ec88d47 · typeable/pandoc

src/Text/Pandoc/Shared.hs+13

compare with master

unifiedsplit

@@ -59,6 +59,7 @@ module Text.Pandoc.Shared (

59 normalizeBlocks,

60 removeFormatting,

61 stringify,

62+ capitalize,

62 compactify,

63 compactify,

63 compactify',

64 compactify',

64 compactify'DL,

65 compactify'DL,

@@ -122,6 +123,7 @@ import qualified Data.ByteString.Char8 as B8

122import Text.Pandoc.Compat.Monoid

123import Text.Pandoc.Compat.Monoid

123import Data.ByteString.Base64 (decodeLenient)

124import Data.ByteString.Base64 (decodeLenient)

124import Data.Sequence (ViewR(..), ViewL(..), viewl, viewr)

125import Data.Sequence (ViewR(..), ViewL(..), viewl, viewr)

126+import qualified Data.Text as T (toUpper, pack, unpack)

125

127

126#ifdef EMBED_DATA_FILES

128#ifdef EMBED_DATA_FILES

127import Text.Pandoc.Data (dataFiles)

129import Text.Pandoc.Data (dataFiles)

@@ -527,6 +529,17 @@ stringify = query go . walk deNote

527 deNote (Note _) = Str ""

529 deNote (Note _) = Str ""

528 deNote x = x

530 deNote x = x

529

531

532+-- | Bring all regular text in a pandoc structure to uppercase.

533+--

534+-- This function correctly handles cases where a lowercase character doesn't

535+-- match to a single uppercase character – e.g. “Straße” would be converted

536+-- to “STRASSE”, not “STRAßE”.

537+capitalize :: Walkable Inline a => a -> a

538+capitalize = walk go

539+ where go :: Inline -> Inline

540+ go (Str s) = Str (T.unpack $ T.toUpper $ T.pack s)

541+ go x = x

542+

530-- | Change final list item from @Para@ to @Plain@ if the list contains

543-- | Change final list item from @Para@ to @Plain@ if the list contains

531-- no other @Para@ blocks.

544-- no other @Para@ blocks.

532compactify :: [[Block]] -- ^ List of list items (each a list of blocks)

545compactify :: [[Block]] -- ^ List of list items (each a list of blocks)

src/Text/Pandoc/Writers/FB2.hs+3−8

@@ -28,7 +28,7 @@ module Text.Pandoc.Writers.FB2 (writeFB2) where

28import Control.Monad.State (StateT, evalStateT, get, modify)

29import Control.Monad.State (liftM, liftM2, liftIO)

30import Data.ByteString.Base64 (encode)

31−import Data.Char (toUpper, toLower, isSpace, isAscii, isControl)

31+import Data.Char (toLower, isSpace, isAscii, isControl)

32import Data.List (intersperse, intercalate, isPrefixOf)

33import Data.Either (lefts, rights)

34import Network.Browser (browse, request, setAllowRedirects, setOutHandler)

@@ -44,8 +44,7 @@ import qualified Text.XML.Light.Cursor as XC

44

45import Text.Pandoc.Definition

46import Text.Pandoc.Options (WriterOptions(..), HTMLMathMethod(..), def)

47−import Text.Pandoc.Shared (orderedListMarkers, isHeaderBlock)

47+import Text.Pandoc.Shared (orderedListMarkers, isHeaderBlock, capitalize)

48−import Text.Pandoc.Walk

49

48

50-- | Data to be written at the end of the document:

49-- | Data to be written at the end of the document:

51-- (foot)notes, URLs, references, images.

50-- (foot)notes, URLs, references, images.

@@ -421,10 +420,6 @@ indent = indentBlock

421 indentLines ins = let lns = split isLineBreak ins :: [[Inline]]

420 indentLines ins = let lns = split isLineBreak ins :: [[Inline]]

422 in intercalate [LineBreak] $ map ((Str spacer):) lns

421 in intercalate [LineBreak] $ map ((Str spacer):) lns

423

422

424−capitalize :: Inline -> Inline

425−capitalize (Str xs) = Str $ map toUpper xs

426−capitalize x = x

427−

428-- | Convert a Pandoc's Inline element to FictionBook XML representation.

423-- | Convert a Pandoc's Inline element to FictionBook XML representation.

429toXml :: Inline -> FBM [Content]

424toXml :: Inline -> FBM [Content]

430toXml (Str s) = return [txt s]

425toXml (Str s) = return [txt s]

@@ -434,7 +429,7 @@ toXml (Strong ss) = list `liftM` wrap "strong" ss

434toXml (Strikeout ss) = list `liftM` wrap "strikethrough" ss

429toXml (Strikeout ss) = list `liftM` wrap "strikethrough" ss

435toXml (Superscript ss) = list `liftM` wrap "sup" ss

430toXml (Superscript ss) = list `liftM` wrap "sup" ss

436toXml (Subscript ss) = list `liftM` wrap "sub" ss

431toXml (Subscript ss) = list `liftM` wrap "sub" ss

437−toXml (SmallCaps ss) = cMapM toXml $ walk capitalize ss

432+toXml (SmallCaps ss) = cMapM toXml $ capitalize ss

438toXml (Quoted SingleQuote ss) = do -- FIXME: should be language-specific

433toXml (Quoted SingleQuote ss) = do -- FIXME: should be language-specific

439 inner <- cMapM toXml ss

434 inner <- cMapM toXml ss

440 return $ [txt "‘"] ++ inner ++ [txt "’"]

435 return $ [txt "‘"] ++ inner ++ [txt "’"]

src/Text/Pandoc/Writers/Markdown.hs+3−7

@@ -39,7 +39,7 @@ import Text.Pandoc.Writers.Shared

39import Text.Pandoc.Options

40import Text.Pandoc.Parsing hiding (blankline, blanklines, char, space)

41import Data.List ( group, isPrefixOf, find, intersperse, transpose, sortBy )

42−import Data.Char ( isSpace, isPunctuation, toUpper )

42+import Data.Char ( isSpace, isPunctuation )

43import Data.Ord ( comparing )

44import Text.Pandoc.Pretty

45import Control.Monad.State

@@ -672,10 +672,6 @@ escapeSpaces (Str s) = Str $ substitute " " "\\ " s

672escapeSpaces Space = Str "\\ "

673escapeSpaces x = x

674

675−toCaps :: Inline -> Inline

676−toCaps (Str s) = Str (map toUpper s)

677−toCaps x = x

678−

679-- | Convert Pandoc inline element to markdown.

675-- | Convert Pandoc inline element to markdown.

680inlineToMarkdown :: WriterOptions -> Inline -> State WriterState Doc

676inlineToMarkdown :: WriterOptions -> Inline -> State WriterState Doc

681inlineToMarkdown opts (Span attrs ils) = do

677inlineToMarkdown opts (Span attrs ils) = do

@@ -693,7 +689,7 @@ inlineToMarkdown opts (Emph lst) = do

693inlineToMarkdown opts (Strong lst) = do

689inlineToMarkdown opts (Strong lst) = do

694 plain <- gets stPlain

690 plain <- gets stPlain

695 if plain

691 if plain

696− then inlineListToMarkdown opts $ walk toCaps lst

692+ then inlineListToMarkdown opts $ capitalize lst

697 else do

693 else do

698 contents <- inlineListToMarkdown opts lst

694 contents <- inlineListToMarkdown opts lst

699 return $ "**" <> contents <> "**"

695 return $ "**" <> contents <> "**"

@@ -716,7 +712,7 @@ inlineToMarkdown opts (Subscript lst) = do

716inlineToMarkdown opts (SmallCaps lst) = do

712inlineToMarkdown opts (SmallCaps lst) = do

717 plain <- gets stPlain

713 plain <- gets stPlain

718 if plain

714 if plain

719− then inlineListToMarkdown opts $ walk toCaps lst

715+ then inlineListToMarkdown opts $ capitalize lst

720 else do

716 else do

721 contents <- inlineListToMarkdown opts lst

717 contents <- inlineListToMarkdown opts lst

722 return $ tagWithAttrs "span"

718 return $ tagWithAttrs "span"

tests/Tests/Writers/Plain.hsnew file+21

@@ -0,0 +1,21 @@

1+{-# LANGUAGE OverloadedStrings #-}

2+module Tests.Writers.Plain (tests) where

3+

4+import Test.Framework

5+import Text.Pandoc.Builder

6+import Text.Pandoc

7+import Tests.Helpers

8+import Tests.Arbitrary()

9+

10+

11+infix 4 =:

12+(=:) :: (ToString a, ToPandoc a)

13+ => String -> (a, String) -> Test

14+(=:) = test (writePlain def . toPandoc)

15+

16+

17+tests :: [Test]

18+tests = [ "strongly emphasized text to uppercase"

19+ =: strong "Straße"

20+ =?> "STRASSE"

21+ ]

tests/test-pandoc.hs+2

@@ -17,6 +17,7 @@ import qualified Tests.Writers.HTML

17import qualified Tests.Writers.Docbook

18import qualified Tests.Writers.Native

19import qualified Tests.Writers.Markdown

20+import qualified Tests.Writers.Plain

20import qualified Tests.Writers.AsciiDoc

21import qualified Tests.Writers.AsciiDoc

21import qualified Tests.Shared

22import qualified Tests.Shared

22import qualified Tests.Walk

23import qualified Tests.Walk

@@ -33,6 +34,7 @@ tests = [ testGroup "Old" Tests.Old.tests

33 , testGroup "HTML" Tests.Writers.HTML.tests

34 , testGroup "HTML" Tests.Writers.HTML.tests

34 , testGroup "Docbook" Tests.Writers.Docbook.tests

35 , testGroup "Docbook" Tests.Writers.Docbook.tests

35 , testGroup "Markdown" Tests.Writers.Markdown.tests

36 , testGroup "Markdown" Tests.Writers.Markdown.tests

37+ , testGroup "Plain" Tests.Writers.Plain.tests

36 , testGroup "AsciiDoc" Tests.Writers.AsciiDoc.tests

38 , testGroup "AsciiDoc" Tests.Writers.AsciiDoc.tests

37 ]

39 ]

38 , testGroup "Readers"

40 , testGroup "Readers"