>
+            "\\begin{figure}[htbp]" $$ "\\centering" $$ img $$
+            ("\\caption" <> captForLof <> braces capt) $$
+            "\\end{figure}" <> cr
   return $ if inNote
               -- can't have figures in notes
               then "\\begin{center}" $$ img $+$ capt $$ "\\end{center}"
-              else "\\begin{figure}[htbp]" $$ "\\centering" $$ img $$
-                    ("\\caption" <> captForLof <> braces capt) $$
-                    "\\end{figure}" $$
-                    footnotes
+              else figure $$ footnotes
 -- . . . indicates pause in beamer slides
 blockToLaTeX (Para [Str ".",Space,Str ".",Space,Str "."]) = do
   beamer <- writerBeamer `fmap` gets stOptions
@@ -717,9 +718,8 @@ sectionHeader :: Bool    -- True for unnumbered
               -> Int
               -> [Inline]
               -> State WriterState Doc
-sectionHeader unnumbered ref level lst = do
+sectionHeader unnumbered ident level lst = do
   txt <- inlineListToLaTeX lst
-  lab <- text `fmap` toLabel ref
   plain <- stringToLaTeX TextString $ foldl (++) "" $ map stringify lst
   let noNote (Note _) = Str ""
       noNote x        = x
@@ -742,16 +742,6 @@ sectionHeader unnumbered ref level lst = do
   book <- gets stBook
   opts <- gets stOptions
   let level' = if book || writerChapters opts then level - 1 else level
-  internalLinks <- gets stInternalLinks
-  let refLabel x = (if ref `elem` internalLinks
-                       then text "\\hypertarget"
-                                <> braces lab
-                                <> braces x
-                       else x)
-  let headerWith x y = refLabel $ text x <> y <>
-                             if null ref
-                                then empty
-                                else text "\\label" <> braces lab
   let sectionType = case level' of
                           0  | writerBeamer opts -> "part"
                              | otherwise -> "chapter"
@@ -767,16 +757,31 @@ sectionHeader unnumbered ref level lst = do
                   -- needed for \paragraph, \subparagraph in quote environment
                   -- see http://tex.stackexchange.com/questions/169830/
                   else empty
+  stuffing' <- refLabel ident $ text ('\\':sectionType) <> stuffing
   return $ if level' > 5
               then txt
-              else prefix $$
-                   headerWith ('\\':sectionType) stuffing
+              else prefix $$ stuffing'
                    $$ if unnumbered
                          then "\\addcontentsline{toc}" <>
                                 braces (text sectionType) <>
                                 braces txtNoNotes
                          else empty
 
+-- | Append label to x and wrap in hypertarget
+refLabel :: String -> Doc -> State WriterState Doc
+refLabel ident x = do
+  ref <- text `fmap` toLabel ident
+  internalLinks <- gets stInternalLinks
+  let hypertarget y = if ident `elem` internalLinks
+                         then text "\\hypertarget"
+                                <> braces ref
+                                <> braces y
+                         else y
+      label = if null ident
+                 then empty
+                 else text "\\label" <> braces ref
+  return $ hypertarget $ x <> label
+
 -- | Convert list of inline elements to LaTeX.
 inlineListToLaTeX :: [Inline]  -- ^ Inlines to convert
                   -> State WriterState Doc
-- 
cgit v1.2.3


From 0b9c54d9f31db88d5cd8e888921dffc2a108f8d4 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Tue, 8 Mar 2016 00:27:09 -0500
Subject: Docx reader: update feature checklist.

The feature checklist in the source code was out of date. Update.
---
 src/Text/Pandoc/Readers/Docx.hs | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx.hs b/src/Text/Pandoc/Readers/Docx.hs
index eb71d8dd8..c399a2174 100644
--- a/src/Text/Pandoc/Readers/Docx.hs
+++ b/src/Text/Pandoc/Readers/Docx.hs
@@ -50,8 +50,7 @@ implemented, [-] means partially implemented):
 * Inlines
 
   - [X] Str
-  - [X] Emph (From italics. `underline` currently read as span. In
-        future, it might optionally be emph as well)
+  - [X] Emph (italics and underline both read as Emph)
   - [X] Strong
   - [X] Strikeout
   - [X] Superscript
@@ -62,11 +61,10 @@ implemented, [-] means partially implemented):
   - [X] Code (styled with `VerbatimChar`)
   - [X] Space
   - [X] LineBreak (these are invisible in Word: entered with Shift-Return)
-  - [ ] Math
+  - [X] Math
   - [X] Link (links to an arbitrary bookmark create a span with the target as
         id and "anchor" class)
-  - [-] Image (Links to path in archive. Future option for
-        data-encoded URI likely.)
+  - [X] Image 
   - [X] Note (Footnotes and Endnotes are silently combined.)
 -}
 
-- 
cgit v1.2.3


From 6bfaa5ad15d2c3acfc61ddf5ec442ca733016373 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Tue, 8 Mar 2016 10:08:14 -0800
Subject: DokuWiki writer: use $$ for display math.

---
 src/Text/Pandoc/Writers/DokuWiki.hs | 5 ++++-
 tests/writer.dokuwiki               | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/DokuWiki.hs b/src/Text/Pandoc/Writers/DokuWiki.hs
index f1088b158..56e2b9027 100644
--- a/src/Text/Pandoc/Writers/DokuWiki.hs
+++ b/src/Text/Pandoc/Writers/DokuWiki.hs
@@ -452,8 +452,11 @@ inlineToDokuWiki _ (Code _ str) =
 
 inlineToDokuWiki _ (Str str) = return $ escapeString str
 
-inlineToDokuWiki _ (Math _ str) = return $ "$" ++ str ++ "$"
+inlineToDokuWiki _ (Math mathType str) = return $ delim ++ str ++ delim
                                  -- note:  str should NOT be escaped
+  where delim = case mathType of
+                     DisplayMath -> "$$"
+                     InlineMath  -> "$"
 
 inlineToDokuWiki _ (RawInline f str)
   | f == Format "dokuwiki" = return str
diff --git a/tests/writer.dokuwiki b/tests/writer.dokuwiki
index fe1f8296a..79fcdde8a 100644
--- a/tests/writer.dokuwiki
+++ b/tests/writer.dokuwiki
@@ -459,7 +459,7 @@ Ellipses…and…and….
   * $\alpha \wedge \omega$
   * $223$
   * $p$-Tree
-  * Here’s some display math: $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$
+  * Here’s some display math: $$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$$
   * Here’s one that has a line break in it: $\alpha + \omega \times x^2$.
 
 These shouldn’t be math:
-- 
cgit v1.2.3


From 4ed64835cb475f3da80ed7b729516c7a90891d94 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 9 Mar 2016 08:33:13 -0800
Subject: Markdown reader:  don't cross line boundary parsing pipe table row.

Previously an emph element could be parsed across the newline
at the end of the pipe table row.

I thought this would help with #2765, but it doesn't.
---
 src/Text/Pandoc/Readers/Markdown.hs | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 587726084..0eeda0fee 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -1372,7 +1372,13 @@ sepPipe = try $ do
 
 -- parse a row, also returning probable alignments for org-table cells
 pipeTableRow :: MarkdownParser (F [Blocks])
-pipeTableRow = do
+pipeTableRow = try $ do
+  scanForPipe
+  raw <- anyLine
+  parseFromString pipeTableRow' (raw ++ "\n")
+
+pipeTableRow' :: MarkdownParser (F [Blocks])
+pipeTableRow' = do
   skipMany spaceChar
   openPipe <- (True <$ char '|') <|> return False
   let cell = mconcat <$>
-- 
cgit v1.2.3


From 6e950a8eb5001314869013395c9c72ee05079110 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 9 Mar 2016 08:44:31 -0800
Subject: Markdown reader:  allow `+` separators in pipe table cells.

We already allowed them in the header, but not in the body
rows, for some reason.  This gives compatibility with org-mode
tables.
---
 src/Text/Pandoc/Readers/Markdown.hs | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 0eeda0fee..6caf1728c 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -1382,16 +1382,14 @@ pipeTableRow' = do
   skipMany spaceChar
   openPipe <- (True <$ char '|') <|> return False
   let cell = mconcat <$>
-                 many (notFollowedBy (blankline <|> char '|') >> inline)
-  first <- cell
-  rest <- many $ sepPipe *> cell
+                 many (notFollowedBy (blankline <|> oneOf "+|") >> inline)
+  cells <- cell `sepBy1` sepPipe
   -- surrounding pipes needed for a one-column table:
-  guard $ not (null rest && not openPipe)
+  guard $ not (length cells == 1 && not openPipe)
   optional (char '|')
   blankline
-  let cells  = sequence (first:rest)
   return $ do
-    cells' <- cells
+    cells' <- sequence cells
     return $ map
         (\ils ->
            case trimInlines ils of
-- 
cgit v1.2.3


From 54a68616d7f9259840fd8a884d806782a73236a9 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 9 Mar 2016 10:11:32 -0800
Subject: Markdown reader: Clean up pipe table parsing.

---
 src/Text/Pandoc/Readers/Markdown.hs | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 6caf1728c..c99838352 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -1354,16 +1354,18 @@ pipeTable = try $ do
   nonindentSpaces
   lookAhead nonspaceChar
   (heads,(aligns, seplengths)) <- (,) <$> pipeTableRow <*> pipeBreak
+  let heads' = take (length aligns) <$> heads
   lines' <- many pipeTableRow
+  let lines'' = map (take (length aligns) <$>) lines'
   let maxlength = maximum $
-       map (\x -> length . stringify $ runF x def) (heads : lines')
+       map (\x -> length . stringify $ runF x def) (heads' : lines'')
   numColumns <- getOption readerColumns
   let widths = if maxlength > numColumns
                   then map (\len ->
                            fromIntegral (len + 1) / fromIntegral numColumns)
                              seplengths
                   else replicate (length aligns) 0.0
-  return $ (aligns, widths, heads, sequence lines')
+  return $ (aligns, widths, heads', sequence lines'')
 
 sepPipe :: MarkdownParser ()
 sepPipe = try $ do
@@ -1375,19 +1377,17 @@ pipeTableRow :: MarkdownParser (F [Blocks])
 pipeTableRow = try $ do
   scanForPipe
   raw <- anyLine
-  parseFromString pipeTableRow' (raw ++ "\n")
+  parseFromString pipeTableRow' raw
 
 pipeTableRow' :: MarkdownParser (F [Blocks])
 pipeTableRow' = do
   skipMany spaceChar
   openPipe <- (True <$ char '|') <|> return False
-  let cell = mconcat <$>
-                 many (notFollowedBy (blankline <|> oneOf "+|") >> inline)
-  cells <- cell `sepBy1` sepPipe
+  let cell = mconcat <$> (many (notFollowedBy (char '|') >> inline))
+  cells <- cell `sepEndBy1` (char '|')
   -- surrounding pipes needed for a one-column table:
   guard $ not (length cells == 1 && not openPipe)
-  optional (char '|')
-  blankline
+  spaces >> eof
   return $ do
     cells' <- sequence cells
     return $ map
-- 
cgit v1.2.3


From 2b55b76ebec87f4d35b2e641e054bd6dfc74be09 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 9 Mar 2016 11:46:00 -0800
Subject: Markdown reader: Improved pipe table parsing.

Fixes #2765.
Added test case.
---
 src/Text/Pandoc/Readers/Markdown.hs | 30 +++++++++++++++---------------
 tests/pipe-tables.native            | 16 +++++++++++++++-
 tests/pipe-tables.txt               |  8 ++++++++
 3 files changed, 38 insertions(+), 16 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index c99838352..b5d175453 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -1376,25 +1376,25 @@ sepPipe = try $ do
 pipeTableRow :: MarkdownParser (F [Blocks])
 pipeTableRow = try $ do
   scanForPipe
-  raw <- anyLine
-  parseFromString pipeTableRow' raw
-
-pipeTableRow' :: MarkdownParser (F [Blocks])
-pipeTableRow' = do
   skipMany spaceChar
   openPipe <- (True <$ char '|') <|> return False
-  let cell = mconcat <$> (many (notFollowedBy (char '|') >> inline))
-  cells <- cell `sepEndBy1` (char '|')
+  -- split into cells
+  let chunk = void (code <|> rawHtmlInline <|> escapedChar <|> rawLaTeXInline')
+       <|> void (noneOf "|\n\r")
+  let cellContents = ((trim . snd) <$> withRaw (many chunk)) >>=
+        parseFromString pipeTableCell
+  cells <- cellContents `sepEndBy1` (char '|')
   -- surrounding pipes needed for a one-column table:
   guard $ not (length cells == 1 && not openPipe)
-  spaces >> eof
-  return $ do
-    cells' <- sequence cells
-    return $ map
-        (\ils ->
-           case trimInlines ils of
-                 ils' | B.isNull ils' -> mempty
-                      | otherwise   -> B.plain $ ils') cells'
+  blankline
+  return $ sequence cells
+
+pipeTableCell :: MarkdownParser (F Blocks)
+pipeTableCell = do
+  result <- many inline
+  if null result
+     then return mempty
+     else return $ B.plain . mconcat <$> sequence result
 
 pipeTableHeaderPart :: Parser [Char] st (Alignment, Int)
 pipeTableHeaderPart = try $ do
diff --git a/tests/pipe-tables.native b/tests/pipe-tables.native
index 6cd37f6ff..63c2c17bc 100644
--- a/tests/pipe-tables.native
+++ b/tests/pipe-tables.native
@@ -98,4 +98,18 @@
 ,Para [Str "Pipe",Space,Str "table",Space,Str "with",Space,Str "no",Space,Str "body:"]
 ,Table [] [AlignDefault] [0.0]
  [[Plain [Str "Header"]]]
- []]
+ []
+,Para [Str "Pipe",Space,Str "table",Space,Str "with",Space,Str "tricky",Space,Str "cell",Space,Str "contents",Space,Str "(see",Space,Str "#2765):"]
+,Table [] [AlignLeft,AlignRight,AlignRight] [0.0,0.0,0.0]
+ [[]
+ ,[Plain [Str "IP_gene8-_1st"]]
+ ,[Plain [Str "IP_gene8+_1st"]]]
+ [[[Plain [Str "IP_gene8-_1st"]]
+  ,[Plain [Str "1.0000000"]]
+  ,[Plain [Str "0.4357325"]]]
+ ,[[Plain [Str "IP_gene8+_1st"]]
+  ,[Plain [Str "0.4357325"]]
+  ,[Plain [Str "1.0000000"]]]
+ ,[[Plain [Str "foo",Code ("",[],[]) "bar|baz"]]
+  ,[Plain [Str "and|escaped"]]
+  ,[Plain [Str "3.0000000"]]]]]
diff --git a/tests/pipe-tables.txt b/tests/pipe-tables.txt
index e93f64af9..c27c71113 100644
--- a/tests/pipe-tables.txt
+++ b/tests/pipe-tables.txt
@@ -72,3 +72,11 @@ Pipe table with no body:
 | Header |
 | ------ |
 
+Pipe table with tricky cell contents (see #2765):
+
+|               | IP_gene8-_1st| IP_gene8+_1st|
+|:--------------|-------------:|-------------:|
+|IP_gene8-_1st  |     1.0000000|     0.4357325|
+|IP_gene8+_1st  |     0.4357325|     1.0000000|
+|foo`bar|baz`   | and\|escaped |     3.0000000|
+
-- 
cgit v1.2.3


From 139fa54d48a878c91f6e56c17ee50e9d589d379f Mon Sep 17 00:00:00 2001
From: mb21 <mb21@users.noreply.github.com>
Date: Wed, 9 Mar 2016 23:16:02 +0100
Subject:  Docx Writer: handle image alt text

 closes #2754
---
 src/Text/Pandoc/Writers/Docx.hs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/Docx.hs b/src/Text/Pandoc/Writers/Docx.hs
index 150e19043..a841e1b66 100644
--- a/src/Text/Pandoc/Writers/Docx.hs
+++ b/src/Text/Pandoc/Writers/Docx.hs
@@ -1103,7 +1103,7 @@ inlineToOpenXML opts (Link _ txt (src,_)) = do
                         M.insert src i extlinks }
               return i
   return [ mknode "w:hyperlink" [("r:id",id')] contents ]
-inlineToOpenXML opts (Image attr alt (src, tit)) = do
+inlineToOpenXML opts (Image attr alt (src, _)) = do
   -- first, check to see if we've already done this image
   pageWidth <- gets stPrintWidth
   imgs <- gets stImages
@@ -1154,7 +1154,7 @@ inlineToOpenXML opts (Image attr alt (src, tit)) = do
                  mknode "wp:inline" []
                   [ mknode "wp:extent" [("cx",show xemu),("cy",show yemu)] ()
                   , mknode "wp:effectExtent" [("b","0"),("l","0"),("r","0"),("t","0")] ()
-                  , mknode "wp:docPr" [("descr",tit),("id","1"),("name","Picture")] ()
+                  , mknode "wp:docPr" [("descr",stringify alt),("id","1"),("name","Picture")] ()
                   , graphic ]
           let imgext = case mt >>= extensionFromMimeType of
                             Just x    -> '.':x
-- 
cgit v1.2.3


From a485c42d78d8bc819f7ad1bef137d54a324c5ea9 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Thu, 10 Mar 2016 19:59:55 -0800
Subject: Fixed behavior of base tag.

+ If the base path does not end with slash, the last component
  will be replaced.  E.g. base = `http://example.com/foo`
  combines with `bar.html` to give `http://example.com/bar.html`.
+ If the href begins with a slash, the whole path of the base
  is replaced.  E.g. base = `http://example.com/foo/` combines
  with `/bar.html` to give `http://example.com/bar.html`.

Closes #2777.
---
 src/Text/Pandoc/Readers/HTML.hs | 28 +++++++++++-----------------
 tests/Tests/Readers/HTML.hs     |  5 ++++-
 2 files changed, 15 insertions(+), 18 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index 69df13aac..959a2d16f 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -63,7 +63,7 @@ import Debug.Trace (trace)
 import Text.TeXMath (readMathML, writeTeX)
 import Data.Default (Default (..), def)
 import Control.Monad.Reader (Reader,ask, asks, local, runReader)
-import Network.URI (isURI)
+import Network.URI (URI, parseURIReference, nonStrictRelativeTo)
 import Text.Pandoc.Error
 import Text.Pandoc.CSS (foldOrElse, pickStyleAttrProps)
 import Text.Pandoc.Compat.Monoid ((<>))
@@ -103,7 +103,7 @@ data HTMLState =
   HTMLState
   {  parserState :: ParserState,
      noteTable   :: [(String, Blocks)],
-     baseHref    :: Maybe String,
+     baseHref    :: Maybe URI,
      identifiers :: Set.Set String,
      headerMap   :: M.Map Inlines String
   }
@@ -145,15 +145,9 @@ pHead = pInTags "head" $ pTitle <|> pMetaTag <|> pBaseTag <|> (mempty <$ pAnyTag
                return mempty
         pBaseTag = do
           bt <- pSatisfy (~== TagOpen "base" [])
-          let baseH = fromAttrib "href" bt
-          if null baseH
-             then return mempty
-             else do
-               let baseH' = case reverse baseH of
-                                  '/':_ -> baseH
-                                  _     -> baseH ++ "/"
-               updateState $ \st -> st{ baseHref = Just baseH' }
-               return mempty
+          updateState $ \st -> st{ baseHref =
+               parseURIReference $ fromAttrib "href" bt }
+          return mempty
 
 block :: TagParser Blocks
 block = do
@@ -610,9 +604,9 @@ pLink = try $ do
   tag <- pSatisfy $ tagOpenLit "a" (const True)
   mbBaseHref <- baseHref <$> getState
   let url' = fromAttrib "href" tag
-  let url = case (isURI url', mbBaseHref) of
-                 (False, Just h) -> h ++ url'
-                 _               -> url'
+  let url = case (parseURIReference url', mbBaseHref) of
+                 (Just rel, Just bs) -> show (rel `nonStrictRelativeTo` bs)
+                 _                   -> url'
   let title = fromAttrib "title" tag
   let uid = fromAttrib "id" tag
   let cls = words $ fromAttrib "class" tag
@@ -624,9 +618,9 @@ pImage = do
   tag <- pSelfClosing (=="img") (isJust . lookup "src")
   mbBaseHref <- baseHref <$> getState
   let url' = fromAttrib "src" tag
-  let url = case (isURI url', mbBaseHref) of
-                 (False, Just h) -> h ++ url'
-                 _               -> url'
+  let url = case (parseURIReference url', mbBaseHref) of
+                 (Just rel, Just bs) -> show (rel `nonStrictRelativeTo` bs)
+                 _                   -> url'
   let title = fromAttrib "title" tag
   let alt = fromAttrib "alt" tag
   let uid = fromAttrib "id" tag
diff --git a/tests/Tests/Readers/HTML.hs b/tests/Tests/Readers/HTML.hs
index 2eb87a2f3..ff27b8aed 100644
--- a/tests/Tests/Readers/HTML.hs
+++ b/tests/Tests/Readers/HTML.hs
@@ -15,11 +15,14 @@ html = handleError . readHtml def
 tests :: [Test]
 tests = [ testGroup "base tag"
           [ test html "simple" $
-            "<head><base href=\"http://www.w3schools.com/images\" ></head><body><img src=\"stickman.gif\" alt=\"Stickman\"></head>" =?>
+            "<head><base href=\"http://www.w3schools.com/images/foo\" ></head><body><img src=\"stickman.gif\" alt=\"Stickman\"></head>" =?>
             plain (image "http://www.w3schools.com/images/stickman.gif" "" (text "Stickman"))
           , test html "slash at end of base" $
             "<head><base href=\"http://www.w3schools.com/images/\" ></head><body><img src=\"stickman.gif\" alt=\"Stickman\"></head>" =?>
             plain (image "http://www.w3schools.com/images/stickman.gif" "" (text "Stickman"))
+          , test html "slash at beginning of href" $
+            "<head><base href=\"http://www.w3schools.com/images/\" ></head><body><img src=\"/stickman.gif\" alt=\"Stickman\"></head>" =?>
+            plain (image "http://www.w3schools.com/stickman.gif" "" (text "Stickman"))
           , test html "absolute URL" $
             "<head><base href=\"http://www.w3schools.com/images/\" ></head><body><img src=\"http://example.com/stickman.gif\" alt=\"Stickman\"></head>" =?>
             plain (image "http://example.com/stickman.gif" "" (text "Stickman"))
-- 
cgit v1.2.3


From 102ba9ecb869da80fac03480b2dd03a695a4f78c Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Thu, 10 Mar 2016 15:19:55 -0500
Subject: Docx Reader: Add state to the parser, for warnings

In order to be able to collect warnings during parsing, we add a state
monad transformer to the D monad. At the moment, this only includes a
list of warning strings (nothing currently triggers them, however). We
use StateT instead of WriterT to correspond more closely with the
warnings behavior in T.P.Parsing.
---
 src/Text/Pandoc/Readers/Docx/Parse.hs | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs
index eec8b12c9..e4cfe4930 100644
--- a/src/Text/Pandoc/Readers/Docx/Parse.hs
+++ b/src/Text/Pandoc/Readers/Docx/Parse.hs
@@ -50,6 +50,7 @@ module Text.Pandoc.Readers.Docx.Parse ( Docx(..)
                                       , Row(..)
                                       , Cell(..)
                                       , archiveToDocx
+                                      , archiveToDocxWithWarnings
                                       ) where
 import Codec.Archive.Zip
 import Text.XML.Light
@@ -60,6 +61,7 @@ import Data.Bits ((.|.))
 import qualified Data.ByteString.Lazy as B
 import qualified Text.Pandoc.UTF8 as UTF8
 import Control.Monad.Reader
+import Control.Monad.State
 import Control.Applicative ((<|>))
 import qualified Data.Map as M
 import Text.Pandoc.Compat.Except
@@ -81,16 +83,20 @@ data ReaderEnv = ReaderEnv { envNotes         :: Notes
                            }
                deriving Show
 
+data ReaderState = ReaderState { stateWarnings :: [String] }
+                 deriving Show
+                                                  
+
 data DocxError = DocxError | WrongElem
                deriving Show
 
 instance Error DocxError where
   noMsg = WrongElem
 
-type D = ExceptT DocxError (Reader ReaderEnv)
+type D = ExceptT DocxError (ReaderT ReaderEnv (State ReaderState))
 
-runD :: D a -> ReaderEnv -> Either DocxError a
-runD dx re = runReader (runExceptT dx) re
+runD :: D a -> ReaderEnv -> ReaderState -> (Either DocxError a, ReaderState)
+runD dx re rs = runState (runReaderT (runExceptT dx) re) rs
 
 maybeToD :: Maybe a -> D a
 maybeToD (Just a) = return a
@@ -257,7 +263,10 @@ type Author = String
 type ChangeDate = String
 
 archiveToDocx :: Archive -> Either DocxError Docx
-archiveToDocx archive = do
+archiveToDocx archive = fst <$> archiveToDocxWithWarnings archive
+
+archiveToDocxWithWarnings :: Archive -> Either DocxError (Docx, [String])
+archiveToDocxWithWarnings archive = do
   let notes     = archiveToNotes archive
       numbering = archiveToNumbering archive
       rels      = archiveToRelationships archive
@@ -265,8 +274,12 @@ archiveToDocx archive = do
       (styles, parstyles) = archiveToStyles archive
       rEnv =
         ReaderEnv notes numbering rels media Nothing styles parstyles InDocument
-  doc <- runD (archiveToDocument archive) rEnv
-  return $ Docx doc
+      rState = ReaderState { stateWarnings = [] }
+      (eitherDoc, st) = runD (archiveToDocument archive) rEnv rState
+  case eitherDoc of
+    Right doc -> Right (Docx doc, stateWarnings st)
+    Left e    -> Left e
+
 
 
 archiveToDocument :: Archive -> D Document
-- 
cgit v1.2.3


From ee03e954d0d3cb76971c91001348762f55224890 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Sat, 12 Mar 2016 10:18:01 -0500
Subject: Add readDocxWithWarnings

The regular readDocx just becomes a special case.
---
 src/Text/Pandoc/Readers/Docx.hs | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx.hs b/src/Text/Pandoc/Readers/Docx.hs
index c399a2174..604bc20de 100644
--- a/src/Text/Pandoc/Readers/Docx.hs
+++ b/src/Text/Pandoc/Readers/Docx.hs
@@ -69,7 +69,8 @@ implemented, [-] means partially implemented):
 -}
 
 module Text.Pandoc.Readers.Docx
-       ( readDocx
+       ( readDocxWithWarnings
+       , readDocx
        ) where
 
 import Codec.Archive.Zip
@@ -96,14 +97,22 @@ import qualified Data.Sequence as Seq (null)
 import Text.Pandoc.Error
 import Text.Pandoc.Compat.Except
 
+readDocxWithWarnings :: ReaderOptions
+                     -> B.ByteString
+                     -> Either PandocError (Pandoc, MediaBag, [String])
+readDocxWithWarnings opts bytes =
+  case archiveToDocxWithWarnings (toArchive bytes) of
+    Right (docx, warnings) -> do
+      (meta, blks, mediaBag) <- docxToOutput opts docx
+      return (Pandoc meta blks, mediaBag, warnings)
+    Left _   -> Left (ParseFailure "couldn't parse docx file")
+
 readDocx :: ReaderOptions
          -> B.ByteString
          -> Either PandocError (Pandoc, MediaBag)
-readDocx opts bytes =
-  case archiveToDocx (toArchive bytes) of
-    Right docx -> (\(meta, blks, mediaBag) -> (Pandoc meta blks, mediaBag))
-                    <$> (docxToOutput opts docx)
-    Left _   -> Left (ParseFailure "couldn't parse docx file")
+readDocx opts bytes = do
+  (pandoc, mediaBag, _) <- readDocxWithWarnings opts bytes
+  return (pandoc, mediaBag)
 
 data DState = DState { docxAnchorMap :: M.Map String String
                      , docxMediaBag      :: MediaBag
-- 
cgit v1.2.3


From 5c055b4cf3cdfac534a74c5c5775aa2d58889150 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Sat, 20 Feb 2016 21:27:08 -0500
Subject: Introduce file-scope parsing (parse-before-combine)

Traditionally pandoc operates on multiple files by first concetenating
them (around extra line breaks) and then processing the joined file. So
it only parses a multi-file document at the document scope. This has the
benefit that footnotes and links can be in different files, but it also
introduces a couple of difficulties:

  - it is difficult to join files with footnotes without some sort of
    preprocessing, which makes it difficult to write academic documents
    in small pieces.

  - it makes it impossible to process multiple binary input files, which
    can't be catted.

  - it makes it impossible to process files from different input
    formats.

This commit introduces alternative method. Instead of catting the files
first, it parses the files first, and then combines the parsed
output. This makes it impossible to have links across multiple files,
and auto-identified headers won't work correctly if headers in multiple
files have the same name. On the other hand, footnotes across multiple
files will work correctly and will allow more freedom for input formats.

Since ByteStringReaders can currently only read one binary file, and
will ignore subsequent files, we also changes the behavior to
automatically parse before combining if using the ByteStringReader. If
we use one file, it will work as normal. If there is more than one file
it will combine them after parsing (assuming that the format is the
same).

Note that this is intended to be an optional method, defaulting to
off. Turn it on with `--file-scope`.
---
 pandoc.hs                  | 27 +++++++++++++++++++++++----
 src/Text/Pandoc/Options.hs |  2 ++
 2 files changed, 25 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/pandoc.hs b/pandoc.hs
index 72a7592d8..59277690a 100644
--- a/pandoc.hs
+++ b/pandoc.hs
@@ -215,6 +215,7 @@ data Opt = Opt
     , optExtractMedia      :: Maybe FilePath -- ^ Path to extract embedded media
     , optTrace             :: Bool       -- ^ Print debug information
     , optTrackChanges      :: TrackChanges -- ^ Accept or reject MS Word track-changes.
+    , optFileScope        :: Bool         -- ^ Parse input files before combining
     , optKaTeXStylesheet   :: Maybe String     -- ^ Path to stylesheet for KaTeX
     , optKaTeXJS           :: Maybe String     -- ^ Path to js file for KaTeX
     }
@@ -278,6 +279,7 @@ defaultOpts = Opt
     , optExtractMedia          = Nothing
     , optTrace                 = False
     , optTrackChanges          = AcceptChanges
+    , optFileScope            = False
     , optKaTeXStylesheet       = Nothing
     , optKaTeXJS               = Nothing
     }
@@ -387,6 +389,11 @@ options =
                   "accept|reject|all")
                  "" -- "Accepting or reject MS Word track-changes.""
 
+    , Option "" ["file-scope"]
+                 (NoArg
+                  (\opt -> return opt { optFileScope = True }))
+                 "" -- "Parse input files before combining"
+
     , Option "" ["extract-media"]
                  (ReqArg
                   (\arg opt ->
@@ -1117,6 +1124,7 @@ convertWithOpts opts args = do
               , optExtractMedia          = mbExtractMedia
               , optTrace                 = trace
               , optTrackChanges          = trackChanges
+              , optFileScope            = fileScope
               , optKaTeXStylesheet       = katexStylesheet
               , optKaTeXJS               = katexJS
              } = opts
@@ -1269,6 +1277,7 @@ convertWithOpts opts args = do
                       , readerDefaultImageExtension = defaultImageExtension
                       , readerTrace = trace
                       , readerTrackChanges = trackChanges
+                      , readerFileScope   = fileScope
                       }
 
   when (not (isTextFormat format) && outputFile == "-") $
@@ -1301,13 +1310,23 @@ convertWithOpts opts args = do
                                then handleIncludes
                                else return . Right
 
-  (doc, media) <- fmap handleError $
-      case reader of
+  let sourceToDoc :: [FilePath] -> IO (Pandoc, MediaBag)
+      sourceToDoc sources' = fmap handleError $
+        case reader of
           StringReader r-> do
-            srcs <- convertTabs . intercalate "\n" <$> readSources sources
+            srcs <- convertTabs . intercalate "\n" <$> readSources sources'
             doc <- handleIncludes' srcs
             either (return . Left) (\s -> fmap (,mempty) <$> r readerOpts s) doc
-          ByteStringReader r -> readFiles sources >>= r readerOpts
+          ByteStringReader r -> readFiles sources' >>= r readerOpts
+
+  -- We parse first if fileScope is set OR if the reader is a
+  -- BSReader. So, if it's a StringReader AND not fileScope, we
+  -- don't.
+  (doc, media) <- case reader of
+    (StringReader _) | not fileScope -> sourceToDoc sources
+    _                                   -> do
+      pairs <- mapM (\s -> sourceToDoc [s]) sources
+      return (mconcat $ map fst pairs, mconcat $ map snd pairs)
 
   let writerOptions = def { writerStandalone       = standalone',
                             writerTemplate         = templ,
diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index 333f499fb..b5736c63d 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -264,6 +264,7 @@ data ReaderOptions = ReaderOptions{
        , readerDefaultImageExtension :: String -- ^ Default extension for images
        , readerTrace           :: Bool -- ^ Print debugging info
        , readerTrackChanges    :: TrackChanges
+       , readerFileScope      :: Bool -- ^ Parse before combining
 } deriving (Show, Read, Data, Typeable, Generic)
 
 instance Default ReaderOptions
@@ -280,6 +281,7 @@ instance Default ReaderOptions
                , readerDefaultImageExtension = ""
                , readerTrace                 = False
                , readerTrackChanges          = AcceptChanges
+               , readerFileScope             = False
                }
 
 --
-- 
cgit v1.2.3


From 855c8b43f0497125f8d24b113ce0df92ed7d074b Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Wed, 16 Mar 2016 12:50:32 -0400
Subject: Docx reader: Don't make numbered heads into lists.

Word uses list numbering styles to number its headings. We only call
something a numbered list if it does not also heave a heading style.
---
 src/Text/Pandoc/Readers/Docx/Parse.hs | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs
index e4cfe4930..cbdd86221 100644
--- a/src/Text/Pandoc/Readers/Docx/Parse.hs
+++ b/src/Text/Pandoc/Readers/Docx/Parse.hs
@@ -589,12 +589,14 @@ elemToBodyPart ns element
       sty <- asks envParStyles
       let parstyle = elemToParagraphStyle ns element sty
       parparts <- mapD (elemToParPart ns) (elChildren element)
-      case pNumInfo parstyle of
-       Just (numId, lvl) -> do
-         num <- asks envNumbering
-         let levelInfo = lookupLevel numId lvl num
-         return $ ListItem parstyle numId lvl levelInfo parparts
-       Nothing -> return $ Paragraph parstyle parparts
+      -- Word uses list enumeration for numbered headings, so we only
+      -- want to infer a list from the styles if it is NOT a heading.
+      case pHeading parstyle of
+        Nothing | Just (numId, lvl) <- pNumInfo parstyle -> do
+                    num <- asks envNumbering
+                    let levelInfo = lookupLevel numId lvl num
+                    return $ ListItem parstyle numId lvl levelInfo parparts
+        _ -> return $ Paragraph parstyle parparts
 elemToBodyPart ns element
   | isElem ns "w" "tbl" element = do
     let caption' = findChild (elemName ns "w" "tblPr") element
-- 
cgit v1.2.3


From 28c7617f19c4d6dd69e2aa9c904af13e11e4e639 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Fri, 18 Mar 2016 09:38:26 -0400
Subject: Docx reader: Handle alternate content

Some word functions -- especially graphics -- give various choices for
content so there can be backwards compatibility. This follows the
largely undocumented feature by working through the choices until we
find one that works.

Note that we had to split out the processing of child elems of runs into
a separate function so we can recurse properly. Any processing of an
element *within* a run (other than a plain run) should go into
`childElemToRun`.
---
 src/Text/Pandoc/Readers/Docx/Parse.hs | 51 +++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 14 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs
index cbdd86221..364483929 100644
--- a/src/Text/Pandoc/Readers/Docx/Parse.hs
+++ b/src/Text/Pandoc/Readers/Docx/Parse.hs
@@ -717,36 +717,58 @@ elemToExtent drawingElem =
       getDim at = findElement (QName "extent" (Just wp_ns) (Just "wp")) drawingElem
                     >>= findAttr (QName at Nothing Nothing) >>= safeRead
 
-elemToRun :: NameSpaces -> Element -> D Run
-elemToRun ns element
-  | isElem ns "w" "r" element
-  , Just drawingElem <- findChild (elemName ns "w" "drawing") element =
+
+childElemToRun :: NameSpaces -> Element -> D Run
+childElemToRun ns element
+  | isElem ns "w" "drawing" element =
     let a_ns = "http://schemas.openxmlformats.org/drawingml/2006/main"
-        drawing = findElement (QName "blip" (Just a_ns) (Just "a")) drawingElem
+        drawing = findElement (QName "blip" (Just a_ns) (Just "a")) element
                   >>= findAttr (QName "embed" (lookup "r" ns) (Just "r"))
     in
      case drawing of
        Just s -> expandDrawingId s >>=
-                 (\(fp, bs) -> return $ InlineDrawing fp bs $ elemToExtent drawingElem)
+                 (\(fp, bs) -> return $ InlineDrawing fp bs $ elemToExtent element)
        Nothing -> throwError WrongElem
-elemToRun ns element
-  | isElem ns "w" "r" element
-  , Just ref <- findChild (elemName ns "w" "footnoteReference") element
-  , Just fnId <- findAttr (elemName ns "w" "id") ref = do
+childElemToRun ns element
+  | isElem ns "w" "footnoteReference" element
+  , Just fnId <- findAttr (elemName ns "w" "id") element = do
     notes <- asks envNotes
     case lookupFootnote fnId notes of
       Just e -> do bps <- local (\r -> r {envLocation=InFootnote}) $ mapD (elemToBodyPart ns) (elChildren e)
                    return $ Footnote bps
       Nothing  -> return $ Footnote []
-elemToRun ns element
-  | isElem ns "w" "r" element
-  , Just ref <- findChild (elemName ns "w" "endnoteReference") element
-  , Just enId <- findAttr (elemName ns "w" "id") ref = do
+childElemToRun ns element
+  | isElem ns "w" "endnoteReference" element
+  , Just enId <- findAttr (elemName ns "w" "id") element = do
     notes <- asks envNotes
     case lookupEndnote enId notes of
       Just e -> do bps <- local (\r -> r {envLocation=InEndnote}) $ mapD (elemToBodyPart ns) (elChildren e)
                    return $ Endnote bps
       Nothing  -> return $ Endnote []
+childElemToRun _ _ = throwError WrongElem
+
+elemToRun :: NameSpaces -> Element -> D Run
+elemToRun ns element
+  | isElem ns "w" "r" element
+  , Just altCont <- findChild (elemName ns "mc" "AlternateContent") element =
+    do let choices = findChildren (elemName ns "mc" "Choice") altCont
+           choiceChildren = map head $ filter (not . null) $ map elChildren choices
+       outputs <- mapD (childElemToRun ns) choiceChildren
+       case outputs of
+         r : _ -> return r
+         []    -> throwError WrongElem
+elemToRun ns element
+  | isElem ns "w" "r" element
+  , Just drawingElem <- findChild (elemName ns "w" "drawing") element =
+    childElemToRun ns drawingElem
+elemToRun ns element
+  | isElem ns "w" "r" element
+  , Just ref <- findChild (elemName ns "w" "footnoteReference") element =
+    childElemToRun ns ref
+elemToRun ns element
+  | isElem ns "w" "r" element
+  , Just ref <- findChild (elemName ns "w" "endnoteReference") element =
+    childElemToRun ns ref
 elemToRun ns element
   | isElem ns "w" "r" element = do
     runElems <- elemToRunElems ns element
@@ -955,3 +977,4 @@ elemToRunElems _ _ = throwError WrongElem
 
 setFont :: Maybe Font -> ReaderEnv -> ReaderEnv
 setFont f s = s{envFont = f}
+
-- 
cgit v1.2.3


From e821b05125c8b18a1c09a5d4fd62ee7483704bbb Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Fri, 18 Mar 2016 16:16:18 -0700
Subject: LaTeX writer: Avoid double toprule in headerless table with caption.

Closes #2742.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 4e4279ec5..52f525fe7 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -571,18 +571,21 @@ blockToLaTeX (Header level (id',classes,_) lst) = do
 blockToLaTeX (Table caption aligns widths heads rows) = do
   headers <- if all null heads
                 then return empty
-                else ($$ "\\midrule\n") `fmap`
-                      (tableRowToLaTeX True aligns widths) heads
+                else do
+                    contents <- (tableRowToLaTeX True aligns widths) heads
+                    return ("\\toprule" $$ contents $$ "\\midrule")
   let endhead = if all null heads
                    then empty
                    else text "\\endhead"
+  let endfirsthead = if all null heads
+                       then empty
+                       else text "\\endfirsthead"
   captionText <- inlineListToLaTeX caption
   let capt = if isEmpty captionText
                 then empty
-                else text "\\caption" <> braces captionText
-                         <> "\\tabularnewline\n\\toprule\n"
-                         <> headers
-                         <> "\\endfirsthead"
+                else text "\\caption" <> braces captionText <> "\\tabularnewline"
+                         $$ headers
+                         $$ endfirsthead
   rows' <- mapM (tableRowToLaTeX False aligns widths) rows
   let colDescriptors = text $ concat $ map toColDescriptor aligns
   modify $ \s -> s{ stTable = True }
@@ -590,7 +593,7 @@ blockToLaTeX (Table caption aligns widths heads rows) = do
               braces ("@{}" <> colDescriptors <> "@{}")
               -- the @{} removes extra space at beginning and end
          $$ capt
-         $$ "\\toprule"
+         $$ (if all null heads then "\\toprule" else empty)
          $$ headers
          $$ endhead
          $$ vcat rows'
-- 
cgit v1.2.3


From 976e7e2054c2a4c889c3f02b83fdd092513f22b4 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Fri, 18 Mar 2016 16:36:56 -0700
Subject: ConTeXt writer: fix whitespace at line beginning in line blocks.

Add a `\strut` after `\crlf` before space.
Closes #2744, #2745.  Thanks to @c-foster.
This uses the fix suggested by @c-foster.

Mid-line spaces are still not supported, because of limitations
of the Markdown parser.
---
 src/Text/Pandoc/Writers/ConTeXt.hs | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/ConTeXt.hs b/src/Text/Pandoc/Writers/ConTeXt.hs
index 498e2d10f..8d54d62bd 100644
--- a/src/Text/Pandoc/Writers/ConTeXt.hs
+++ b/src/Text/Pandoc/Writers/ConTeXt.hs
@@ -279,7 +279,17 @@ blockListToConTeXt lst = liftM vcat $ mapM blockToConTeXt lst
 -- | Convert list of inline elements to ConTeXt.
 inlineListToConTeXt :: [Inline]  -- ^ Inlines to convert
                     -> State WriterState Doc
-inlineListToConTeXt lst = liftM hcat $ mapM inlineToConTeXt lst
+inlineListToConTeXt lst = liftM hcat $ mapM inlineToConTeXt $ addStruts lst
+  -- We add a \strut after a line break that precedes a space,
+  -- or the space gets swallowed
+  where addStruts (LineBreak : s : xs) | isSpacey s =
+           LineBreak : RawInline (Format "context") "\\strut " : s :
+             addStruts xs
+        addStruts (x:xs) = x : addStruts xs
+        addStruts [] = []
+        isSpacey Space = True
+        isSpacey (Str ('\160':_)) = True
+        isSpacey _ = False
 
 -- | Convert inline element to ConTeXt
 inlineToConTeXt :: Inline    -- ^ Inline to convert
-- 
cgit v1.2.3


From 44f95484a4b4544ef41dab087af92a80fc5996cd Mon Sep 17 00:00:00 2001
From: Mauro Bieg <mb21@users.noreply.github.com>
Date: Fri, 19 Feb 2016 10:10:12 +0100
Subject: LaTeX Writer: fix polyglossia to babel env mapping

allow for optional argument in square brackets, closes #2728
---
 src/Text/Pandoc/Writers/LaTeX.hs | 2 +-
 tests/writers-lang-and-dir.latex | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 0f47132b3..3f7c28e81 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -223,7 +223,7 @@ pandocToLaTeX options (Pandoc meta blocks) = do
                       ++ poly ++ "}{##2}}}\n"
                else "\\newcommand{\\text" ++ poly ++ "}[2][]{\\foreignlanguage{"
                       ++ babel ++ "}{#2}}\n" ++
-                    "\\newenvironment{" ++ poly ++ "}[1]{\\begin{otherlanguage}{"
+                    "\\newenvironment{" ++ poly ++ "}[2][]{\\begin{otherlanguage}{"
                       ++ babel ++ "}}{\\end{otherlanguage}}\n"
             )
             -- eliminate duplicates that have same polyglossia name
diff --git a/tests/writers-lang-and-dir.latex b/tests/writers-lang-and-dir.latex
index 056809a5e..db2611cff 100644
--- a/tests/writers-lang-and-dir.latex
+++ b/tests/writers-lang-and-dir.latex
@@ -29,14 +29,14 @@
 \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex
   \usepackage[shorthands=off,ngerman,british,ngerman,spanish,french,main=english]{babel}
   \newcommand{\textgerman}[2][]{\foreignlanguage{ngerman}{#2}}
-  \newenvironment{german}[1]{\begin{otherlanguage}{ngerman}}{\end{otherlanguage}}
+  \newenvironment{german}[2][]{\begin{otherlanguage}{ngerman}}{\end{otherlanguage}}
   \newcommand{\textenglish}[2][]{\foreignlanguage{british}{#2}}
-  \newenvironment{english}[1]{\begin{otherlanguage}{british}}{\end{otherlanguage}}
+  \newenvironment{english}[2][]{\begin{otherlanguage}{british}}{\end{otherlanguage}}
   \let\oritextspanish\textspanish
   \AddBabelHook{spanish}{beforeextras}{\renewcommand{\textspanish}{\oritextspanish}}
   \AddBabelHook{spanish}{afterextras}{\renewcommand{\textspanish}[2][]{\foreignlanguage{spanish}{##2}}}
   \newcommand{\textfrench}[2][]{\foreignlanguage{french}{#2}}
-  \newenvironment{french}[1]{\begin{otherlanguage}{french}}{\end{otherlanguage}}
+  \newenvironment{french}[2][]{\begin{otherlanguage}{french}}{\end{otherlanguage}}
 \else
   \usepackage{polyglossia}
   \setmainlanguage[]{english}
-- 
cgit v1.2.3


From b1ffdf3b01c5acec18ee5f776841f478eb7b7810 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Tue, 22 Mar 2016 16:56:10 -0700
Subject: Fixed bug in Markdown raw HTML parsing.

This was a regression, with the rewrite of `htmlInBalanced`
(from `Text.Pandoc.Readers.HTML`) in 1.17.

It caused newlines to be omitted in raw HTML blocks.

Closes #2804.
---
 src/Text/Pandoc/Readers/HTML.hs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index 959a2d16f..fb936cff7 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -939,7 +939,7 @@ htmlInBalanced f = try $ do
                         (TagClose _ : TagPosition er ec : _) -> do
                           let ls = er - sr
                           let cs = ec - sc
-                          lscontents <- concat <$> count ls anyLine
+                          lscontents <- unlines <$> count ls anyLine
                           cscontents <- count cs anyChar
                           (_,closetag) <- htmlTag (~== TagClose tn)
                           return (lscontents ++ cscontents ++ closetag)
-- 
cgit v1.2.3


From 499985c1a30cb711b1dcf9ae80ccb876ae31f0ec Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Tue, 22 Mar 2016 17:20:39 -0700
Subject: Updated copyright dates to include 2016.

---
 pandoc.cabal                     | 2 +-
 src/Text/Pandoc.hs               | 4 ++--
 src/Text/Pandoc/Asciify.hs       | 4 ++--
 src/Text/Pandoc/Error.hs         | 4 ++--
 src/Text/Pandoc/Highlighting.hs  | 4 ++--
 src/Text/Pandoc/ImageSize.hs     | 4 ++--
 src/Text/Pandoc/MIME.hs          | 4 ++--
 src/Text/Pandoc/Options.hs       | 4 ++--
 src/Text/Pandoc/PDF.hs           | 4 ++--
 src/Text/Pandoc/Parsing.hs       | 4 ++--
 src/Text/Pandoc/Pretty.hs        | 4 ++--
 src/Text/Pandoc/Process.hs       | 4 ++--
 src/Text/Pandoc/SelfContained.hs | 4 ++--
 src/Text/Pandoc/Shared.hs        | 4 ++--
 src/Text/Pandoc/Slides.hs        | 4 ++--
 src/Text/Pandoc/Templates.hs     | 4 ++--
 src/Text/Pandoc/UTF8.hs          | 4 ++--
 src/Text/Pandoc/UUID.hs          | 4 ++--
 src/Text/Pandoc/XML.hs           | 4 ++--
 19 files changed, 37 insertions(+), 37 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/pandoc.cabal b/pandoc.cabal
index e91d007a9..08f1950b4 100644
--- a/pandoc.cabal
+++ b/pandoc.cabal
@@ -4,7 +4,7 @@ Cabal-Version:   >= 1.10
 Build-Type:      Custom
 License:         GPL
 License-File:    COPYING
-Copyright:       (c) 2006-2015 John MacFarlane
+Copyright:       (c) 2006-2016 John MacFarlane
 Author:          John MacFarlane <jgm@berkeley.edu>
 Maintainer:      John MacFarlane <jgm@berkeley.edu>
 Bug-Reports:     https://github.com/jgm/pandoc/issues
diff --git a/src/Text/Pandoc.hs b/src/Text/Pandoc.hs
index d59ee7846..b67a53f5b 100644
--- a/src/Text/Pandoc.hs
+++ b/src/Text/Pandoc.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE ScopedTypeVariables, FlexibleInstances #-}
 {-
-Copyright (C) 2006-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2006-2016 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
@@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc
-   Copyright   : Copyright (C) 2006-2015 John MacFarlane
+   Copyright   : Copyright (C) 2006-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Asciify.hs b/src/Text/Pandoc/Asciify.hs
index c183458e4..8eb1ba663 100644
--- a/src/Text/Pandoc/Asciify.hs
+++ b/src/Text/Pandoc/Asciify.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2013-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2013-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Asciify
-   Copyright   : Copyright (C) 2013-2015 John MacFarlane
+   Copyright   : Copyright (C) 2013-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Error.hs b/src/Text/Pandoc/Error.hs
index 0a4e08175..792098b35 100644
--- a/src/Text/Pandoc/Error.hs
+++ b/src/Text/Pandoc/Error.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE DeriveDataTypeable, DeriveGeneric #-}
 {-
-Copyright (C) 2006-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2006-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 -}
 {- |
    Module      : Text.Pandoc.Error
-   Copyright   : Copyright (C) 2006-2015 John MacFarlane
+   Copyright   : Copyright (C) 2006-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Highlighting.hs b/src/Text/Pandoc/Highlighting.hs
index ecfef1832..1b9e92ae2 100644
--- a/src/Text/Pandoc/Highlighting.hs
+++ b/src/Text/Pandoc/Highlighting.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2008-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2008-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Highlighting
-   Copyright   : Copyright (C) 2008-2015 John MacFarlane
+   Copyright   : Copyright (C) 2008-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/ImageSize.hs b/src/Text/Pandoc/ImageSize.hs
index 571fdd665..90dfbb5fb 100644
--- a/src/Text/Pandoc/ImageSize.hs
+++ b/src/Text/Pandoc/ImageSize.hs
@@ -1,7 +1,7 @@
 {-# LANGUAGE OverloadedStrings, ScopedTypeVariables, CPP #-}
 {-# OPTIONS_GHC -fno-warn-type-defaults #-}
 {-
-  Copyright (C) 2011-2015 John MacFarlane <jgm@berkeley.edu>
+  Copyright (C) 2011-2016 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
@@ -20,7 +20,7 @@
 
 {- |
 Module      : Text.Pandoc.ImageSize
-Copyright   : Copyright (C) 2011-2015 John MacFarlane
+Copyright   : Copyright (C) 2011-2016 John MacFarlane
 License     : GNU GPL, version 2 or above
 
 Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/MIME.hs b/src/Text/Pandoc/MIME.hs
index 6fd9ac373..1164e04b3 100644
--- a/src/Text/Pandoc/MIME.hs
+++ b/src/Text/Pandoc/MIME.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2011-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2011-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.MIME
-   Copyright   : Copyright (C) 2011-2015 John MacFarlane
+   Copyright   : Copyright (C) 2011-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index b5736c63d..171210962 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE DeriveDataTypeable, DeriveGeneric #-}
 {-
-Copyright (C) 2012-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2012-2016 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
@@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Options
-   Copyright   : Copyright (C) 2012-2015 John MacFarlane
+   Copyright   : Copyright (C) 2012-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/PDF.hs b/src/Text/Pandoc/PDF.hs
index da4ee4e33..4dbe1f000 100644
--- a/src/Text/Pandoc/PDF.hs
+++ b/src/Text/Pandoc/PDF.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE OverloadedStrings, CPP, ScopedTypeVariables #-}
 {-
-Copyright (C) 2012-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2012-2016 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
@@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.PDF
-   Copyright   : Copyright (C) 2012-2015 John MacFarlane
+   Copyright   : Copyright (C) 2012-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Parsing.hs b/src/Text/Pandoc/Parsing.hs
index 325231846..7bf827019 100644
--- a/src/Text/Pandoc/Parsing.hs
+++ b/src/Text/Pandoc/Parsing.hs
@@ -5,7 +5,7 @@
 , MultiParamTypeClasses
 , FlexibleInstances #-}
 {-
-Copyright (C) 2006-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2006-2016 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
@@ -24,7 +24,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Parsing
-   Copyright   : Copyright (C) 2006-2015 John MacFarlane
+   Copyright   : Copyright (C) 2006-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Pretty.hs b/src/Text/Pandoc/Pretty.hs
index 88b7dd09e..f3ef0ef10 100644
--- a/src/Text/Pandoc/Pretty.hs
+++ b/src/Text/Pandoc/Pretty.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE GeneralizedNewtypeDeriving, CPP #-}
 {-
-Copyright (C) 2010-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2010-2016 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
@@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111(-1)307  USA
 
 {- |
    Module      : Text.Pandoc.Pretty
-   Copyright   : Copyright (C) 2010-2015 John MacFarlane
+   Copyright   : Copyright (C) 2010-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Process.hs b/src/Text/Pandoc/Process.hs
index e5245638d..bc71f1392 100644
--- a/src/Text/Pandoc/Process.hs
+++ b/src/Text/Pandoc/Process.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2013-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2013-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Process
-   Copyright   : Copyright (C) 2013-2015 John MacFarlane
+   Copyright   : Copyright (C) 2013-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/SelfContained.hs b/src/Text/Pandoc/SelfContained.hs
index 390a7a21a..d08d636df 100644
--- a/src/Text/Pandoc/SelfContained.hs
+++ b/src/Text/Pandoc/SelfContained.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE OverloadedStrings #-}
 {-
-Copyright (C) 2011-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2011-2016 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
@@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.SelfContained
-   Copyright   : Copyright (C) 2011-2015 John MacFarlane
+   Copyright   : Copyright (C) 2011-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs
index 075d76847..d6b088338 100644
--- a/src/Text/Pandoc/Shared.hs
+++ b/src/Text/Pandoc/Shared.hs
@@ -2,7 +2,7 @@
     FlexibleContexts, ScopedTypeVariables, PatternGuards,
     ViewPatterns #-}
 {-
-Copyright (C) 2006-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2006-2016 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
@@ -21,7 +21,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Shared
-   Copyright   : Copyright (C) 2006-2015 John MacFarlane
+   Copyright   : Copyright (C) 2006-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Slides.hs b/src/Text/Pandoc/Slides.hs
index 1a27ab5ac..e19dba3e2 100644
--- a/src/Text/Pandoc/Slides.hs
+++ b/src/Text/Pandoc/Slides.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2012-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2012-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Slides
-   Copyright   : Copyright (C) 2012-2015 John MacFarlane
+   Copyright   : Copyright (C) 2012-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/Templates.hs b/src/Text/Pandoc/Templates.hs
index a010433fa..925925872 100644
--- a/src/Text/Pandoc/Templates.hs
+++ b/src/Text/Pandoc/Templates.hs
@@ -1,7 +1,7 @@
 {-# LANGUAGE TypeSynonymInstances, FlexibleInstances, CPP,
     OverloadedStrings, GeneralizedNewtypeDeriving #-}
 {-
-Copyright (C) 2009-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2009-2016 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
@@ -20,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.Templates
-   Copyright   : Copyright (C) 2009-2015 John MacFarlane
+   Copyright   : Copyright (C) 2009-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/UTF8.hs b/src/Text/Pandoc/UTF8.hs
index de3314a0d..87ed5312b 100644
--- a/src/Text/Pandoc/UTF8.hs
+++ b/src/Text/Pandoc/UTF8.hs
@@ -1,6 +1,6 @@
 {-# LANGUAGE CPP #-}
 {-
-Copyright (C) 2010-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2010-2016 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
@@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.UTF8
-   Copyright   : Copyright (C) 2010-2015 John MacFarlane
+   Copyright   : Copyright (C) 2010-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/UUID.hs b/src/Text/Pandoc/UUID.hs
index 463be044c..5d05fa303 100644
--- a/src/Text/Pandoc/UUID.hs
+++ b/src/Text/Pandoc/UUID.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2010-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2010-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.UUID
-   Copyright   : Copyright (C) 2010-2015 John MacFarlane
+   Copyright   : Copyright (C) 2010-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
diff --git a/src/Text/Pandoc/XML.hs b/src/Text/Pandoc/XML.hs
index 70d8efba6..4cc2141b4 100644
--- a/src/Text/Pandoc/XML.hs
+++ b/src/Text/Pandoc/XML.hs
@@ -1,5 +1,5 @@
 {-
-Copyright (C) 2006-2015 John MacFarlane <jgm@berkeley.edu>
+Copyright (C) 2006-2016 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
@@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
 {- |
    Module      : Text.Pandoc.XML
-   Copyright   : Copyright (C) 2006-2015 John MacFarlane
+   Copyright   : Copyright (C) 2006-2016 John MacFarlane
    License     : GNU GPL, version 2 or above
 
    Maintainer  : John MacFarlane <jgm@berkeley.edu>
-- 
cgit v1.2.3


From bb6897a13ed8ec9fd2d15930bd013bc7b315120e Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Thu, 24 Mar 2016 09:41:45 -0700
Subject: LaTeX writer: Fixed position of label in figures.

Partially addresses #2813.

This isn't perfect, because now the hypertarget is in the
wrong place -- when you link to the figure, the screen
is positioned with the caption at the top, and most of
the figure off screen.

So this needs a bit more tweaking.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 0f47132b3..a63aca1c5 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -415,10 +415,10 @@ blockToLaTeX (Para [Image attr@(ident, _, _) txt (src,'f':'i':'g':':':tit)]) = d
                    else brackets <$> inlineListToLaTeX (walk deNote txt)
   img <- inlineToLaTeX (Image attr txt (src,tit))
   let footnotes = notesToLaTeX notes
-  figure <- refLabel ident $ cr <>
+  caption <- refLabel ident ("\\caption" <> captForLof <> braces capt)
+  let figure = cr <>
             "\\begin{figure}[htbp]" $$ "\\centering" $$ img $$
-            ("\\caption" <> captForLof <> braces capt) $$
-            "\\end{figure}" <> cr
+            caption $$ "\\end{figure}" <> cr
   return $ if inNote
               -- can't have figures in notes
               then "\\begin{center}" $$ img $+$ capt $$ "\\end{center}"
-- 
cgit v1.2.3


From f47b369f37484c153a1d12ca8049c384fb16929b Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Thu, 24 Mar 2016 16:44:33 -0700
Subject: LaTeX writer:  better positioning for hypertarget in figures.

Closes #2813.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 39 +++++++++++++++++++++++----------------
 1 file changed, 23 insertions(+), 16 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index a63aca1c5..dd5b14424 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -409,16 +409,20 @@ blockToLaTeX (Para [Image attr@(ident, _, _) txt (src,'f':'i':'g':':':tit)]) = d
   capt <- inlineListToLaTeX txt
   notes <- gets stNotes
   modify $ \st -> st{ stInMinipage = False, stNotes = [] }
+  ref <- text `fmap` toLabel ident
+  internalLinks <- gets stInternalLinks
+
   -- We can't have footnotes in the list of figures, so remove them:
   captForLof <- if null notes
                    then return empty
                    else brackets <$> inlineListToLaTeX (walk deNote txt)
   img <- inlineToLaTeX (Image attr txt (src,tit))
   let footnotes = notesToLaTeX notes
-  caption <- refLabel ident ("\\caption" <> captForLof <> braces capt)
-  let figure = cr <>
+  lab <- labelFor ident
+  let caption = "\\caption" <> captForLof <> braces capt <> lab
+  figure <- hypertarget ident (cr <>
             "\\begin{figure}[htbp]" $$ "\\centering" $$ img $$
-            caption $$ "\\end{figure}" <> cr
+            caption $$ "\\end{figure}" <> cr)
   return $ if inNote
               -- can't have figures in notes
               then "\\begin{center}" $$ img $+$ capt $$ "\\end{center}"
@@ -755,7 +759,8 @@ sectionHeader unnumbered ident level lst = do
                   -- needed for \paragraph, \subparagraph in quote environment
                   -- see http://tex.stackexchange.com/questions/169830/
                   else empty
-  stuffing' <- refLabel ident $ text ('\\':sectionType) <> stuffing
+  lab <- labelFor ident
+  stuffing' <- hypertarget ident $ text ('\\':sectionType) <> stuffing <> lab
   return $ if level' > 5
               then txt
               else prefix $$ stuffing'
@@ -765,20 +770,22 @@ sectionHeader unnumbered ident level lst = do
                                 braces txtNoNotes
                          else empty
 
--- | Append label to x and wrap in hypertarget
-refLabel :: String -> Doc -> State WriterState Doc
-refLabel ident x = do
+hypertarget :: String -> Doc -> State WriterState Doc
+hypertarget ident x = do
   ref <- text `fmap` toLabel ident
   internalLinks <- gets stInternalLinks
-  let hypertarget y = if ident `elem` internalLinks
-                         then text "\\hypertarget"
-                                <> braces ref
-                                <> braces y
-                         else y
-      label = if null ident
-                 then empty
-                 else text "\\label" <> braces ref
-  return $ hypertarget $ x <> label
+  return $
+    if ident `elem` internalLinks
+       then text "\\hypertarget"
+              <> braces ref
+              <> braces x
+       else x
+
+labelFor :: String -> State WriterState Doc
+labelFor ""    = return empty
+labelFor ident = do
+  ref <- text `fmap` toLabel ident
+  return $ text "\\label" <> braces ref
 
 -- | Convert list of inline elements to LaTeX.
 inlineListToLaTeX :: [Inline]  -- ^ Inlines to convert
-- 
cgit v1.2.3


From 9742c486478e414b495670377923c44c840b9e01 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Fri, 25 Mar 2016 09:05:38 -0700
Subject: Removed two superfluous lines.

---
 src/Text/Pandoc/Writers/LaTeX.hs | 2 --
 1 file changed, 2 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index dd5b14424..693de93fa 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -409,8 +409,6 @@ blockToLaTeX (Para [Image attr@(ident, _, _) txt (src,'f':'i':'g':':':tit)]) = d
   capt <- inlineListToLaTeX txt
   notes <- gets stNotes
   modify $ \st -> st{ stInMinipage = False, stNotes = [] }
-  ref <- text `fmap` toLabel ident
-  internalLinks <- gets stInternalLinks
 
   -- We can't have footnotes in the list of figures, so remove them:
   captForLof <- if null notes
-- 
cgit v1.2.3


From f74498cb47d360f58e5c28ad848c94197978cc6e Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sat, 26 Mar 2016 13:14:50 -0700
Subject: EPUB writer: set 'navpage' variable on nav page.

This allows templates to treat it differently.
---
 src/Text/Pandoc/Writers/EPUB.hs | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/EPUB.hs b/src/Text/Pandoc/Writers/EPUB.hs
index 804dbb926..90f502f6f 100644
--- a/src/Text/Pandoc/Writers/EPUB.hs
+++ b/src/Text/Pandoc/Writers/EPUB.hs
@@ -667,7 +667,8 @@ writeEPUB opts doc@(Pandoc meta _) = do
                             ]
                           ]
                      else []
-  let navData = renderHtml $ writeHtml opts'
+  let navData = renderHtml $ writeHtml
+                      opts'{ writerVariables = ("navpage","true"):vars }
             (Pandoc (setMeta "title"
                      (walk removeNote $ fromList $ docTitle' meta) nullMeta)
                (navBlocks ++ landmarks))
-- 
cgit v1.2.3


From 0c37a7c4881fd5018fd5b60588c9899b11bbb86a Mon Sep 17 00:00:00 2001
From: Andrew Dunning <adunning@users.noreply.github.com>
Date: Wed, 30 Mar 2016 14:15:47 +0100
Subject: Recognize `la-x-classic` as Classical Latin.

This allows one to access the hyphenation patterns at <http://mirrors.ctan.org/language/hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-la-x-classic.tex>, using its private language tag.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 693de93fa..9526333c1 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -1153,6 +1153,7 @@ toPolyglossia ("en":"UK":_)        = ("english", "variant=british")
 toPolyglossia ("en":"US":_)        = ("english", "variant=american")
 toPolyglossia ("grc":_)            = ("greek",   "variant=ancient")
 toPolyglossia ("hsb":_)            = ("usorbian", "")
+toPolyglossia ("la":"x-classic":_) = ("latin",   "variant=classic")
 toPolyglossia ("sl":_)             = ("slovenian", "")
 toPolyglossia x                    = (commonFromBcp47 x, "")
 
@@ -1177,6 +1178,7 @@ toBabel ("fr":"CA":_)        = "canadien"
 toBabel ("fra":"aca":_)      = "acadian"
 toBabel ("grc":_)            = "polutonikogreek"
 toBabel ("hsb":_)            = "uppersorbian"
+toBabel ("la":"x-classic":_) = "classiclatin"
 toBabel ("sl":_)             = "slovene"
 toBabel x                    = commonFromBcp47 x
 
-- 
cgit v1.2.3


From 9765ef2ce6abda60be0fa9f50571e752bd42009c Mon Sep 17 00:00:00 2001
From: Andrew Dunning <adunning@users.noreply.github.com>
Date: Thu, 31 Mar 2016 02:51:23 +0100
Subject: LaTeX writer: Add missing languages.

Updates the list from the hyphenation files at <http://mirror.ctan.org/language/hyph-utf8/tex/generic/hyph-utf8/loadhyph/>.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 24 +++++++++++++++++-------
 tests/writers-lang-and-dir.latex |  2 +-
 2 files changed, 18 insertions(+), 8 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 9526333c1..1b3393853 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -1125,7 +1125,7 @@ toPolyglossiaEnv l =
 
 -- Takes a list of the constituents of a BCP 47 language code and
 -- converts it to a Polyglossia (language, options) tuple
--- http://mirrors.concertpass.com/tex-archive/macros/latex/contrib/polyglossia/polyglossia.pdf
+-- http://mirrors.ctan.org/macros/latex/contrib/polyglossia/polyglossia.pdf
 toPolyglossia :: [String] -> (String, String)
 toPolyglossia ("ar":"DZ":_)        = ("arabic", "locale=algeria")
 toPolyglossia ("ar":"IQ":_)        = ("arabic", "locale=mashriq")
@@ -1153,18 +1153,21 @@ toPolyglossia ("en":"UK":_)        = ("english", "variant=british")
 toPolyglossia ("en":"US":_)        = ("english", "variant=american")
 toPolyglossia ("grc":_)            = ("greek",   "variant=ancient")
 toPolyglossia ("hsb":_)            = ("usorbian", "")
-toPolyglossia ("la":"x-classic":_) = ("latin",   "variant=classic")
+toPolyglossia ("la":"x":"classic":_) = ("latin", "variant=classic")
 toPolyglossia ("sl":_)             = ("slovenian", "")
 toPolyglossia x                    = (commonFromBcp47 x, "")
 
 -- Takes a list of the constituents of a BCP 47 language code and
 -- converts it to a Babel language string.
--- http://mirrors.concertpass.com/tex-archive/macros/latex/required/babel/base/babel.pdf
--- Note that the PDF unfortunately does not contain a complete list of supported languages.
+-- http://mirrors.ctan.org/macros/latex/required/babel/base/babel.pdf
+-- List of supported languages (slightly outdated):
+-- http://tug.ctan.org/language/hyph-utf8/doc/generic/hyph-utf8/hyphenation.pdf
 toBabel :: [String] -> String
 toBabel ("de":"1901":_)      = "german"
 toBabel ("de":"AT":"1901":_) = "austrian"
 toBabel ("de":"AT":_)        = "naustrian"
+toBabel ("de":"CH":"1901":_) = "swissgerman"
+toBabel ("de":"CH":_)        = "nswissgerman"
 toBabel ("de":_)             = "ngerman"
 toBabel ("dsb":_)            = "lowersorbian"
 toBabel ("el":"polyton":_)   = "polutonikogreek"
@@ -1178,7 +1181,7 @@ toBabel ("fr":"CA":_)        = "canadien"
 toBabel ("fra":"aca":_)      = "acadian"
 toBabel ("grc":_)            = "polutonikogreek"
 toBabel ("hsb":_)            = "uppersorbian"
-toBabel ("la":"x-classic":_) = "classiclatin"
+toBabel ("la":"x":"classic":_) = "classiclatin"
 toBabel ("sl":_)             = "slovene"
 toBabel x                    = commonFromBcp47 x
 
@@ -1187,12 +1190,15 @@ toBabel x                    = commonFromBcp47 x
 -- https://tools.ietf.org/html/bcp47#section-2.1
 commonFromBcp47 :: [String] -> String
 commonFromBcp47 [] = ""
-commonFromBcp47 ("pt":"BR":_) = "brazilian"
+commonFromBcp47 ("pt":"BR":_)            = "brazilian"
+commonFromBcp47 ("sr":"Cyrl":_)          = "serbianc"
+commonFromBcp47 ("zh":"Latn":"pinyin":_) = "pinyin"
 commonFromBcp47 x = fromIso $ head x
   where
     fromIso "af"  = "afrikaans"
     fromIso "am"  = "amharic"
     fromIso "ar"  = "arabic"
+    fromIso "as"  = "assamese"
     fromIso "ast" = "asturian"
     fromIso "bg"  = "bulgarian"
     fromIso "bn"  = "bengali"
@@ -1216,12 +1222,13 @@ commonFromBcp47 x = fromIso $ head x
     fromIso "fur" = "friulan"
     fromIso "ga"  = "irish"
     fromIso "gd"  = "scottish"
+    fromIso "gez" = "ethiopic"
     fromIso "gl"  = "galician"
     fromIso "he"  = "hebrew"
     fromIso "hi"  = "hindi"
     fromIso "hr"  = "croatian"
-    fromIso "hy"  = "armenian"
     fromIso "hu"  = "magyar"
+    fromIso "hy"  = "armenian"
     fromIso "ia"  = "interlingua"
     fromIso "id"  = "indonesian"
     fromIso "ie"  = "interlingua"
@@ -1229,6 +1236,7 @@ commonFromBcp47 x = fromIso $ head x
     fromIso "it"  = "italian"
     fromIso "jp"  = "japanese"
     fromIso "km"  = "khmer"
+    fromIso "kmr" = "kurmanji"
     fromIso "kn"  = "kannada"
     fromIso "ko"  = "korean"
     fromIso "la"  = "latin"
@@ -1244,6 +1252,7 @@ commonFromBcp47 x = fromIso $ head x
     fromIso "no"  = "norsk"
     fromIso "nqo" = "nko"
     fromIso "oc"  = "occitan"
+    fromIso "pa"  = "panjabi"
     fromIso "pl"  = "polish"
     fromIso "pms" = "piedmontese"
     fromIso "pt"  = "portuguese"
@@ -1260,6 +1269,7 @@ commonFromBcp47 x = fromIso $ head x
     fromIso "ta"  = "tamil"
     fromIso "te"  = "telugu"
     fromIso "th"  = "thai"
+    fromIso "ti"  = "ethiopic"
     fromIso "tk"  = "turkmen"
     fromIso "tr"  = "turkish"
     fromIso "uk"  = "ukrainian"
diff --git a/tests/writers-lang-and-dir.latex b/tests/writers-lang-and-dir.latex
index 056809a5e..dbe58ebf0 100644
--- a/tests/writers-lang-and-dir.latex
+++ b/tests/writers-lang-and-dir.latex
@@ -27,7 +27,7 @@
             breaklinks=true}
 \urlstyle{same}  % don't use monospace font for urls
 \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex
-  \usepackage[shorthands=off,ngerman,british,ngerman,spanish,french,main=english]{babel}
+  \usepackage[shorthands=off,ngerman,british,nswissgerman,spanish,french,main=english]{babel}
   \newcommand{\textgerman}[2][]{\foreignlanguage{ngerman}{#2}}
   \newenvironment{german}[1]{\begin{otherlanguage}{ngerman}}{\end{otherlanguage}}
   \newcommand{\textenglish}[2][]{\foreignlanguage{british}{#2}}
-- 
cgit v1.2.3


From 773bbb8fc73a3b6598188dbae64a841eb6680b38 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sun, 10 Apr 2016 07:39:36 -0700
Subject: Markdown + HTML readers:  be more forgiving about unescaped &.

We are now more forgiving about parsing invalid HTML with
unescaped `&` as raw HTML.  (Previously any unescaped `&`
would cause pandoc not to recognize the string as raw HTML.)

Closes #2410.
---
 src/Text/Pandoc/Readers/HTML.hs | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index fb936cff7..8ee5da543 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -971,11 +971,20 @@ htmlTag :: Monad m
 htmlTag f = try $ do
   lookAhead (char '<')
   inp <- getInput
-  let (next : rest) = canonicalizeTags $ parseTagsOptions
-                       parseOptions{ optTagWarning = True } inp
+  let (next : _) = canonicalizeTags $ parseTagsOptions
+                       parseOptions{ optTagWarning = False } inp
   guard $ f next
+  let handleTag tagname = do
+       -- <www.boe.es/buscar/act.php?id=BOE-A-1996-8930#a66>
+       -- should NOT be parsed as an HTML tag, see #2277
+       guard $ not ('.' `elem` tagname)
+       -- <https://example.org> should NOT be a tag either.
+       -- tagsoup will parse it as TagOpen "https:" [("example.org","")]
+       guard $ not (null tagname)
+       guard $ last tagname /= ':'
+       rendered <- manyTill anyChar (char '>')
+       return (next, rendered ++ ">")
   case next of
-       TagWarning _ -> fail "encountered TagWarning"
        TagComment s
          | "<!--" `isPrefixOf` inp -> do
           count (length s + 4) anyChar
@@ -983,13 +992,9 @@ htmlTag f = try $ do
           char '>'
           return (next, "<!--" ++ s ++ "-->")
          | otherwise -> fail "bogus comment mode, HTML5 parse error"
-       _            -> do
-          -- we get a TagWarning on things like
-          -- <www.boe.es/buscar/act.php?id=BOE-A-1996-8930#a66>
-          -- which should NOT be parsed as an HTML tag, see #2277
-          guard $ not $ hasTagWarning rest
-          rendered <- manyTill anyChar (char '>')
-          return (next, rendered ++ ">")
+       TagOpen tagname _attr -> handleTag tagname
+       TagClose tagname -> handleTag tagname
+       _ -> mzero
 
 mkAttr :: [(String, String)] -> Attr
 mkAttr attr = (attribsId, attribsClasses, attribsKV)
-- 
cgit v1.2.3


From 4b49f923cbfd74287742f7d9634406580d48515b Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sun, 10 Apr 2016 09:13:53 -0700
Subject: Markdown reader: Fix pandoc title blocks with lines ending in 2
 spaces.

Closes #2799.

Also added -s to markdown-reader-more test.
---
 src/Text/Pandoc/Readers/Markdown.hs | 42 ++++++++++++++++++++-----------------
 tests/Tests/Old.hs                  |  2 +-
 tests/markdown-reader-more.native   |  4 ++--
 3 files changed, 26 insertions(+), 22 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index b5d175453..e43714526 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -122,9 +122,6 @@ inList = do
   ctx <- stateParserContext <$> getState
   guard (ctx == ListItemState)
 
-isNull :: F Inlines -> Bool
-isNull ils = B.isNull $ runF ils def
-
 spnl :: Parser [Char] st ()
 spnl = try $ do
   skipSpaces
@@ -188,31 +185,38 @@ charsInBalancedBrackets openBrackets =
 -- document structure
 --
 
-titleLine :: MarkdownParser (F Inlines)
-titleLine = try $ do
+rawTitleBlockLine :: MarkdownParser String
+rawTitleBlockLine = do
   char '%'
   skipSpaces
-  res <- many $ (notFollowedBy newline >> inline)
-             <|> try (endline >> whitespace)
-  newline
+  first <- anyLine
+  rest <- many $ try $ do spaceChar
+                          notFollowedBy blankline
+                          skipSpaces
+                          anyLine
+  return $ trim $ unlines (first:rest)
+
+titleLine :: MarkdownParser (F Inlines)
+titleLine = try $ do
+  raw <- rawTitleBlockLine
+  res <- parseFromString (many inline) raw
   return $ trimInlinesF $ mconcat res
 
 authorsLine :: MarkdownParser (F [Inlines])
 authorsLine = try $ do
-  char '%'
-  skipSpaces
-  authors <- sepEndBy (many (notFollowedBy (satisfy $ \c ->
-                                c == ';' || c == '\n') >> inline))
-                       (char ';' <|>
-                        try (newline >> notFollowedBy blankline >> spaceChar))
-  newline
-  return $ sequence $ filter (not . isNull) $ map (trimInlinesF . mconcat) authors
+  raw <- rawTitleBlockLine
+  let sep = (char ';' <* spaces) <|> newline
+  let pAuthors = sepEndBy
+            (trimInlinesF . mconcat <$> many
+                 (try $ notFollowedBy sep >> inline))
+            sep
+  sequence <$> parseFromString pAuthors raw
 
 dateLine :: MarkdownParser (F Inlines)
 dateLine = try $ do
-  char '%'
-  skipSpaces
-  trimInlinesF . mconcat <$> manyTill inline newline
+  raw <- rawTitleBlockLine
+  res <- parseFromString (many inline) raw
+  return $ trimInlinesF $ mconcat res
 
 titleBlock :: MarkdownParser ()
 titleBlock = pandocTitleBlock <|> mmdTitleBlock
diff --git a/tests/Tests/Old.hs b/tests/Tests/Old.hs
index 36bb3398e..b292b1f11 100644
--- a/tests/Tests/Old.hs
+++ b/tests/Tests/Old.hs
@@ -57,7 +57,7 @@ tests = [ testGroup "markdown"
               "tables.txt" "tables.native"
             , test "pipe tables" ["-r", "markdown", "-w", "native", "--columns=80"]
               "pipe-tables.txt" "pipe-tables.native"
-            , test "more" ["-r", "markdown", "-w", "native", "-S"]
+            , test "more" ["-r", "markdown", "-w", "native", "-s", "-S"]
               "markdown-reader-more.txt" "markdown-reader-more.native"
             , lhsReaderTest "markdown+lhs"
             ]
diff --git a/tests/markdown-reader-more.native b/tests/markdown-reader-more.native
index 0148e9394..c38ffe038 100644
--- a/tests/markdown-reader-more.native
+++ b/tests/markdown-reader-more.native
@@ -1,5 +1,5 @@
-[Para [Str "spanning",Space,Str "multiple",Space,Str "lines",SoftBreak,Str "%",Space,Str "Author",Space,Str "One",SoftBreak,Str "Author",Space,Str "Two;",Space,Str "Author",Space,Str "Three;",SoftBreak,Str "Author",Space,Str "Four"]
-,Header 1 ("additional-markdown-reader-tests",[],[]) [Str "Additional",Space,Str "markdown",Space,Str "reader",Space,Str "tests"]
+Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "Author",Space,Str "One"],MetaInlines [Str "Author",Space,Str "Two"],MetaInlines [Str "Author",Space,Str "Three"],MetaInlines [Str "Author",Space,Str "Four"]]),("title",MetaInlines [Str "Title",SoftBreak,Str "spanning",Space,Str "multiple",Space,Str "lines"])]})
+[Header 1 ("additional-markdown-reader-tests",[],[]) [Str "Additional",Space,Str "markdown",Space,Str "reader",Space,Str "tests"]
 ,Header 2 ("blank-line-before-url-in-link-reference",[],[]) [Str "Blank",Space,Str "line",Space,Str "before",Space,Str "URL",Space,Str "in",Space,Str "link",Space,Str "reference"]
 ,Para [Link ("",[],[]) [Str "foo"] ("/url",""),Space,Str "and",Space,Link ("",[],[]) [Str "bar"] ("/url","title")]
 ,Header 2 ("raw-context-environments",[],[]) [Str "Raw",Space,Str "ConTeXt",Space,Str "environments"]
-- 
cgit v1.2.3


From a385ee1d4fad05eb2cd45a9206182e90cd856012 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Fri, 15 Apr 2016 14:09:18 -0400
Subject: Docx Reader: parse `moveTo` and `moveFrom`

`moveTo` and `moveFrom` are track-changes tags that are used when a
block of text is moved in the document. We now recognize these tags and
treat them the same as `insert` and `delete`, respectively. So,
`--track-changes=accept` will show the moved version, while
`--track-changes=reject` will show the original version.
---
 src/Text/Pandoc/Readers/Docx/Parse.hs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs
index 364483929..7265ef8dd 100644
--- a/src/Text/Pandoc/Readers/Docx/Parse.hs
+++ b/src/Text/Pandoc/Readers/Docx/Parse.hs
@@ -661,14 +661,14 @@ elemToParPart ns element
   | isElem ns "w" "r" element =
     elemToRun ns element >>= (\r -> return $ PlainRun r)
 elemToParPart ns element
-  | isElem ns "w" "ins" element
+  | isElem ns "w" "ins" element || isElem ns "w" "moveTo" element
   , Just cId <- findAttr (elemName ns "w" "id") element
   , Just cAuthor <- findAttr (elemName ns "w" "author") element
   , Just cDate <- findAttr (elemName ns "w" "date") element = do
     runs <- mapD (elemToRun ns) (elChildren element)
     return $ Insertion cId cAuthor cDate runs
 elemToParPart ns element
-  | isElem ns "w" "del" element
+  | isElem ns "w" "del" element || isElem ns "w" "moveFrom" element
   , Just cId <- findAttr (elemName ns "w" "id") element
   , Just cAuthor <- findAttr (elemName ns "w" "author") element
   , Just cDate <- findAttr (elemName ns "w" "date") element = do
-- 
cgit v1.2.3


From 1bfe39e24cb58c361a05f419ef9a4a5263f558f6 Mon Sep 17 00:00:00 2001
From: Emanuel Evans <mail@emanuel.industries>
Date: Sun, 24 Apr 2016 21:58:53 -0700
Subject: Ignore leading space in org code blocks

Fixes #2862

Also fix up tab handling for leading whitespace in code blocks.
---
 src/Text/Pandoc/Readers/Org.hs | 24 ++++++++++++++++++++----
 tests/Tests/Readers/Org.hs     | 27 +++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index 7dd611be3..5e98be31d 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -391,6 +391,9 @@ lookupBlockAttribute key =
 
 type BlockProperties = (Int, String)  -- (Indentation, Block-Type)
 
+updateIndent :: BlockProperties -> Int -> BlockProperties
+updateIndent (_, blkType) indent = (indent, blkType)
+
 orgBlock :: OrgParser (F Blocks)
 orgBlock = try $ do
   blockProp@(_, blkType) <- blockHeaderStart
@@ -407,11 +410,23 @@ orgBlock = try $ do
       _         -> withParsed (fmap $ divWithClass blkType)
 
 blockHeaderStart :: OrgParser (Int, String)
-blockHeaderStart = try $ (,) <$> indent <*> blockType
+blockHeaderStart = try $ (,) <$> indentation <*> blockType
  where
-  indent    = length      <$> many spaceChar
   blockType = map toLower <$> (stringAnyCase "#+begin_" *> orgArgWord)
 
+indentation :: OrgParser Int
+indentation = try $ do
+  tabStop  <- getOption readerTabStop
+  s        <- many spaceChar
+  return $ spaceLength tabStop s
+
+spaceLength :: Int -> String -> Int
+spaceLength tabStop s = (sum . map charLen) s
+ where
+  charLen ' '  = 1
+  charLen '\t' = tabStop
+  charLen _    = 0
+
 withRaw'   :: (String   -> F Blocks) -> BlockProperties -> OrgParser (F Blocks)
 withRaw'   f blockProp = (ignHeaders *> (f <$> rawBlockContent blockProp))
 
@@ -450,7 +465,8 @@ codeBlock blkProp = do
   skipSpaces
   (classes, kv)     <- codeHeaderArgs <|> (mempty <$ ignHeaders)
   id'               <- fromMaybe "" <$> lookupBlockAttribute "name"
-  content           <- rawBlockContent blkProp
+  leadingIndent     <- lookAhead indentation
+  content           <- rawBlockContent (updateIndent blkProp leadingIndent)
   resultsContent    <- followingResultsBlock
   let includeCode    = exportsCode kv
   let includeResults = exportsResults kv
@@ -472,7 +488,7 @@ rawBlockContent (indent, blockType) = try $
   unlines . map commaEscaped <$> manyTill indentedLine blockEnder
  where
    indentedLine = try $ ("" <$ blankline) <|> (indentWith indent *> anyLine)
-   blockEnder = try $ indentWith indent *> stringAnyCase ("#+end_" <> blockType)
+   blockEnder = try $ skipSpaces *> stringAnyCase ("#+end_" <> blockType)
 
 parsedBlockContent :: BlockProperties -> OrgParser (F Blocks)
 parsedBlockContent blkProps = try $ do
diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs
index b095ac60a..bb9b37d13 100644
--- a/tests/Tests/Readers/Org.hs
+++ b/tests/Tests/Readers/Org.hs
@@ -1054,6 +1054,33 @@ tests =
                        "  where greeting = \"moin\"\n"
            in codeBlockWith attr' code'
 
+      , "Source block with indented code" =:
+           unlines [ "  #+BEGIN_SRC haskell"
+                   , "    main = putStrLn greeting"
+                   , "      where greeting = \"moin\""
+                   , "  #+END_SRC" ] =?>
+           let attr' = ("", ["haskell"], [])
+               code' = "main = putStrLn greeting\n" ++
+                       "  where greeting = \"moin\"\n"
+           in codeBlockWith attr' code'
+
+      , "Source block with tab-indented code" =:
+           unlines [ "\t#+BEGIN_SRC haskell"
+                   , "\tmain = putStrLn greeting"
+                   , "\t  where greeting = \"moin\""
+                   , "\t#+END_SRC" ] =?>
+           let attr' = ("", ["haskell"], [])
+               code' = "main = putStrLn greeting\n" ++
+                       "  where greeting = \"moin\"\n"
+           in codeBlockWith attr' code'
+
+      , "Empty source block" =:
+           unlines [ "  #+BEGIN_SRC haskell"
+                   , "  #+END_SRC" ] =?>
+           let attr' = ("", ["haskell"], [])
+               code' = ""
+           in codeBlockWith attr' code'
+
       , "Source block between paragraphs" =:
            unlines [ "Low German greeting"
                    , "  #+BEGIN_SRC haskell"
-- 
cgit v1.2.3


From 1985164816e49386e256d53d2846c90dc4168fd5 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Tue, 26 Apr 2016 21:50:37 -0700
Subject: LaTeX writer: ignore --incremental unless -t beamer.

Closes #2843.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 9526333c1..5b3283573 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -508,7 +508,8 @@ blockToLaTeX (RawBlock f x)
 blockToLaTeX (BulletList []) = return empty  -- otherwise latex error
 blockToLaTeX (BulletList lst) = do
   incremental <- gets stIncremental
-  let inc = if incremental then "[<+->]" else ""
+  beamer <- writerBeamer `fmap` gets stOptions
+  let inc = if beamer && incremental then "[<+->]" else ""
   items <- mapM listItemToLaTeX lst
   let spacing = if isTightList lst
                    then text "\\tightlist"
-- 
cgit v1.2.3


From 32f1b0a5f14c93271aaf42acaa9d06c4e59c1604 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Wed, 27 Apr 2016 17:25:45 -0700
Subject: Revert "LaTeX writer: Add `\strut` to fix multiline tables"

This reverts commit 4c684561ee0665b014e887ae559b7020e4e9f2d3.

See
https://groups.google.com/d/msg/pandoc-discuss/u6J-_aCProU/UufN3IYRAgAJ

This should fix uneven spacing issues in multiline tables.
---
 src/Text/Pandoc/Writers/LaTeX.hs |  3 +-
 tests/tables.latex               | 90 ++++++++++++++++++++--------------------
 2 files changed, 46 insertions(+), 47 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 948bbedaa..038f27480 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -669,8 +669,7 @@ tableCellToLaTeX header (width, align, blocks) = do
                AlignDefault -> "\\raggedright"
   return $ ("\\begin{minipage}" <> valign <>
             braces (text (printf "%.2f\\columnwidth" width)) <>
-            (halign <> "\\strut" <> cr <> cellContents <> cr) <>
-            "\\strut\\end{minipage}") $$
+            (halign <> cr <> cellContents <> cr) <> "\\end{minipage}") $$
             notesToLaTeX notes
 
 notesToLaTeX :: [Doc] -> Doc
diff --git a/tests/tables.latex b/tests/tables.latex
index 96cbc9579..9f3f97e53 100644
--- a/tests/tables.latex
+++ b/tests/tables.latex
@@ -52,47 +52,47 @@ Multiline table with caption:
 \begin{longtable}[]{@{}clrl@{}}
 \caption{Here's the caption. It may span multiple lines.}\tabularnewline
 \toprule
-\begin{minipage}[b]{0.13\columnwidth}\centering\strut
+\begin{minipage}[b]{0.13\columnwidth}\centering
 Centered Header
-\strut\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright
 Left Aligned
-\strut\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft
 Right Aligned
-\strut\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright
 Default aligned
-\strut\end{minipage}\tabularnewline
+\end{minipage}\tabularnewline
 \midrule
 \endfirsthead
 \toprule
-\begin{minipage}[b]{0.13\columnwidth}\centering\strut
+\begin{minipage}[b]{0.13\columnwidth}\centering
 Centered Header
-\strut\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright
 Left Aligned
-\strut\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft
 Right Aligned
-\strut\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright
 Default aligned
-\strut\end{minipage}\tabularnewline
+\end{minipage}\tabularnewline
 \midrule
 \endhead
-\begin{minipage}[t]{0.13\columnwidth}\centering\strut
+\begin{minipage}[t]{0.13\columnwidth}\centering
 First
-\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright
 row
-\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft
 12.0
-\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright
 Example of a row that spans multiple lines.
-\strut\end{minipage}\tabularnewline
-\begin{minipage}[t]{0.13\columnwidth}\centering\strut
+\end{minipage}\tabularnewline
+\begin{minipage}[t]{0.13\columnwidth}\centering
 Second
-\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright
 row
-\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft
 5.0
-\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright
 Here's another one. Note the blank line between rows.
-\strut\end{minipage}\tabularnewline
+\end{minipage}\tabularnewline
 \bottomrule
 \end{longtable}
 
@@ -100,35 +100,35 @@ Multiline table without caption:
 
 \begin{longtable}[]{@{}clrl@{}}
 \toprule
-\begin{minipage}[b]{0.13\columnwidth}\centering\strut
+\begin{minipage}[b]{0.13\columnwidth}\centering
 Centered Header
-\strut\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright
 Left Aligned
-\strut\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft
 Right Aligned
-\strut\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright
 Default aligned
-\strut\end{minipage}\tabularnewline
+\end{minipage}\tabularnewline
 \midrule
 \endhead
-\begin{minipage}[t]{0.13\columnwidth}\centering\strut
+\begin{minipage}[t]{0.13\columnwidth}\centering
 First
-\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright
 row
-\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft
 12.0
-\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright
 Example of a row that spans multiple lines.
-\strut\end{minipage}\tabularnewline
-\begin{minipage}[t]{0.13\columnwidth}\centering\strut
+\end{minipage}\tabularnewline
+\begin{minipage}[t]{0.13\columnwidth}\centering
 Second
-\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright
 row
-\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft
 5.0
-\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright
 Here's another one. Note the blank line between rows.
-\strut\end{minipage}\tabularnewline
+\end{minipage}\tabularnewline
 \bottomrule
 \end{longtable}
 
@@ -146,23 +146,23 @@ Multiline table without column headers:
 
 \begin{longtable}[]{@{}clrl@{}}
 \toprule
-\begin{minipage}[t]{0.13\columnwidth}\centering\strut
+\begin{minipage}[t]{0.13\columnwidth}\centering
 First
-\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright
 row
-\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft
 12.0
-\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright
 Example of a row that spans multiple lines.
-\strut\end{minipage}\tabularnewline
-\begin{minipage}[t]{0.13\columnwidth}\centering\strut
+\end{minipage}\tabularnewline
+\begin{minipage}[t]{0.13\columnwidth}\centering
 Second
-\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright
 row
-\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut
+\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft
 5.0
-\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut
+\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright
 Here's another one. Note the blank line between rows.
-\strut\end{minipage}\tabularnewline
+\end{minipage}\tabularnewline
 \bottomrule
 \end{longtable}
-- 
cgit v1.2.3


From 271cb4d8457b2252cddc76a476f3681e8b2a1486 Mon Sep 17 00:00:00 2001
From: Ivo Clarysse <ivo@bcdevices.com>
Date: Fri, 29 Apr 2016 14:00:46 -0700
Subject: Add docbook5 writer support

---
 src/Text/Pandoc.hs                 |    2 +
 src/Text/Pandoc/Options.hs         |    2 +
 src/Text/Pandoc/Writers/Docbook.hs |   10 +-
 tests/Tests/Old.hs                 |    3 +
 tests/tables.docbook5              |  432 +++++++++++
 tests/writer.docbook5              | 1394 ++++++++++++++++++++++++++++++++++++
 6 files changed, 1840 insertions(+), 3 deletions(-)
 create mode 100644 tests/tables.docbook5
 create mode 100644 tests/writer.docbook5

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc.hs b/src/Text/Pandoc.hs
index b67a53f5b..58f666939 100644
--- a/src/Text/Pandoc.hs
+++ b/src/Text/Pandoc.hs
@@ -291,6 +291,8 @@ writers = [
      writeHtmlString o{ writerSlideVariant = RevealJsSlides
                       , writerHtml5 = True })
   ,("docbook"      , PureStringWriter writeDocbook)
+  ,("docbook5"     , PureStringWriter $ \o ->
+     writeDocbook o{ writerDocBook5 = True })
   ,("opml"         , PureStringWriter writeOPML)
   ,("opendocument" , PureStringWriter writeOpenDocument)
   ,("latex"        , PureStringWriter writeLaTeX)
diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index 171210962..fcf6537c0 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -357,6 +357,7 @@ data WriterOptions = WriterOptions
   , writerSourceURL        :: Maybe String  -- ^ Absolute URL + directory of 1st source file
   , writerUserDataDir      :: Maybe FilePath -- ^ Path of user data directory
   , writerCiteMethod       :: CiteMethod -- ^ How to print cites
+  , writerDocBook5         :: Bool       -- ^ Produce DocBook5
   , writerHtml5            :: Bool       -- ^ Produce HTML5
   , writerHtmlQTags        :: Bool       -- ^ Use @<q>@ tags for quotes in HTML
   , writerBeamer           :: Bool       -- ^ Produce beamer LaTeX slide show
@@ -403,6 +404,7 @@ instance Default WriterOptions where
                       , writerSourceURL        = Nothing
                       , writerUserDataDir      = Nothing
                       , writerCiteMethod       = Citeproc
+                      , writerDocBook5         = False
                       , writerHtml5            = False
                       , writerHtmlQTags        = False
                       , writerBeamer           = False
diff --git a/src/Text/Pandoc/Writers/Docbook.hs b/src/Text/Pandoc/Writers/Docbook.hs
index 2aaebf99f..5528714a2 100644
--- a/src/Text/Pandoc/Writers/Docbook.hs
+++ b/src/Text/Pandoc/Writers/Docbook.hs
@@ -112,7 +112,9 @@ elementToDocbook opts lvl (Sec _ _num (id',_,_) title elements) =
                     else elements
       tag = case lvl of
                  n | n == 0           -> "chapter"
-                   | n >= 1 && n <= 5 -> "sect" ++ show n
+                   | n >= 1 && n <= 5 -> if writerDocBook5 opts
+                                              then "section"
+                                              else "sect" ++ show n
                    | otherwise        -> "simplesect"
   in  inTags True tag [("id", writerIdentifierPrefix opts ++ id') |
                        not (null id')] $
@@ -227,9 +229,11 @@ blockToDocbook opts (OrderedList (start, numstyle, _) (first:rest)) =
 blockToDocbook opts (DefinitionList lst) =
   let attribs = [("spacing", "compact") | isTightList $ concatMap snd lst]
   in  inTags True "variablelist" attribs $ deflistItemsToDocbook opts lst
-blockToDocbook _ (RawBlock f str)
+blockToDocbook opts (RawBlock f str)
   | f == "docbook" = text str -- raw XML block
-  | f == "html"    = text str -- allow html for backwards compatibility
+  | 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) =
diff --git a/tests/Tests/Old.hs b/tests/Tests/Old.hs
index b292b1f11..4e0eb46a4 100644
--- a/tests/Tests/Old.hs
+++ b/tests/Tests/Old.hs
@@ -108,6 +108,9 @@ tests = [ testGroup "markdown"
           , test "reader" ["-r", "docbook", "-w", "native", "-s"]
             "docbook-xref.docbook" "docbook-xref.native"
           ]
+        , testGroup "docbook5"
+          [ testGroup "writer" $ writerTests "docbook5"
+          ]
         , testGroup "native"
           [ testGroup "writer" $ writerTests "native"
           , test "reader" ["-r", "native", "-w", "native", "-s"]
diff --git a/tests/tables.docbook5 b/tests/tables.docbook5
new file mode 100644
index 000000000..6224cf222
--- /dev/null
+++ b/tests/tables.docbook5
@@ -0,0 +1,432 @@
+<para>
+  Simple table with caption:
+</para>
+<table>
+  <title>
+    Demonstration of simple table syntax.
+  </title>
+  <tgroup cols="4">
+    <colspec align="right" />
+    <colspec align="left" />
+    <colspec align="center" />
+    <colspec align="left" />
+    <thead>
+      <row>
+        <entry>
+          Right
+        </entry>
+        <entry>
+          Left
+        </entry>
+        <entry>
+          Center
+        </entry>
+        <entry>
+          Default
+        </entry>
+      </row>
+    </thead>
+    <tbody>
+      <row>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+      </row>
+      <row>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+      </row>
+      <row>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</table>
+<para>
+  Simple table without caption:
+</para>
+<informaltable>
+  <tgroup cols="4">
+    <colspec align="right" />
+    <colspec align="left" />
+    <colspec align="center" />
+    <colspec align="left" />
+    <thead>
+      <row>
+        <entry>
+          Right
+        </entry>
+        <entry>
+          Left
+        </entry>
+        <entry>
+          Center
+        </entry>
+        <entry>
+          Default
+        </entry>
+      </row>
+    </thead>
+    <tbody>
+      <row>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+      </row>
+      <row>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+      </row>
+      <row>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</informaltable>
+<para>
+  Simple table indented two spaces:
+</para>
+<table>
+  <title>
+    Demonstration of simple table syntax.
+  </title>
+  <tgroup cols="4">
+    <colspec align="right" />
+    <colspec align="left" />
+    <colspec align="center" />
+    <colspec align="left" />
+    <thead>
+      <row>
+        <entry>
+          Right
+        </entry>
+        <entry>
+          Left
+        </entry>
+        <entry>
+          Center
+        </entry>
+        <entry>
+          Default
+        </entry>
+      </row>
+    </thead>
+    <tbody>
+      <row>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+      </row>
+      <row>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+      </row>
+      <row>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</table>
+<para>
+  Multiline table with caption:
+</para>
+<table>
+  <title>
+    Here's the caption. It may span multiple lines.
+  </title>
+  <tgroup cols="4">
+    <colspec colwidth="15*" align="center" />
+    <colspec colwidth="13*" align="left" />
+    <colspec colwidth="16*" align="right" />
+    <colspec colwidth="33*" align="left" />
+    <thead>
+      <row>
+        <entry>
+          Centered Header
+        </entry>
+        <entry>
+          Left Aligned
+        </entry>
+        <entry>
+          Right Aligned
+        </entry>
+        <entry>
+          Default aligned
+        </entry>
+      </row>
+    </thead>
+    <tbody>
+      <row>
+        <entry>
+          First
+        </entry>
+        <entry>
+          row
+        </entry>
+        <entry>
+          12.0
+        </entry>
+        <entry>
+          Example of a row that spans multiple lines.
+        </entry>
+      </row>
+      <row>
+        <entry>
+          Second
+        </entry>
+        <entry>
+          row
+        </entry>
+        <entry>
+          5.0
+        </entry>
+        <entry>
+          Here's another one. Note the blank line between rows.
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</table>
+<para>
+  Multiline table without caption:
+</para>
+<informaltable>
+  <tgroup cols="4">
+    <colspec colwidth="15*" align="center" />
+    <colspec colwidth="13*" align="left" />
+    <colspec colwidth="16*" align="right" />
+    <colspec colwidth="33*" align="left" />
+    <thead>
+      <row>
+        <entry>
+          Centered Header
+        </entry>
+        <entry>
+          Left Aligned
+        </entry>
+        <entry>
+          Right Aligned
+        </entry>
+        <entry>
+          Default aligned
+        </entry>
+      </row>
+    </thead>
+    <tbody>
+      <row>
+        <entry>
+          First
+        </entry>
+        <entry>
+          row
+        </entry>
+        <entry>
+          12.0
+        </entry>
+        <entry>
+          Example of a row that spans multiple lines.
+        </entry>
+      </row>
+      <row>
+        <entry>
+          Second
+        </entry>
+        <entry>
+          row
+        </entry>
+        <entry>
+          5.0
+        </entry>
+        <entry>
+          Here's another one. Note the blank line between rows.
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</informaltable>
+<para>
+  Table without column headers:
+</para>
+<informaltable>
+  <tgroup cols="4">
+    <colspec align="right" />
+    <colspec align="left" />
+    <colspec align="center" />
+    <colspec align="right" />
+    <tbody>
+      <row>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+        <entry>
+          12
+        </entry>
+      </row>
+      <row>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+        <entry>
+          123
+        </entry>
+      </row>
+      <row>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+        <entry>
+          1
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</informaltable>
+<para>
+  Multiline table without column headers:
+</para>
+<informaltable>
+  <tgroup cols="4">
+    <colspec colwidth="15*" align="center" />
+    <colspec colwidth="13*" align="left" />
+    <colspec colwidth="16*" align="right" />
+    <colspec colwidth="33*" align="left" />
+    <tbody>
+      <row>
+        <entry>
+          First
+        </entry>
+        <entry>
+          row
+        </entry>
+        <entry>
+          12.0
+        </entry>
+        <entry>
+          Example of a row that spans multiple lines.
+        </entry>
+      </row>
+      <row>
+        <entry>
+          Second
+        </entry>
+        <entry>
+          row
+        </entry>
+        <entry>
+          5.0
+        </entry>
+        <entry>
+          Here's another one. Note the blank line between rows.
+        </entry>
+      </row>
+    </tbody>
+  </tgroup>
+</informaltable>
diff --git a/tests/writer.docbook5 b/tests/writer.docbook5
new file mode 100644
index 000000000..494489ab5
--- /dev/null
+++ b/tests/writer.docbook5
@@ -0,0 +1,1394 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<!DOCTYPE article>
+<article xmlns="http://docbook.org/ns/docbook" version="5.0">
+  <info>
+    <title>Pandoc Test Suite</title>
+    <authorgroup>
+      <author>
+        <firstname>John</firstname>
+        <surname>MacFarlane</surname>
+      </author>
+      <author>
+        <firstname></firstname>
+        <surname>Anonymous</surname>
+      </author>
+    </authorgroup>
+    <date>July 17, 2006</date>
+  </info>
+<para>
+  This is a set of tests for pandoc. Most of them are adapted from John
+  Gruber’s markdown test suite.
+</para>
+<section id="headers">
+  <title>Headers</title>
+  <section id="level-2-with-an-embedded-link">
+    <title>Level 2 with an <ulink url="/url">embedded link</ulink></title>
+    <section id="level-3-with-emphasis">
+      <title>Level 3 with <emphasis>emphasis</emphasis></title>
+      <section id="level-4">
+        <title>Level 4</title>
+        <section id="level-5">
+          <title>Level 5</title>
+          <para>
+          </para>
+        </section>
+      </section>
+    </section>
+  </section>
+</section>
+<section id="level-1">
+  <title>Level 1</title>
+  <section id="level-2-with-emphasis">
+    <title>Level 2 with <emphasis>emphasis</emphasis></title>
+    <section id="level-3">
+      <title>Level 3</title>
+      <para>
+        with no blank line
+      </para>
+    </section>
+  </section>
+  <section id="level-2">
+    <title>Level 2</title>
+    <para>
+      with no blank line
+    </para>
+  </section>
+</section>
+<section id="paragraphs">
+  <title>Paragraphs</title>
+  <para>
+    Here’s a regular paragraph.
+  </para>
+  <para>
+    In Markdown 1.0.0 and earlier. Version 8. This line turns into a list
+    item. Because a hard-wrapped line in the middle of a paragraph looked like
+    a list item.
+  </para>
+  <para>
+    Here’s one with a bullet. * criminey.
+  </para>
+<literallayout>There should be a hard line break
+here.</literallayout>
+</section>
+<section id="block-quotes">
+  <title>Block Quotes</title>
+  <para>
+    E-mail style:
+  </para>
+  <blockquote>
+    <para>
+      This is a block quote. It is pretty short.
+    </para>
+  </blockquote>
+  <blockquote>
+    <para>
+      Code in a block quote:
+    </para>
+    <programlisting>
+sub status {
+    print &quot;working&quot;;
+}
+</programlisting>
+    <para>
+      A list:
+    </para>
+    <orderedlist numeration="arabic" spacing="compact">
+      <listitem>
+        <para>
+          item one
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          item two
+        </para>
+      </listitem>
+    </orderedlist>
+    <para>
+      Nested block quotes:
+    </para>
+    <blockquote>
+      <para>
+        nested
+      </para>
+    </blockquote>
+    <blockquote>
+      <para>
+        nested
+      </para>
+    </blockquote>
+  </blockquote>
+  <para>
+    This should not be a block quote: 2 &gt; 1.
+  </para>
+  <para>
+    And a following paragraph.
+  </para>
+</section>
+<section id="code-blocks">
+  <title>Code Blocks</title>
+  <para>
+    Code:
+  </para>
+  <programlisting>
+---- (should be four hyphens)
+
+sub status {
+    print &quot;working&quot;;
+}
+
+this code block is indented by one tab
+</programlisting>
+  <para>
+    And:
+  </para>
+  <programlisting>
+    this code block is indented by two tabs
+
+These should not be escaped:  \$ \\ \&gt; \[ \{
+</programlisting>
+</section>
+<section id="lists">
+  <title>Lists</title>
+  <section id="unordered">
+    <title>Unordered</title>
+    <para>
+      Asterisks tight:
+    </para>
+    <itemizedlist spacing="compact">
+      <listitem>
+        <para>
+          asterisk 1
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          asterisk 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          asterisk 3
+        </para>
+      </listitem>
+    </itemizedlist>
+    <para>
+      Asterisks loose:
+    </para>
+    <itemizedlist>
+      <listitem>
+        <para>
+          asterisk 1
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          asterisk 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          asterisk 3
+        </para>
+      </listitem>
+    </itemizedlist>
+    <para>
+      Pluses tight:
+    </para>
+    <itemizedlist spacing="compact">
+      <listitem>
+        <para>
+          Plus 1
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Plus 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Plus 3
+        </para>
+      </listitem>
+    </itemizedlist>
+    <para>
+      Pluses loose:
+    </para>
+    <itemizedlist>
+      <listitem>
+        <para>
+          Plus 1
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Plus 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Plus 3
+        </para>
+      </listitem>
+    </itemizedlist>
+    <para>
+      Minuses tight:
+    </para>
+    <itemizedlist spacing="compact">
+      <listitem>
+        <para>
+          Minus 1
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Minus 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Minus 3
+        </para>
+      </listitem>
+    </itemizedlist>
+    <para>
+      Minuses loose:
+    </para>
+    <itemizedlist>
+      <listitem>
+        <para>
+          Minus 1
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Minus 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Minus 3
+        </para>
+      </listitem>
+    </itemizedlist>
+  </section>
+  <section id="ordered">
+    <title>Ordered</title>
+    <para>
+      Tight:
+    </para>
+    <orderedlist numeration="arabic" spacing="compact">
+      <listitem>
+        <para>
+          First
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Second
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Third
+        </para>
+      </listitem>
+    </orderedlist>
+    <para>
+      and:
+    </para>
+    <orderedlist numeration="arabic" spacing="compact">
+      <listitem>
+        <para>
+          One
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Two
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Three
+        </para>
+      </listitem>
+    </orderedlist>
+    <para>
+      Loose using tabs:
+    </para>
+    <orderedlist numeration="arabic">
+      <listitem>
+        <para>
+          First
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Second
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Third
+        </para>
+      </listitem>
+    </orderedlist>
+    <para>
+      and using spaces:
+    </para>
+    <orderedlist numeration="arabic">
+      <listitem>
+        <para>
+          One
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Two
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Three
+        </para>
+      </listitem>
+    </orderedlist>
+    <para>
+      Multiple paragraphs:
+    </para>
+    <orderedlist numeration="arabic">
+      <listitem>
+        <para>
+          Item 1, graf one.
+        </para>
+        <para>
+          Item 1. graf two. The quick brown fox jumped over the lazy dog’s
+          back.
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Item 2.
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Item 3.
+        </para>
+      </listitem>
+    </orderedlist>
+  </section>
+  <section id="nested">
+    <title>Nested</title>
+    <itemizedlist spacing="compact">
+      <listitem>
+        <para>
+          Tab
+        </para>
+        <itemizedlist spacing="compact">
+          <listitem>
+            <para>
+              Tab
+            </para>
+            <itemizedlist spacing="compact">
+              <listitem>
+                <para>
+                  Tab
+                </para>
+              </listitem>
+            </itemizedlist>
+          </listitem>
+        </itemizedlist>
+      </listitem>
+    </itemizedlist>
+    <para>
+      Here’s another:
+    </para>
+    <orderedlist numeration="arabic" spacing="compact">
+      <listitem>
+        <para>
+          First
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Second:
+        </para>
+        <itemizedlist spacing="compact">
+          <listitem>
+            <para>
+              Fee
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              Fie
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              Foe
+            </para>
+          </listitem>
+        </itemizedlist>
+      </listitem>
+      <listitem>
+        <para>
+          Third
+        </para>
+      </listitem>
+    </orderedlist>
+    <para>
+      Same thing but with paragraphs:
+    </para>
+    <orderedlist numeration="arabic">
+      <listitem>
+        <para>
+          First
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          Second:
+        </para>
+        <itemizedlist spacing="compact">
+          <listitem>
+            <para>
+              Fee
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              Fie
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              Foe
+            </para>
+          </listitem>
+        </itemizedlist>
+      </listitem>
+      <listitem>
+        <para>
+          Third
+        </para>
+      </listitem>
+    </orderedlist>
+  </section>
+  <section id="tabs-and-spaces">
+    <title>Tabs and spaces</title>
+    <itemizedlist>
+      <listitem>
+        <para>
+          this is a list item indented with tabs
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          this is a list item indented with spaces
+        </para>
+        <itemizedlist>
+          <listitem>
+            <para>
+              this is an example list item indented with tabs
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              this is an example list item indented with spaces
+            </para>
+          </listitem>
+        </itemizedlist>
+      </listitem>
+    </itemizedlist>
+  </section>
+  <section id="fancy-list-markers">
+    <title>Fancy list markers</title>
+    <orderedlist numeration="arabic">
+      <listitem override="2">
+        <para>
+          begins with 2
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          and now 3
+        </para>
+        <para>
+          with a continuation
+        </para>
+        <orderedlist numeration="lowerroman" spacing="compact">
+          <listitem override="4">
+            <para>
+              sublist with roman numerals, starting with 4
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              more items
+            </para>
+            <orderedlist numeration="upperalpha" spacing="compact">
+              <listitem>
+                <para>
+                  a subsublist
+                </para>
+              </listitem>
+              <listitem>
+                <para>
+                  a subsublist
+                </para>
+              </listitem>
+            </orderedlist>
+          </listitem>
+        </orderedlist>
+      </listitem>
+    </orderedlist>
+    <para>
+      Nesting:
+    </para>
+    <orderedlist numeration="upperalpha" spacing="compact">
+      <listitem>
+        <para>
+          Upper Alpha
+        </para>
+        <orderedlist numeration="upperroman" spacing="compact">
+          <listitem>
+            <para>
+              Upper Roman.
+            </para>
+            <orderedlist numeration="arabic" spacing="compact">
+              <listitem override="6">
+                <para>
+                  Decimal start with 6
+                </para>
+                <orderedlist numeration="loweralpha" spacing="compact">
+                  <listitem override="3">
+                    <para>
+                      Lower alpha with paren
+                    </para>
+                  </listitem>
+                </orderedlist>
+              </listitem>
+            </orderedlist>
+          </listitem>
+        </orderedlist>
+      </listitem>
+    </orderedlist>
+    <para>
+      Autonumbering:
+    </para>
+    <orderedlist spacing="compact">
+      <listitem>
+        <para>
+          Autonumber.
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          More.
+        </para>
+        <orderedlist spacing="compact">
+          <listitem>
+            <para>
+              Nested.
+            </para>
+          </listitem>
+        </orderedlist>
+      </listitem>
+    </orderedlist>
+    <para>
+      Should not be a list item:
+    </para>
+    <para>
+      M.A. 2007
+    </para>
+    <para>
+      B. Williams
+    </para>
+  </section>
+</section>
+<section id="definition-lists">
+  <title>Definition Lists</title>
+  <para>
+    Tight using spaces:
+  </para>
+  <variablelist spacing="compact">
+    <varlistentry>
+      <term>
+        apple
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        orange
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        banana
+      </term>
+      <listitem>
+        <para>
+          yellow fruit
+        </para>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+  <para>
+    Tight using tabs:
+  </para>
+  <variablelist spacing="compact">
+    <varlistentry>
+      <term>
+        apple
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        orange
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        banana
+      </term>
+      <listitem>
+        <para>
+          yellow fruit
+        </para>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+  <para>
+    Loose:
+  </para>
+  <variablelist>
+    <varlistentry>
+      <term>
+        apple
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        orange
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        banana
+      </term>
+      <listitem>
+        <para>
+          yellow fruit
+        </para>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+  <para>
+    Multiple blocks with italics:
+  </para>
+  <variablelist>
+    <varlistentry>
+      <term>
+        <emphasis>apple</emphasis>
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+        <para>
+          contains seeds, crisp, pleasant to taste
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        <emphasis>orange</emphasis>
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+        <programlisting>
+{ orange code block }
+</programlisting>
+        <blockquote>
+          <para>
+            orange block quote
+          </para>
+        </blockquote>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+  <para>
+    Multiple definitions, tight:
+  </para>
+  <variablelist spacing="compact">
+    <varlistentry>
+      <term>
+        apple
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+        <para>
+          computer
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        orange
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+        <para>
+          bank
+        </para>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+  <para>
+    Multiple definitions, loose:
+  </para>
+  <variablelist>
+    <varlistentry>
+      <term>
+        apple
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+        <para>
+          computer
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        orange
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+        <para>
+          bank
+        </para>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+  <para>
+    Blank line after term, indented marker, alternate markers:
+  </para>
+  <variablelist>
+    <varlistentry>
+      <term>
+        apple
+      </term>
+      <listitem>
+        <para>
+          red fruit
+        </para>
+        <para>
+          computer
+        </para>
+      </listitem>
+    </varlistentry>
+    <varlistentry>
+      <term>
+        orange
+      </term>
+      <listitem>
+        <para>
+          orange fruit
+        </para>
+        <orderedlist numeration="arabic" spacing="compact">
+          <listitem>
+            <para>
+              sublist
+            </para>
+          </listitem>
+          <listitem>
+            <para>
+              sublist
+            </para>
+          </listitem>
+        </orderedlist>
+      </listitem>
+    </varlistentry>
+  </variablelist>
+</section>
+<section id="html-blocks">
+  <title>HTML Blocks</title>
+  <para>
+    Simple block on one line:
+  </para>
+  <para>
+    foo
+  </para>
+  <para>
+    And nested without indentation:
+  </para>
+  <para>
+    foo
+  </para>
+  <para>
+    bar
+  </para>
+  <para>
+    Interpreted markdown in a table:
+  </para>
+  This is <emphasis>emphasized</emphasis>
+  And this is <emphasis role="strong">strong</emphasis>
+  <para>
+    Here’s a simple block:
+  </para>
+  <para>
+    foo
+  </para>
+  <para>
+    This should be a code block, though:
+  </para>
+  <programlisting>
+&lt;div&gt;
+    foo
+&lt;/div&gt;
+</programlisting>
+  <para>
+    As should this:
+  </para>
+  <programlisting>
+&lt;div&gt;foo&lt;/div&gt;
+</programlisting>
+  <para>
+    Now, nested:
+  </para>
+  <para>
+    foo
+  </para>
+  <para>
+    This should just be an HTML comment:
+  </para>
+  <para>
+    Multiline:
+  </para>
+  <para>
+    Code block:
+  </para>
+  <programlisting>
+&lt;!-- Comment --&gt;
+</programlisting>
+  <para>
+    Just plain comment, with trailing spaces on the line:
+  </para>
+  <para>
+    Code:
+  </para>
+  <programlisting>
+&lt;hr /&gt;
+</programlisting>
+  <para>
+    Hr’s:
+  </para>
+</section>
+<section id="inline-markup">
+  <title>Inline Markup</title>
+  <para>
+    This is <emphasis>emphasized</emphasis>, and so <emphasis>is
+    this</emphasis>.
+  </para>
+  <para>
+    This is <emphasis role="strong">strong</emphasis>, and so
+    <emphasis role="strong">is this</emphasis>.
+  </para>
+  <para>
+    An <emphasis><ulink url="/url">emphasized link</ulink></emphasis>.
+  </para>
+  <para>
+    <emphasis role="strong"><emphasis>This is strong and
+    em.</emphasis></emphasis>
+  </para>
+  <para>
+    So is <emphasis role="strong"><emphasis>this</emphasis></emphasis> word.
+  </para>
+  <para>
+    <emphasis role="strong"><emphasis>This is strong and
+    em.</emphasis></emphasis>
+  </para>
+  <para>
+    So is <emphasis role="strong"><emphasis>this</emphasis></emphasis> word.
+  </para>
+  <para>
+    This is code: <literal>&gt;</literal>, <literal>$</literal>,
+    <literal>\</literal>, <literal>\$</literal>,
+    <literal>&lt;html&gt;</literal>.
+  </para>
+  <para>
+    <emphasis role="strikethrough">This is
+    <emphasis>strikeout</emphasis>.</emphasis>
+  </para>
+  <para>
+    Superscripts: a<superscript>bc</superscript>d
+    a<superscript><emphasis>hello</emphasis></superscript>
+    a<superscript>hello there</superscript>.
+  </para>
+  <para>
+    Subscripts: H<subscript>2</subscript>O, H<subscript>23</subscript>O,
+    H<subscript>many of them</subscript>O.
+  </para>
+  <para>
+    These should not be superscripts or subscripts, because of the unescaped
+    spaces: a^b c^d, a~b c~d.
+  </para>
+</section>
+<section id="smart-quotes-ellipses-dashes">
+  <title>Smart quotes, ellipses, dashes</title>
+  <para>
+    <quote>Hello,</quote> said the spider. <quote><quote>Shelob</quote> is my
+    name.</quote>
+  </para>
+  <para>
+    <quote>A</quote>, <quote>B</quote>, and <quote>C</quote> are letters.
+  </para>
+  <para>
+    <quote>Oak,</quote> <quote>elm,</quote> and <quote>beech</quote> are names
+    of trees. So is <quote>pine.</quote>
+  </para>
+  <para>
+    <quote>He said, <quote>I want to go.</quote></quote> Were you alive in the
+    70’s?
+  </para>
+  <para>
+    Here is some quoted <quote><literal>code</literal></quote> and a
+    <quote><ulink url="http://example.com/?foo=1&amp;bar=2">quoted
+    link</ulink></quote>.
+  </para>
+  <para>
+    Some dashes: one—two — three—four — five.
+  </para>
+  <para>
+    Dashes between numbers: 5–7, 255–66, 1987–1999.
+  </para>
+  <para>
+    Ellipses…and…and….
+  </para>
+</section>
+<section id="latex">
+  <title>LaTeX</title>
+  <itemizedlist spacing="compact">
+    <listitem>
+      <para>
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        2 + 2 = 4
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        <emphasis>x</emphasis> ∈ <emphasis>y</emphasis>
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        <emphasis>α</emphasis> ∧ <emphasis>ω</emphasis>
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        223
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        <emphasis>p</emphasis>-Tree
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        Here’s some display math:
+        $$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$$
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        Here’s one that has a line break in it:
+        <emphasis>α</emphasis> + <emphasis>ω</emphasis> × <emphasis>x</emphasis><superscript>2</superscript>.
+      </para>
+    </listitem>
+  </itemizedlist>
+  <para>
+    These shouldn’t be math:
+  </para>
+  <itemizedlist spacing="compact">
+    <listitem>
+      <para>
+        To get the famous equation, write <literal>$e = mc^2$</literal>.
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        $22,000 is a <emphasis>lot</emphasis> of money. So is $34,000. (It
+        worked if <quote>lot</quote> is emphasized.)
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        Shoes ($20) and socks ($5).
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        Escaped <literal>$</literal>: $73 <emphasis>this should be
+        emphasized</emphasis> 23$.
+      </para>
+    </listitem>
+  </itemizedlist>
+  <para>
+    Here’s a LaTeX table:
+  </para>
+</section>
+<section id="special-characters">
+  <title>Special Characters</title>
+  <para>
+    Here is some unicode:
+  </para>
+  <itemizedlist spacing="compact">
+    <listitem>
+      <para>
+        I hat: Î
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        o umlaut: ö
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        section: §
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        set membership: ∈
+      </para>
+    </listitem>
+    <listitem>
+      <para>
+        copyright: ©
+      </para>
+    </listitem>
+  </itemizedlist>
+  <para>
+    AT&amp;T has an ampersand in their name.
+  </para>
+  <para>
+    AT&amp;T is another way to write it.
+  </para>
+  <para>
+    This &amp; that.
+  </para>
+  <para>
+    4 &lt; 5.
+  </para>
+  <para>
+    6 &gt; 5.
+  </para>
+  <para>
+    Backslash: \
+  </para>
+  <para>
+    Backtick: `
+  </para>
+  <para>
+    Asterisk: *
+  </para>
+  <para>
+    Underscore: _
+  </para>
+  <para>
+    Left brace: {
+  </para>
+  <para>
+    Right brace: }
+  </para>
+  <para>
+    Left bracket: [
+  </para>
+  <para>
+    Right bracket: ]
+  </para>
+  <para>
+    Left paren: (
+  </para>
+  <para>
+    Right paren: )
+  </para>
+  <para>
+    Greater-than: &gt;
+  </para>
+  <para>
+    Hash: #
+  </para>
+  <para>
+    Period: .
+  </para>
+  <para>
+    Bang: !
+  </para>
+  <para>
+    Plus: +
+  </para>
+  <para>
+    Minus: -
+  </para>
+</section>
+<section id="links">
+  <title>Links</title>
+  <section id="explicit">
+    <title>Explicit</title>
+    <para>
+      Just a <ulink url="/url/">URL</ulink>.
+    </para>
+    <para>
+      <ulink url="/url/">URL and title</ulink>.
+    </para>
+    <para>
+      <ulink url="/url/">URL and title</ulink>.
+    </para>
+    <para>
+      <ulink url="/url/">URL and title</ulink>.
+    </para>
+    <para>
+      <ulink url="/url/">URL and title</ulink>
+    </para>
+    <para>
+      <ulink url="/url/">URL and title</ulink>
+    </para>
+    <para>
+      <ulink url="/url/with_underscore">with_underscore</ulink>
+    </para>
+    <para>
+      Email link (<email>nobody@nowhere.net</email>)
+    </para>
+    <para>
+      <ulink url="">Empty</ulink>.
+    </para>
+  </section>
+  <section id="reference">
+    <title>Reference</title>
+    <para>
+      Foo <ulink url="/url/">bar</ulink>.
+    </para>
+    <para>
+      Foo <ulink url="/url/">bar</ulink>.
+    </para>
+    <para>
+      Foo <ulink url="/url/">bar</ulink>.
+    </para>
+    <para>
+      With <ulink url="/url/">embedded [brackets]</ulink>.
+    </para>
+    <para>
+      <ulink url="/url/">b</ulink> by itself should be a link.
+    </para>
+    <para>
+      Indented <ulink url="/url">once</ulink>.
+    </para>
+    <para>
+      Indented <ulink url="/url">twice</ulink>.
+    </para>
+    <para>
+      Indented <ulink url="/url">thrice</ulink>.
+    </para>
+    <para>
+      This should [not][] be a link.
+    </para>
+    <programlisting>
+[not]: /url
+</programlisting>
+    <para>
+      Foo <ulink url="/url/">bar</ulink>.
+    </para>
+    <para>
+      Foo <ulink url="/url/">biz</ulink>.
+    </para>
+  </section>
+  <section id="with-ampersands">
+    <title>With ampersands</title>
+    <para>
+      Here’s a <ulink url="http://example.com/?foo=1&amp;bar=2">link with an
+      ampersand in the URL</ulink>.
+    </para>
+    <para>
+      Here’s a link with an amersand in the link text:
+      <ulink url="http://att.com/">AT&amp;T</ulink>.
+    </para>
+    <para>
+      Here’s an <ulink url="/script?foo=1&amp;bar=2">inline link</ulink>.
+    </para>
+    <para>
+      Here’s an <ulink url="/script?foo=1&amp;bar=2">inline link in pointy
+      braces</ulink>.
+    </para>
+  </section>
+  <section id="autolinks">
+    <title>Autolinks</title>
+    <para>
+      With an ampersand:
+      <ulink url="http://example.com/?foo=1&amp;bar=2">http://example.com/?foo=1&amp;bar=2</ulink>
+    </para>
+    <itemizedlist spacing="compact">
+      <listitem>
+        <para>
+          In a list?
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          <ulink url="http://example.com/">http://example.com/</ulink>
+        </para>
+      </listitem>
+      <listitem>
+        <para>
+          It should.
+        </para>
+      </listitem>
+    </itemizedlist>
+    <para>
+      An e-mail address: <email>nobody@nowhere.net</email>
+    </para>
+    <blockquote>
+      <para>
+        Blockquoted:
+        <ulink url="http://example.com/">http://example.com/</ulink>
+      </para>
+    </blockquote>
+    <para>
+      Auto-links should not occur here:
+      <literal>&lt;http://example.com/&gt;</literal>
+    </para>
+    <programlisting>
+or here: &lt;http://example.com/&gt;
+</programlisting>
+  </section>
+</section>
+<section id="images">
+  <title>Images</title>
+  <para>
+    From <quote>Voyage dans la Lune</quote> by Georges Melies (1902):
+  </para>
+  <figure>
+    <title>lalune</title>
+    <mediaobject>
+      <imageobject>
+        <imagedata fileref="lalune.jpg" />
+      </imageobject>
+      <textobject><phrase>lalune</phrase></textobject>
+    </mediaobject>
+  </figure>
+  <para>
+    Here is a movie <inlinemediaobject>
+      <imageobject>
+        <imagedata fileref="movie.jpg" />
+      </imageobject>
+    </inlinemediaobject> icon.
+  </para>
+</section>
+<section id="footnotes">
+  <title>Footnotes</title>
+  <para>
+    Here is a footnote reference,<footnote>
+      <para>
+        Here is the footnote. It can go anywhere after the footnote reference.
+        It need not be placed at the end of the document.
+      </para>
+    </footnote> and another.<footnote>
+      <para>
+        Here’s the long note. This one contains multiple blocks.
+      </para>
+      <para>
+        Subsequent blocks are indented to show that they belong to the
+        footnote (as with list items).
+      </para>
+      <programlisting>
+  { &lt;code&gt; }
+</programlisting>
+      <para>
+        If you want, you can indent every line, but you can also be lazy and
+        just indent the first line of each block.
+      </para>
+    </footnote> This should <emphasis>not</emphasis> be a footnote reference,
+    because it contains a space.[^my note] Here is an inline note.<footnote>
+      <para>
+        This is <emphasis>easier</emphasis> to type. Inline notes may contain
+        <ulink url="http://google.com">links</ulink> and <literal>]</literal>
+        verbatim characters, as well as [bracketed text].
+      </para>
+    </footnote>
+  </para>
+  <blockquote>
+    <para>
+      Notes can go in quotes.<footnote>
+        <para>
+          In quote.
+        </para>
+      </footnote>
+    </para>
+  </blockquote>
+  <orderedlist numeration="arabic" spacing="compact">
+    <listitem>
+      <para>
+        And in list items.<footnote>
+          <para>
+            In list.
+          </para>
+        </footnote>
+      </para>
+    </listitem>
+  </orderedlist>
+  <para>
+    This paragraph should not be part of the note, as it is not indented.
+  </para>
+</section>
+</article>
-- 
cgit v1.2.3


From aa4a1d527a3ecbc291a70a872f06fa7a525d8e39 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Fri, 29 Apr 2016 14:54:54 -0700
Subject: HTML writer: ensure mathjax link is added when math appears in
 footnote.

Previously if a document only had math in a footnote,
the MathJax link would not be added.

Closes #2881.
---
 src/Text/Pandoc/Writers/HTML.hs | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs
index c5b6a6db2..d8b8384e7 100644
--- a/src/Text/Pandoc/Writers/HTML.hs
+++ b/src/Text/Pandoc/Writers/HTML.hs
@@ -855,13 +855,12 @@ inlineToHtml opts inline =
     (Note contents)
       | writerIgnoreNotes opts -> return mempty
       | otherwise              -> do
-                        st <- get
-                        let notes = stNotes st
+                        notes <- gets stNotes
                         let number = (length notes) + 1
                         let ref = show number
                         htmlContents <- blockListToNote opts ref contents
                         -- push contents onto front of notes
-                        put $ st {stNotes = (htmlContents:notes)}
+                        modify $ \st -> st {stNotes = (htmlContents:notes)}
                         let revealSlash = ['/' | writerSlideVariant opts
                                                  == RevealJsSlides]
                         let link = H.a ! A.href (toValue $ "#" ++
-- 
cgit v1.2.3


From 987ec3a7523f4fe529575004d76d93680f127fa3 Mon Sep 17 00:00:00 2001
From: Ivo Clarysse <ivo@bcdevices.com>
Date: Fri, 29 Apr 2016 15:43:15 -0700
Subject: Write out Docbook 5 namespace

---
 src/Text/Pandoc.hs                 |  2 +-
 src/Text/Pandoc/Options.hs         |  4 ++--
 src/Text/Pandoc/Writers/Docbook.hs | 11 +++++++----
 3 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc.hs b/src/Text/Pandoc.hs
index 58f666939..0330c46e2 100644
--- a/src/Text/Pandoc.hs
+++ b/src/Text/Pandoc.hs
@@ -292,7 +292,7 @@ writers = [
                       , writerHtml5 = True })
   ,("docbook"      , PureStringWriter writeDocbook)
   ,("docbook5"     , PureStringWriter $ \o ->
-     writeDocbook o{ writerDocBook5 = True })
+     writeDocbook o{ writerDocbook5 = True })
   ,("opml"         , PureStringWriter writeOPML)
   ,("opendocument" , PureStringWriter writeOpenDocument)
   ,("latex"        , PureStringWriter writeLaTeX)
diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index fcf6537c0..701cd8bd1 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -357,7 +357,7 @@ data WriterOptions = WriterOptions
   , writerSourceURL        :: Maybe String  -- ^ Absolute URL + directory of 1st source file
   , writerUserDataDir      :: Maybe FilePath -- ^ Path of user data directory
   , writerCiteMethod       :: CiteMethod -- ^ How to print cites
-  , writerDocBook5         :: Bool       -- ^ Produce DocBook5
+  , writerDocbook5         :: Bool       -- ^ Produce DocBook5
   , writerHtml5            :: Bool       -- ^ Produce HTML5
   , writerHtmlQTags        :: Bool       -- ^ Use @<q>@ tags for quotes in HTML
   , writerBeamer           :: Bool       -- ^ Produce beamer LaTeX slide show
@@ -404,7 +404,7 @@ instance Default WriterOptions where
                       , writerSourceURL        = Nothing
                       , writerUserDataDir      = Nothing
                       , writerCiteMethod       = Citeproc
-                      , writerDocBook5         = False
+                      , writerDocbook5         = False
                       , writerHtml5            = False
                       , writerHtmlQTags        = False
                       , writerBeamer           = False
diff --git a/src/Text/Pandoc/Writers/Docbook.hs b/src/Text/Pandoc/Writers/Docbook.hs
index 5528714a2..79ccde9af 100644
--- a/src/Text/Pandoc/Writers/Docbook.hs
+++ b/src/Text/Pandoc/Writers/Docbook.hs
@@ -112,12 +112,15 @@ elementToDocbook opts lvl (Sec _ _num (id',_,_) title elements) =
                     else elements
       tag = case lvl of
                  n | n == 0           -> "chapter"
-                   | n >= 1 && n <= 5 -> if writerDocBook5 opts
+                   | n >= 1 && n <= 5 -> if writerDocbook5 opts
                                               then "section"
                                               else "sect" ++ show n
                    | otherwise        -> "simplesect"
-  in  inTags True tag [("id", writerIdentifierPrefix opts ++ id') |
-                       not (null id')] $
+      idAttr = [("id", writerIdentifierPrefix opts ++ id') | not (null id')]
+      nsAttr = if writerDocbook5 opts && lvl == 0 then [("xmlns", "http://docbook.org/ns/docbook")]
+                                      else []
+      attribs = nsAttr ++ idAttr
+  in  inTags True tag attribs $
       inTagsSimple "title" (inlinesToDocbook opts title) $$
       vcat (map (elementToDocbook opts (lvl + 1)) elements')
 
@@ -231,7 +234,7 @@ blockToDocbook opts (DefinitionList 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
+  | f == "html"    = if writerDocbook5 opts
                         then empty -- No html in Docbook5
                         else text str -- allow html for backwards compatibility
   | otherwise      = empty
-- 
cgit v1.2.3


From fd36e6b64a516ffd281af0667afc6d9c00a70d64 Mon Sep 17 00:00:00 2001
From: Ivo Clarysse <ivo@bcdevices.com>
Date: Fri, 29 Apr 2016 16:06:55 -0700
Subject: Docbook5 writer: Properly handle ulink/link

---
 src/Text/Pandoc/Writers/Docbook.hs |  4 ++-
 tests/writer.docbook5              | 67 +++++++++++++++++++-------------------
 2 files changed, 37 insertions(+), 34 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/Docbook.hs b/src/Text/Pandoc/Writers/Docbook.hs
index 79ccde9af..9acfe289a 100644
--- a/src/Text/Pandoc/Writers/Docbook.hs
+++ b/src/Text/Pandoc/Writers/Docbook.hs
@@ -351,7 +351,9 @@ inlineToDocbook opts (Link attr txt (src, _))
   | otherwise =
       (if isPrefixOf "#" src
             then inTags False "link" $ ("linkend", drop 1 src) : idAndRole attr
-            else inTags False "ulink" $ ("url", 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
diff --git a/tests/writer.docbook5 b/tests/writer.docbook5
index 494489ab5..5261a35be 100644
--- a/tests/writer.docbook5
+++ b/tests/writer.docbook5
@@ -22,7 +22,8 @@
 <section id="headers">
   <title>Headers</title>
   <section id="level-2-with-an-embedded-link">
-    <title>Level 2 with an <ulink url="/url">embedded link</ulink></title>
+    <title>Level 2 with an <link xlink:href="/url">embedded
+    link</link></title>
     <section id="level-3-with-emphasis">
       <title>Level 3 with <emphasis>emphasis</emphasis></title>
       <section id="level-4">
@@ -940,7 +941,7 @@ These should not be escaped:  \$ \\ \&gt; \[ \{
     <emphasis role="strong">is this</emphasis>.
   </para>
   <para>
-    An <emphasis><ulink url="/url">emphasized link</ulink></emphasis>.
+    An <emphasis><link xlink:href="/url">emphasized link</link></emphasis>.
   </para>
   <para>
     <emphasis role="strong"><emphasis>This is strong and
@@ -998,8 +999,8 @@ These should not be escaped:  \$ \\ \&gt; \[ \{
   </para>
   <para>
     Here is some quoted <quote><literal>code</literal></quote> and a
-    <quote><ulink url="http://example.com/?foo=1&amp;bar=2">quoted
-    link</ulink></quote>.
+    <quote><link xlink:href="http://example.com/?foo=1&amp;bar=2">quoted
+    link</link></quote>.
   </para>
   <para>
     Some dashes: one—two — three—four — five.
@@ -1188,58 +1189,58 @@ These should not be escaped:  \$ \\ \&gt; \[ \{
   <section id="explicit">
     <title>Explicit</title>
     <para>
-      Just a <ulink url="/url/">URL</ulink>.
+      Just a <link xlink:href="/url/">URL</link>.
     </para>
     <para>
-      <ulink url="/url/">URL and title</ulink>.
+      <link xlink:href="/url/">URL and title</link>.
     </para>
     <para>
-      <ulink url="/url/">URL and title</ulink>.
+      <link xlink:href="/url/">URL and title</link>.
     </para>
     <para>
-      <ulink url="/url/">URL and title</ulink>.
+      <link xlink:href="/url/">URL and title</link>.
     </para>
     <para>
-      <ulink url="/url/">URL and title</ulink>
+      <link xlink:href="/url/">URL and title</link>
     </para>
     <para>
-      <ulink url="/url/">URL and title</ulink>
+      <link xlink:href="/url/">URL and title</link>
     </para>
     <para>
-      <ulink url="/url/with_underscore">with_underscore</ulink>
+      <link xlink:href="/url/with_underscore">with_underscore</link>
     </para>
     <para>
       Email link (<email>nobody@nowhere.net</email>)
     </para>
     <para>
-      <ulink url="">Empty</ulink>.
+      <link xlink:href="">Empty</link>.
     </para>
   </section>
   <section id="reference">
     <title>Reference</title>
     <para>
-      Foo <ulink url="/url/">bar</ulink>.
+      Foo <link xlink:href="/url/">bar</link>.
     </para>
     <para>
-      Foo <ulink url="/url/">bar</ulink>.
+      Foo <link xlink:href="/url/">bar</link>.
     </para>
     <para>
-      Foo <ulink url="/url/">bar</ulink>.
+      Foo <link xlink:href="/url/">bar</link>.
     </para>
     <para>
-      With <ulink url="/url/">embedded [brackets]</ulink>.
+      With <link xlink:href="/url/">embedded [brackets]</link>.
     </para>
     <para>
-      <ulink url="/url/">b</ulink> by itself should be a link.
+      <link xlink:href="/url/">b</link> by itself should be a link.
     </para>
     <para>
-      Indented <ulink url="/url">once</ulink>.
+      Indented <link xlink:href="/url">once</link>.
     </para>
     <para>
-      Indented <ulink url="/url">twice</ulink>.
+      Indented <link xlink:href="/url">twice</link>.
     </para>
     <para>
-      Indented <ulink url="/url">thrice</ulink>.
+      Indented <link xlink:href="/url">thrice</link>.
     </para>
     <para>
       This should [not][] be a link.
@@ -1248,35 +1249,35 @@ These should not be escaped:  \$ \\ \&gt; \[ \{
 [not]: /url
 </programlisting>
     <para>
-      Foo <ulink url="/url/">bar</ulink>.
+      Foo <link xlink:href="/url/">bar</link>.
     </para>
     <para>
-      Foo <ulink url="/url/">biz</ulink>.
+      Foo <link xlink:href="/url/">biz</link>.
     </para>
   </section>
   <section id="with-ampersands">
     <title>With ampersands</title>
     <para>
-      Here’s a <ulink url="http://example.com/?foo=1&amp;bar=2">link with an
-      ampersand in the URL</ulink>.
+      Here’s a <link xlink:href="http://example.com/?foo=1&amp;bar=2">link
+      with an ampersand in the URL</link>.
     </para>
     <para>
       Here’s a link with an amersand in the link text:
-      <ulink url="http://att.com/">AT&amp;T</ulink>.
+      <link xlink:href="http://att.com/">AT&amp;T</link>.
     </para>
     <para>
-      Here’s an <ulink url="/script?foo=1&amp;bar=2">inline link</ulink>.
+      Here’s an <link xlink:href="/script?foo=1&amp;bar=2">inline link</link>.
     </para>
     <para>
-      Here’s an <ulink url="/script?foo=1&amp;bar=2">inline link in pointy
-      braces</ulink>.
+      Here’s an <link xlink:href="/script?foo=1&amp;bar=2">inline link in
+      pointy braces</link>.
     </para>
   </section>
   <section id="autolinks">
     <title>Autolinks</title>
     <para>
       With an ampersand:
-      <ulink url="http://example.com/?foo=1&amp;bar=2">http://example.com/?foo=1&amp;bar=2</ulink>
+      <link xlink:href="http://example.com/?foo=1&amp;bar=2">http://example.com/?foo=1&amp;bar=2</link>
     </para>
     <itemizedlist spacing="compact">
       <listitem>
@@ -1286,7 +1287,7 @@ These should not be escaped:  \$ \\ \&gt; \[ \{
       </listitem>
       <listitem>
         <para>
-          <ulink url="http://example.com/">http://example.com/</ulink>
+          <link xlink:href="http://example.com/">http://example.com/</link>
         </para>
       </listitem>
       <listitem>
@@ -1301,7 +1302,7 @@ These should not be escaped:  \$ \\ \&gt; \[ \{
     <blockquote>
       <para>
         Blockquoted:
-        <ulink url="http://example.com/">http://example.com/</ulink>
+        <link xlink:href="http://example.com/">http://example.com/</link>
       </para>
     </blockquote>
     <para>
@@ -1362,8 +1363,8 @@ or here: &lt;http://example.com/&gt;
     because it contains a space.[^my note] Here is an inline note.<footnote>
       <para>
         This is <emphasis>easier</emphasis> to type. Inline notes may contain
-        <ulink url="http://google.com">links</ulink> and <literal>]</literal>
-        verbatim characters, as well as [bracketed text].
+        <link xlink:href="http://google.com">links</link> and
+        <literal>]</literal> verbatim characters, as well as [bracketed text].
       </para>
     </footnote>
   </para>
-- 
cgit v1.2.3


From 91dc334249883b658e2b91fce80ced6635e07c28 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Sun, 1 May 2016 12:17:12 -0400
Subject: Docx Reader: Throw PandocError on unzip failure

Previously, readDocx would error out if zip-archive failed. We change
the archive extraction step from `toArchive` to `toArchiveOrFail`, which
returns an Either value.
---
 src/Text/Pandoc/Readers/Docx.hs | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Docx.hs b/src/Text/Pandoc/Readers/Docx.hs
index 604bc20de..9c7c3b264 100644
--- a/src/Text/Pandoc/Readers/Docx.hs
+++ b/src/Text/Pandoc/Readers/Docx.hs
@@ -100,12 +100,13 @@ import Text.Pandoc.Compat.Except
 readDocxWithWarnings :: ReaderOptions
                      -> B.ByteString
                      -> Either PandocError (Pandoc, MediaBag, [String])
-readDocxWithWarnings opts bytes =
-  case archiveToDocxWithWarnings (toArchive bytes) of
-    Right (docx, warnings) -> do
+readDocxWithWarnings opts bytes
+  | Right archive <- toArchiveOrFail bytes
+  , Right (docx, warnings) <- archiveToDocxWithWarnings archive = do
       (meta, blks, mediaBag) <- docxToOutput opts docx
       return (Pandoc meta blks, mediaBag, warnings)
-    Left _   -> Left (ParseFailure "couldn't parse docx file")
+readDocxWithWarnings _ _ =
+  Left (ParseFailure "couldn't parse docx file")
 
 readDocx :: ReaderOptions
          -> B.ByteString
-- 
cgit v1.2.3


From 1fbe79db05c55495cf9096cb5be15e499d9a21ec Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sun, 1 May 2016 11:20:26 -0700
Subject: LaTeX writer: use {} around options containing special chars.

Closes #2892.
---
 src/Text/Pandoc/Writers/LaTeX.hs | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 038f27480..283c8bc44 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -40,7 +40,8 @@ import Text.Printf ( printf )
 import Network.URI ( isURI, unEscapeString )
 import Data.Aeson (object, (.=), FromJSON)
 import Data.List ( (\\), isInfixOf, stripPrefix, intercalate, intersperse, nub, nubBy )
-import Data.Char ( toLower, isPunctuation, isAscii, isLetter, isDigit, ord )
+import Data.Char ( toLower, isPunctuation, isAscii, isLetter, isDigit,
+                   ord, isAlphaNum )
 import Data.Maybe ( fromMaybe, isJust, catMaybes )
 import qualified Data.Text as T
 import Control.Applicative ((<|>))
@@ -471,23 +472,27 @@ blockToLaTeX (CodeBlock (identifier,classes,keyvalAttr) str) = do
         st <- get
         let params = if writerListings (stOptions st)
                      then (case getListingsLanguage classes of
-                                Just l  -> [ "language=" ++ l ]
+                                Just l  -> [ "language=" ++ mbBraced l ]
                                 Nothing -> []) ++
                           [ "numbers=left" | "numberLines" `elem` classes
                              || "number" `elem` classes
                              || "number-lines" `elem` classes ] ++
                           [ (if key == "startFrom"
                                 then "firstnumber"
-                                else key) ++ "=" ++ attr |
+                                else key) ++ "=" ++ mbBraced attr |
                                 (key,attr) <- keyvalAttr ] ++
                           (if identifier == ""
                                 then []
                                 else [ "label=" ++ ref ])
 
                      else []
+            mbBraced x = if not (all isAlphaNum x)
+                            then "{" <> x <> "}"
+                            else x
             printParams
                 | null params = empty
-                | otherwise   = brackets $ hcat (intersperse ", " (map text params))
+                | otherwise   = brackets $ hcat (intersperse ", "
+                      (map text params))
         return $ flush ("\\begin{lstlisting}" <> printParams $$ text str $$
                  "\\end{lstlisting}") $$ cr
   let highlightedCodeBlock =
-- 
cgit v1.2.3


From 99eac312feb258ac4129c923e5b4fde57da9fbc3 Mon Sep 17 00:00:00 2001
From: Jesse Rosenthal <jrosenthal@jhu.edu>
Date: Sun, 1 May 2016 17:40:04 -0400
Subject: Binary fmts throw PandocError on zip-archive fail

Commit 91dc3342 made `readDocx` throw PandocError if there was an
unarchiving error. This extends that fix to `readOdt` and `readEPUB`.
---
 src/Text/Pandoc/Readers/EPUB.hs | 6 ++++--
 src/Text/Pandoc/Readers/Odt.hs  | 4 +++-
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/EPUB.hs b/src/Text/Pandoc/Readers/EPUB.hs
index 07d282708..144ba9ca2 100644
--- a/src/Text/Pandoc/Readers/EPUB.hs
+++ b/src/Text/Pandoc/Readers/EPUB.hs
@@ -19,7 +19,7 @@ import Text.Pandoc.Compat.Except (MonadError, throwError, runExcept, Except)
 import Text.Pandoc.Compat.Monoid ((<>))
 import Text.Pandoc.MIME (MimeType)
 import qualified Text.Pandoc.Builder as B
-import Codec.Archive.Zip ( Archive (..), toArchive, fromEntry
+import Codec.Archive.Zip ( Archive (..), toArchiveOrFail, fromEntry
                          , findEntryByPath, Entry)
 import qualified Data.ByteString.Lazy as BL (ByteString)
 import System.FilePath ( takeFileName, (</>), dropFileName, normalise
@@ -39,7 +39,9 @@ import Text.Pandoc.Error
 type Items = M.Map String (FilePath, MimeType)
 
 readEPUB :: ReaderOptions -> BL.ByteString -> Either PandocError (Pandoc, MediaBag)
-readEPUB opts bytes = runEPUB (archiveToEPUB opts $ toArchive bytes)
+readEPUB opts bytes = case toArchiveOrFail bytes of
+  Right archive -> runEPUB $ archiveToEPUB opts $ archive
+  Left  _       -> Left $ ParseFailure "Couldn't extract ePub file"
 
 runEPUB :: Except PandocError a -> Either PandocError a
 runEPUB = runExcept
diff --git a/src/Text/Pandoc/Readers/Odt.hs b/src/Text/Pandoc/Readers/Odt.hs
index a925c1d84..68e89263c 100644
--- a/src/Text/Pandoc/Readers/Odt.hs
+++ b/src/Text/Pandoc/Readers/Odt.hs
@@ -59,7 +59,9 @@ readOdt _ bytes = case bytesToOdt bytes of
 
 --
 bytesToOdt :: B.ByteString -> Either PandocError Pandoc
-bytesToOdt bytes = archiveToOdt $ toArchive bytes
+bytesToOdt bytes = case toArchiveOrFail bytes of
+  Right archive -> archiveToOdt archive
+  Left _        -> Left $ ParseFailure "Couldn't parse odt file."
 
 --
 archiveToOdt :: Archive -> Either PandocError Pandoc
-- 
cgit v1.2.3


From d5e4bc179c0517a5da84ed95d55e1f10f1f16a94 Mon Sep 17 00:00:00 2001
From: Albert Krewinkel <albert@zeitkraut.de>
Date: Tue, 3 May 2016 22:52:10 +0200
Subject: Org reader: stop padding short table rows

Emacs Org-mode doesn't add any padding to table rows.  The first
row (header or first body row) is used to determine the column count, no
other magic is performed.

The org reader was padding rows to the length of the longest table row.
This was done due to a misunderstanding of how Org handles tables.  This
feature reflected how Org-mode handles tables when pressing <TAB>.  The
Org exporter however, which is what the reader should implement, doesn't
do any of this.  So this was a mis-feature that made the reader more
complex and reduced comparability.  It was hence removed.
---
 src/Text/Pandoc/Readers/Org.hs | 44 +++++++++++++++++++-----------------------
 tests/Tests/Readers/Org.hs     |  8 ++++----
 2 files changed, 24 insertions(+), 28 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index 5e98be31d..0de64c663 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -774,9 +774,13 @@ data OrgTableRow = OrgContentRow (F [Blocks])
                  | OrgAlignRow [Alignment]
                  | OrgHlineRow
 
+-- OrgTable is strongly related to the pandoc table ADT.  Using the same
+-- (i.e. pandoc-global) ADT would mean that the reader would break if the
+-- global structure was to be changed, which would be bad.  The final table
+-- should be generated using a builder function.  Column widths aren't
+-- implemented yet, so they are not tracked here.
 data OrgTable = OrgTable
-  { orgTableColumns    :: Int
-  , orgTableAlignments :: [Alignment]
+  { orgTableAlignments :: [Alignment]
   , orgTableHeader     :: [Blocks]
   , orgTableRows       :: [[Blocks]]
   }
@@ -792,7 +796,7 @@ table = try $ do
 orgToPandocTable :: OrgTable
                  -> Inlines
                  -> Blocks
-orgToPandocTable (OrgTable _ aligns heads lns) caption =
+orgToPandocTable (OrgTable aligns heads lns) caption =
   B.table caption (zip aligns $ repeat 0) heads lns
 
 tableStart :: OrgParser Char
@@ -840,20 +844,18 @@ tableHline = try $
 
 rowsToTable :: [OrgTableRow]
             -> F OrgTable
-rowsToTable = foldM (flip rowToContent) zeroTable
-  where zeroTable = OrgTable 0 mempty mempty mempty
-
-normalizeTable :: OrgTable
-               -> OrgTable
-normalizeTable (OrgTable cols aligns heads lns) =
-  let aligns' = fillColumns aligns AlignDefault
-      heads'  = if heads == mempty
-                then mempty
-                else fillColumns heads (B.plain mempty)
-      lns'    = map (`fillColumns` B.plain mempty) lns
-      fillColumns base padding = take cols $ base ++ repeat padding
-  in OrgTable cols aligns' heads' lns'
+rowsToTable = foldM (flip rowToContent) emptyTable
+ where emptyTable = OrgTable mempty mempty mempty
 
+normalizeTable :: OrgTable -> OrgTable
+normalizeTable (OrgTable aligns heads rows) = OrgTable aligns' heads rows
+ where
+   refRow = if heads /= mempty
+            then heads
+            else if rows == mempty then mempty else head rows
+   cols = length refRow
+   fillColumns base padding = take cols $ base ++ repeat padding
+   aligns' = fillColumns aligns AlignDefault
 
 -- One or more horizontal rules after the first content line mark the previous
 -- line as a header.  All other horizontal lines are discarded.
@@ -861,16 +863,10 @@ rowToContent :: OrgTableRow
              -> OrgTable
              -> F OrgTable
 rowToContent OrgHlineRow        t = maybeBodyToHeader t
-rowToContent (OrgAlignRow as)   t = setLongestRow as =<< setAligns as t
+rowToContent (OrgAlignRow as)   t = setAligns as t
 rowToContent (OrgContentRow rf) t = do
   rs <- rf
-  setLongestRow rs =<< appendToBody rs t
-
-setLongestRow :: [a]
-              -> OrgTable
-              -> F OrgTable
-setLongestRow rs t =
-  return t{ orgTableColumns = max (length rs) (orgTableColumns t) }
+  appendToBody rs t
 
 maybeBodyToHeader :: OrgTable
                   -> F OrgTable
diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs
index bb9b37d13..98658482c 100644
--- a/tests/Tests/Readers/Org.hs
+++ b/tests/Tests/Readers/Org.hs
@@ -1024,10 +1024,10 @@ tests =
                   , "| 1       | One  | foo  |"
                   , "| 2"
                   ] =?>
-          table "" (zip [AlignCenter, AlignRight, AlignDefault] [0, 0, 0])
-                [ plain "Numbers", plain "Text" , plain mempty ]
-                [ [ plain "1"      , plain "One"  , plain "foo"  ]
-                , [ plain "2"      , plain mempty , plain mempty  ]
+          table "" (zip [AlignCenter, AlignRight] [0, 0])
+                [ plain "Numbers", plain "Text" ]
+                [ [ plain "1" , plain "One" , plain "foo" ]
+                , [ plain "2" ]
                 ]
 
       , "Table with caption" =:
-- 
cgit v1.2.3


From a51e4e82156d8d6f0d3dc616c4f38c70b25be616 Mon Sep 17 00:00:00 2001
From: Albert Krewinkel <albert@zeitkraut.de>
Date: Wed, 4 May 2016 00:03:48 +0200
Subject: Org reader: refactor rows-to-table conversion

This refactores the codes conversing a list table lines to an org table
ADT.  The old code was simplified and is now slightly less ugly.
---
 src/Text/Pandoc/Readers/Org.hs | 50 +++++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 25 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index 0de64c663..e41dd5dd8 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -844,7 +844,7 @@ tableHline = try $
 
 rowsToTable :: [OrgTableRow]
             -> F OrgTable
-rowsToTable = foldM (flip rowToContent) emptyTable
+rowsToTable = foldM rowToContent emptyTable
  where emptyTable = OrgTable mempty mempty mempty
 
 normalizeTable :: OrgTable -> OrgTable
@@ -859,31 +859,31 @@ normalizeTable (OrgTable aligns heads rows) = OrgTable aligns' heads rows
 
 -- One or more horizontal rules after the first content line mark the previous
 -- line as a header.  All other horizontal lines are discarded.
-rowToContent :: OrgTableRow
-             -> OrgTable
+rowToContent :: OrgTable
+             -> OrgTableRow
              -> F OrgTable
-rowToContent OrgHlineRow        t = maybeBodyToHeader t
-rowToContent (OrgAlignRow as)   t = setAligns as t
-rowToContent (OrgContentRow rf) t = do
-  rs <- rf
-  appendToBody rs t
-
-maybeBodyToHeader :: OrgTable
-                  -> F OrgTable
-maybeBodyToHeader t = case t of
-  OrgTable{ orgTableHeader = [], orgTableRows = b:[] } ->
-         return t{ orgTableHeader = b , orgTableRows = [] }
-  _   -> return t
-
-appendToBody :: [Blocks]
-             -> OrgTable
-             -> F OrgTable
-appendToBody r t = return t{ orgTableRows = orgTableRows t ++ [r] }
-
-setAligns :: [Alignment]
-          -> OrgTable
-          -> F OrgTable
-setAligns aligns t = return $ t{ orgTableAlignments = aligns }
+rowToContent orgTable row =
+  case row of
+    OrgHlineRow       -> return singleRowPromotedToHeader
+    OrgAlignRow as    -> return . setAligns $ as
+    OrgContentRow cs  -> appendToBody cs
+ where
+   singleRowPromotedToHeader :: OrgTable
+   singleRowPromotedToHeader = case orgTable of
+     OrgTable{ orgTableHeader = [], orgTableRows = b:[] } ->
+            orgTable{ orgTableHeader = b , orgTableRows = [] }
+     _   -> orgTable
+
+   setAligns :: [Alignment] -> OrgTable
+   setAligns aligns = orgTable{ orgTableAlignments = aligns }
+
+   appendToBody :: F [Blocks] -> F OrgTable
+   appendToBody frow = do
+     newRow <- frow
+     let oldRows = orgTableRows orgTable
+     -- NOTE: This is an inefficient O(n) operation.  This should be changed
+     -- if performance ever becomes a problem.
+     return orgTable{ orgTableRows = oldRows ++ [newRow] }
 
 
 --
-- 
cgit v1.2.3


From 2d825603c684d6c7af6adb08f26ed34a078a5afe Mon Sep 17 00:00:00 2001
From: Albert Krewinkel <albert@zeitkraut.de>
Date: Wed, 4 May 2016 15:33:18 +0200
Subject: Org reader: fix handling of empty table cells, rows

This fixes Org mode parsing of some corner cases regarding empty cells
and rows.  Empty cells weren't parsed correctly, e.g. `|||` should be
two empty cells, but would be parsed as a single cell containing a pipe
character.  Empty rows where parsed as alignment rows and dropped from
the output.

This fixes #2616.
---
 src/Text/Pandoc/Readers/Org.hs | 30 +++++++++++++++++-------------
 tests/Tests/Readers/Org.hs     | 13 ++++++++++++-
 2 files changed, 29 insertions(+), 14 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index e41dd5dd8..493e94d2e 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -35,6 +35,7 @@ import           Text.Pandoc.Builder ( Inlines, Blocks, HasMeta(..),
                                        trimInlines )
 import           Text.Pandoc.Definition
 import           Text.Pandoc.Compat.Monoid ((<>))
+import           Text.Pandoc.Error
 import           Text.Pandoc.Options
 import qualified Text.Pandoc.Parsing as P
 import           Text.Pandoc.Parsing hiding ( F, unF, askF, asksF, runF
@@ -57,8 +58,6 @@ import qualified Data.Set as Set
 import           Data.Maybe (fromMaybe, isJust)
 import           Network.HTTP (urlEncode)
 
-import           Text.Pandoc.Error
-
 -- | Parse org-mode string and return a Pandoc document.
 readOrg :: ReaderOptions -- ^ Reader options
         -> String        -- ^ String to parse (assuming @'\n'@ line endings)
@@ -807,18 +806,19 @@ tableRows = try $ many (tableAlignRow <|> tableHline <|> tableContentRow)
 
 tableContentRow :: OrgParser OrgTableRow
 tableContentRow = try $
-  OrgContentRow . sequence <$> (tableStart *> manyTill tableContentCell newline)
+  OrgContentRow . sequence <$> (tableStart *> many1Till tableContentCell newline)
 
 tableContentCell :: OrgParser (F Blocks)
 tableContentCell = try $
-  fmap B.plain . trimInlinesF . mconcat <$> many1Till inline endOfCell
-
-endOfCell :: OrgParser Char
-endOfCell = try $ char '|' <|> lookAhead newline
+  fmap B.plain . trimInlinesF . mconcat <$> manyTill inline endOfCell
 
 tableAlignRow :: OrgParser OrgTableRow
-tableAlignRow = try $
-  OrgAlignRow <$> (tableStart *> manyTill tableAlignCell newline)
+tableAlignRow = try $ do
+  tableStart
+  cells <- many1Till tableAlignCell newline
+  -- Empty rows are regular (i.e. content) rows, not alignment rows.
+  guard $ any (/= AlignDefault) cells
+  return $ OrgAlignRow cells
 
 tableAlignCell :: OrgParser Alignment
 tableAlignCell =
@@ -833,15 +833,19 @@ tableAlignCell =
     where emptyCell = try $ skipSpaces *> endOfCell
 
 tableAlignFromChar :: OrgParser Alignment
-tableAlignFromChar = try $ choice [ char 'l' *> return AlignLeft
-                                  , char 'c' *> return AlignCenter
-                                  , char 'r' *> return AlignRight
-                                  ]
+tableAlignFromChar = try $
+  choice [ char 'l' *> return AlignLeft
+         , char 'c' *> return AlignCenter
+         , char 'r' *> return AlignRight
+         ]
 
 tableHline :: OrgParser OrgTableRow
 tableHline = try $
   OrgHlineRow <$ (tableStart *> char '-' *> anyLine)
 
+endOfCell :: OrgParser Char
+endOfCell = try $ char '|' <|> lookAhead newline
+
 rowsToTable :: [OrgTableRow]
             -> F OrgTable
 rowsToTable = foldM rowToContent emptyTable
diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs
index 98658482c..81684d8ef 100644
--- a/tests/Tests/Readers/Org.hs
+++ b/tests/Tests/Readers/Org.hs
@@ -941,7 +941,7 @@ tests =
 
       , "Empty table" =:
           "||" =?>
-          simpleTable' 1 mempty mempty
+          simpleTable' 1 mempty [[mempty]]
 
       , "Glider Table" =:
           unlines [ "| 1 | 0 | 0 |"
@@ -996,6 +996,17 @@ tests =
                 , [ plain "dynamic", plain "Lisp" ]
                 ]
 
+      , "Table with empty cells" =:
+          "|||c|" =?>
+          simpleTable' 3 mempty [[mempty, mempty, plain "c"]]
+
+      , "Table with empty rows" =:
+          unlines [ "| first  |"
+                  , "|        |"
+                  , "| third  |"
+                  ] =?>
+          simpleTable' 1 mempty [[plain "first"], [mempty], [plain "third"]]
+
       , "Table with alignment row" =:
           unlines [ "| Numbers | Text | More |"
                   , "| <c>     | <r>  |      |"
-- 
cgit v1.2.3


From 405c3e9c36837226b0f714f241b115c72f0b8861 Mon Sep 17 00:00:00 2001
From: Albert Krewinkel <albert@zeitkraut.de>
Date: Wed, 4 May 2016 23:16:23 +0200
Subject: Org reader: fix spacing after LaTeX-style symbols
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The org-reader was droping space after unescaped LaTeX-style symbol
commands: `\ForAll \Auml` resulted in `∀Ä` but should give `∀ Ä`
instead.  This seems to be because the LaTeX-reader treats the
command-terminating space as part of the command.  Dropping the trailing
space from the symbol-command fixes this issue.
---
 src/Text/Pandoc/Readers/Org.hs | 12 +++++++-----
 tests/Tests/Readers/Org.hs     |  4 ++++
 2 files changed, 11 insertions(+), 5 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index 5e98be31d..a7987475a 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -49,7 +49,7 @@ import qualified Text.TeXMath.Readers.MathML.EntityMap as MathMLEntityMap
 import           Control.Arrow (first)
 import           Control.Monad (foldM, guard, liftM, liftM2, mplus, mzero, when)
 import           Control.Monad.Reader (Reader, runReader, ask, asks, local)
-import           Data.Char (isAlphaNum, toLower)
+import           Data.Char (isAlphaNum, isSpace, toLower)
 import           Data.Default
 import           Data.List (intersperse, isPrefixOf, isSuffixOf)
 import qualified Data.Map as M
@@ -1587,8 +1587,8 @@ inlineLaTeX = try $ do
    state :: ParserState
    state = def{ stateOptions = def{ readerParseRaw = True }}
 
-   texMathToPandoc inp = (maybeRight $ readTeX inp) >>=
-                         writePandoc DisplayInline
+   texMathToPandoc :: String -> Maybe [Inline]
+   texMathToPandoc cs = (maybeRight $ readTeX cs) >>= writePandoc DisplayInline
 
 maybeRight :: Either a b -> Maybe b
 maybeRight = either (const Nothing) Just
@@ -1598,9 +1598,11 @@ inlineLaTeXCommand = try $ do
   rest <- getInput
   case runParser rawLaTeXInline def "source" rest of
     Right (RawInline _ cs) -> do
-      let len = length cs
+      -- drop any trailing whitespace, those should not be part of the command
+      let cmdNoSpc = takeWhile (not . isSpace) $ cs
+      let len = length cmdNoSpc
       count len anyChar
-      return cs
+      return cmdNoSpc
     _ -> mzero
 
 smart :: OrgParser (F Inlines)
diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs
index bb9b37d13..6112055ba 100644
--- a/tests/Tests/Readers/Org.hs
+++ b/tests/Tests/Readers/Org.hs
@@ -328,6 +328,10 @@ tests =
           "\\copy" =?>
           para "©"
 
+      , "MathML symbols, space separated" =:
+          "\\ForAll \\Auml" =?>
+          para "∀ Ä"
+
       , "LaTeX citation" =:
           "\\cite{Coffee}" =?>
           let citation = Citation
-- 
cgit v1.2.3


From acd492c7f49e31f65ec044ce3ba66ffb80844e27 Mon Sep 17 00:00:00 2001
From: roblabla <robinlambertz+dev@gmail.com>
Date: Mon, 9 May 2016 15:22:02 +0200
Subject: Allow spaces before '!' in MediaWiki table header

---
 src/Text/Pandoc/Readers/MediaWiki.hs | 2 +-
 tests/mediawiki-reader.native        | 5 +++++
 tests/mediawiki-reader.wiki          | 8 ++++++++
 3 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/MediaWiki.hs b/src/Text/Pandoc/Readers/MediaWiki.hs
index 950497992..d3cee08e2 100644
--- a/src/Text/Pandoc/Readers/MediaWiki.hs
+++ b/src/Text/Pandoc/Readers/MediaWiki.hs
@@ -225,7 +225,7 @@ table = do
                          Nothing -> 1.0
   caption <- option mempty tableCaption
   optional rowsep
-  hasheader <- option False $ True <$ (lookAhead (char '!'))
+  hasheader <- option False $ True <$ (lookAhead (skipSpaces *> char '!'))
   (cellspecs',hdr) <- unzip <$> tableRow
   let widths = map ((tableWidth *) . snd) cellspecs'
   let restwidth = tableWidth - sum widths
diff --git a/tests/mediawiki-reader.native b/tests/mediawiki-reader.native
index cf80d0664..6afeb602c 100644
--- a/tests/mediawiki-reader.native
+++ b/tests/mediawiki-reader.native
@@ -252,6 +252,11 @@ Pandoc (Meta {unMeta = fromList []})
  [[]]
  [[[Para [Str "Orange"]]]]
 ,Para [Str "Paragraph",Space,Str "after",Space,Str "the",Space,Str "table."]
+,Table [] [AlignDefault,AlignDefault] [0.0,0.0]
+ [[Para [Str "fruit"]]
+ ,[Para [Str "topping"]]]
+ [[[Para [Str "apple"]]
+  ,[Para [Str "ice",Space,Str "cream"]]]]
 ,Header 2 ("notes",[],[]) [Str "notes"]
 ,Para [Str "My",Space,Str "note!",Note [Plain [Str "This."]]]
 ,Para [Str "URL",Space,Str "note.",Note [Plain [Link ("",[],[]) [Str "http://docs.python.org/library/functions.html#range"] ("http://docs.python.org/library/functions.html#range","")]]]]
diff --git a/tests/mediawiki-reader.wiki b/tests/mediawiki-reader.wiki
index 862bb3b48..11cd52d9c 100644
--- a/tests/mediawiki-reader.wiki
+++ b/tests/mediawiki-reader.wiki
@@ -381,6 +381,14 @@ and cheese
 |Orange
 |}Paragraph after the table.
 
+{|
+ !fruit
+ !topping
+ |-
+ |apple
+ |ice cream
+ |}
+
 == notes ==
 
 My note!<ref>This.</ref>
-- 
cgit v1.2.3


From 10a809f1260945b61cae6aa8912399ad83051552 Mon Sep 17 00:00:00 2001
From: Albert Krewinkel <albert@zeitkraut.de>
Date: Mon, 9 May 2016 17:50:27 +0200
Subject: Org reader: fix inline-LaTeX regression

The last fix for whitespace handling of inline LaTeX commands was
incorrect, preventing correct recognition of inline LaTeX commands which
contain spaces.  This fix ensures that only trailing whitespace is cut
off.
---
 src/Text/Pandoc/Readers/Org.hs | 13 +++++++++----
 tests/Tests/Readers/Org.hs     |  4 ++++
 2 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index db1e70ea0..5a50a8f34 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -1581,8 +1581,8 @@ inlineLaTeX = try $ do
 
    parseAsMathMLSym :: String -> Maybe Inlines
    parseAsMathMLSym cs = B.str <$> MathMLEntityMap.getUnicode (clean cs)
-    -- dropWhileEnd would be nice here, but it's not available before base 4.5
-    where clean = reverse . dropWhile (`elem` ("{}" :: String)) . reverse . drop 1
+    -- drop initial backslash and any trailing "{}"
+    where clean = dropWhileEnd (`elem` ("{}" :: String)) . drop 1
 
    state :: ParserState
    state = def{ stateOptions = def{ readerParseRaw = True }}
@@ -1598,13 +1598,18 @@ inlineLaTeXCommand = try $ do
   rest <- getInput
   case runParser rawLaTeXInline def "source" rest of
     Right (RawInline _ cs) -> do
-      -- drop any trailing whitespace, those should not be part of the command
-      let cmdNoSpc = takeWhile (not . isSpace) $ cs
+      -- drop any trailing whitespace, those are not be part of the command as
+      -- far as org mode is concerned.
+      let cmdNoSpc = dropWhileEnd isSpace cs
       let len = length cmdNoSpc
       count len anyChar
       return cmdNoSpc
     _ -> mzero
 
+-- Taken from Data.OldList.
+dropWhileEnd :: (a -> Bool) -> [a] -> [a]
+dropWhileEnd p = foldr (\x xs -> if p x && null xs then [] else x : xs) []
+
 smart :: OrgParser (F Inlines)
 smart = do
   getOption readerSmart >>= guard
diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs
index 3fab92e53..17682fb32 100644
--- a/tests/Tests/Readers/Org.hs
+++ b/tests/Tests/Readers/Org.hs
@@ -308,6 +308,10 @@ tests =
           "\\textit{Emphasised}" =?>
           para (emph "Emphasised")
 
+      , "Inline LaTeX command with spaces" =:
+          "\\emph{Emphasis mine}" =?>
+          para (emph "Emphasis mine")
+
       , "Inline LaTeX math symbol" =:
           "\\tau" =?>
           para (emph "τ")
-- 
cgit v1.2.3


From d32878b84b08f2f8e007b9b06c393a41e2ebe5fe Mon Sep 17 00:00:00 2001
From: Albert Krewinkel <albert@zeitkraut.de>
Date: Mon, 9 May 2016 18:53:29 +0200
Subject: Org writer: print empty table rows

Empty table rows should not be dropped from the output, so row-height is
always set to be at least 1.
---
 src/Text/Pandoc/Writers/Org.hs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/Org.hs b/src/Text/Pandoc/Writers/Org.hs
index 20086ed19..e57a6fc11 100644
--- a/src/Text/Pandoc/Writers/Org.hs
+++ b/src/Text/Pandoc/Writers/Org.hs
@@ -170,7 +170,7 @@ blockToOrg (Table caption' _ _ headers rows) =  do
        map ((+2) . numChars) $ transpose (headers' : rawRows)
   -- FIXME: Org doesn't allow blocks with height more than 1.
   let hpipeBlocks blocks = hcat [beg, middle, end]
-        where h      = maximum (map height blocks)
+        where h      = maximum (1 : map height blocks)
               sep'   = lblock 3 $ vcat (map text $ replicate h " | ")
               beg    = lblock 2 $ vcat (map text $ replicate h "| ")
               end    = lblock 2 $ vcat (map text $ replicate h " |")
-- 
cgit v1.2.3


From f7601297f0ff184a59efdc3ea279137fc6012eef Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Mon, 9 May 2016 10:00:36 -0700
Subject: Avoid lazy foldl in LaTeX writer.

---
 src/Text/Pandoc/Writers/LaTeX.hs | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'src/Text/Pandoc')

diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index 283c8bc44..804e0febc 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -39,7 +39,8 @@ import Text.Pandoc.Templates
 import Text.Printf ( printf )
 import Network.URI ( isURI, unEscapeString )
 import Data.Aeson (object, (.=), FromJSON)
-import Data.List ( (\\), isInfixOf, stripPrefix, intercalate, intersperse, nub, nubBy )
+import Data.List ( (\\), isInfixOf, stripPrefix, intercalate, intersperse,
+                   nub, nubBy, foldl' )
 import Data.Char ( toLower, isPunctuation, isAscii, isLetter, isDigit,
                    ord, isAlphaNum )
 import Data.Maybe ( fromMaybe, isJust, catMaybes )
@@ -725,7 +726,7 @@ sectionHeader :: Bool    -- True for unnumbered
               -> State WriterState Doc
 sectionHeader unnumbered ident level lst = do
   txt <- inlineListToLaTeX lst
-  plain <- stringToLaTeX TextString $ foldl (++) "" $ map stringify lst
+  plain <- stringToLaTeX TextString $ concatMap stringify lst
   let noNote (Note _) = Str ""
       noNote x        = x
   let lstNoNotes = walk noNote lst
@@ -1037,7 +1038,7 @@ citationsToNatbib (c:cs) | citationMode c == AuthorInText = do
 
 citationsToNatbib cits = do
   cits' <- mapM convertOne cits
-  return $ text "\\citetext{" <> foldl combineTwo empty cits' <> text "}"
+  return $ text "\\citetext{" <> foldl' combineTwo empty cits' <> text "}"
   where
     combineTwo a b | isEmpty a = b
                    | otherwise = a <> text "; " <> b
@@ -1086,7 +1087,7 @@ citationsToBiblatex (one:[])
 
 citationsToBiblatex (c:cs) = do
   args <- mapM convertOne (c:cs)
-  return $ text cmd <> foldl (<>) empty args
+  return $ text cmd <> foldl' (<>) empty args
     where
        cmd = case citationMode c of
                   AuthorInText -> "\\textcites"
-- 
cgit v1.2.3