diff --git a/INSTALL b/INSTALL --- a/INSTALL +++ b/INSTALL @@ -40,6 +40,15 @@ make test + Note: if you see errors like the following, they're due to differences + between different versions of the xhtml library, and can safely be + disregarded: + + 2c2 + < is present (previously, + only part of the document would be parsed if an error was + found; now a proper error message is given). + + Added new constant eitherBlockOrInline with elements that may + count either as block-level or as inline. Modified isInline and + isBlock to take this into account. + + Modified rawHtmlBlock to accept any tag (even an inline tag): + this is innocuous, because rawHtmlBlock is tried only if a regular + inline element can't be parsed. + + Added a necessary 'try' in definition of 'para'. + + * Fixed bug in markdown ordered list parsing. The problem was that + anyOrderedListStart did not check for a space following the + ordered list marker. So in 'A.B. 2007' the parser would be + expecting a list item, but would not find one, causing an error. + Fixed a similar bug in the RST reader. Resolves Issue #22. + + * Refactored RST and Markdown readers using parseFromString. + + * LaTeX reader will now skip anything after \end{document}. + + * Fixed blockquote output in markdown writer: previously, block + quotes in indented contexts would be indented only in the first + line. + + * Added note to INSTALL about variations in versions of the xhtml + library that can lead to failed tests (thanks to Leif LeBaron). + + -- John MacFarlane Sun, 19 Aug 2007 00:00:00 -0400 + pandoc (0.4) unstable; urgency=low [ John MacFarlane ] @@ -404,7 +439,6 @@ libghc6-xhtml-dev. Removed libghc6-html-dev. + Suggest texlive-latex-recommended | tetex-extra instead of tetex-bin. This brings in fancyvrb and unicode support. - -- Recai Oktaş Tue, 16 Jan 2007 00:37:21 +0200 diff --git a/pandoc.cabal b/pandoc.cabal --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ Name: pandoc -Version: 0.4 +Version: 0.41 License: GPL License-File: COPYING Copyright: (c) 2006-2007 John MacFarlane diff --git a/src/Main.hs b/src/Main.hs --- a/src/Main.hs +++ b/src/Main.hs @@ -43,7 +43,7 @@ import Control.Monad ( (>>=) ) version :: String -version = "0.4" +version = "0.41" copyrightMessage :: String copyrightMessage = "\nCopyright (C) 2006-7 John MacFarlane\n\ diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -59,12 +59,22 @@ -- Constants -- +eitherBlockOrInline = ["applet", "button", "del", "iframe", "ins", + "map", "area", "object", "script"] + inlineHtmlTags = ["a", "abbr", "acronym", "b", "basefont", "bdo", "big", "br", "cite", "code", "dfn", "em", "font", "i", "img", "input", "kbd", "label", "q", "s", "samp", "select", "small", "span", "strike", "strong", "sub", "sup", - "textarea", "tt", "u", "var"] + "textarea", "tt", "u", "var"] ++ eitherBlockOrInline +blockHtmlTags = ["address", "blockquote", "center", "dir", "div", + "dl", "fieldset", "form", "h1", "h2", "h3", "h4", + "h5", "h6", "hr", "isindex", "menu", "noframes", + "noscript", "ol", "p", "pre", "table", "ul", "dd", + "dt", "frameset", "li", "tbody", "td", "tfoot", + "th", "thead", "tr"] ++ eitherBlockOrInline + -- -- HTML utility functions -- @@ -171,12 +181,15 @@ char '>' return $ "" --- | Returns @True@ if the tag is an inline tag. +-- | Returns @True@ if the tag is (or can be) an inline tag. isInline tag = (extractTagType tag) `elem` inlineHtmlTags +-- | Returns @True@ if the tag is (or can be) a block tag. +isBlock tag = (extractTagType tag) `elem` blockHtmlTags + anyHtmlBlockTag = try $ do tag <- anyHtmlTag <|> anyHtmlEndTag - if isInline tag then fail "inline tag" else return tag + if isBlock tag then return tag else fail "inline tag" anyHtmlInlineTag = try $ do tag <- anyHtmlTag <|> anyHtmlEndTag @@ -193,7 +206,7 @@ rawHtmlBlock = try $ do notFollowedBy' (htmlTag "/body" <|> htmlTag "/html") - body <- htmlBlockElement <|> anyHtmlBlockTag + body <- htmlBlockElement <|> anyHtmlTag <|> anyHtmlEndTag sp <- many space state <- getState if stateParseRaw state then return (RawHtml (body ++ sp)) else return Null @@ -260,8 +273,7 @@ spaces optional (htmlEndTag "body") spaces - optional (htmlEndTag "html") - many anyChar -- ignore anything after + optional (htmlEndTag "html" >> many anyChar) -- ignore anything after eof return $ Pandoc (Meta title authors date) blocks @@ -383,7 +395,8 @@ -- paragraph block -- -para = htmlTag "p" >> inlinesTilEnd "p" >>= return . Para . normalizeSpaces +para = try $ htmlTag "p" >> inlinesTilEnd "p" >>= + return . Para . normalizeSpaces -- -- plain block 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 @@ -117,7 +117,8 @@ spaces blocks <- parseBlocks spaces - optional $ try (string "\\end{document}") -- might not be present (fragment) + optional $ try (string "\\end{document}" >> many anyChar) + -- might not be present (fragment) spaces eof state <- getState 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 @@ -195,10 +195,7 @@ raw <- sepBy rawLines (try (blankline >> indentSpaces)) optional blanklines -- parse the extracted text, which may contain various block elements: - rest <- getInput - setInput $ (joinWithSep "\n" raw) ++ "\n\n" - contents <- parseBlocks - setInput rest + contents <- parseFromString parseBlocks $ (joinWithSep "\n" raw) ++ "\n\n" return $ NoteBlock ref contents -- @@ -307,10 +304,7 @@ blockQuote = do raw <- emailBlockQuote <|> emacsBoxQuote -- parse the extracted block, which may contain various block elements: - rest <- getInput - setInput $ (joinWithSep "\n" raw) ++ "\n\n" - contents <- parseBlocks - setInput rest + contents <- parseFromString parseBlocks $ (joinWithSep "\n" raw) ++ "\n\n" return $ BlockQuote contents -- @@ -334,8 +328,9 @@ if stateStrict state then do many1 digit char '.' + spaceChar return (1, DefaultStyle, DefaultDelim) - else anyOrderedListMarker + else anyOrderedListMarker >>~ spaceChar orderedListStart style delim = try $ do optional newline -- if preceded by a Plain block in a list context @@ -346,7 +341,7 @@ char '.' return 1 else orderedListMarker style delim - oneOf spaceChars + spaceChar skipSpaces -- parse a line of a list item (start = parser for beginning of list item) @@ -392,11 +387,8 @@ let oldContext = stateParserContext state setState $ state {stateParserContext = ListItemState} -- parse the extracted block, which may contain various block elements: - rest <- getInput let raw = concat (first:continuations) - setInput raw - contents <- parseBlocks - setInput rest + contents <- parseFromString parseBlocks raw updateState (\st -> st {stateParserContext = oldContext}) return contents @@ -418,10 +410,7 @@ state <- getState let oldContext = stateParserContext state -- parse the extracted block, which may contain various block elements: - rest <- getInput - setInput (concat raw) - contents <- parseBlocks - setInput rest + contents <- parseFromString parseBlocks $ concat raw updateState (\st -> st {stateParserContext = oldContext}) return ((normalizeSpaces term), contents) diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -328,10 +328,7 @@ blockQuote = try $ do raw <- indentedBlock True -- parse the extracted block, which may contain various block elements: - rest <- getInput - setInput $ raw ++ "\n\n" - contents <- parseBlocks - setInput rest + contents <- parseFromString parseBlocks $ raw ++ "\n\n" return $ BlockQuote contents -- @@ -344,10 +341,7 @@ term <- many1Till inline endline raw <- indentedBlock True -- parse the extracted block, which may contain various block elements: - rest <- getInput - setInput $ raw ++ "\n\n" - contents <- parseBlocks - setInput rest + contents <- parseFromString parseBlocks $ raw ++ "\n\n" return (normalizeSpaces term, contents) definitionList = try $ do @@ -408,17 +402,14 @@ -- see definition of "endline" state <- getState let oldContext = stateParserContext state - remaining <- getInput setState $ state {stateParserContext = ListItemState} -- parse the extracted block, which may itself contain block elements - setInput $ concat (first:rest) ++ blanks - parsed <- parseBlocks - setInput remaining + parsed <- parseFromString parseBlocks $ concat (first:rest) ++ blanks updateState (\st -> st {stateParserContext = oldContext}) return parsed orderedList = try $ do - (start, style, delim) <- lookAhead anyOrderedListMarker + (start, style, delim) <- lookAhead (anyOrderedListMarker >>~ spaceChar) items <- many1 (listItem (orderedListStart style delim)) let items' = compactify items return $ OrderedList (start, style, delim) items' @@ -551,7 +542,8 @@ -- parse potential list-starts at beginning of line differently in a list: st <- getState if ((stateParserContext st) == ListItemState) - then notFollowedBy' anyOrderedListMarker >> notFollowedBy' bulletListStart + then notFollowedBy (anyOrderedListMarker >> spaceChar) >> + notFollowedBy' bulletListStart else return () return Space 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 @@ -91,8 +91,8 @@ -- | Return markdown representation of a note. noteToMarkdown :: WriterOptions -> Int -> [Block] -> State WriterState Doc -noteToMarkdown opts num note = do - contents <- blockListToMarkdown opts note +noteToMarkdown opts num blocks = do + contents <- blockListToMarkdown opts blocks let marker = text "[^" <> text (show num) <> text "]:" return $ hang marker (writerTabStop opts) contents @@ -163,8 +163,8 @@ (nest (writerTabStop opts) $ vcat $ map text (lines str)) <> text "\n" blockToMarkdown opts (BlockQuote blocks) = do contents <- blockListToMarkdown opts blocks - let quotedContents = unlines $ map ("> " ++) $ lines $ render contents - return $ text quotedContents + return $ (vcat $ map (text . ("> " ++)) $ lines $ render contents) <> + text "\n" blockToMarkdown opts (Table caption aligns widths headers rows) = do caption' <- inlineListToMarkdown opts caption let caption'' = if null caption diff --git a/tests/testsuite.native b/tests/testsuite.native --- a/tests/testsuite.native +++ b/tests/testsuite.native @@ -178,6 +178,8 @@ , OrderedList (1,DefaultStyle,DefaultDelim) [ [ Plain [Str "Nested",Str "."] ] ] ] ] +, Para [Str "Should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "list",Space,Str "item:"] +, Para [Str "M",Str ".",Str "A",Str ".",Space,Str "2007"] , HorizontalRule , Header 1 [Str "Definition",Space,Str "Lists"] , Para [Str "Tight",Space,Str "using",Space,Str "spaces:"] diff --git a/tests/testsuite.txt b/tests/testsuite.txt --- a/tests/testsuite.txt +++ b/tests/testsuite.txt @@ -281,6 +281,10 @@ #. More. #. Nested. +Should not be a list item: + +M.A. 2007 + * * * * * # Definition Lists diff --git a/tests/writer.context b/tests/writer.context --- a/tests/writer.context +++ b/tests/writer.context @@ -399,6 +399,10 @@ \item Nested. \stopltxenum \stopltxenum +Should not be a list item: + +M.A. 2007 + \thinrule \section{Definition Lists} diff --git a/tests/writer.docbook b/tests/writer.docbook --- a/tests/writer.docbook +++ b/tests/writer.docbook @@ -642,6 +642,12 @@ + + Should not be a list item: + + + M.A. 2007 +
diff --git a/tests/writer.html b/tests/writer.html --- a/tests/writer.html +++ b/tests/writer.html @@ -449,6 +449,10 @@ >

Should not be a list item:

M.A. 2007

Definition Lists