X-Git-Url: http://git.megacz.com/?a=blobdiff_plain;f=GHC%2FUnicode.hs;h=0c0cc1203f946ba1f66c6525515f825028a488de;hb=6b1a36a595eddf1e124529646afdb75c76a9966d;hp=da74685c0adb8fe42c703340b8d53f1a6ed5029b;hpb=62de77e9a5d1f19ab333f1796437e1b16f78d23e;p=haskell-directory.git diff --git a/GHC/Unicode.hs b/GHC/Unicode.hs index da74685..0c0cc12 100644 --- a/GHC/Unicode.hs +++ b/GHC/Unicode.hs @@ -16,6 +16,7 @@ -- ----------------------------------------------------------------------------- +-- #hide module GHC.Unicode ( isAscii, isLatin1, isControl, isAsciiUpper, isAsciiLower, @@ -44,8 +45,14 @@ isAscii c = c < '\x80' isLatin1 :: Char -> Bool isLatin1 c = c <= '\xff' -isAsciiUpper, isAsciiLower :: Char -> Bool +-- | Selects ASCII lower-case letters, +-- i.e. characters satisfying both 'isAscii' and 'isLower'. +isAsciiLower :: Char -> Bool isAsciiLower c = c >= 'a' && c <= 'z' + +-- | Selects ASCII upper-case letters, +-- i.e. characters satisfying both 'isAscii' and 'isUpper'. +isAsciiUpper :: Char -> Bool isAsciiUpper c = c >= 'A' && c <= 'Z' -- | Selects control characters, which are the non-printing characters of @@ -71,15 +78,17 @@ isSpace c = c == ' ' || c == '\xa0' || iswspace (fromIntegral (ord c)) /= 0 --- | Selects alphabetic Unicode characters (letters) that are not lower-case. --- (In Unicode terms, this includes letters in upper and title cases, --- as well as modifier letters and other letters.) +-- | Selects upper-case or title-case alphabetic Unicode characters (letters). +-- Title case is used by a small number of letter ligatures like the +-- single-character form of /Lj/. isUpper :: Char -> Bool -- | Selects lower-case alphabetic Unicode characters (letters). isLower :: Char -> Bool --- | Selects alphabetic Unicode characters (letters). +-- | Selects alphabetic Unicode characters (lower-case, upper-case and +-- title-case letters, plus letters of caseless scripts and modifiers letters). +-- This function is equivalent to 'Data.Char.isLetter'. isAlpha :: Char -> Bool -- | Selects alphabetic or numeric digit Unicode characters. @@ -103,19 +112,18 @@ isHexDigit :: Char -> Bool isHexDigit c = isDigit c || c >= 'A' && c <= 'F' || c >= 'a' && c <= 'f' --- | Convert a letter to the corresponding upper-case letter, leaving any --- other character unchanged. Any Unicode letter which has an upper-case --- equivalent is transformed. +-- | Convert a letter to the corresponding upper-case letter, if any. +-- Any other character is returned unchanged. toUpper :: Char -> Char --- | Convert a letter to the corresponding lower-case letter, leaving any --- other character unchanged. Any Unicode letter which has a lower-case --- equivalent is transformed. +-- | Convert a letter to the corresponding lower-case letter, if any. +-- Any other character is returned unchanged. toLower :: Char -> Char --- | Convert a letter to the corresponding title-case letter, leaving any --- other character unchanged. Any Unicode letter which has a lower-case --- equivalent is transformed. +-- | Convert a letter to the corresponding title-case or upper-case +-- letter, if any. (Title case differs from upper case only for a small +-- number of ligature letters.) +-- Any other character is returned unchanged. toTitle :: Char -> Char -- ----------------------------------------------------------------------------- @@ -126,7 +134,6 @@ toTitle :: Char -> Char -- Regardless of the O/S and Library, use the functions contained in WCsubst.c -type WInt = HTYPE_WINT_T type CInt = HTYPE_INT isAlpha c = iswalpha (fromIntegral (ord c)) /= 0 @@ -175,7 +182,7 @@ foreign import ccall unsafe "u_towtitle" towtitle :: CInt -> CInt foreign import ccall unsafe "u_gencat" - wgencat :: CInt -> Int + wgencat :: CInt -> CInt -- ----------------------------------------------------------------------------- -- No libunicode, so fall back to the ASCII-only implementation (never used, indeed)