1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
|
{-# LANGUAGE Trustworthy #-}
{-# LANGUAGE CPP, NoImplicitPrelude, ForeignFunctionInterface #-}
{-# OPTIONS -#include "WCsubst.h" #-}
{-# OPTIONS_HADDOCK hide #-}
-----------------------------------------------------------------------------
-- |
-- Module : GHC.Unicode
-- Copyright : (c) The University of Glasgow, 2003
-- License : see libraries/base/LICENSE
--
-- Maintainer : cvs-ghc@haskell.org
-- Stability : internal
-- Portability : non-portable (GHC extensions)
--
-- Implementations for the character predicates (isLower, isUpper, etc.)
-- and the conversions (toUpper, toLower). The implementation uses
-- libunicode on Unix systems if that is available.
--
-----------------------------------------------------------------------------
-- #hide
module GHC.Unicode (
isAscii, isLatin1, isControl,
isAsciiUpper, isAsciiLower,
isPrint, isSpace, isUpper,
isLower, isAlpha, isDigit,
isOctDigit, isHexDigit, isAlphaNum,
toUpper, toLower, toTitle,
wgencat
) where
import GHC.Base
import GHC.Real (fromIntegral)
import Foreign.C.Types (CInt)
#include "HsBaseConfig.h"
-- | Selects the first 128 characters of the Unicode character set,
-- corresponding to the ASCII character set.
isAscii :: Char -> Bool
isAscii c = c < '\x80'
-- | Selects the first 256 characters of the Unicode character set,
-- corresponding to the ISO 8859-1 (Latin-1) character set.
isLatin1 :: Char -> Bool
isLatin1 c = c <= '\xff'
-- | 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
-- the Latin-1 subset of Unicode.
isControl :: Char -> Bool
-- | Selects printable Unicode characters
-- (letters, numbers, marks, punctuation, symbols and spaces).
isPrint :: Char -> Bool
-- | Returns 'True' for any Unicode space character, and the control
-- characters @\\t@, @\\n@, @\\r@, @\\f@, @\\v@.
isSpace :: Char -> Bool
-- isSpace includes non-breaking space
-- Done with explicit equalities both for efficiency, and to avoid a tiresome
-- recursion with GHC.List elem
isSpace c = c == ' ' ||
c == '\t' ||
c == '\n' ||
c == '\r' ||
c == '\f' ||
c == '\v' ||
c == '\xa0' ||
iswspace (fromIntegral (ord c)) /= 0
-- | 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 (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.
--
-- Note that numeric digits outside the ASCII range are selected by this
-- function but not by 'isDigit'. Such digits may be part of identifiers
-- but are not used by the printer and reader to represent numbers.
isAlphaNum :: Char -> Bool
-- | Selects ASCII digits, i.e. @\'0\'@..@\'9\'@.
isDigit :: Char -> Bool
isDigit c = c >= '0' && c <= '9'
-- | Selects ASCII octal digits, i.e. @\'0\'@..@\'7\'@.
isOctDigit :: Char -> Bool
isOctDigit c = c >= '0' && c <= '7'
-- | Selects ASCII hexadecimal digits,
-- i.e. @\'0\'@..@\'9\'@, @\'a\'@..@\'f\'@, @\'A\'@..@\'F\'@.
isHexDigit :: Char -> Bool
isHexDigit c = isDigit c || c >= 'A' && c <= 'F' ||
c >= 'a' && c <= 'f'
-- | 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, if any.
-- Any other character is returned unchanged.
toLower :: Char -> Char
-- | 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
-- -----------------------------------------------------------------------------
-- Implementation with the supplied auto-generated Unicode character properties
-- table (default)
#if 1
-- Regardless of the O/S and Library, use the functions contained in WCsubst.c
isAlpha c = iswalpha (fromIntegral (ord c)) /= 0
isAlphaNum c = iswalnum (fromIntegral (ord c)) /= 0
--isSpace c = iswspace (fromIntegral (ord c)) /= 0
isControl c = iswcntrl (fromIntegral (ord c)) /= 0
isPrint c = iswprint (fromIntegral (ord c)) /= 0
isUpper c = iswupper (fromIntegral (ord c)) /= 0
isLower c = iswlower (fromIntegral (ord c)) /= 0
toLower c = chr (fromIntegral (towlower (fromIntegral (ord c))))
toUpper c = chr (fromIntegral (towupper (fromIntegral (ord c))))
toTitle c = chr (fromIntegral (towtitle (fromIntegral (ord c))))
foreign import ccall unsafe "u_iswalpha"
iswalpha :: CInt -> CInt
foreign import ccall unsafe "u_iswalnum"
iswalnum :: CInt -> CInt
foreign import ccall unsafe "u_iswcntrl"
iswcntrl :: CInt -> CInt
foreign import ccall unsafe "u_iswspace"
iswspace :: CInt -> CInt
foreign import ccall unsafe "u_iswprint"
iswprint :: CInt -> CInt
foreign import ccall unsafe "u_iswlower"
iswlower :: CInt -> CInt
foreign import ccall unsafe "u_iswupper"
iswupper :: CInt -> CInt
foreign import ccall unsafe "u_towlower"
towlower :: CInt -> CInt
foreign import ccall unsafe "u_towupper"
towupper :: CInt -> CInt
foreign import ccall unsafe "u_towtitle"
towtitle :: CInt -> CInt
foreign import ccall unsafe "u_gencat"
wgencat :: CInt -> CInt
-- -----------------------------------------------------------------------------
-- No libunicode, so fall back to the ASCII-only implementation (never used, indeed)
#else
isControl c = c < ' ' || c >= '\DEL' && c <= '\x9f'
isPrint c = not (isControl c)
-- The upper case ISO characters have the multiplication sign dumped
-- randomly in the middle of the range. Go figure.
isUpper c = c >= 'A' && c <= 'Z' ||
c >= '\xC0' && c <= '\xD6' ||
c >= '\xD8' && c <= '\xDE'
-- The lower case ISO characters have the division sign dumped
-- randomly in the middle of the range. Go figure.
isLower c = c >= 'a' && c <= 'z' ||
c >= '\xDF' && c <= '\xF6' ||
c >= '\xF8' && c <= '\xFF'
isAlpha c = isLower c || isUpper c
isAlphaNum c = isAlpha c || isDigit c
-- Case-changing operations
toUpper c@(C# c#)
| isAsciiLower c = C# (chr# (ord# c# -# 32#))
| isAscii c = c
-- fall-through to the slower stuff.
| isLower c && c /= '\xDF' && c /= '\xFF'
= unsafeChr (ord c `minusInt` ord 'a' `plusInt` ord 'A')
| otherwise
= c
toLower c@(C# c#)
| isAsciiUpper c = C# (chr# (ord# c# +# 32#))
| isAscii c = c
| isUpper c = unsafeChr (ord c `minusInt` ord 'A' `plusInt` ord 'a')
| otherwise = c
#endif
|
