1 // Copyright 2010, Google Inc. All rights reserved. 2 // 3 // Redistribution and use in source and binary forms, with or without 4 // modification, are permitted provided that the following conditions are 5 // met: 6 // 7 // * Redistributions of source code must retain the above copyright 8 // notice, this list of conditions and the following disclaimer. 9 // * Redistributions in binary form must reproduce the above 10 // copyright notice, this list of conditions and the following disclaimer 11 // in the documentation and/or other materials provided with the 12 // distribution. 13 // * Neither the name of Google Inc. nor the names of its 14 // contributors may be used to endorse or promote products derived from 15 // this software without specific prior written permission. 16 // 17 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 18 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 19 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 20 // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 21 // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 22 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 23 // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 24 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 25 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 26 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 27 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 28 29 #include "config.h" 30 #include "URLCharacterTypes.h" 31 32 namespace WTF { 33 34 const unsigned char URLCharacterTypes::characterTypeTable[0x100] = { 35 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 36 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 37 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 38 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0x00 - 0x0f 39 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 40 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 41 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 42 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0x10 - 0x1f 43 InvalidCharacter, // 0x20 ' ' (escape spaces in queries) 44 QueryCharacter | UserInfoCharacter, // 0x21 ! 45 InvalidCharacter, // 0x22 " 46 InvalidCharacter, // 0x23 # (invalid in query since it marks the ref) 47 QueryCharacter | UserInfoCharacter, // 0x24 $ 48 QueryCharacter | UserInfoCharacter, // 0x25 % 49 QueryCharacter | UserInfoCharacter, // 0x26 & 50 QueryCharacter | UserInfoCharacter, // 0x27 ' 51 QueryCharacter | UserInfoCharacter, // 0x28 ( 52 QueryCharacter | UserInfoCharacter, // 0x29 ) 53 QueryCharacter | UserInfoCharacter, // 0x2a * 54 QueryCharacter | UserInfoCharacter, // 0x2b + 55 QueryCharacter | UserInfoCharacter, // 0x2c , 56 QueryCharacter | UserInfoCharacter, // 0x2d - 57 QueryCharacter | UserInfoCharacter | IPv4Character, // 0x2e . 58 QueryCharacter, // 0x2f / 59 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x30 0 60 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x31 1 61 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x32 2 62 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x33 3 63 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x34 4 64 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x35 5 65 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x36 6 66 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter | OctalCharacter, // 0x37 7 67 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter, // 0x38 8 68 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter | DecimalCharacter, // 0x39 9 69 QueryCharacter, // 0x3a : 70 QueryCharacter, // 0x3b ; 71 InvalidCharacter, // 0x3c < 72 QueryCharacter, // 0x3d = 73 InvalidCharacter, // 0x3e > 74 QueryCharacter, // 0x3f ? 75 QueryCharacter, // 0x40 @ 76 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x41 A 77 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x42 B 78 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x43 C 79 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x44 D 80 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x45 E 81 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x46 F 82 QueryCharacter | UserInfoCharacter, // 0x47 G 83 QueryCharacter | UserInfoCharacter, // 0x48 H 84 QueryCharacter | UserInfoCharacter, // 0x49 I 85 QueryCharacter | UserInfoCharacter, // 0x4a J 86 QueryCharacter | UserInfoCharacter, // 0x4b K 87 QueryCharacter | UserInfoCharacter, // 0x4c L 88 QueryCharacter | UserInfoCharacter, // 0x4d M 89 QueryCharacter | UserInfoCharacter, // 0x4e N 90 QueryCharacter | UserInfoCharacter, // 0x4f O 91 QueryCharacter | UserInfoCharacter, // 0x50 P 92 QueryCharacter | UserInfoCharacter, // 0x51 Q 93 QueryCharacter | UserInfoCharacter, // 0x52 R 94 QueryCharacter | UserInfoCharacter, // 0x53 S 95 QueryCharacter | UserInfoCharacter, // 0x54 T 96 QueryCharacter | UserInfoCharacter, // 0x55 U 97 QueryCharacter | UserInfoCharacter, // 0x56 V 98 QueryCharacter | UserInfoCharacter, // 0x57 W 99 QueryCharacter | UserInfoCharacter | IPv4Character, // 0x58 X 100 QueryCharacter | UserInfoCharacter, // 0x59 Y 101 QueryCharacter | UserInfoCharacter, // 0x5a Z 102 QueryCharacter, // 0x5b [ 103 QueryCharacter, // 0x5c '\' 104 QueryCharacter, // 0x5d ] 105 QueryCharacter, // 0x5e ^ 106 QueryCharacter | UserInfoCharacter, // 0x5f _ 107 QueryCharacter, // 0x60 ` 108 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x61 a 109 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x62 b 110 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x63 c 111 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x64 d 112 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x65 e 113 QueryCharacter | UserInfoCharacter | IPv4Character | HexCharacter, // 0x66 f 114 QueryCharacter | UserInfoCharacter, // 0x67 g 115 QueryCharacter | UserInfoCharacter, // 0x68 h 116 QueryCharacter | UserInfoCharacter, // 0x69 i 117 QueryCharacter | UserInfoCharacter, // 0x6a j 118 QueryCharacter | UserInfoCharacter, // 0x6b k 119 QueryCharacter | UserInfoCharacter, // 0x6c l 120 QueryCharacter | UserInfoCharacter, // 0x6d m 121 QueryCharacter | UserInfoCharacter, // 0x6e n 122 QueryCharacter | UserInfoCharacter, // 0x6f o 123 QueryCharacter | UserInfoCharacter, // 0x70 p 124 QueryCharacter | UserInfoCharacter, // 0x71 q 125 QueryCharacter | UserInfoCharacter, // 0x72 r 126 QueryCharacter | UserInfoCharacter, // 0x73 s 127 QueryCharacter | UserInfoCharacter, // 0x74 t 128 QueryCharacter | UserInfoCharacter, // 0x75 u 129 QueryCharacter | UserInfoCharacter, // 0x76 v 130 QueryCharacter | UserInfoCharacter, // 0x77 w 131 QueryCharacter | UserInfoCharacter | IPv4Character, // 0x78 x 132 QueryCharacter | UserInfoCharacter, // 0x79 y 133 QueryCharacter | UserInfoCharacter, // 0x7a z 134 QueryCharacter, // 0x7b { 135 QueryCharacter, // 0x7c | 136 QueryCharacter, // 0x7d } 137 QueryCharacter | UserInfoCharacter, // 0x7e ~ 138 InvalidCharacter, // 0x7f 139 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 140 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 141 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 142 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0x80 - 0x8f 143 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 144 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 145 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 146 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0x90 - 0x9f 147 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 148 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 149 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 150 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0xa0 - 0xaf 151 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 152 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 153 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 154 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0xb0 - 0xbf 155 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 156 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 157 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 158 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0xc0 - 0xcf 159 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 160 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 161 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 162 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0xd0 - 0xdf 163 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 164 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 165 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 166 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0xe0 - 0xef 167 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 168 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 169 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, 170 InvalidCharacter, InvalidCharacter, InvalidCharacter, InvalidCharacter, // 0xf0 - 0xff 171 }; 172 173 } 174