2 * Copyright (C) 2007, 2008, 2009 Apple Inc. All rights reserved.
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
13 * 3. Neither the name of Apple Computer, Inc. ("Apple") nor the names of
14 * its contributors may be used to endorse or promote products derived
15 * from this software without specific prior written permission.
17 * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY
18 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
19 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
20 * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY
21 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
22 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
23 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
24 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
26 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29 #ifndef WTF_ASCIICType_h
30 #define WTF_ASCIICType_h
32 #include <wtf/Assertions.h>
34 // The behavior of many of the functions in the <ctype.h> header is dependent
35 // on the current locale. But in the WebKit project, all uses of those functions
36 // are in code processing something that's not locale-specific. These equivalents
37 // for some of the <ctype.h> functions are named more explicitly, not dependent
38 // on the C library locale, and we should also optimize them as needed.
40 // All functions return false or leave the character unchanged if passed a character
41 // that is outside the range 0-7F. So they can be used on Unicode strings or
42 // characters if the intent is to do processing only if the character is ASCII.
46 inline bool isASCII(char c) { return !(c & ~0x7F); }
47 inline bool isASCII(unsigned short c) { return !(c & ~0x7F); }
48 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
49 inline bool isASCII(wchar_t c) { return !(c & ~0x7F); }
51 inline bool isASCII(int c) { return !(c & ~0x7F); }
52 inline bool isASCII(unsigned c) { return !(c & ~0x7F); }
54 inline bool isASCIIAlpha(char c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; }
55 inline bool isASCIIAlpha(unsigned short c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; }
56 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
57 inline bool isASCIIAlpha(wchar_t c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; }
59 inline bool isASCIIAlpha(int c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; }
60 inline bool isASCIIAlpha(unsigned c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; }
62 inline bool isASCIIAlphanumeric(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); }
63 inline bool isASCIIAlphanumeric(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); }
64 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
65 inline bool isASCIIAlphanumeric(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); }
67 inline bool isASCIIAlphanumeric(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); }
68 inline bool isASCIIAlphanumeric(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); }
70 inline bool isASCIIDigit(char c) { return (c >= '0') & (c <= '9'); }
71 inline bool isASCIIDigit(unsigned short c) { return (c >= '0') & (c <= '9'); }
72 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
73 inline bool isASCIIDigit(wchar_t c) { return (c >= '0') & (c <= '9'); }
75 inline bool isASCIIDigit(int c) { return (c >= '0') & (c <= '9'); }
76 inline bool isASCIIDigit(unsigned c) { return (c >= '0') & (c <= '9'); }
78 inline bool isASCIIHexDigit(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); }
79 inline bool isASCIIHexDigit(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); }
80 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
81 inline bool isASCIIHexDigit(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); }
83 inline bool isASCIIHexDigit(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); }
84 inline bool isASCIIHexDigit(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); }
86 inline bool isASCIIOctalDigit(char c) { return (c >= '0') & (c <= '7'); }
87 inline bool isASCIIOctalDigit(unsigned short c) { return (c >= '0') & (c <= '7'); }
88 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
89 inline bool isASCIIOctalDigit(wchar_t c) { return (c >= '0') & (c <= '7'); }
91 inline bool isASCIIOctalDigit(int c) { return (c >= '0') & (c <= '7'); }
92 inline bool isASCIIOctalDigit(unsigned c) { return (c >= '0') & (c <= '7'); }
94 inline bool isASCIILower(char c) { return c >= 'a' && c <= 'z'; }
95 inline bool isASCIILower(unsigned short c) { return c >= 'a' && c <= 'z'; }
96 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
97 inline bool isASCIILower(wchar_t c) { return c >= 'a' && c <= 'z'; }
99 inline bool isASCIILower(int c) { return c >= 'a' && c <= 'z'; }
100 inline bool isASCIILower(unsigned c) { return c >= 'a' && c <= 'z'; }
102 inline bool isASCIIUpper(char c) { return c >= 'A' && c <= 'Z'; }
103 inline bool isASCIIUpper(unsigned short c) { return c >= 'A' && c <= 'Z'; }
104 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
105 inline bool isASCIIUpper(wchar_t c) { return c >= 'A' && c <= 'Z'; }
107 inline bool isASCIIUpper(int c) { return c >= 'A' && c <= 'Z'; }
108 inline bool isASCIIUpper(unsigned c) { return c >= 'A' && c <= 'Z'; }
111 Statistics from a run of Apple's page load test for callers of isASCIISpace:
123 inline bool isASCIISpace(char c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); }
124 inline bool isASCIISpace(unsigned short c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); }
125 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
126 inline bool isASCIISpace(wchar_t c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); }
128 inline bool isASCIISpace(int c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); }
129 inline bool isASCIISpace(unsigned c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); }
131 inline char toASCIILower(char c) { return c | ((c >= 'A' && c <= 'Z') << 5); }
132 inline unsigned short toASCIILower(unsigned short c) { return c | ((c >= 'A' && c <= 'Z') << 5); }
133 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
134 inline wchar_t toASCIILower(wchar_t c) { return c | ((c >= 'A' && c <= 'Z') << 5); }
136 inline int toASCIILower(int c) { return c | ((c >= 'A' && c <= 'Z') << 5); }
137 inline unsigned toASCIILower(unsigned c) { return c | ((c >= 'A' && c <= 'Z') << 5); }
139 // FIXME: Why do these need static_cast?
140 inline char toASCIIUpper(char c) { return static_cast<char>(c & ~((c >= 'a' && c <= 'z') << 5)); }
141 inline unsigned short toASCIIUpper(unsigned short c) { return static_cast<unsigned short>(c & ~((c >= 'a' && c <= 'z') << 5)); }
142 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
143 inline wchar_t toASCIIUpper(wchar_t c) { return static_cast<wchar_t>(c & ~((c >= 'a' && c <= 'z') << 5)); }
145 inline int toASCIIUpper(int c) { return static_cast<int>(c & ~((c >= 'a' && c <= 'z') << 5)); }
146 inline unsigned toASCIIUpper(unsigned c) { return static_cast<unsigned>(c & ~((c >= 'a' && c <= 'z') << 5)); }
148 inline int toASCIIHexValue(char c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; }
149 inline int toASCIIHexValue(char upperValue, char lowerValue) { ASSERT(isASCIIHexDigit(upperValue) && isASCIIHexDigit(lowerValue)); return ((toASCIIHexValue(upperValue) << 4) & 0xF0) | toASCIIHexValue(lowerValue); }
150 inline int toASCIIHexValue(unsigned short c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; }
151 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
152 inline int toASCIIHexValue(wchar_t c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; }
154 inline int toASCIIHexValue(int c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; }
155 inline int toASCIIHexValue(unsigned c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; }
157 inline char lowerNibbleToASCIIHexDigit(char c) { char nibble = c & 0xF; return nibble < 10 ? '0' + nibble : 'A' + nibble - 10; }
158 inline char upperNibbleToASCIIHexDigit(char c) { char nibble = (c >> 4) & 0xF; return nibble < 10 ? '0' + nibble : 'A' + nibble - 10; }
160 inline bool isASCIIPrintable(char c) { return c >= ' ' && c <= '~'; }
161 inline bool isASCIIPrintable(unsigned short c) { return c >= ' ' && c <= '~'; }
162 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED)
163 inline bool isASCIIPrintable(wchar_t c) { return c >= ' ' && c <= '~'; }
165 inline bool isASCIIPrintable(int c) { return c >= ' ' && c <= '~'; }
166 inline bool isASCIIPrintable(unsigned c) { return c >= ' ' && c <= '~'; }
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 using WTF::lowerNibbleToASCIIHexDigit;
183 using WTF::upperNibbleToASCIIHexDigit;