Wed, 31 Dec 2014 06:09:35 +0100
Cloned upstream origin tor-browser at tor-browser-31.3.0esr-4.5-1-build1
revision ID fc1c9ff7c1b2defdbc039f12214767608f46423f for hacking purpose.
michael@0 | 1 | /* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 4 -*- |
michael@0 | 2 | * vim: set ts=8 sts=4 et sw=4 tw=99: |
michael@0 | 3 | * |
michael@0 | 4 | * ***** BEGIN LICENSE BLOCK ***** |
michael@0 | 5 | * Copyright (C) 2007, 2008, 2009 Apple Inc. All rights reserved. |
michael@0 | 6 | * |
michael@0 | 7 | * Redistribution and use in source and binary forms, with or without |
michael@0 | 8 | * modification, are permitted provided that the following conditions |
michael@0 | 9 | * are met: |
michael@0 | 10 | * |
michael@0 | 11 | * 1. Redistributions of source code must retain the above copyright |
michael@0 | 12 | * notice, this list of conditions and the following disclaimer. |
michael@0 | 13 | * 2. Redistributions in binary form must reproduce the above copyright |
michael@0 | 14 | * notice, this list of conditions and the following disclaimer in the |
michael@0 | 15 | * documentation and/or other materials provided with the distribution. |
michael@0 | 16 | * 3. Neither the name of Apple Computer, Inc. ("Apple") nor the names of |
michael@0 | 17 | * its contributors may be used to endorse or promote products derived |
michael@0 | 18 | * from this software without specific prior written permission. |
michael@0 | 19 | * |
michael@0 | 20 | * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY |
michael@0 | 21 | * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED |
michael@0 | 22 | * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
michael@0 | 23 | * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY |
michael@0 | 24 | * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
michael@0 | 25 | * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
michael@0 | 26 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
michael@0 | 27 | * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
michael@0 | 28 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
michael@0 | 29 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
michael@0 | 30 | * |
michael@0 | 31 | * ***** END LICENSE BLOCK ***** */ |
michael@0 | 32 | |
michael@0 | 33 | #ifndef yarr_ASCIICType_h |
michael@0 | 34 | #define yarr_ASCIICType_h |
michael@0 | 35 | |
michael@0 | 36 | #include "assembler/wtf/Assertions.h" |
michael@0 | 37 | |
michael@0 | 38 | // The behavior of many of the functions in the <ctype.h> header is dependent |
michael@0 | 39 | // on the current locale. But in the WebKit project, all uses of those functions |
michael@0 | 40 | // are in code processing something that's not locale-specific. These equivalents |
michael@0 | 41 | // for some of the <ctype.h> functions are named more explicitly, not dependent |
michael@0 | 42 | // on the C library locale, and we should also optimize them as needed. |
michael@0 | 43 | |
michael@0 | 44 | // All functions return false or leave the character unchanged if passed a character |
michael@0 | 45 | // that is outside the range 0-7F. So they can be used on Unicode strings or |
michael@0 | 46 | // characters if the intent is to do processing only if the character is ASCII. |
michael@0 | 47 | |
michael@0 | 48 | namespace WTF { |
michael@0 | 49 | |
michael@0 | 50 | inline bool isASCII(char c) { return !(c & ~0x7F); } |
michael@0 | 51 | inline bool isASCII(unsigned short c) { return !(c & ~0x7F); } |
michael@0 | 52 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 53 | inline bool isASCII(wchar_t c) { return !(c & ~0x7F); } |
michael@0 | 54 | #endif |
michael@0 | 55 | inline bool isASCII(int c) { return !(c & ~0x7F); } |
michael@0 | 56 | inline bool isASCII(unsigned c) { return !(c & ~0x7F); } |
michael@0 | 57 | |
michael@0 | 58 | inline bool isASCIIAlpha(char c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
michael@0 | 59 | inline bool isASCIIAlpha(unsigned short c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
michael@0 | 60 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 61 | inline bool isASCIIAlpha(wchar_t c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
michael@0 | 62 | #endif |
michael@0 | 63 | inline bool isASCIIAlpha(int c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
michael@0 | 64 | inline bool isASCIIAlpha(unsigned c) { return (c | 0x20) >= 'a' && (c | 0x20) <= 'z'; } |
michael@0 | 65 | |
michael@0 | 66 | inline bool isASCIIAlphanumeric(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
michael@0 | 67 | inline bool isASCIIAlphanumeric(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
michael@0 | 68 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 69 | inline bool isASCIIAlphanumeric(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
michael@0 | 70 | #endif |
michael@0 | 71 | inline bool isASCIIAlphanumeric(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
michael@0 | 72 | inline bool isASCIIAlphanumeric(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'z'); } |
michael@0 | 73 | |
michael@0 | 74 | inline bool isASCIIDigit(char c) { return (c >= '0') & (c <= '9'); } |
michael@0 | 75 | inline bool isASCIIDigit(unsigned short c) { return (c >= '0') & (c <= '9'); } |
michael@0 | 76 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 77 | inline bool isASCIIDigit(wchar_t c) { return (c >= '0') & (c <= '9'); } |
michael@0 | 78 | #endif |
michael@0 | 79 | inline bool isASCIIDigit(int c) { return (c >= '0') & (c <= '9'); } |
michael@0 | 80 | inline bool isASCIIDigit(unsigned c) { return (c >= '0') & (c <= '9'); } |
michael@0 | 81 | |
michael@0 | 82 | inline bool isASCIIHexDigit(char c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
michael@0 | 83 | inline bool isASCIIHexDigit(unsigned short c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
michael@0 | 84 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 85 | inline bool isASCIIHexDigit(wchar_t c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
michael@0 | 86 | #endif |
michael@0 | 87 | inline bool isASCIIHexDigit(int c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
michael@0 | 88 | inline bool isASCIIHexDigit(unsigned c) { return (c >= '0' && c <= '9') || ((c | 0x20) >= 'a' && (c | 0x20) <= 'f'); } |
michael@0 | 89 | |
michael@0 | 90 | inline bool isASCIIOctalDigit(char c) { return (c >= '0') & (c <= '7'); } |
michael@0 | 91 | inline bool isASCIIOctalDigit(unsigned short c) { return (c >= '0') & (c <= '7'); } |
michael@0 | 92 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 93 | inline bool isASCIIOctalDigit(wchar_t c) { return (c >= '0') & (c <= '7'); } |
michael@0 | 94 | #endif |
michael@0 | 95 | inline bool isASCIIOctalDigit(int c) { return (c >= '0') & (c <= '7'); } |
michael@0 | 96 | inline bool isASCIIOctalDigit(unsigned c) { return (c >= '0') & (c <= '7'); } |
michael@0 | 97 | |
michael@0 | 98 | inline bool isASCIILower(char c) { return c >= 'a' && c <= 'z'; } |
michael@0 | 99 | inline bool isASCIILower(unsigned short c) { return c >= 'a' && c <= 'z'; } |
michael@0 | 100 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 101 | inline bool isASCIILower(wchar_t c) { return c >= 'a' && c <= 'z'; } |
michael@0 | 102 | #endif |
michael@0 | 103 | inline bool isASCIILower(int c) { return c >= 'a' && c <= 'z'; } |
michael@0 | 104 | inline bool isASCIILower(unsigned c) { return c >= 'a' && c <= 'z'; } |
michael@0 | 105 | |
michael@0 | 106 | inline bool isASCIIUpper(char c) { return c >= 'A' && c <= 'Z'; } |
michael@0 | 107 | inline bool isASCIIUpper(unsigned short c) { return c >= 'A' && c <= 'Z'; } |
michael@0 | 108 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 109 | inline bool isASCIIUpper(wchar_t c) { return c >= 'A' && c <= 'Z'; } |
michael@0 | 110 | #endif |
michael@0 | 111 | inline bool isASCIIUpper(int c) { return c >= 'A' && c <= 'Z'; } |
michael@0 | 112 | inline bool isASCIIUpper(unsigned c) { return c >= 'A' && c <= 'Z'; } |
michael@0 | 113 | |
michael@0 | 114 | /* |
michael@0 | 115 | Statistics from a run of Apple's page load test for callers of isASCIISpace: |
michael@0 | 116 | |
michael@0 | 117 | character count |
michael@0 | 118 | --------- ----- |
michael@0 | 119 | non-spaces 689383 |
michael@0 | 120 | 20 space 294720 |
michael@0 | 121 | 0A \n 89059 |
michael@0 | 122 | 09 \t 28320 |
michael@0 | 123 | 0D \r 0 |
michael@0 | 124 | 0C \f 0 |
michael@0 | 125 | 0B \v 0 |
michael@0 | 126 | */ |
michael@0 | 127 | inline bool isASCIISpace(char c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
michael@0 | 128 | inline bool isASCIISpace(unsigned short c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
michael@0 | 129 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 130 | inline bool isASCIISpace(wchar_t c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
michael@0 | 131 | #endif |
michael@0 | 132 | inline bool isASCIISpace(int c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
michael@0 | 133 | inline bool isASCIISpace(unsigned c) { return c <= ' ' && (c == ' ' || (c <= 0xD && c >= 0x9)); } |
michael@0 | 134 | |
michael@0 | 135 | inline char toASCIILower(char c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
michael@0 | 136 | inline unsigned short toASCIILower(unsigned short c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
michael@0 | 137 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 138 | inline wchar_t toASCIILower(wchar_t c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
michael@0 | 139 | #endif |
michael@0 | 140 | inline int toASCIILower(int c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
michael@0 | 141 | inline unsigned toASCIILower(unsigned c) { return c | ((c >= 'A' && c <= 'Z') << 5); } |
michael@0 | 142 | |
michael@0 | 143 | // FIXME: Why do these need static_cast? |
michael@0 | 144 | inline char toASCIIUpper(char c) { return static_cast<char>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
michael@0 | 145 | inline unsigned short toASCIIUpper(unsigned short c) { return static_cast<unsigned short>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
michael@0 | 146 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 147 | inline wchar_t toASCIIUpper(wchar_t c) { return static_cast<wchar_t>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
michael@0 | 148 | #endif |
michael@0 | 149 | inline int toASCIIUpper(int c) { return static_cast<int>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
michael@0 | 150 | inline unsigned toASCIIUpper(unsigned c) { return static_cast<unsigned>(c & ~((c >= 'a' && c <= 'z') << 5)); } |
michael@0 | 151 | |
michael@0 | 152 | inline int toASCIIHexValue(char c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
michael@0 | 153 | inline int toASCIIHexValue(unsigned short c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
michael@0 | 154 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 155 | inline int toASCIIHexValue(wchar_t c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
michael@0 | 156 | #endif |
michael@0 | 157 | inline int toASCIIHexValue(int c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
michael@0 | 158 | inline int toASCIIHexValue(unsigned c) { ASSERT(isASCIIHexDigit(c)); return c < 'A' ? c - '0' : (c - 'A' + 10) & 0xF; } |
michael@0 | 159 | |
michael@0 | 160 | inline bool isASCIIPrintable(char c) { return c >= ' ' && c <= '~'; } |
michael@0 | 161 | inline bool isASCIIPrintable(unsigned short c) { return c >= ' ' && c <= '~'; } |
michael@0 | 162 | #if !WTF_COMPILER_MSVC || defined(_NATIVE_WCHAR_T_DEFINED) |
michael@0 | 163 | inline bool isASCIIPrintable(wchar_t c) { return c >= ' ' && c <= '~'; } |
michael@0 | 164 | #endif |
michael@0 | 165 | inline bool isASCIIPrintable(int c) { return c >= ' ' && c <= '~'; } |
michael@0 | 166 | inline bool isASCIIPrintable(unsigned c) { return c >= ' ' && c <= '~'; } |
michael@0 | 167 | } |
michael@0 | 168 | |
michael@0 | 169 | using WTF::isASCII; |
michael@0 | 170 | using WTF::isASCIIAlpha; |
michael@0 | 171 | using WTF::isASCIIAlphanumeric; |
michael@0 | 172 | using WTF::isASCIIDigit; |
michael@0 | 173 | using WTF::isASCIIHexDigit; |
michael@0 | 174 | using WTF::isASCIILower; |
michael@0 | 175 | using WTF::isASCIIOctalDigit; |
michael@0 | 176 | using WTF::isASCIIPrintable; |
michael@0 | 177 | using WTF::isASCIISpace; |
michael@0 | 178 | using WTF::isASCIIUpper; |
michael@0 | 179 | using WTF::toASCIIHexValue; |
michael@0 | 180 | using WTF::toASCIILower; |
michael@0 | 181 | using WTF::toASCIIUpper; |
michael@0 | 182 | |
michael@0 | 183 | #endif /* yarr_ASCIICType_h */ |