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 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. 39 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. 43 44 namespace WTF { 45 isASCII(char c)46 inline bool isASCII(char c) { return !(c & ~0x7F); } isASCII(unsigned short c)47 inline bool isASCII(unsigned short c) { return !(c & ~0x7F); } 48 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCII(wchar_t c)49 inline bool isASCII(wchar_t c) { return !(c & ~0x7F); } 50 #endif isASCII(int c)51 inline bool isASCII(int c) { return !(c & ~0x7F); } isASCII(unsigned c)52 inline bool isASCII(unsigned 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'; } isASCIIAlpha(unsigned c)60 inline bool isASCIIAlpha(unsigned c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } 61 isASCIIAlphanumeric(char c)62 inline bool isASCIIAlphanumeric(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } isASCIIAlphanumeric(unsigned short c)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) isASCIIAlphanumeric(wchar_t c)65 inline bool isASCIIAlphanumeric(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } 66 #endif isASCIIAlphanumeric(int c)67 inline bool isASCIIAlphanumeric(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } isASCIIAlphanumeric(unsigned c)68 inline bool isASCIIAlphanumeric(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } 69 isASCIIDigit(char c)70 inline bool isASCIIDigit(char c) { return (c >= '0') & (c <= '9'); } isASCIIDigit(unsigned short c)71 inline bool isASCIIDigit(unsigned short c) { return (c >= '0') & (c <= '9'); } 72 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIDigit(wchar_t c)73 inline bool isASCIIDigit(wchar_t c) { return (c >= '0') & (c <= '9'); } 74 #endif isASCIIDigit(int c)75 inline bool isASCIIDigit(int c) { return (c >= '0') & (c <= '9'); } isASCIIDigit(unsigned c)76 inline bool isASCIIDigit(unsigned c) { return (c >= '0') & (c <= '9'); } 77 isASCIIHexDigit(char c)78 inline bool isASCIIHexDigit(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } isASCIIHexDigit(unsigned short c)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) isASCIIHexDigit(wchar_t c)81 inline bool isASCIIHexDigit(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } 82 #endif isASCIIHexDigit(int c)83 inline bool isASCIIHexDigit(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } isASCIIHexDigit(unsigned c)84 inline bool isASCIIHexDigit(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } 85 isASCIIOctalDigit(char c)86 inline bool isASCIIOctalDigit(char c) { return (c >= '0') & (c <= '7'); } isASCIIOctalDigit(unsigned short c)87 inline bool isASCIIOctalDigit(unsigned short c) { return (c >= '0') & (c <= '7'); } 88 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIOctalDigit(wchar_t c)89 inline bool isASCIIOctalDigit(wchar_t c) { return (c >= '0') & (c <= '7'); } 90 #endif isASCIIOctalDigit(int c)91 inline bool isASCIIOctalDigit(int c) { return (c >= '0') & (c <= '7'); } isASCIIOctalDigit(unsigned c)92 inline bool isASCIIOctalDigit(unsigned c) { return (c >= '0') & (c <= '7'); } 93 isASCIILower(char c)94 inline bool isASCIILower(char c) { return c >= 'a' && c <= 'z'; } isASCIILower(unsigned short c)95 inline bool isASCIILower(unsigned short c) { return c >= 'a' && c <= 'z'; } 96 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIILower(wchar_t c)97 inline bool isASCIILower(wchar_t c) { return c >= 'a' && c <= 'z'; } 98 #endif isASCIILower(int c)99 inline bool isASCIILower(int c) { return c >= 'a' && c <= 'z'; } isASCIILower(unsigned c)100 inline bool isASCIILower(unsigned c) { return c >= 'a' && c <= 'z'; } 101 isASCIIUpper(char c)102 inline bool isASCIIUpper(char c) { return c >= 'A' && c <= 'Z'; } isASCIIUpper(unsigned short c)103 inline bool isASCIIUpper(unsigned short c) { return c >= 'A' && c <= 'Z'; } 104 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIUpper(wchar_t c)105 inline bool isASCIIUpper(wchar_t c) { return c >= 'A' && c <= 'Z'; } 106 #endif isASCIIUpper(int c)107 inline bool isASCIIUpper(int c) { return c >= 'A' && c <= 'Z'; } isASCIIUpper(unsigned c)108 inline bool isASCIIUpper(unsigned c) { return c >= 'A' && c <= 'Z'; } 109 110 /* 111 Statistics from a run of Apple's page load test for callers of isASCIISpace: 112 113 character count 114 --------- ----- 115 non-spaces 689383 116 20 space 294720 117 0A \n 89059 118 09 \t 28320 119 0D \r 0 120 0C \f 0 121 0B \v 0 122 */ isASCIISpace(char c)123 inline bool isASCIISpace(char c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } isASCIISpace(unsigned short c)124 inline bool isASCIISpace(unsigned short c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } 125 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIISpace(wchar_t c)126 inline bool isASCIISpace(wchar_t c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } 127 #endif isASCIISpace(int c)128 inline bool isASCIISpace(int c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } isASCIISpace(unsigned c)129 inline bool isASCIISpace(unsigned c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } 130 toASCIILower(char c)131 inline char toASCIILower(char c) { return c | ((c >= 'A' && c <= 'Z') << 5); } toASCIILower(unsigned short c)132 inline unsigned short toASCIILower(unsigned short c) { return c | ((c >= 'A' && c <= 'Z') << 5); } 133 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) toASCIILower(wchar_t c)134 inline wchar_t toASCIILower(wchar_t c) { return c | ((c >= 'A' && c <= 'Z') << 5); } 135 #endif toASCIILower(int c)136 inline int toASCIILower(int c) { return c | ((c >= 'A' && c <= 'Z') << 5); } toASCIILower(unsigned c)137 inline unsigned toASCIILower(unsigned c) { return c | ((c >= 'A' && c <= 'Z') << 5); } 138 139 // FIXME: Why do these need static_cast? toASCIIUpper(char c)140 inline char toASCIIUpper(char c) { return static_cast<char>(c & ~((c >= 'a' && c <= 'z') << 5)); } toASCIIUpper(unsigned short c)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) toASCIIUpper(wchar_t c)143 inline wchar_t toASCIIUpper(wchar_t c) { return static_cast<wchar_t>(c & ~((c >= 'a' && c <= 'z') << 5)); } 144 #endif toASCIIUpper(int c)145 inline int toASCIIUpper(int c) { return static_cast<int>(c & ~((c >= 'a' && c <= 'z') << 5)); } toASCIIUpper(unsigned c)146 inline unsigned toASCIIUpper(unsigned c) { return static_cast<unsigned>(c & ~((c >= 'a' && c <= 'z') << 5)); } 147 toASCIIHexValue(char c)148 inline int toASCIIHexValue(char c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } toASCIIHexValue(unsigned short c)149 inline int toASCIIHexValue(unsigned short c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } 150 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) toASCIIHexValue(wchar_t c)151 inline int toASCIIHexValue(wchar_t c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } 152 #endif toASCIIHexValue(int c)153 inline int toASCIIHexValue(int c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } toASCIIHexValue(unsigned c)154 inline int toASCIIHexValue(unsigned c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } 155 isASCIIPrintable(char c)156 inline bool isASCIIPrintable(char c) { return c >= ' ' && c <= '~'; } isASCIIPrintable(unsigned short c)157 inline bool isASCIIPrintable(unsigned short c) { return c >= ' ' && c <= '~'; } 158 #if !COMPILER(MSVC) || defined(_NATIVE_WCHAR_T_DEFINED) isASCIIPrintable(wchar_t c)159 inline bool isASCIIPrintable(wchar_t c) { return c >= ' ' && c <= '~'; } 160 #endif isASCIIPrintable(int c)161 inline bool isASCIIPrintable(int c) { return c >= ' ' && c <= '~'; } isASCIIPrintable(unsigned c)162 inline bool isASCIIPrintable(unsigned c) { return c >= ' ' && c <= '~'; } 163 } 164 165 using WTF::isASCII; 166 using WTF::isASCIIAlpha; 167 using WTF::isASCIIAlphanumeric; 168 using WTF::isASCIIDigit; 169 using WTF::isASCIIHexDigit; 170 using WTF::isASCIILower; 171 using WTF::isASCIIOctalDigit; 172 using WTF::isASCIIPrintable; 173 using WTF::isASCIISpace; 174 using WTF::isASCIIUpper; 175 using WTF::toASCIIHexValue; 176 using WTF::toASCIILower; 177 using WTF::toASCIIUpper; 178 179 #endif 180