Html blocks can be
Html blocks can be
+inlined
+as well.
+ + * Improved default template lookup for custom lua scripts (#2625). + Previously, if you tried to do `pandoc -s -t /path/to/lua/script.lua`, + pandoc would look for the template in + `~/.pandoc/templates/default./path/to/lua/script.lua`. + With this change it will look in the more reasonable + `~/.pandoc/templates/default.script.lua`. This makes it possible to + store default templates for custom writers. + + * RST, Markdown writers: Fixed rendering of grid tables with blank rows + (#2615). + + * LaTeX writer: restore old treatment of Span (#2624). A Span is + now rendered with surrounding `{}`, as it was before 1.16. + + * Entity handling fixes: improved handling of entities like + `⟨` that require a trailing semicolon. Allow uppercase + `x` in numerical hexidecimal character references, working + around a tagsoup bug. + + * `stack.yaml` - use lts-4.0, but with older aeson to avoid excessive + memory use on compile. With aeson 0.10 we were getting an out of + memory error on a 2GB Ubuntu 64-bit VM. + + * Improved deb package creation script. Made `DPKGVER` work. + Renamed `COMMIT` to `TREE`. You should now be able to do + `TREE=1.16.0.1 DPKGVER=2 make deb`. + + pandoc (1.16) * Added `Attr` field to `Link` and `Image` (Mauro Bieg, #261, API change). diff --git a/man/pandoc.1 b/man/pandoc.1 --- a/man/pandoc.1 +++ b/man/pandoc.1 @@ -1,5 +1,5 @@ .\"t -.TH PANDOC 1 "November 12, 2015" "pandoc 1.16" +.TH PANDOC 1 "January 9, 2016" "pandoc 1.16.0.1" .SH NAME pandoc - general markup converter .SH SYNOPSIS diff --git a/pandoc.cabal b/pandoc.cabal --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ Name: pandoc -Version: 1.16 +Version: 1.16.0.1 Cabal-Version: >= 1.10 Build-Type: Custom License: GPL diff --git a/pandoc.hs b/pandoc.hs --- a/pandoc.hs +++ b/pandoc.hs @@ -110,8 +110,7 @@ wrap' cols (remaining - length x - 2) xs isTextFormat :: String -> Bool -isTextFormat s = takeWhile (`notElem` "+-") s `notElem` binaries - where binaries = ["odt","docx","epub","epub3"] +isTextFormat s = s `notElem` ["odt","docx","epub","epub3"] externalFilter :: FilePath -> [String] -> Pandoc -> IO Pandoc externalFilter f args' d = do @@ -1162,23 +1161,24 @@ "epub2" -> "epub" "html4" -> "html" x -> x + let format = takeWhile (`notElem` ['+','-']) + $ takeFileName writerName' -- in case path to lua script let pdfOutput = map toLower (takeExtension outputFile) == ".pdf" - let laTeXOutput = "latex" `isPrefixOf` writerName' || - "beamer" `isPrefixOf` writerName' - let conTeXtOutput = "context" `isPrefixOf` writerName' - let html5Output = "html5" `isPrefixOf` writerName' + let laTeXOutput = format `elem` ["latex", "beamer"] + let conTeXtOutput = format == "context" + let html5Output = format == "html5" let laTeXInput = "latex" `isPrefixOf` readerName' || "beamer" `isPrefixOf` readerName' - writer <- if ".lua" `isSuffixOf` writerName' + writer <- if ".lua" `isSuffixOf` format -- note: use non-lowercased version writerName then return $ IOStringWriter $ writeCustom writerName else case getWriter writerName' of Left e -> err 9 $ - if writerName' == "pdf" + if format == "pdf" then e ++ "\nTo create a pdf with pandoc, use " ++ "the latex or beamer writer and specify\n" ++ @@ -1201,18 +1201,17 @@ "\nPandoc can convert from DOCX, but not from DOC.\nTry using Word to save your DOC file as DOCX, and convert that with pandoc." _ -> e - let standalone' = standalone || not (isTextFormat writerName') || pdfOutput + let standalone' = standalone || not (isTextFormat format) || pdfOutput templ <- case templatePath of _ | not standalone' -> return "" Nothing -> do - deftemp <- getDefaultTemplate datadir writerName' + deftemp <- getDefaultTemplate datadir format case deftemp of Left e -> throwIO e Right t -> return t Just tp -> do -- strip off extensions - let format = takeWhile (`notElem` "+-") writerName' let tp' = case takeExtension tp of "" -> tp <.> format _ -> tp @@ -1234,7 +1233,7 @@ return $ ("mathml-script", s) : variables _ -> return variables - variables'' <- if "dzslides" `isPrefixOf` writerName' + variables'' <- if format == "dzslides" then do dztempl <- readDataFileUTF8 datadir ("dzslides" "template.html") @@ -1270,8 +1269,8 @@ , readerTrackChanges = trackChanges } - when (not (isTextFormat writerName') && outputFile == "-") $ - err 5 $ "Cannot write " ++ writerName' ++ " output to stdout.\n" ++ + when (not (isTextFormat format) && outputFile == "-") $ + err 5 $ "Cannot write " ++ format ++ " output to stdout.\n" ++ "Specify an output file using the -o option." let readSources [] = mapM readSource ["-"] @@ -1354,7 +1353,7 @@ doc' <- (maybe return (extractMedia media) mbExtractMedia >=> adjustMetadata metadata >=> applyTransforms transforms >=> - applyFilters filters' [writerName']) doc + applyFilters filters' [format]) doc let writeBinary :: B.ByteString -> IO () writeBinary = B.writeFile (UTF8.encodePath outputFile) @@ -1370,7 +1369,7 @@ | pdfOutput -> do -- make sure writer is latex or beamer or context or html5 unless (laTeXOutput || conTeXtOutput || html5Output) $ - err 47 $ "cannot produce pdf output with " ++ writerName' ++ + err 47 $ "cannot produce pdf output with " ++ format ++ " writer" let pdfprog = case () of @@ -1393,9 +1392,8 @@ | otherwise -> selfcontain (f writerOptions doc' ++ ['\n' | not standalone']) >>= writerFn outputFile . handleEntities - where htmlFormat = writerName' `elem` - ["html","html+lhs","html5","html5+lhs", - "s5","slidy","slideous","dzslides","revealjs"] + where htmlFormat = format `elem` + ["html","html5","s5","slidy","slideous","dzslides","revealjs"] selfcontain = if selfContained && htmlFormat then makeSelfContained writerOptions else return diff --git a/src/Text/Pandoc/PDF.hs b/src/Text/Pandoc/PDF.hs --- a/src/Text/Pandoc/PDF.hs +++ b/src/Text/Pandoc/PDF.hs @@ -99,9 +99,9 @@ doc' <- handleImages opts tmpdir doc let source = writer opts doc' args = writerLaTeXArgs opts - case program of + case takeBaseName program of "context" -> context2pdf (writerVerbose opts) tmpdir source - _ | program `elem` ["pdflatex", "lualatex", "xelatex"] + prog | prog `elem` ["pdflatex", "lualatex", "xelatex"] -> tex2pdf' (writerVerbose opts) args tmpdir program source _ -> return $ Left $ UTF8.fromStringLazy $ "Unknown program " ++ program diff --git a/src/Text/Pandoc/Parsing.hs b/src/Text/Pandoc/Parsing.hs --- a/src/Text/Pandoc/Parsing.hs +++ b/src/Text/Pandoc/Parsing.hs @@ -573,7 +573,11 @@ characterReference = try $ do char '&' ent <- many1Till nonspaceChar (char ';') - case lookupEntity ent of + let ent' = case ent of + '#':'X':xs -> '#':'x':xs -- workaround tagsoup bug + '#':_ -> ent + _ -> ent ++ ";" + case lookupEntity ent' of Just c -> return c Nothing -> fail "entity not found" diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1452,11 +1452,16 @@ caption <- case frontCaption of Nothing -> option (return mempty) tableCaption Just c -> return c + -- renormalize widths if greater than 100%: + let totalWidth = sum widths + let widths' = if totalWidth < 1 + then widths + else map (/ totalWidth) widths return $ do caption' <- caption heads' <- heads lns' <- lns - return $ B.table caption' (zip aligns widths) heads' lns' + return $ B.table caption' (zip aligns widths') heads' lns' -- -- inline diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs --- a/src/Text/Pandoc/Readers/Org.hs +++ b/src/Text/Pandoc/Readers/Org.hs @@ -87,8 +87,10 @@ -- | Drop COMMENT headers and the document tree below those headers. dropCommentTrees :: [Block] -> [Block] dropCommentTrees [] = [] -dropCommentTrees blks@(b:bs) = - maybe blks (flip dropUntilHeaderAboveLevel bs) $ commentHeaderLevel b +dropCommentTrees (b:bs) = + maybe (b:dropCommentTrees bs) + (dropCommentTrees . flip dropUntilHeaderAboveLevel bs) + (commentHeaderLevel b) -- | Return the level of a header starting a comment or :noexport: tree and -- Nothing otherwise. diff --git a/src/Text/Pandoc/Readers/Textile.hs b/src/Text/Pandoc/Readers/Textile.hs --- a/src/Text/Pandoc/Readers/Textile.hs +++ b/src/Text/Pandoc/Readers/Textile.hs @@ -57,7 +57,7 @@ import qualified Text.Pandoc.Builder as B import Text.Pandoc.Options import Text.Pandoc.Parsing -import Text.Pandoc.Readers.HTML ( htmlTag, isBlockTag ) +import Text.Pandoc.Readers.HTML ( htmlTag, isBlockTag, isInlineTag ) import Text.Pandoc.Shared (trim) import Text.Pandoc.Readers.LaTeX ( rawLaTeXInline, rawLaTeXBlock ) import Text.HTML.TagSoup (parseTags, innerText, fromAttrib, Tag(..)) @@ -504,7 +504,7 @@ return B.linebreak rawHtmlInline :: Parser [Char] ParserState Inlines -rawHtmlInline = B.rawInline "html" . snd <$> htmlTag (const True) +rawHtmlInline = B.rawInline "html" . snd <$> htmlTag isInlineTag -- | Raw LaTeX Inline rawLaTeXInline' :: Parser [Char] ParserState Inlines diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs --- a/src/Text/Pandoc/Writers/LaTeX.hs +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -810,28 +810,26 @@ inlineToLaTeX :: Inline -- ^ Inline to convert -> State WriterState Doc inlineToLaTeX (Span (id',classes,kvs) ils) = do - let noEmph = "csl-no-emph" `elem` classes - let noStrong = "csl-no-strong" `elem` classes - let noSmallCaps = "csl-no-smallcaps" `elem` classes - let rtl = ("dir","rtl") `elem` kvs - let ltr = ("dir","ltr") `elem` kvs ref <- toLabel id' let linkAnchor = if null id' then empty else "\\protect\\hypertarget" <> braces (text ref) <> braces empty - fmap (linkAnchor <>) - ((if noEmph then inCmd "textup" else id) . - (if noStrong then inCmd "textnormal" else id) . - (if noSmallCaps then inCmd "textnormal" else id) . - (if rtl then inCmd "RL" else id) . - (if ltr then inCmd "LR" else id) . - (case lookup "lang" kvs of - Just lng -> let (l, o) = toPolyglossia $ splitBy (=='-') lng - ops = if null o then "" else brackets (text o) - in \c -> char '\\' <> "text" <> text l <> ops <> braces c - Nothing -> id) - ) `fmap` inlineListToLaTeX ils + let cmds = ["textup" | "csl-no-emph" `elem` classes] ++ + ["textnormal" | "csl-no-strong" `elem` classes || + "csl-no-smallcaps" `elem` classes] ++ + ["RL" | ("dir", "rtl") `elem` kvs] ++ + ["LR" | ("dir", "ltr") `elem` kvs] ++ + (case lookup "lang" kvs of + Just lng -> let (l, o) = toPolyglossia $ splitBy (=='-') lng + ops = if null o then "" else ("[" ++ o ++ "]") + in ["text" ++ l ++ ops] + Nothing -> []) + contents <- inlineListToLaTeX ils + return $ linkAnchor <> + if null cmds + then braces contents + else foldr inCmd contents cmds inlineToLaTeX (Emph lst) = inlineListToLaTeX lst >>= return . inCmd "emph" inlineToLaTeX (Strong lst) = diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs --- a/src/Text/Pandoc/Writers/Markdown.hs +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -572,7 +572,7 @@ else widths let widthsInChars = map (floor . (fromIntegral (writerColumns opts) *)) widths' 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 " |") diff --git a/src/Text/Pandoc/Writers/RST.hs b/src/Text/Pandoc/Writers/RST.hs --- a/src/Text/Pandoc/Writers/RST.hs +++ b/src/Text/Pandoc/Writers/RST.hs @@ -267,7 +267,7 @@ then map ((+2) . numChars) $ transpose (headers' : rawRows) else map (floor . (fromIntegral (writerColumns opts) *)) widths 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 " |") diff --git a/src/Text/Pandoc/XML.hs b/src/Text/Pandoc/XML.hs --- a/src/Text/Pandoc/XML.hs +++ b/src/Text/Pandoc/XML.hs @@ -100,11 +100,16 @@ -- Unescapes XML entities fromEntities :: String -> String fromEntities ('&':xs) = - case lookupEntity ent of + case lookupEntity ent' of Just c -> c : fromEntities rest Nothing -> '&' : fromEntities xs where (ent, rest) = case break (\c -> isSpace c || c == ';') xs of (zs,';':ys) -> (zs,ys) - _ -> ("",xs) + (zs, ys) -> (zs,ys) + ent' = case ent of + '#':'X':ys -> '#':'x':ys -- workaround tagsoup bug + '#':_ -> ent + _ -> ent ++ ";" + fromEntities (x:xs) = x : fromEntities xs fromEntities [] = [] diff --git a/stack.yaml b/stack.yaml --- a/stack.yaml +++ b/stack.yaml @@ -10,5 +10,7 @@ extra-deps: - 'cmark-0.5.0' - 'pandoc-citeproc-0.9' -- 'pandoc-types-1.16' -resolver: lts-3.20 +- 'pandoc-types-1.16.0.1' +# Use older aeson to avoid excessive memory use in compilation: +- 'aeson-0.8.0.2' +resolver: lts-4.0 diff --git a/tests/Tests/Readers/Markdown.hs b/tests/Tests/Readers/Markdown.hs --- a/tests/Tests/Readers/Markdown.hs +++ b/tests/Tests/Readers/Markdown.hs @@ -371,6 +371,15 @@ , plain "b" , plain "c" <> bulletList [plain "d"] ] ] + , testGroup "entities" + [ "character references" =: + "⟨ ö" =?> para (text "\10216 ö") + , "numeric" =: + ",DD" =?> para (text ",DD") + , "in link title" =: + "[link](/url \"title ⟨ ö ,\")" =?> + para (link "/url" "title \10216 ö ," (text "link")) + ] , testGroup "citations" [ "simple" =: "@item1" =?> para (cite [ diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs --- a/tests/Tests/Readers/Org.hs +++ b/tests/Tests/Readers/Org.hs @@ -569,6 +569,16 @@ ] =?> (mempty::Blocks) + , "Subtree with :noexport:" =: + unlines [ "* Exported" + , "** This isn't exported :noexport:" + , "*** This neither" + , "** But this is" + ] =?> + mconcat [ headerWith ("exported", [], []) 1 "Exported" + , headerWith ("but-this-is", [], []) 2 "But this is" + ] + , "Paragraph starting with an asterisk" =: "*five" =?> para "*five" diff --git a/tests/textile-reader.native b/tests/textile-reader.native --- a/tests/textile-reader.native +++ b/tests/textile-reader.native @@ -150,10 +150,11 @@ ,RawBlock (Format "html") "" -,Para [Str "Html",Space,Str "blocks",Space,Str "can",Space,Str "be",Space,RawInline (Format "html") "