1 /* 2 * Copyright (C) 2007, 2008, 2009 Apple Inc. All rights reserved. 3 * 4 * Redistribution and use in source and binary forms, with or without 5 * modification, are permitted provided that the following conditions 6 * are met: 7 * 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. 16 * 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. 27 */ 28 29 #ifndef WTF_ASCIICType_h 30 #define WTF_ASCIICType_h 31 32 #include <wtf/Assertions.h> 33 #include <wtf/Platform.h> 34 35 // The behavior of many of the functions in the <ctype.h> header is dependent 36 // on the current locale. But in the WebKit project, all uses of those functions 37 // are in code processing something that's not locale-specific. These equivalents 38 // for some of the <ctype.h> functions are named more explicitly, not dependent 39 // on the C library locale, and we should also optimize them as needed. 40 41 // All functions return false or leave the character unchanged if passed a character 42 // that is outside the range 0-7F. So they can be used on Unicode strings or 43 // characters if the intent is to do processing only if the character is ASCII. 44 45 namespace WTF { 46 isASCII(char c)47 inline bool isASCII(char c) { return !(c & ~0x7F); } isASCII(unsigned short c)48 inline bool isASCII(unsigned short c) { return !(c & ~0x7F); } 49 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCII(wchar_t c)50 inline bool isASCII(wchar_t c) { return !(c & ~0x7F); } 51 #endif isASCII(int c)52 inline bool isASCII(int c) { return !(c & ~0x7F); } 53 isASCIIAlpha(char c)54 inline bool isASCIIAlpha(char c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } isASCIIAlpha(unsigned short c)55 inline bool isASCIIAlpha(unsigned short c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } 56 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIAlpha(wchar_t c)57 inline bool isASCIIAlpha(wchar_t c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } 58 #endif isASCIIAlpha(int c)59 inline bool isASCIIAlpha(int c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } 60 isASCIIAlphanumeric(char c)61 inline bool isASCIIAlphanumeric(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } isASCIIAlphanumeric(unsigned short c)62 inline bool isASCIIAlphanumeric(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } 63 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIAlphanumeric(wchar_t c)64 inline bool isASCIIAlphanumeric(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } 65 #endif isASCIIAlphanumeric(int c)66 inline bool isASCIIAlphanumeric(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } 67 isASCIIDigit(char c)68 inline bool isASCIIDigit(char c) { return (c >= '0') & (c <= '9'); } isASCIIDigit(unsigned short c)69 inline bool isASCIIDigit(unsigned short c) { return (c >= '0') & (c <= '9'); } 70 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIDigit(wchar_t c)71 inline bool isASCIIDigit(wchar_t c) { return (c >= '0') & (c <= '9'); } 72 #endif isASCIIDigit(int c)73 inline bool isASCIIDigit(int c) { return (c >= '0') & (c <= '9'); } 74 isASCIIHexDigit(char c)75 inline bool isASCIIHexDigit(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } isASCIIHexDigit(unsigned short c)76 inline bool isASCIIHexDigit(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } 77 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIHexDigit(wchar_t c)78 inline bool isASCIIHexDigit(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } 79 #endif isASCIIHexDigit(int c)80 inline bool isASCIIHexDigit(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } 81 isASCIIOctalDigit(char c)82 inline bool isASCIIOctalDigit(char c) { return (c >= '0') & (c <= '7'); } isASCIIOctalDigit(unsigned short c)83 inline bool isASCIIOctalDigit(unsigned short c) { return (c >= '0') & (c <= '7'); } 84 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIOctalDigit(wchar_t c)85 inline bool isASCIIOctalDigit(wchar_t c) { return (c >= '0') & (c <= '7'); } 86 #endif isASCIIOctalDigit(int c)87 inline bool isASCIIOctalDigit(int c) { return (c >= '0') & (c <= '7'); } 88 isASCIILower(char c)89 inline bool isASCIILower(char c) { return c >= 'a' && c <= 'z'; } isASCIILower(unsigned short c)90 inline bool isASCIILower(unsigned short c) { return c >= 'a' && c <= 'z'; } 91 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIILower(wchar_t c)92 inline bool isASCIILower(wchar_t c) { return c >= 'a' && c <= 'z'; } 93 #endif isASCIILower(int c)94 inline bool isASCIILower(int c) { return c >= 'a' && c <= 'z'; } 95 isASCIIUpper(char c)96 inline bool isASCIIUpper(char c) { return c >= 'A' && c <= 'Z'; } isASCIIUpper(unsigned short c)97 inline bool isASCIIUpper(unsigned short c) { return c >= 'A' && c <= 'Z'; } 98 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIUpper(wchar_t c)99 inline bool isASCIIUpper(wchar_t c) { return c >= 'A' && c <= 'Z'; } 100 #endif isASCIIUpper(int c)101 inline bool isASCIIUpper(int c) { return c >= 'A' && c <= 'Z'; } 102 103 /* 104 Statistics from a run of Apple's page load test for callers of isASCIISpace: 105 106 character count 107 --------- ----- 108 non-spaces 689383 109 20 space 294720 110 0A \n 89059 111 09 \t 28320 112 0D \r 0 113 0C \f 0 114 0B \v 0 115 */ isASCIISpace(char c)116 inline bool isASCIISpace(char c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } isASCIISpace(unsigned short c)117 inline bool isASCIISpace(unsigned short c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } 118 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIISpace(wchar_t c)119 inline bool isASCIISpace(wchar_t c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } 120 #endif isASCIISpace(int c)121 inline bool isASCIISpace(int c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } 122 toASCIILower(char c)123 inline char toASCIILower(char c) { return c | ((c >= 'A' && c <= 'Z') << 5); } toASCIILower(unsigned short c)124 inline unsigned short toASCIILower(unsigned short c) { return c | ((c >= 'A' && c <= 'Z') << 5); } 125 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) toASCIILower(wchar_t c)126 inline wchar_t toASCIILower(wchar_t c) { return c | ((c >= 'A' && c <= 'Z') << 5); } 127 #endif toASCIILower(int c)128 inline int toASCIILower(int c) { return c | ((c >= 'A' && c <= 'Z') << 5); } 129 toASCIIUpper(char c)130 inline char toASCIIUpper(char c) { return static_cast<char>(c & ~((c >= 'a' && c <= 'z') << 5)); } toASCIIUpper(unsigned short c)131 inline unsigned short toASCIIUpper(unsigned short c) { return static_cast<unsigned short>(c & ~((c >= 'a' && c <= 'z') << 5)); } 132 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) toASCIIUpper(wchar_t c)133 inline wchar_t toASCIIUpper(wchar_t c) { return static_cast<wchar_t>(c & ~((c >= 'a' && c <= 'z') << 5)); } 134 #endif toASCIIUpper(int c)135 inline int toASCIIUpper(int c) { return static_cast<int>(c & ~((c >= 'a' && c <= 'z') << 5)); } 136 toASCIIHexValue(char c)137 inline int toASCIIHexValue(char c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } toASCIIHexValue(unsigned short c)138 inline int toASCIIHexValue(unsigned short c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } 139 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) toASCIIHexValue(wchar_t c)140 inline int toASCIIHexValue(wchar_t c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } 141 #endif toASCIIHexValue(int c)142 inline int toASCIIHexValue(int c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } 143 isASCIIPrintable(char c)144 inline bool isASCIIPrintable(char c) { return c >= ' ' && c <= '~'; } isASCIIPrintable(unsigned short c)145 inline bool isASCIIPrintable(unsigned short c) { return c >= ' ' && c <= '~'; } 146 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIPrintable(wchar_t c)147 inline bool isASCIIPrintable(wchar_t c) { return c >= ' ' && c <= '~'; } 148 #endif isASCIIPrintable(int c)149 inline bool isASCIIPrintable(int c) { return c >= ' ' && c <= '~'; } 150 } 151 152 using WTF::isASCII; 153 using WTF::isASCIIAlpha; 154 using WTF::isASCIIAlphanumeric; 155 using WTF::isASCIIDigit; 156 using WTF::isASCIIHexDigit; 157 using WTF::isASCIILower; 158 using WTF::isASCIIOctalDigit; 159 using WTF::isASCIIPrintable; 160 using WTF::isASCIISpace; 161 using WTF::isASCIIUpper; 162 using WTF::toASCIIHexValue; 163 using WTF::toASCIILower; 164 using WTF::toASCIIUpper; 165 166 #endif 167