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
|
{-# OPTIONS_GHC -XNoImplicitPrelude #-}
-----------------------------------------------------------------------------
-- |
-- Module : Data.Char
-- Copyright : (c) The University of Glasgow 2001
-- License : BSD-style (see the file libraries/base/LICENSE)
--
-- Maintainer : libraries@haskell.org
-- Stability : stable
-- Portability : portable
--
-- The Char type and associated operations.
--
-----------------------------------------------------------------------------
module Data.Char
(
Char
-- * Character classification
-- | Unicode characters are divided into letters, numbers, marks,
-- punctuation, symbols, separators (including spaces) and others
-- (including control characters).
, isControl, isSpace
, isLower, isUpper, isAlpha, isAlphaNum, isPrint
, isDigit, isOctDigit, isHexDigit
, isLetter, isMark, isNumber, isPunctuation, isSymbol, isSeparator
-- ** Subranges
, isAscii, isLatin1
, isAsciiUpper, isAsciiLower
-- ** Unicode general categories
, GeneralCategory(..), generalCategory
-- * Case conversion
, toUpper, toLower, toTitle -- :: Char -> Char
-- * Single digit characters
, digitToInt -- :: Char -> Int
, intToDigit -- :: Int -> Char
-- * Numeric representations
, ord -- :: Char -> Int
, chr -- :: Int -> Char
-- * String representations
, showLitChar -- :: Char -> ShowS
, lexLitChar -- :: ReadS String
, readLitChar -- :: ReadS Char
-- Implementation checked wrt. Haskell 98 lib report, 1/99.
) where
#ifdef __GLASGOW_HASKELL__
import GHC.Base
import GHC.Arr (Ix)
import GHC.Real (fromIntegral)
import GHC.Show
import GHC.Read (Read, readLitChar, lexLitChar)
import GHC.Unicode
import GHC.Num
import GHC.Enum
#endif
#ifdef __HUGS__
import Hugs.Prelude (Ix)
import Hugs.Char
#endif
#ifdef __NHC__
import Prelude
import Prelude(Char,String)
import Char
import Ix
import NHC.FFI (CInt)
foreign import ccall unsafe "WCsubst.h u_gencat" wgencat :: CInt -> CInt
#endif
-- | Convert a single digit 'Char' to the corresponding 'Int'.
-- This function fails unless its argument satisfies 'isHexDigit',
-- but recognises both upper and lower-case hexadecimal digits
-- (i.e. @\'0\'@..@\'9\'@, @\'a\'@..@\'f\'@, @\'A\'@..@\'F\'@).
digitToInt :: Char -> Int
digitToInt c
| isDigit c = ord c - ord '0'
| c >= 'a' && c <= 'f' = ord c - ord 'a' + 10
| c >= 'A' && c <= 'F' = ord c - ord 'A' + 10
| otherwise = error ("Char.digitToInt: not a digit " ++ show c) -- sigh
#ifndef __GLASGOW_HASKELL__
isAsciiUpper, isAsciiLower :: Char -> Bool
isAsciiLower c = c >= 'a' && c <= 'z'
isAsciiUpper c = c >= 'A' && c <= 'Z'
#endif
-- | Unicode General Categories (column 2 of the UnicodeData table)
-- in the order they are listed in the Unicode standard.
data GeneralCategory
= UppercaseLetter -- ^ Lu: Letter, Uppercase
| LowercaseLetter -- ^ Ll: Letter, Lowercase
| TitlecaseLetter -- ^ Lt: Letter, Titlecase
| ModifierLetter -- ^ Lm: Letter, Modifier
| OtherLetter -- ^ Lo: Letter, Other
| NonSpacingMark -- ^ Mn: Mark, Non-Spacing
| SpacingCombiningMark -- ^ Mc: Mark, Spacing Combining
| EnclosingMark -- ^ Me: Mark, Enclosing
| DecimalNumber -- ^ Nd: Number, Decimal
| LetterNumber -- ^ Nl: Number, Letter
| OtherNumber -- ^ No: Number, Other
| ConnectorPunctuation -- ^ Pc: Punctuation, Connector
| DashPunctuation -- ^ Pd: Punctuation, Dash
| OpenPunctuation -- ^ Ps: Punctuation, Open
| ClosePunctuation -- ^ Pe: Punctuation, Close
| InitialQuote -- ^ Pi: Punctuation, Initial quote
| FinalQuote -- ^ Pf: Punctuation, Final quote
| OtherPunctuation -- ^ Po: Punctuation, Other
| MathSymbol -- ^ Sm: Symbol, Math
| CurrencySymbol -- ^ Sc: Symbol, Currency
| ModifierSymbol -- ^ Sk: Symbol, Modifier
| OtherSymbol -- ^ So: Symbol, Other
| Space -- ^ Zs: Separator, Space
| LineSeparator -- ^ Zl: Separator, Line
| ParagraphSeparator -- ^ Zp: Separator, Paragraph
| Control -- ^ Cc: Other, Control
| Format -- ^ Cf: Other, Format
| Surrogate -- ^ Cs: Other, Surrogate
| PrivateUse -- ^ Co: Other, Private Use
| NotAssigned -- ^ Cn: Other, Not Assigned
deriving (Eq, Ord, Enum, Read, Show, Bounded, Ix)
-- | The Unicode general category of the character.
generalCategory :: Char -> GeneralCategory
#if defined(__GLASGOW_HASKELL__) || defined(__NHC__)
generalCategory c = toEnum $ fromIntegral $ wgencat $ fromIntegral $ ord c
#endif
#ifdef __HUGS__
generalCategory c = toEnum (primUniGenCat c)
#endif
-- derived character classifiers
-- | 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.isAlpha'.
isLetter :: Char -> Bool
isLetter c = case generalCategory c of
UppercaseLetter -> True
LowercaseLetter -> True
TitlecaseLetter -> True
ModifierLetter -> True
OtherLetter -> True
_ -> False
-- | Selects Unicode mark characters, e.g. accents and the like, which
-- combine with preceding letters.
isMark :: Char -> Bool
isMark c = case generalCategory c of
NonSpacingMark -> True
SpacingCombiningMark -> True
EnclosingMark -> True
_ -> False
-- | Selects Unicode numeric characters, including digits from various
-- scripts, Roman numerals, etc.
isNumber :: Char -> Bool
isNumber c = case generalCategory c of
DecimalNumber -> True
LetterNumber -> True
OtherNumber -> True
_ -> False
-- | Selects Unicode punctuation characters, including various kinds
-- of connectors, brackets and quotes.
isPunctuation :: Char -> Bool
isPunctuation c = case generalCategory c of
ConnectorPunctuation -> True
DashPunctuation -> True
OpenPunctuation -> True
ClosePunctuation -> True
InitialQuote -> True
FinalQuote -> True
OtherPunctuation -> True
_ -> False
-- | Selects Unicode symbol characters, including mathematical and
-- currency symbols.
isSymbol :: Char -> Bool
isSymbol c = case generalCategory c of
MathSymbol -> True
CurrencySymbol -> True
ModifierSymbol -> True
OtherSymbol -> True
_ -> False
-- | Selects Unicode space and separator characters.
isSeparator :: Char -> Bool
isSeparator c = case generalCategory c of
Space -> True
LineSeparator -> True
ParagraphSeparator -> True
_ -> False
#ifdef __NHC__
-- dummy implementation
toTitle :: Char -> Char
toTitle = toUpper
#endif
|
