diff options
Diffstat (limited to 'src/Text/Pandoc/Readers')
| -rw-r--r-- | src/Text/Pandoc/Readers/Docx/Parse.hs | 17 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/HTML.hs | 4 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/LaTeX.hs | 2 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/Markdown.hs | 11 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/Org.hs | 10 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/RST.hs | 20 |
6 files changed, 45 insertions, 19 deletions
diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs index 29b661d10..5fd6b7a81 100644 --- a/src/Text/Pandoc/Readers/Docx/Parse.hs +++ b/src/Text/Pandoc/Readers/Docx/Parse.hs @@ -663,17 +663,20 @@ elemToParPart ns element return $ BookMark bmId bmName elemToParPart ns element | isElem ns "w" "hyperlink" element - , Just anchor <- findAttr (elemName ns "w" "anchor") element = do + , Just relId <- findAttr (elemName ns "r" "id") element = do runs <- mapD (elemToRun ns) (elChildren element) - return $ InternalHyperLink anchor runs + rels <- asks envRelationships + case lookupRelationship relId rels of + Just target -> do + case findAttr (elemName ns "w" "anchor") element of + Just anchor -> return $ ExternalHyperLink (target ++ '#':anchor) runs + Nothing -> return $ ExternalHyperLink target runs + Nothing -> return $ ExternalHyperLink "" runs elemToParPart ns element | isElem ns "w" "hyperlink" element - , Just relId <- findAttr (elemName ns "r" "id") element = do + , Just anchor <- findAttr (elemName ns "w" "anchor") element = do runs <- mapD (elemToRun ns) (elChildren element) - rels <- asks envRelationships - return $ case lookupRelationship relId rels of - Just target -> ExternalHyperLink target runs - Nothing -> ExternalHyperLink "" runs + return $ InternalHyperLink anchor runs elemToParPart ns element | isElem ns "m" "oMath" element = (eitherToD $ readOMML $ showElement element) >>= (return . PlainOMath) diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index 4e0bb375a..2a23f2a62 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -740,7 +740,7 @@ pSpace = many1 (satisfy isSpace) >> return B.space -- eitherBlockOrInline :: [String] -eitherBlockOrInline = ["audio", "applet", "button", "iframe", +eitherBlockOrInline = ["audio", "applet", "button", "iframe", "embed", "del", "ins", "progress", "map", "area", "noscript", "script", "object", "svg", "video", "source"] @@ -758,7 +758,7 @@ blockHtmlTags :: [String] blockHtmlTags = ["?xml", "!DOCTYPE", "address", "article", "aside", "blockquote", "body", "button", "canvas", "caption", "center", "col", "colgroup", "dd", "dir", "div", - "dl", "dt", "embed", "fieldset", "figcaption", "figure", + "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "head", "header", "hgroup", "hr", "html", "isindex", "menu", "noframes", "ol", "output", "p", "pre", diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 9f51e9a8f..9420d602f 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -494,6 +494,7 @@ inlineCommands = M.fromList $ , ("citealp", citation "citealp" NormalCitation False) , ("citealp*", citation "citealp*" NormalCitation False) , ("autocite", citation "autocite" NormalCitation False) + , ("smartcite", citation "smartcite" NormalCitation False) , ("footcite", inNote <$> citation "footcite" NormalCitation False) , ("parencite", citation "parencite" NormalCitation False) , ("supercite", citation "supercite" NormalCitation False) @@ -516,6 +517,7 @@ inlineCommands = M.fromList $ , ("supercites", citation "supercites" NormalCitation True) , ("footcitetexts", inNote <$> citation "footcitetexts" NormalCitation True) , ("Autocite", citation "Autocite" NormalCitation False) + , ("Smartcite", citation "Smartcite" NormalCitation False) , ("Footcite", citation "Footcite" NormalCitation False) , ("Parencite", citation "Parencite" NormalCitation False) , ("Supercite", citation "Supercite" NormalCitation False) diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 7a3be8291..b8487b4e6 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -117,6 +117,12 @@ isBlank _ = False -- auxiliary functions -- +-- | Succeeds when we're in list context. +inList :: MarkdownParser () +inList = do + ctx <- stateParserContext <$> getState + guard (ctx == ListItemState) + isNull :: F Inlines -> Bool isNull ils = B.isNull $ runF ils def @@ -926,6 +932,8 @@ para = try $ do <|> (guardEnabled Ext_backtick_code_blocks >> () <$ lookAhead codeBlockFenced) <|> (guardDisabled Ext_blank_before_header >> () <$ lookAhead header) <|> (guardEnabled Ext_lists_without_preceding_blankline >> + -- Avoid creating a paragraph in a nested list. + notFollowedBy' inList >> () <$ lookAhead listStart) <|> do guardEnabled Ext_native_divs inHtmlBlock <- stateInHtmlBlock <$> getState @@ -1610,8 +1618,7 @@ endline = try $ do newline notFollowedBy blankline -- parse potential list-starts differently if in a list: - st <- getState - when (stateParserContext st == ListItemState) $ notFollowedBy listStart + notFollowedBy (inList >> listStart) guardDisabled Ext_lists_without_preceding_blankline <|> notFollowedBy listStart guardEnabled Ext_blank_before_blockquote <|> notFollowedBy emailBlockQuoteStart guardEnabled Ext_blank_before_header <|> notFollowedBy (char '#') -- atx header diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs index 4c34b7bd5..579e38a38 100644 --- a/src/Text/Pandoc/Readers/Org.hs +++ b/src/Text/Pandoc/Readers/Org.hs @@ -879,18 +879,18 @@ bulletListStart = bulletListStart' Nothing bulletListStart' :: Maybe Int -> OrgParser Int -- returns length of bulletList prefix, inclusive of marker -bulletListStart' Nothing = do ind <- many spaceChar +bulletListStart' Nothing = do ind <- length <$> many spaceChar + when (ind == 0) $ notFollowedBy (char '*') oneOf bullets many1 spaceChar - return $ length ind + 1 + return (ind + 1) -- Unindented lists are legal, but they can't use '*' bullets -- We return n to maintain compatibility with the generic listItem bulletListStart' (Just n) = do count (n-1) spaceChar - oneOf validBullets + when (n == 1) $ notFollowedBy (char '*') + oneOf bullets many1 spaceChar return n - where validBullets = if n == 1 then noAsterisks else bullets - noAsterisks = filter (/= '*') bullets bullets :: String bullets = "*+-" diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs index e5eccb116..732956981 100644 --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -47,7 +47,7 @@ import Text.Pandoc.Builder (Inlines, Blocks, trimInlines, (<>)) import qualified Text.Pandoc.Builder as B import Data.Monoid (mconcat, mempty) import Data.Sequence (viewr, ViewR(..)) -import Data.Char (toLower, isHexDigit) +import Data.Char (toLower, isHexDigit, isSpace) -- | Parse reStructuredText string and return Pandoc document. readRST :: ReaderOptions -- ^ Reader options @@ -335,6 +335,13 @@ indentedBlock = try $ do optional blanklines return $ unlines lns +quotedBlock :: Parser [Char] st [Char] +quotedBlock = try $ do + quote <- lookAhead $ oneOf "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~" + lns <- many1 $ lookAhead (char quote) >> anyLine + optional blanklines + return $ unlines lns + codeBlockStart :: Parser [Char] st Char codeBlockStart = string "::" >> blankline >> blankline @@ -342,7 +349,8 @@ codeBlock :: Parser [Char] st Blocks codeBlock = try $ codeBlockStart >> codeBlockBody codeBlockBody :: Parser [Char] st Blocks -codeBlockBody = try $ B.codeBlock . stripTrailingNewlines <$> indentedBlock +codeBlockBody = try $ B.codeBlock . stripTrailingNewlines <$> + (indentedBlock <|> quotedBlock) lhsCodeBlock :: RSTParser Blocks lhsCodeBlock = try $ do @@ -513,7 +521,6 @@ directive = try $ do -- TODO: line-block, parsed-literal, table, csv-table, list-table -- date -- include --- class -- title directive' :: RSTParser Blocks directive' = do @@ -594,6 +601,13 @@ directive' = do Just t -> B.link (escapeURI $ trim t) "" $ B.image src "" alt Nothing -> B.image src "" alt + "class" -> do + let attrs = ("", (splitBy isSpace $ trim top), map (\(k,v) -> (k, trimr v)) fields) + -- directive content or the first immediately following element + children <- case body of + "" -> block + _ -> parseFromString parseBlocks body' + return $ B.divWith attrs children _ -> return mempty -- TODO: |