pandoc/Text/Pandoc/UTF8.hs
fiddlosopher 4a841bfc54 Use template haskell to avoid the need for templates:
+ Added library Text.Pandoc.Include, with a template haskell
  function $(includeStrFrom fname) to include a file as a string
  constant at compile time.
+ This removes the need for the 'templates' directory or Makefile
  target.  These have been removed.
+ The base source directory has been changed from src to .
+ A new 'data' directory has been added, containing the ASCIIMathML.js
  script, writer headers, and S5 files.
+ The src/wrappers directory has been moved to 'wrappers'.
+ The Text.Pandoc.ASCIIMathML library is no longer needed, since
  Text.Pandoc.Writers.HTML can use includeStrFrom to include the
  ASCIIMathML.js code directly.  It has been removed.


git-svn-id: https://pandoc.googlecode.com/svn/trunk@1063 788f1e2b-df1e-0410-8736-df70ead52e1b
2007-11-03 22:14:03 +00:00

45 lines
1.6 KiB
Haskell

-- | Functions for converting Unicode strings to UTF-8 and vice versa.
--
-- Taken from <http://www.cse.ogi.edu/~hallgren/Talks/LHiH/base/lib/UTF8.hs>.
-- (c) 2003, OGI School of Science & Engineering, Oregon Health and
-- Science University.
--
-- Modified by Martin Norbaeck
-- to pass illegal UTF-8 sequences through unchanged.
module Text.Pandoc.UTF8 (
fromUTF8,
toUTF8
) where
-- From the Char module supplied with HBC.
-- | Take a UTF-8 string and decode it into a Unicode string.
fromUTF8 :: String -> String
fromUTF8 "" = ""
fromUTF8 ('\xef':'\xbb':'\xbf':cs) = fromUTF8 cs -- skip BOM (byte order marker)
fromUTF8 (c:c':cs) | '\xc0' <= c && c <= '\xdf' &&
'\x80' <= c' && c' <= '\xbf' =
toEnum ((fromEnum c `mod` 0x20) * 0x40 + fromEnum c' `mod` 0x40) : fromUTF8 cs
fromUTF8 (c:c':c'':cs) | '\xe0' <= c && c <= '\xef' &&
'\x80' <= c' && c' <= '\xbf' &&
'\x80' <= c'' && c'' <= '\xbf' =
toEnum ((fromEnum c `mod` 0x10 * 0x1000) + (fromEnum c' `mod` 0x40) * 0x40 + fromEnum c'' `mod` 0x40) : fromUTF8 cs
fromUTF8 (c:cs) = c : fromUTF8 cs
-- | Take a Unicode string and encode it as a UTF-8 string.
toUTF8 :: String -> String
toUTF8 "" = ""
toUTF8 (c:cs) =
if c > '\x0000' && c < '\x0080' then
c : toUTF8 cs
else if c < toEnum 0x0800 then
let i = fromEnum c
in toEnum (0xc0 + i `div` 0x40) :
toEnum (0x80 + i `mod` 0x40) :
toUTF8 cs
else
let i = fromEnum c
in toEnum (0xe0 + i `div` 0x1000) :
toEnum (0x80 + (i `mod` 0x1000) `div` 0x40) :
toEnum (0x80 + i `mod` 0x40) :
toUTF8 cs