diff options
Diffstat (limited to 'src/Text/Pandoc/UTF8.hs')
-rw-r--r-- | src/Text/Pandoc/UTF8.hs | 32 |
1 files changed, 16 insertions, 16 deletions
diff --git a/src/Text/Pandoc/UTF8.hs b/src/Text/Pandoc/UTF8.hs index 927157ba5..be26f4993 100644 --- a/src/Text/Pandoc/UTF8.hs +++ b/src/Text/Pandoc/UTF8.hs @@ -7,38 +7,38 @@ -- Modified by Martin Norbaeck -- to pass illegal UTF-8 sequences through unchanged. module Text.Pandoc.UTF8 ( - decodeUTF8, - encodeUTF8 + fromUTF8, + toUTF8 ) where -- From the Char module supplied with HBC. -- | Take a UTF-8 string and decode it into a Unicode string. -decodeUTF8 :: String -> String -decodeUTF8 "" = "" -decodeUTF8 (c:c':cs) | '\xc0' <= c && c <= '\xdf' && - '\x80' <= c' && c' <= '\xbf' = - toEnum ((fromEnum c `mod` 0x20) * 0x40 + fromEnum c' `mod` 0x40) : decodeUTF8 cs -decodeUTF8 (c:c':c'':cs) | '\xe0' <= c && c <= '\xef' && +fromUTF8 :: String -> String +fromUTF8 "" = "" +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) : decodeUTF8 cs -decodeUTF8 (c:cs) = c : decodeUTF8 cs + 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. -encodeUTF8 :: String -> String -encodeUTF8 "" = "" -encodeUTF8 (c:cs) = +toUTF8 :: String -> String +toUTF8 "" = "" +toUTF8 (c:cs) = if c > '\x0000' && c < '\x0080' then - c : encodeUTF8 cs + c : toUTF8 cs else if c < toEnum 0x0800 then let i = fromEnum c in toEnum (0xc0 + i `div` 0x40) : toEnum (0x80 + i `mod` 0x40) : - encodeUTF8 cs + 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) : - encodeUTF8 cs + toUTF8 cs |