30375bb · typeable/pandoc

git.iko.soy/typeable/pandoc

Changed encodeUTF8 to toUTF8, decodeUTF8 to fromUTF8,

for clarity. git-svn-id: https://pandoc.googlecode.com/svn/trunk@692 788f1e2b-df1e-0410-8736-df70ead52e1b

commit30375bb84737bd9536a73fc1929c15c50a80a655 authorfiddlosopher <fiddlosopher@788f1e2b-df1e-0410-8736-df70ead52e1b> dateFri 13 Jul 2007, 06:34 (19 years ago) parentbd5a5d4

3 files changed+23−25

compare with master

unifiedsplit

src/Main.hs+5−7 src/Text/Pandoc.hs+2−2 src/Text/Pandoc/UTF8.hs+16−16

src/Main.hs+5−7

@@ -30,8 +30,8 @@ writers.

3030-}

3131module Main where

3232import Text.Pandoc

33−import Text.Pandoc.UTF8 ( encodeUTF8, decodeUTF8 )

34−import Text.Pandoc.ASCIIMathML ( asciiMathMLScript )

33+import Text.Pandoc.UTF8

34+import Text.Pandoc.ASCIIMathML

3535import Text.Pandoc.Shared ( joinWithSep, tabsToSpaces )

3636import Text.Regex ( mkRegex, matchRegex )

3737import System.Environment ( getArgs, getProgName, getEnvironment )

@@ -439,9 +439,7 @@ main = do

439439 Nothing -> stateColumns defaultParserState

440440

441441 let tabFilter = if preserveTabs then id else (tabsToSpaces tabStop)

442− let addBlank str = str

443442 let removeCRs str = filter (/= '\r') str -- remove DOS-style line endings

444− let filter = tabFilter . addBlank . removeCRs

445443 let startParserState =

446444 defaultParserState { stateParseRaw = parseRaw,

447445 stateTabStop = tabStop,

@@ -475,10 +473,10 @@ main = do

475473 writerStrictMarkdown = strict,

476474 writerReferenceLinks = referenceLinks }

477475

478− (readSources sources) >>= (hPutStr output . encodeUTF8 .

476+ (readSources sources) >>= (hPutStr output . toUTF8 .

479477 (writer writerOptions) .

480− (reader startParserState) . filter .

481− decodeUTF8 . (joinWithSep "\n")) >>

478+ (reader startParserState) . tabFilter .

479+ removeCRs . fromUTF8 . (joinWithSep "\n")) >>

482480 hClose output

483481

484482 where

src/Text/Pandoc.hs+2−2

@@ -38,9 +38,9 @@ inline links:

3838> import Text.Pandoc

3939>

4040> markdownToRST :: String -> String

41−> markdownToRST = encodeUTF8 .

41+> markdownToRST = toUTF8 .

4242> (writeRST defaultWriterOptions {writerReferenceLinks = True}) .

43−> (readMarkdown defaultParserState) . decodeUTF8

43+> (readMarkdown defaultParserState) . fromUTF8

4444>

4545> main = interact markdownToRST

4646

src/Text/Pandoc/UTF8.hs+16−16

@@ -7,38 +7,38 @@

77-- Modified by Martin Norbaeck

88-- to pass illegal UTF-8 sequences through unchanged.

99module Text.Pandoc.UTF8 (

10− decodeUTF8,

11− encodeUTF8

10+ fromUTF8,

11+ toUTF8

1212 ) where

1313

1414-- From the Char module supplied with HBC.

1515

1616-- | Take a UTF-8 string and decode it into a Unicode string.

17−decodeUTF8 :: String -> String

18−decodeUTF8 "" = ""

19−decodeUTF8 (c:c':cs) | '\xc0' <= c && c <= '\xdf' &&

20− '\x80' <= c' && c' <= '\xbf' =

21− toEnum ((fromEnum c `mod` 0x20) * 0x40 + fromEnum c' `mod` 0x40) : decodeUTF8 cs

22−decodeUTF8 (c:c':c'':cs) | '\xe0' <= c && c <= '\xef' &&

17+fromUTF8 :: String -> String

18+fromUTF8 "" = ""

19+fromUTF8 (c:c':cs) | '\xc0' <= c && c <= '\xdf' &&

20+ '\x80' <= c' && c' <= '\xbf' =

21+ toEnum ((fromEnum c `mod` 0x20) * 0x40 + fromEnum c' `mod` 0x40) : fromUTF8 cs

22+fromUTF8 (c:c':c'':cs) | '\xe0' <= c && c <= '\xef' &&

2323 '\x80' <= c' && c' <= '\xbf' &&

2424 '\x80' <= c'' && c'' <= '\xbf' =

25− toEnum ((fromEnum c `mod` 0x10 * 0x1000) + (fromEnum c' `mod` 0x40) * 0x40 + fromEnum c'' `mod` 0x40) : decodeUTF8 cs

26−decodeUTF8 (c:cs) = c : decodeUTF8 cs

25+ toEnum ((fromEnum c `mod` 0x10 * 0x1000) + (fromEnum c' `mod` 0x40) * 0x40 + fromEnum c'' `mod` 0x40) : fromUTF8 cs

26+fromUTF8 (c:cs) = c : fromUTF8 cs

2727

2828-- | Take a Unicode string and encode it as a UTF-8 string.

29−encodeUTF8 :: String -> String

30−encodeUTF8 "" = ""

31−encodeUTF8 (c:cs) =

29+toUTF8 :: String -> String

30+toUTF8 "" = ""

31+toUTF8 (c:cs) =

3232 if c > '\x0000' && c < '\x0080' then

33− c : encodeUTF8 cs

33+ c : toUTF8 cs

3434 else if c < toEnum 0x0800 then

3535 let i = fromEnum c

3636 in toEnum (0xc0 + i `div` 0x40) :

3737 toEnum (0x80 + i `mod` 0x40) :

38− encodeUTF8 cs

38+ toUTF8 cs

3939 else

4040 let i = fromEnum c

4141 in toEnum (0xe0 + i `div` 0x1000) :

4242 toEnum (0x80 + (i `mod` 0x1000) `div` 0x40) :

4343 toEnum (0x80 + i `mod` 0x40) :

44− encodeUTF8 cs

44+ toUTF8 cs