Merge branch 'master' of github.com:jgm/pandoc

6 files changed, 14 insertions, 322 deletions

diff --git a/src/Text/Pandoc/Biblio.hs b/src/Text/Pandoc/Biblio.hs
deleted file mode 100644
index 1c0975f11..000000000
--- a/src/Text/Pandoc/Biblio.hs
+++ /dev/null
@@ -1,216 +0,0 @@
-{-# LANGUAGE PatternGuards #-}
-{-
-Copyright (C) 2008 Andrea Rossato <andrea.rossato@ing.unitn.it>
-
-This program is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program; if not, write to the Free Software
-Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
--}
-
-{- |
-   Module      : Text.Pandoc.Biblio
-   Copyright   : Copyright (C) 2008-2010 Andrea Rossato
-   License     : GNU GPL, version 2 or above
-
-   Maintainer  : Andrea Rossato <andrea.rossato@unitn.it>
-   Stability   : alpha
-   Portability : portable
--}
-
-module Text.Pandoc.Biblio ( processBiblio ) where
-
-import Data.List
-import Data.Char ( isDigit, isPunctuation )
-import qualified Data.Map as M
-import Text.CSL hiding ( Cite(..), Citation(..), endWithPunct )
-import qualified Text.CSL as CSL ( Cite(..) )
-import Text.Pandoc.Definition
-import Text.Pandoc.Generic
-import Text.Pandoc.Walk
-import Text.Pandoc.Shared (stringify)
-import Text.Parsec hiding (State)
-import Control.Monad
-import Control.Monad.State
-
--- | Process a 'Pandoc' document by adding citations formatted
--- according to a CSL style, using 'citeproc' from citeproc-hs.
-processBiblio :: Maybe Style -> [Reference] -> Pandoc -> Pandoc
-processBiblio Nothing _ p = p
-processBiblio _      [] p = p
-processBiblio (Just style) r p =
-  let p'         = evalState (bottomUpM setHash p) 1
-      grps       = query getCitation p'
-      result     = citeproc procOpts style r (setNearNote style $
-                      map (map toCslCite) grps)
-      cits_map   = M.fromList $ zip grps (citations result)
-      biblioList = map (renderPandoc' style) (bibliography result)
-      Pandoc m b = bottomUp mvPunct . deNote . topDown (processCite style cits_map) $ p'
-      (bs, lastb) = case reverse b of
-                         x@(Header _ _ _) : xs -> (reverse xs, [x])
-                         _                     -> (b,  [])
-  in  Pandoc m $ bs ++ [Div ("",["references"],[]) (lastb ++ biblioList)]
-
--- | Substitute 'Cite' elements with formatted citations.
-processCite :: Style -> M.Map [Citation] [FormattedOutput] -> Inline -> Inline
-processCite s cs (Cite t _) =
-   case M.lookup t cs of
-        Just (x:xs)
-          | isTextualCitation t && not (null xs) ->
-             let xs' = renderPandoc s xs
-             in  if styleClass s == "note"
-                    then Cite t (renderPandoc s [x] ++ [Note [Para xs']])
-                    else Cite t (renderPandoc s [x] ++ [Space | not (startWithPunct xs')] ++ xs')
-          | otherwise -> if styleClass s == "note"
-                            then Cite t [Note [Para $ renderPandoc s (x:xs)]]
-                            else Cite t (renderPandoc s (x:xs))
-        _             -> Strong [Str "???"]  -- TODO raise error instead?
-processCite _ _ x = x
-
-isNote :: Inline -> Bool
-isNote (Note _) = True
-isNote (Cite _ [Note _]) = True
-isNote _ = False
-
-mvPunct :: [Inline] -> [Inline]
-mvPunct (Space : Space : xs) = Space : xs
-mvPunct (Space : x : ys) | isNote x, startWithPunct ys =
-   Str (headInline ys) : x : tailFirstInlineStr ys
-mvPunct (Space : x : ys) | isNote x = x : ys
-mvPunct xs = xs
-
--- A replacement for citeproc-hs's endWithPunct, which wrongly treats
--- a sentence ending in '.)' as not ending with punctuation, leading
--- to an extra period.
-endWithPunct :: [Inline] -> Bool
-endWithPunct [] = True
-endWithPunct xs@(_:_) = case reverse (stringify [last xs]) of
-                              []                       -> True
-                              (')':c:_) | isEndPunct c -> True
-                              (c:_) | isEndPunct c     -> True
-                                    | otherwise        -> False
-  where isEndPunct c = c `elem` ".,;:!?"
-
-deNote :: Pandoc -> Pandoc
-deNote = topDown go
-  where go (Cite (c:cs) [Note xs]) =
-            Cite (c:cs) [Note $ bottomUp go' $ sanitize c xs]
-        go (Note xs) = Note $ bottomUp go' xs
-        go x = x
-        go' (Note [Para xs]:ys) =
-             if startWithPunct ys && endWithPunct xs
-                then initInline xs ++ ys
-                else xs ++ ys
-        go' xs = xs
-        sanitize :: Citation -> [Block] -> [Block]
-        sanitize Citation{citationPrefix = pref} [Para xs] =
-           case (null pref, endWithPunct xs) of
-                (True, False)  -> [Para $ xs ++ [Str "."]]
-                (True, True)   -> [Para xs]
-                (False, False) -> [Para $ toCapital $ xs ++ [Str "."]]
-                (False, True)  -> [Para $ toCapital xs]
-        sanitize _ bs = bs
-
-isTextualCitation :: [Citation] -> Bool
-isTextualCitation (c:_) = citationMode c == AuthorInText
-isTextualCitation _     = False
-
--- | Retrieve all citations from a 'Pandoc' docuument. To be used with
--- 'query'.
-getCitation :: Inline -> [[Citation]]
-getCitation i | Cite t _ <- i = [t]
-              | otherwise     = []
-
-setHash :: Citation -> State Int Citation
-setHash c = do
-  ident <- get
-  put $ ident + 1
-  return c{ citationHash = ident }
-
-toCslCite :: Citation -> CSL.Cite
-toCslCite c
-    = let (l, s)  = locatorWords $ citationSuffix c
-          (la,lo) = parseLocator l
-          s'      = case (l,s) of
-                         -- treat a bare locator as if it begins with space
-                         -- so @item1 [blah] is like [@item1, blah]
-                         ("",(x:_))
-                           | not (isPunct x) -> [Space] ++ s
-                         _                   -> s
-          isPunct (Str (x:_)) = isPunctuation x
-          isPunct _           = False
-          citMode = case citationMode c of
-                      AuthorInText   -> (True, False)
-                      SuppressAuthor -> (False,True )
-                      NormalCitation -> (False,False)
-      in   emptyCite { CSL.citeId         = citationId c
-                     , CSL.citePrefix     = PandocText $ citationPrefix c
-                     , CSL.citeSuffix     = PandocText s'
-                     , CSL.citeLabel      = la
-                     , CSL.citeLocator    = lo
-                     , CSL.citeNoteNumber = show $ citationNoteNum c
-                     , CSL.authorInText   = fst citMode
-                     , CSL.suppressAuthor = snd citMode
-                     , CSL.citeHash       = citationHash c
-                     }
-
-locatorWords :: [Inline] -> (String, [Inline])
-locatorWords inp =
-  case parse pLocatorWords "suffix" $ breakup inp of
-       Right r   -> r
-       Left _    -> ("",inp)
-   where breakup [] = []
-         breakup (Str x : xs) = map Str (splitup x) ++ breakup xs
-         breakup (x : xs) = x : breakup xs
-         splitup = groupBy (\x y -> x /= '\160' && y /= '\160')
-
-pLocatorWords :: Parsec [Inline] st (String, [Inline])
-pLocatorWords = do
-  l <- pLocator
-  s <- getInput -- rest is suffix
-  if length l > 0 && last l == ','
-     then return (init l, Str "," : s)
-     else return (l, s)
-
-pMatch :: (Inline -> Bool) -> Parsec [Inline] st Inline
-pMatch condition = try $ do
-  t <- anyToken
-  guard $ condition t
-  return t
-
-pSpace :: Parsec [Inline] st Inline
-pSpace = pMatch (\t -> t == Space || t == Str "\160")
-
-pLocator :: Parsec [Inline] st String
-pLocator = try $ do
-  optional $ pMatch (== Str ",")
-  optional pSpace
-  f  <- (guardFollowingDigit >> return [Str "p"]) -- "page" the default
-     <|> many1 (notFollowedBy pSpace >> anyToken)
-  gs <- many1 pWordWithDigits
-  return $ stringify f ++ (' ' : unwords gs)
-
-guardFollowingDigit :: Parsec [Inline] st ()
-guardFollowingDigit = do
-  t <- lookAhead anyToken
-  case t of
-       Str (d:_) | isDigit d -> return ()
-       _                     -> mzero
-
-pWordWithDigits :: Parsec [Inline] st String
-pWordWithDigits = try $ do
-  optional pSpace
-  r <- many1 (notFollowedBy pSpace >> anyToken)
-  let s = stringify r
-  guard $ any isDigit s
-  return s
-
diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index c7c37d6b8..48e418ab2 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -48,7 +48,6 @@ import Data.Set (Set)
 import qualified Data.Set as Set
 import Data.Default
 import Text.Pandoc.Highlighting (Style, pygments)
-import qualified Text.CSL as CSL
 
 -- | Individually selectable syntax extensions.
 data Extension =
@@ -205,8 +204,6 @@ data ReaderOptions = ReaderOptions{
        , readerOldDashes       :: Bool -- ^ Use pandoc <= 1.8.2.1 behavior
                                        --   in parsing dashes; -- is em-dash;
                                        --   - before numerial is en-dash
-       , readerReferences      :: [CSL.Reference]  -- ^ Bibliographic references
-       , readerCitationStyle   :: Maybe CSL.Style -- ^ Citation style
        , readerApplyMacros     :: Bool -- ^ Apply macros to TeX math
        , readerIndentedCodeClasses :: [String] -- ^ Default classes for
                                        -- indented code blocks
@@ -223,8 +220,6 @@ instance Default ReaderOptions
                , readerColumns               = 80
                , readerTabStop               = 4
                , readerOldDashes             = False
-               , readerReferences            = []
-               , readerCitationStyle         = Nothing
                , readerApplyMacros           = True
                , readerIndentedCodeClasses   = []
                , readerDefaultImageExtension = ""
@@ -289,7 +284,6 @@ data WriterOptions = WriterOptions
   , writerSourceURL        :: Maybe String  -- ^ Absolute URL + directory of 1st source file
   , writerUserDataDir      :: Maybe FilePath -- ^ Path of user data directory
   , writerCiteMethod       :: CiteMethod -- ^ How to print cites
-  , writerBiblioFiles      :: [FilePath] -- ^ Biblio files to use for citations
   , writerHtml5            :: Bool       -- ^ Produce HTML5
   , writerHtmlQTags        :: Bool       -- ^ Use @<q>@ tags for quotes in HTML
   , writerBeamer           :: Bool       -- ^ Produce beamer LaTeX slide show
@@ -332,7 +326,6 @@ instance Default WriterOptions where
                       , writerSourceURL        = Nothing
                       , writerUserDataDir      = Nothing
                       , writerCiteMethod       = Citeproc
-                      , writerBiblioFiles      = []
                       , writerHtml5            = False
                       , writerHtmlQTags        = False
                       , writerBeamer           = False
diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs
index 028d83e24..5d73134cd 100644
--- a/src/Text/Pandoc/Readers/LaTeX.hs
+++ b/src/Text/Pandoc/Readers/LaTeX.hs
@@ -38,7 +38,6 @@ import Text.Pandoc.Definition
 import Text.Pandoc.Walk
 import Text.Pandoc.Shared
 import Text.Pandoc.Options
-import Text.Pandoc.Biblio (processBiblio)
 import Text.Pandoc.Parsing hiding ((<|>), many, optional, space)
 import qualified Text.Pandoc.UTF8 as UTF8
 import Data.Char ( chr, ord )
@@ -47,6 +46,7 @@ import Text.Pandoc.Builder
 import Data.Char (isLetter)
 import Control.Applicative
 import Data.Monoid
+import Data.Maybe (fromMaybe)
 import System.Environment (getEnv)
 import System.FilePath (replaceExtension, (</>))
 import Data.List (intercalate, intersperse)
@@ -67,9 +67,7 @@ parseLaTeX = do
   eof
   st <- getState
   let meta = stateMeta st
-  refs <- getOption readerReferences
-  mbsty <- getOption readerCitationStyle
-  let (Pandoc _ bs') = processBiblio mbsty refs $ doc bs
+  let (Pandoc _ bs') = doc bs
   return $ Pandoc meta bs'
 
 type LP = Parser [Char] ParserState
@@ -903,7 +901,7 @@ environments = M.fromList
                                       lookup "numbers" options == Just "left" ]
                                  ++ maybe [] (:[]) (lookup "language" options
                                          >>= fromListingsLanguage)
-                      let attr = ("",classes,kvs)
+                      let attr = (fromMaybe "" (lookup "label" options),classes,kvs)
                       codeBlockWith attr <$> (verbEnv "lstlisting"))
   , ("minted",     do options <- option [] keyvals
                       lang <- grouped (many1 $ satisfy (/='}'))
diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 05662d9b5..658335202 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -54,7 +54,6 @@ import Text.Pandoc.Parsing hiding (tableWith)
 import Text.Pandoc.Readers.LaTeX ( rawLaTeXInline, rawLaTeXBlock )
 import Text.Pandoc.Readers.HTML ( htmlTag, htmlInBalanced, isInlineTag, isBlockTag,
                                   isTextTag, isCommentTag )
-import Text.Pandoc.Biblio (processBiblio)
 import Data.Monoid (mconcat, mempty)
 import Control.Applicative ((<$>), (<*), (*>), (<$))
 import Control.Monad
@@ -327,9 +326,7 @@ parseMarkdown = do
   st <- getState
   let meta = runF (stateMeta' st) st
   let Pandoc _ bs = B.doc $ runF blocks st
-  mbsty <- getOption readerCitationStyle
-  refs <- getOption readerReferences
-  return $ processBiblio mbsty refs $ Pandoc meta bs
+  return $ Pandoc meta bs
 
 addWarning :: Maybe SourcePos -> String -> MarkdownParser ()
 addWarning mbpos msg =
diff --git a/src/Text/Pandoc/Readers/TeXMath.hs b/src/Text/Pandoc/Readers/TeXMath.hs
index fe49a992e..1f7088f72 100644
--- a/src/Text/Pandoc/Readers/TeXMath.hs
+++ b/src/Text/Pandoc/Readers/TeXMath.hs
@@ -30,93 +30,13 @@ Conversion of TeX math to a list of 'Pandoc' inline elements.
 module Text.Pandoc.Readers.TeXMath ( readTeXMath ) where
 
 import Text.Pandoc.Definition
-import Text.TeXMath.Types
-import Text.TeXMath.Parser
+import Text.TeXMath
 
 -- | Converts a raw TeX math formula to a list of 'Pandoc' inlines.
 -- Defaults to raw formula between @$@ characters if entire formula
 -- can't be converted.
 readTeXMath :: String    -- ^ String to parse (assumes @'\n'@ line endings)
             -> [Inline]
-readTeXMath inp = case texMathToPandoc inp of
+readTeXMath inp = case texMathToPandoc DisplayInline inp of
                         Left _    -> [Str ("$" ++ inp ++ "$")]
                         Right res -> res
-
-texMathToPandoc :: String -> Either String [Inline]
-texMathToPandoc inp = inp `seq`
-  case parseFormula inp of
-         Left err    -> Left err
-         Right exps  -> case expsToInlines exps of
-                             Nothing  -> Left "Formula too complex for [Inline]"
-                             Just r   -> Right r
-
-expsToInlines :: [Exp] -> Maybe [Inline]
-expsToInlines xs = do
-  res <- mapM expToInlines xs
-  return (concat res)
-
-expToInlines :: Exp -> Maybe [Inline]
-expToInlines (ENumber s) = Just [Str s]
-expToInlines (EIdentifier s) = Just [Emph [Str s]]
-expToInlines (EMathOperator s) = Just [Str s]
-expToInlines (ESymbol t s) = Just $ addSpace t (Str s)
-  where addSpace Op x = [x, thinspace]
-        addSpace Bin x = [medspace, x, medspace]
-        addSpace Rel x = [widespace, x, widespace]
-        addSpace Pun x = [x, thinspace]
-        addSpace _ x = [x]
-        thinspace = Str "\x2006"
-        medspace  = Str "\x2005"
-        widespace = Str "\x2004"
-expToInlines (EStretchy x) = expToInlines x
-expToInlines (EDelimited start end xs) = do
-  xs' <- mapM expToInlines xs
-  return $ [Str start] ++ concat xs' ++ [Str end]
-expToInlines (EGrouped xs) = expsToInlines xs
-expToInlines (ESpace "0.167em") = Just [Str "\x2009"]
-expToInlines (ESpace "0.222em") = Just [Str "\x2005"]
-expToInlines (ESpace "0.278em") = Just [Str "\x2004"]
-expToInlines (ESpace "0.333em") = Just [Str "\x2004"]
-expToInlines (ESpace "1em")     = Just [Str "\x2001"]
-expToInlines (ESpace "2em")     = Just [Str "\x2001\x2001"]
-expToInlines (ESpace _)         = Just [Str " "]
-expToInlines (EBinary _ _ _) = Nothing
-expToInlines (ESub x y) = do
-  x' <- expToInlines x
-  y' <- expToInlines y
-  return $ x' ++ [Subscript y']
-expToInlines (ESuper x y) = do
-  x' <- expToInlines x
-  y' <- expToInlines y
-  return $ x' ++ [Superscript y']
-expToInlines (ESubsup x y z) = do
-  x' <- expToInlines x
-  y' <- expToInlines y
-  z' <- expToInlines z
-  return $ x' ++ [Subscript y'] ++ [Superscript z']
-expToInlines (EDown x y) = expToInlines (ESub x y)
-expToInlines (EUp x y) = expToInlines (ESuper x y)
-expToInlines (EDownup x y z) = expToInlines (ESubsup x y z)
-expToInlines (EText TextNormal x) = Just [Str x]
-expToInlines (EText TextBold x) = Just [Strong [Str x]]
-expToInlines (EText TextMonospace x) = Just [Code nullAttr x]
-expToInlines (EText TextItalic x) = Just [Emph [Str x]]
-expToInlines (EText _ x) = Just [Str x]
-expToInlines (EOver (EGrouped [EIdentifier [c]]) (ESymbol Accent [accent])) =
-    case accent of
-         '\x203E' -> Just [Emph [Str [c,'\x0304']]]  -- bar
-         '\x00B4' -> Just [Emph [Str [c,'\x0301']]]  -- acute
-         '\x0060' -> Just [Emph [Str [c,'\x0300']]]  -- grave
-         '\x02D8' -> Just [Emph [Str [c,'\x0306']]]  -- breve
-         '\x02C7' -> Just [Emph [Str [c,'\x030C']]]  -- check
-         '.'      -> Just [Emph [Str [c,'\x0307']]]  -- dot
-         '\x00B0' -> Just [Emph [Str [c,'\x030A']]]  -- ring
-         '\x20D7' -> Just [Emph [Str [c,'\x20D7']]]  -- arrow right
-         '\x20D6' -> Just [Emph [Str [c,'\x20D6']]]  -- arrow left
-         '\x005E' -> Just [Emph [Str [c,'\x0302']]]  -- hat
-         '\x0302' -> Just [Emph [Str [c,'\x0302']]]  -- hat
-         '~'      -> Just [Emph [Str [c,'\x0303']]]  -- tilde
-         _        -> Nothing
-expToInlines _ = Nothing
-
-
diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs
index ab579a326..37ca60ce3 100644
--- a/src/Text/Pandoc/Writers/LaTeX.hs
+++ b/src/Text/Pandoc/Writers/LaTeX.hs
@@ -43,7 +43,6 @@ import Data.Char ( toLower, isPunctuation )
 import Control.Applicative ((<|>))
 import Control.Monad.State
 import Text.Pandoc.Pretty
-import System.FilePath (dropExtension)
 import Text.Pandoc.Slides
 import Text.Pandoc.Highlighting (highlight, styleToLaTeX,
                                  formatLaTeXInline, formatLaTeXBlock,
@@ -120,7 +119,6 @@ pandocToLaTeX options (Pandoc meta blocks) = do
   (biblioTitle :: String) <- liftM (render colwidth) $ inlineListToLaTeX lastHeader
   let main = render colwidth $ vsep body
   st <- get
-  let biblioFiles = intercalate "," $ map dropExtension $  writerBiblioFiles options
   let context  =  defField "toc" (writerTableOfContents options) $
                   defField "toc-depth" (show (writerTOCDepth options -
                                               if writerChapters options
@@ -152,11 +150,9 @@ pandocToLaTeX options (Pandoc meta blocks) = do
                                 $ writerHighlightStyle options )
                       else id) $
                   (case writerCiteMethod options of
-                         Natbib   -> defField "biblio-files" biblioFiles .
-                                     defField "biblio-title" biblioTitle .
+                         Natbib   -> defField "biblio-title" biblioTitle .
                                      defField "natbib" True
-                         Biblatex -> defField "biblio-files" biblioFiles .
-                                     defField "biblio-title" biblioTitle .
+                         Biblatex -> defField "biblio-title" biblioTitle .
                                      defField "biblatex" True
                          _        -> id) $
                   metadata
@@ -313,7 +309,7 @@ blockToLaTeX (BlockQuote lst) = do
        _ -> do
          contents <- blockListToLaTeX lst
          return $ "\\begin{quote}" $$ contents $$ "\\end{quote}"
-blockToLaTeX (CodeBlock (_,classes,keyvalAttr) str) = do
+blockToLaTeX (CodeBlock (identifier,classes,keyvalAttr) str) = do
   opts <- gets stOptions
   case () of
      _ | isEnabled Ext_literate_haskell opts && "haskell" `elem` classes &&
@@ -344,7 +340,11 @@ blockToLaTeX (CodeBlock (_,classes,keyvalAttr) str) = do
                              [ (if key == "startFrom"
                                    then "firstnumber"
                                    else key) ++ "=" ++ attr |
-                                   (key,attr) <- keyvalAttr ]
+                                   (key,attr) <- keyvalAttr ] ++
+                             (if identifier == ""
+                                   then []
+                                   else [ "label=" ++ identifier ])
+
                         else []
                printParams
                    | null params = empty