7807564 · typeable/pandoc

git.iko.soy/typeable/pandoc

Moved extractSpaces to Shared.hs

Generalised and move the extractSpaces function from `HTML.hs` to `Shared.hs` so that the docx reader can also use it.

commit7807564d4493af1462d61138c63d8ec365abc792 authormpickering <matthewtpickering@gmail.com> dateMon 16 Jun 2014, 20:45 (12 years ago) parent4b6e279

2 files changed+20−13

compare with master

unifiedsplit

src/Text/Pandoc/Readers/HTML.hs+4−13 src/Text/Pandoc/Shared.hs+16

src/Text/Pandoc/Readers/HTML.hs+4−13

@@ -50,7 +50,6 @@ import Data.Char ( isDigit )

5050import Control.Monad ( liftM, guard, when, mzero )

5151import Control.Applicative ( (<$>), (<$), (<*) )

5252import Data.Monoid

53−import Data.Sequence (ViewL(..), ViewR(..), viewr, viewl)

5453

5554isSpace :: Char -> Bool

5655isSpace ' ' = True

@@ -369,9 +368,9 @@ pQ = do

369368 then InSingleQuote

370369 else InDoubleQuote

371370 let constructor = case quoteType of

372− SingleQuote -> B.singleQuoted

371+ SingleQuote -> B.singleQuoted

373372 DoubleQuote -> B.doubleQuoted

374− withQuoteContext innerQuoteContext $

373+ withQuoteContext innerQuoteContext $

375374 pInlinesInTags "q" constructor

376375

377376pEmph :: TagParser Inlines

@@ -406,7 +405,7 @@ pLink = try $ do

406405 let url = fromAttrib "href" tag

407406 let title = fromAttrib "title" tag

408407 lab <- trimInlines . mconcat <$> manyTill inline (pCloses "a")

409− return $ B.link (escapeURI url) title lab

408+ return $ B.link (escapeURI url) title lab

410409

411410pImage :: TagParser Inlines

412411pImage = do

@@ -439,15 +438,7 @@ pRawHtmlInline = do

439438

440439pInlinesInTags :: String -> (Inlines -> Inlines)

441440 -> TagParser Inlines

442−pInlinesInTags tagtype f = do

443− contents <- B.unMany <$> pInTags tagtype inline

444− let left = case viewl contents of

445− (Space :< _) -> B.space

446− _ -> mempty

447− let right = case viewr contents of

448− (_ :> Space) -> B.space

449− _ -> mempty

450− return (left <> f (trimInlines . B.Many $ contents) <> right)

441+pInlinesInTags tagtype f = extractSpaces f <$> pInTags tagtype inline

451442

452443pInTags :: (Monoid a) => String -> TagParser a

453444 -> TagParser a

src/Text/Pandoc/Shared.hs+16

@@ -53,6 +53,7 @@ module Text.Pandoc.Shared (

5353 -- * Pandoc block and inline list processing

5454 orderedListMarkers,

5555 normalizeSpaces,

56+ extractSpaces,

5657 normalize,

5758 stringify,

5859 compactify,

@@ -113,6 +114,7 @@ import qualified Data.ByteString as BS

113114import qualified Data.ByteString.Char8 as B8

114115import Text.Pandoc.Compat.Monoid

115116import Data.ByteString.Base64 (decodeLenient)

117+import Data.Sequence (ViewR(..), ViewL(..), viewl, viewr)

116118

117119#ifdef EMBED_DATA_FILES

118120import Text.Pandoc.Data (dataFiles)

@@ -331,6 +333,20 @@ isSpaceOrEmpty Space = True

331333isSpaceOrEmpty (Str "") = True

332334isSpaceOrEmpty _ = False

333335

336+-- | Extract the leading and trailing spaces from inside an inline element

337+-- and place them outside the element.

338+

339+extractSpaces :: (Inlines -> Inlines) -> Inlines -> Inlines

340+extractSpaces f is =

341+ let contents = B.unMany is

342+ left = case viewl contents of

343+ (Space :< _) -> B.space

344+ _ -> mempty

345+ right = case viewr contents of

346+ (_ :> Space) -> B.space

347+ _ -> mempty in

348+ (left <> f (B.trimInlines . B.Many $ contents) <> right)

349+

334350-- | Normalize @Pandoc@ document, consolidating doubled 'Space's,

335351-- combining adjacent 'Str's and 'Emph's, remove 'Null's and

336352-- empty elements, etc.