diff --git a/README b/README --- a/README +++ b/README @@ -442,7 +442,7 @@ By default, pandoc will include the following metadata elements: `` (from the document title), `` (from the document authors), `` (from the document date, which should - be is in [ISO 8601 format]), `` (from the `lang` + be in [ISO 8601 format]), `` (from the `lang` variable, or, if is not set, the locale), and `` (a randomly generated UUID). Any of these may be overridden by elements in the metadata file. @@ -1275,10 +1275,9 @@ - a. uno - b. dos - c. tres - + 1. uno + 2. dos + 3. tres Horizontal rules ---------------- diff --git a/changelog b/changelog --- a/changelog +++ b/changelog @@ -1,3 +1,32 @@ +pandoc (1.9.1) + + * LaTeX reader: + + + Fixed regression in 1.9; properly handle escaped $ in latex math. + + Put LaTeX verse environments in blockquotes. + + * Markdown reader: + + + Limit nesting of strong/emph. This avoids exponential lookahead + in parasitic cases, like `a**a*a**a*a**a*a**a*a**a*a**a*a**a*a**`. + + Improved attributes syntax (inn code blocks/spans): + (1) Attributes can contain line breaks. (2) Values in key-value + attributes can be surrounded by either double or single quotes, or + left unquoted if they contain no spaces. + + * Don't wrap headers in markdown or RST writers. + + * Added `stateMaxNestingLevel` to `ParserState`. + We set this to 6, so you can still have `Emph` inside `Emph`, + just not indefinitely. + + * More efficient implementation of `nowrap` in `Text.Pandoc.Pretty`. + + * `Text.Pandoc.PDF`: Only run latex twice if `\tableofcontents` + is present. + + * Require highlighting-kate >= 0.5.0.2, texmath >= 0.6.0.2. + pandoc (1.9.0.5) * Changed cabal file so that build-depends for the test program @@ -196,6 +225,15 @@ will not be wrapped in `` tags. + + * The LaTeX parser has been completely rewritten; it is now much more + accurate, robust, and extensible. However, there are two important + changes in how it treats unknown LaTeX. (1) Previously, unknown + environments became BlockQuote elements; now, they are treated + as "transparent", so `\begin{unknown}xyz\end{unknown}` is the + same as `xyz`. (2) Previously, arguments of unknown commands + were passed through with their braces; now the braces are stripped + off. * `--smart` is no longer selected automatically with `man` output. @@ -378,9 +416,6 @@ * Removed dependency on dlist. * New slidy directory for "self-contained." - - * LaTeX parser completely rewritten; it is now much more accurate, - robust, and extensible. * TeXMath writer: Use unicode thin spaces for thin spaces. diff --git a/man/man1/pandoc.1 b/man/man1/pandoc.1 --- a/man/man1/pandoc.1 +++ b/man/man1/pandoc.1 @@ -613,7 +613,7 @@ By default, pandoc will include the following metadata elements: \f[C]\f[] (from the document title), \f[C]\f[] (from the document authors), \f[C]\f[] (from the document date, -which should be is in ISO 8601 format), \f[C]\f[] (from the +which should be in ISO 8601 format), \f[C]\f[] (from the \f[C]lang\f[] variable, or, if is not set, the locale), and \f[C]\f[] (a randomly generated UUID). Any of these may be overridden by elements in the metadata file. diff --git a/man/man5/pandoc_markdown.5 b/man/man5/pandoc_markdown.5 --- a/man/man5/pandoc_markdown.5 +++ b/man/man5/pandoc_markdown.5 @@ -726,9 +726,9 @@ -a.\ \ uno -b.\ \ dos -c.\ \ tres +1.\ \ uno +2.\ \ dos +3.\ \ tres \f[] .fi .SH HORIZONTAL RULES diff --git a/pandoc.cabal b/pandoc.cabal --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ Name: pandoc -Version: 1.9.0.5 +Version: 1.9.1 Cabal-Version: >= 1.10 Build-Type: Custom License: GPL @@ -203,7 +203,7 @@ old-locale >= 1 && < 1.1, time >= 1.2 && < 1.5, HTTP >= 4000.0.5 && < 4000.3, - texmath >= 0.6 && < 0.7, + texmath >= 0.6.0.2 && < 0.7, xml >= 1.3.12 && < 1.4, random >= 1 && < 1.1, extensible-exceptions >= 0.1 && < 0.2, @@ -213,7 +213,7 @@ tagsoup >= 0.12.5 && < 0.13, base64-bytestring >= 0.1 && < 0.2, zlib >= 0.5 && <= 0.6, - highlighting-kate >= 0.5.0.1 && < 0.6, + highlighting-kate >= 0.5.0.2 && < 0.6, temporary >= 1.1 && < 1.2 if impl(ghc >= 6.10) Build-depends: base >= 4 && < 5, syb >= 0.1 && < 0.4 @@ -301,7 +301,7 @@ old-locale >= 1 && < 1.1, time >= 1.2 && < 1.5, HTTP >= 4000.0.5 && < 4000.3, - texmath >= 0.6 && < 0.7, + texmath >= 0.6.0.2 && < 0.7, xml >= 1.3.12 && < 1.4, random >= 1 && < 1.1, extensible-exceptions >= 0.1 && < 0.2, @@ -311,7 +311,7 @@ tagsoup >= 0.12.5 && < 0.13, base64-bytestring >= 0.1 && < 0.2, zlib >= 0.5 && <= 0.6, - highlighting-kate >= 0.5.0.1 && < 0.6, + highlighting-kate >= 0.5.0.2 && < 0.6, temporary >= 1.1 && < 1.2 if impl(ghc >= 6.10) Build-depends: base >= 4 && < 5, syb >= 0.1 && < 0.4 @@ -359,7 +359,7 @@ old-locale >= 1 && < 1.1, time >= 1.2 && < 1.5, HTTP >= 4000.0.5 && < 4000.3, - texmath >= 0.6 && < 0.7, + texmath >= 0.6.0.2 && < 0.7, xml >= 1.3.12 && < 1.4, random >= 1 && < 1.1, extensible-exceptions >= 0.1 && < 0.2, @@ -369,7 +369,7 @@ tagsoup >= 0.12.5 && < 0.13, base64-bytestring >= 0.1 && < 0.2, zlib >= 0.5 && <= 0.6, - highlighting-kate >= 0.5.0.1 && < 0.6, + highlighting-kate >= 0.5.0.2 && < 0.6, temporary >= 1.1 && < 1.2 if impl(ghc >= 6.10) Build-depends: base >= 4 && < 5, syb >= 0.1 && < 0.4 diff --git a/src/Tests/Readers/LaTeX.hs b/src/Tests/Readers/LaTeX.hs --- a/src/Tests/Readers/LaTeX.hs +++ b/src/Tests/Readers/LaTeX.hs @@ -41,6 +41,11 @@ header 1 ("text" <> space <> link "/url" "" "link") ] + , testGroup "math" + [ "escaped $" =: + "$x=\\$4$" =?> para (math "x=\\$4") + ] + , testGroup "space and comments" [ "blank lines + space at beginning" =: "\n \n hi" =?> para "hi" 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 @@ -43,6 +43,7 @@ import Control.Concurrent (putMVar, takeMVar, newEmptyMVar, forkIO) import Text.Pandoc.UTF8 as UTF8 import Control.Monad (unless) +import Data.List (isInfixOf) tex2pdf :: String -- ^ tex program (pdflatex, lualatex, xelatex) -> String -- ^ latex source @@ -55,7 +56,9 @@ -> String -- ^ tex source -> IO (Either ByteString ByteString) tex2pdf' tmpDir program source = do - let numruns = 2 -- should suffice for toc and hyperrefs + let numruns = if "\\tableofcontents" `isInfixOf` source + then 2 + else 1 (exit, log', mbPdf) <- runTeXProgram program numruns tmpDir source let msg = "Error producing PDF from TeX source." case (exit, mbPdf) of 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 @@ -629,6 +629,7 @@ { stateParseRaw :: Bool, -- ^ Parse raw HTML and LaTeX? stateParserContext :: ParserContext, -- ^ Inside list? stateQuoteContext :: QuoteContext, -- ^ Inside quoted environment? + stateMaxNestingLevel :: Int, -- ^ Max # of nested Strong/Emph stateLastStrPos :: Maybe SourcePos, -- ^ Position after last str parsed stateKeys :: KeyTable, -- ^ List of reference keys stateCitations :: [String], -- ^ List of available citations @@ -660,6 +661,7 @@ ParserState { stateParseRaw = False, stateParserContext = NullState, stateQuoteContext = NoQuote, + stateMaxNestingLevel = 6, stateLastStrPos = Nothing, stateKeys = M.empty, stateCitations = [], diff --git a/src/Text/Pandoc/Pretty.hs b/src/Text/Pandoc/Pretty.hs --- a/src/Text/Pandoc/Pretty.hs +++ b/src/Text/Pandoc/Pretty.hs @@ -72,7 +72,7 @@ ) where -import Data.Sequence (Seq, fromList, (<|), singleton) +import Data.Sequence (Seq, fromList, (<|), singleton, mapWithIndex) import Data.Foldable (toList) import Data.List (intercalate) import Data.Monoid @@ -408,9 +408,9 @@ -- | Makes a 'Doc' non-reflowable. nowrap :: Doc -> Doc -nowrap doc = Doc $ fromList $ map replaceSpace $ toList $ unDoc doc - where replaceSpace BreakingSpace = Text 1 " " - replaceSpace x = x +nowrap doc = Doc $ mapWithIndex replaceSpace $ unDoc doc + where replaceSpace _ BreakingSpace = Text 1 " " + replaceSpace _ x = x -- | Returns the width of a 'Doc'. offset :: Doc -> Int diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -136,6 +136,12 @@ mathInline :: LP String -> LP Inlines mathInline p = math <$> (try p >>= applyMacros') +mathChars :: LP String +mathChars = concat <$> + many ( many1 (satisfy (\c -> c /= '$' && c /='\\')) + <|> (\c -> ['\\',c]) <$> (try $ char '\\' *> anyChar) + ) + double_quote :: LP Inlines double_quote = (doubleQuoted . mconcat) <$> (try $ string "``" *> manyTill inline (try $ string "''")) @@ -158,8 +164,8 @@ <|> single_quote <|> (str "’" <$ char '\'') <|> (str "\160" <$ char '~') - <|> (mathDisplay $ string "$$" *> manyTill anyChar (try $ string "$$")) - <|> (mathInline $ char '$' *> manyTill anyChar (char '$')) + <|> (mathDisplay $ string "$$" *> mathChars <* string "$$") + <|> (mathInline $ char '$' *> mathChars <* char '$') <|> (superscript <$> (char '^' *> tok)) <|> (subscript <$> (char '_' *> tok)) <|> (failUnlessLHS *> char '|' *> doLHSverb) @@ -667,6 +673,7 @@ , ("tabular", env "tabular" simpTable) , ("quote", blockQuote <$> env "quote" blocks) , ("quotation", blockQuote <$> env "quotation" blocks) + , ("verse", blockQuote <$> env "verse" blocks) , ("itemize", bulletList <$> listenv "itemize" (many item)) , ("description", definitionList <$> listenv "description" (many descItem)) , ("enumerate", ordered_list) 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 @@ -390,8 +390,8 @@ attributes :: GenParser Char st ([Char], [[Char]], [([Char], [Char])]) attributes = try $ do char '{' - many spaceChar - attrs <- many (attribute >>~ many spaceChar) + spnl + attrs <- many (attribute >>~ spnl) char '}' let (ids, classes, keyvals) = unzip3 attrs let firstNonNull [] = "" @@ -424,8 +424,9 @@ keyValAttr = try $ do key <- identifier char '=' - char '"' - val <- manyTill (satisfy (/='\n')) (char '"') + val <- enclosed (char '"') (char '"') anyChar + <|> enclosed (char '\'') (char '\'') anyChar + <|> many nonspaceChar return ("",[],[(key,val)]) codeBlockDelimited :: GenParser Char st Block @@ -1041,8 +1042,20 @@ where inner = innerSpace <|> (notFollowedBy' whitespace >> inline) innerSpace = try $ whitespace >>~ notFollowedBy' end +-- This is used to prevent exponential blowups for things like: +-- a**a*a**a*a**a*a**a*a**a*a**a*a** +nested :: GenParser Char ParserState a + -> GenParser Char ParserState a +nested p = do + nestlevel <- stateMaxNestingLevel `fmap` getState + guard $ nestlevel > 0 + updateState $ \st -> st{ stateMaxNestingLevel = stateMaxNestingLevel st - 1 } + res <- p + updateState $ \st -> st{ stateMaxNestingLevel = nestlevel } + return res + emph :: GenParser Char ParserState Inline -emph = Emph `liftM` +emph = Emph `fmap` nested (inlinesBetween starStart starEnd <|> inlinesBetween ulStart ulEnd) where starStart = char '*' >> lookAhead nonspaceChar starEnd = notFollowedBy' strong >> char '*' @@ -1050,7 +1063,7 @@ ulEnd = notFollowedBy' strong >> char '_' strong :: GenParser Char ParserState Inline -strong = Strong `liftM` +strong = Strong `liftM` nested (inlinesBetween starStart starEnd <|> inlinesBetween ulStart ulEnd) where starStart = string "**" >> lookAhead nonspaceChar starEnd = try $ string "**" 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 @@ -234,7 +234,8 @@ contents <- inlineListToMarkdown opts inlines st <- get let setext = writerSetextHeaders opts - return $ case level of + return $ nowrap + $ case level of 1 | setext -> contents <> cr <> text (replicate (offset contents) '=') <> blankline 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 @@ -157,7 +157,7 @@ contents <- inlineListToRST inlines let headerChar = if level > 5 then ' ' else "=-~^'" !! (level - 1) let border = text $ replicate (offset contents) headerChar - return $ contents $$ border $$ blankline + return $ nowrap $ contents $$ border $$ blankline blockToRST (CodeBlock (_,classes,_) str) = do opts <- stOptions <$> get let tabstop = writerTabStop opts