|
1 /* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 4 -*- |
|
2 * vim: set ts=8 sts=4 et sw=4 tw=99: |
|
3 * |
|
4 * ***** BEGIN LICENSE BLOCK ***** |
|
5 * Copyright (C) 2007, 2008, 2009 Apple Inc. All rights reserved. |
|
6 * |
|
7 * Redistribution and use in source and binary forms, with or without |
|
8 * modification, are permitted provided that the following conditions |
|
9 * are met: |
|
10 * |
|
11 * 1. Redistributions of source code must retain the above copyright |
|
12 * notice, this list of conditions and the following disclaimer. |
|
13 * 2. Redistributions in binary form must reproduce the above copyright |
|
14 * notice, this list of conditions and the following disclaimer in the |
|
15 * documentation and/or other materials provided with the distribution. |
|
16 * 3. Neither the name of Apple Computer, Inc. ("Apple") nor the names of |
|
17 * its contributors may be used to endorse or promote products derived |
|
18 * from this software without specific prior written permission. |
|
19 * |
|
20 * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY |
|
21 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED |
|
22 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
|
23 * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY |
|
24 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
|
25 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
|
26 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
|
27 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
|
28 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
|
29 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
|
30 * |
|
31 * ***** END LICENSE BLOCK ***** */ |
|
32 |
|
33 #ifndef yarr_ASCIICType_h |
|
34 #define yarr_ASCIICType_h |
|
35 |
|
36 #include "assembler/wtf/Assertions.h" |
|
37 |
|
38 // The behavior of many of the functions in the <ctype.h> header is dependent |
|
39 // on the current locale. But in the WebKit project, all uses of those functions |
|
40 // are in code processing something that's not locale-specific. These equivalents |
|
41 // for some of the <ctype.h> functions are named more explicitly, not dependent |
|
42 // on the C library locale, and we should also optimize them as needed. |
|
43 |
|
44 // All functions return false or leave the character unchanged if passed a character |
|
45 // that is outside the range 0-7F. So they can be used on Unicode strings or |
|
46 // characters if the intent is to do processing only if the character is ASCII. |
|
47 |
|
48 namespace WTF { |
|
49 |
|
50 inline bool isASCII(char c) { return !(c & ~0x7F); } |
|
51 inline bool isASCII(unsigned short c) { return !(c & ~0x7F); } |
|
52 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
53 inline bool isASCII(wchar_t c) { return !(c & ~0x7F); } |
|
54 #endif |
|
55 inline bool isASCII(int c) { return !(c & ~0x7F); } |
|
56 inline bool isASCII(unsigned c) { return !(c & ~0x7F); } |
|
57 |
|
58 inline bool isASCIIAlpha(char c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
|
59 inline bool isASCIIAlpha(unsigned short c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
|
60 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
61 inline bool isASCIIAlpha(wchar_t c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
|
62 #endif |
|
63 inline bool isASCIIAlpha(int c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
|
64 inline bool isASCIIAlpha(unsigned c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
|
65 |
|
66 inline bool isASCIIAlphanumeric(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
|
67 inline bool isASCIIAlphanumeric(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
|
68 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
69 inline bool isASCIIAlphanumeric(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
|
70 #endif |
|
71 inline bool isASCIIAlphanumeric(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
|
72 inline bool isASCIIAlphanumeric(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
|
73 |
|
74 inline bool isASCIIDigit(char c) { return (c >= '0') & (c <= '9'); } |
|
75 inline bool isASCIIDigit(unsigned short c) { return (c >= '0') & (c <= '9'); } |
|
76 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
77 inline bool isASCIIDigit(wchar_t c) { return (c >= '0') & (c <= '9'); } |
|
78 #endif |
|
79 inline bool isASCIIDigit(int c) { return (c >= '0') & (c <= '9'); } |
|
80 inline bool isASCIIDigit(unsigned c) { return (c >= '0') & (c <= '9'); } |
|
81 |
|
82 inline bool isASCIIHexDigit(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
|
83 inline bool isASCIIHexDigit(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
|
84 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
85 inline bool isASCIIHexDigit(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
|
86 #endif |
|
87 inline bool isASCIIHexDigit(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
|
88 inline bool isASCIIHexDigit(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
|
89 |
|
90 inline bool isASCIIOctalDigit(char c) { return (c >= '0') & (c <= '7'); } |
|
91 inline bool isASCIIOctalDigit(unsigned short c) { return (c >= '0') & (c <= '7'); } |
|
92 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
93 inline bool isASCIIOctalDigit(wchar_t c) { return (c >= '0') & (c <= '7'); } |
|
94 #endif |
|
95 inline bool isASCIIOctalDigit(int c) { return (c >= '0') & (c <= '7'); } |
|
96 inline bool isASCIIOctalDigit(unsigned c) { return (c >= '0') & (c <= '7'); } |
|
97 |
|
98 inline bool isASCIILower(char c) { return c >= 'a' && c <= 'z'; } |
|
99 inline bool isASCIILower(unsigned short c) { return c >= 'a' && c <= 'z'; } |
|
100 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
101 inline bool isASCIILower(wchar_t c) { return c >= 'a' && c <= 'z'; } |
|
102 #endif |
|
103 inline bool isASCIILower(int c) { return c >= 'a' && c <= 'z'; } |
|
104 inline bool isASCIILower(unsigned c) { return c >= 'a' && c <= 'z'; } |
|
105 |
|
106 inline bool isASCIIUpper(char c) { return c >= 'A' && c <= 'Z'; } |
|
107 inline bool isASCIIUpper(unsigned short c) { return c >= 'A' && c <= 'Z'; } |
|
108 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
109 inline bool isASCIIUpper(wchar_t c) { return c >= 'A' && c <= 'Z'; } |
|
110 #endif |
|
111 inline bool isASCIIUpper(int c) { return c >= 'A' && c <= 'Z'; } |
|
112 inline bool isASCIIUpper(unsigned c) { return c >= 'A' && c <= 'Z'; } |
|
113 |
|
114 /* |
|
115 Statistics from a run of Apple's page load test for callers of isASCIISpace: |
|
116 |
|
117 character count |
|
118 --------- ----- |
|
119 non-spaces 689383 |
|
120 20 space 294720 |
|
121 0A \n 89059 |
|
122 09 \t 28320 |
|
123 0D \r 0 |
|
124 0C \f 0 |
|
125 0B \v 0 |
|
126 */ |
|
127 inline bool isASCIISpace(char c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
|
128 inline bool isASCIISpace(unsigned short c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
|
129 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
130 inline bool isASCIISpace(wchar_t c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
|
131 #endif |
|
132 inline bool isASCIISpace(int c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
|
133 inline bool isASCIISpace(unsigned c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
|
134 |
|
135 inline char toASCIILower(char c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
|
136 inline unsigned short toASCIILower(unsigned short c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
|
137 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
138 inline wchar_t toASCIILower(wchar_t c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
|
139 #endif |
|
140 inline int toASCIILower(int c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
|
141 inline unsigned toASCIILower(unsigned c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
|
142 |
|
143 // FIXME: Why do these need static_cast? |
|
144 inline char toASCIIUpper(char c) { return static_cast<char>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
|
145 inline unsigned short toASCIIUpper(unsigned short c) { return static_cast<unsigned short>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
|
146 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
147 inline wchar_t toASCIIUpper(wchar_t c) { return static_cast<wchar_t>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
|
148 #endif |
|
149 inline int toASCIIUpper(int c) { return static_cast<int>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
|
150 inline unsigned toASCIIUpper(unsigned c) { return static_cast<unsigned>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
|
151 |
|
152 inline int toASCIIHexValue(char c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
|
153 inline int toASCIIHexValue(unsigned short c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
|
154 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
155 inline int toASCIIHexValue(wchar_t c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
|
156 #endif |
|
157 inline int toASCIIHexValue(int c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
|
158 inline int toASCIIHexValue(unsigned c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
|
159 |
|
160 inline bool isASCIIPrintable(char c) { return c >= ' ' && c <= '~'; } |
|
161 inline bool isASCIIPrintable(unsigned short c) { return c >= ' ' && c <= '~'; } |
|
162 #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
|
163 inline bool isASCIIPrintable(wchar_t c) { return c >= ' ' && c <= '~'; } |
|
164 #endif |
|
165 inline bool isASCIIPrintable(int c) { return c >= ' ' && c <= '~'; } |
|
166 inline bool isASCIIPrintable(unsigned c) { return c >= ' ' && c <= '~'; } |
|
167 } |
|
168 |
|
169 using WTF::isASCII; |
|
170 using WTF::isASCIIAlpha; |
|
171 using WTF::isASCIIAlphanumeric; |
|
172 using WTF::isASCIIDigit; |
|
173 using WTF::isASCIIHexDigit; |
|
174 using WTF::isASCIILower; |
|
175 using WTF::isASCIIOctalDigit; |
|
176 using WTF::isASCIIPrintable; |
|
177 using WTF::isASCIISpace; |
|
178 using WTF::isASCIIUpper; |
|
179 using WTF::toASCIIHexValue; |
|
180 using WTF::toASCIILower; |
|
181 using WTF::toASCIIUpper; |
|
182 |
|
183 #endif /* yarr_ASCIICType_h */ |