diff options
Diffstat (limited to 'src/Text/Pandoc/Readers/HTML.hs')
| -rw-r--r-- | src/Text/Pandoc/Readers/HTML.hs | 26 |
1 files changed, 21 insertions, 5 deletions
diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index 80279bf61..d1e4d0024 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -76,9 +76,18 @@ pBody :: TagParser [Block] pBody = pInTags "body" block pHead :: TagParser [Block] -pHead = pInTags "head" $ pTitle <|> ([] <$ pAnyTag) +pHead = pInTags "head" $ pTitle <|> pMetaTag <|> ([] <$ pAnyTag) where pTitle = pInTags "title" inline >>= setTitle . normalizeSpaces setTitle t = [] <$ (updateState $ B.setMeta "title" (B.fromList t)) + pMetaTag = do + mt <- pSatisfy (~== TagOpen "meta" []) + let name = fromAttrib "name" mt + if null name + then return [] + else do + let content = fromAttrib "content" mt + updateState $ B.setMeta name (B.text content) + return [] block :: TagParser [Block] block = choice @@ -207,7 +216,7 @@ pHeader = try $ do let bodyTitle = TagOpen tagtype attr ~== TagOpen "h1" [("class","title")] let level = read (drop 1 tagtype) contents <- liftM concat $ manyTill inline (pCloses tagtype <|> eof) - let ident = maybe "" id $ lookup "id" attr + let ident = fromMaybe "" $ lookup "id" attr let classes = maybe [] words $ lookup "class" attr let keyvals = [(k,v) | (k,v) <- attr, k /= "class", k /= "id"] return $ if bodyTitle @@ -257,7 +266,7 @@ pCol = try $ do skipMany pBlank return $ case lookup "width" attribs of Just x | not (null x) && last x == '%' -> - maybe 0.0 id $ safeRead ('0':'.':init x) + fromMaybe 0.0 $ safeRead ('0':'.':init x) _ -> 0.0 pColgroup :: TagParser [Double] @@ -467,7 +476,13 @@ pBlank = try $ do pTagContents :: Parser [Char] ParserState Inline pTagContents = - pStr <|> pSpace <|> smartPunctuation pTagContents <|> pSymbol <|> pBad + Math DisplayMath `fmap` mathDisplay + <|> Math InlineMath `fmap` mathInline + <|> pStr + <|> pSpace + <|> smartPunctuation pTagContents + <|> pSymbol + <|> pBad pStr :: Parser [Char] ParserState Inline pStr = do @@ -482,6 +497,7 @@ isSpecial '"' = True isSpecial '\'' = True isSpecial '.' = True isSpecial '-' = True +isSpecial '$' = True isSpecial '\8216' = True isSpecial '\8217' = True isSpecial '\8220' = True @@ -557,7 +573,7 @@ blockHtmlTags = ["address", "article", "aside", "blockquote", "body", "button", "noframes", "noscript", "object", "ol", "output", "p", "pre", "progress", "section", "table", "tbody", "textarea", "thead", "tfoot", "ul", "dd", "dt", "frameset", "li", "tbody", "td", "tfoot", - "th", "thead", "tr", "script", "style", "video"] + "th", "thead", "tr", "script", "style", "svg", "video"] -- We want to allow raw docbook in markdown documents, so we -- include docbook block tags here too. |