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 30 #ifndef URLQueryCanonicalizer_h 31 #define URLQueryCanonicalizer_h 32 33 #include "RawURLBuffer.h" 34 #include "URLBuffer.h" 35 #include "URLCharacterTypes.h" 36 #include "URLComponent.h" 37 #include "URLEscape.h" 38 39 namespace WTF { 40 41 template<typename InChar, typename OutChar, void convertCharset(const InChar*, int length, URLBuffer<char>&)> 42 class URLQueryCanonicalizer { 43 public: canonicalize(const InChar * spec,const URLComponent & query,URLBuffer<OutChar> & buffer,URLComponent & resultQuery)44 static void canonicalize(const InChar* spec, const URLComponent& query, URLBuffer<OutChar>& buffer, URLComponent& resultQuery) 45 { 46 if (query.length() < 0) { 47 resultQuery = URLComponent(); 48 return; 49 } 50 51 buffer->append('?'); 52 resultQuery.setBegin(buffer->length()); 53 convertToQueryEncoding(spec, query, buffer); 54 resultQuery.setLength(buffer->length() - resultQuery.begin()); 55 } 56 57 private: isAllASCII(const InChar * spec,const URLComponent & query)58 static bool isAllASCII(const InChar* spec, const URLComponent& query) 59 { 60 int end = query.end(); 61 for (int i = query.begin(); i < end; ++i) { 62 if (static_cast<unsigned>(spec[i]) >= 0x80) 63 return false; 64 } 65 return true; 66 } 67 68 #ifndef NDEBUG isRaw8Bit(const InChar * source,int length)69 static bool isRaw8Bit(const InChar* source, int length) 70 { 71 for (int i = source; i < length; ++i) { 72 if (source[i] & 0xFF != source[i]) 73 return false; 74 } 75 return true; 76 } 77 #endif 78 appendRaw8BitQueryString(const InChar * source,int length,URLBuffer<OutChar> * buffer)79 static void appendRaw8BitQueryString(const InChar* source, int length, URLBuffer<OutChar>* buffer) 80 { 81 ASSERT(isRaw8Bit(source, length)); 82 for (int i = 0; i < length; ++i) { 83 if (!URLCharacterTypes::isQueryChar(source[i])) 84 appendURLEscapedCharacter(static_cast<unsigned char>(source[i]), buffer); 85 else 86 buffer->append(static_cast<char>(source[i])); 87 } 88 } 89 convertToQueryEncoding(const InChar * spec,const URLComponent & query,URLBuffer<OutChar> & buffer)90 static void convertToQueryEncoding(const InChar* spec, const URLComponent& query, URLBuffer<OutChar>& buffer) 91 { 92 if (isAllASCII(spec, query)) { 93 appendRaw8BitQueryString(&spec[query.begin()], query.length(), buffer); 94 return; 95 } 96 97 RawURLBuffer<char, 1024> convertedQuery; 98 convertCharset(spec, query, convertedQuery); 99 appendRaw8BitQueryString(convertedQuery.data(), convertedQuery.length(), buffer); 100 } 101 }; 102 103 } 104 105 #endif 106 107 108