1 // Copyright 2007, Google Inc. 2 // 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 are 6 // met: 7 // 8 // * Redistributions of source code must retain the above copyright 9 // notice, this list of conditions and the following disclaimer. 10 // * Redistributions in binary form must reproduce the above 11 // copyright notice, this list of conditions and the following disclaimer 12 // in the documentation and/or other materials provided with the 13 // distribution. 14 // * Neither the name of Google Inc. nor the names of its 15 // contributors may be used to endorse or promote products derived from 16 // this software without specific prior written permission. 17 // 18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 19 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 20 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 21 // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 22 // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 23 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 24 // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 25 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 26 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 27 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 28 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 29 30 #ifndef GOOGLEURL_SRC_URL_UTIL_H__ 31 #define GOOGLEURL_SRC_URL_UTIL_H__ 32 33 #include <string> 34 35 #include "base/string16.h" 36 #include "googleurl/src/url_common.h" 37 #include "googleurl/src/url_parse.h" 38 #include "googleurl/src/url_canon.h" 39 40 namespace url_util { 41 42 // Init ------------------------------------------------------------------------ 43 44 // Initialization is NOT required, it will be implicitly initialized when first 45 // used. However, this implicit initialization is NOT threadsafe. If you are 46 // using this library in a threaded environment and don't have a consistent 47 // "first call" (an example might be calling "AddStandardScheme" with your 48 // special application-specific schemes) then you will want to call initialize 49 // before spawning any threads. 50 // 51 // It is OK to call this function more than once, subsequent calls will simply 52 // "noop", unless Shutdown() was called in the mean time. This will also be a 53 // "noop" if other calls to the library have forced an initialization 54 // beforehand. 55 GURL_API void Initialize(); 56 57 // Cleanup is not required, except some strings may leak. For most user 58 // applications, this is fine. If you're using it in a library that may get 59 // loaded and unloaded, you'll want to unload to properly clean up your 60 // library. 61 GURL_API void Shutdown(); 62 63 // Schemes -------------------------------------------------------------------- 64 65 // Adds an application-defined scheme to the internal list of "standard" URL 66 // schemes. This function is not threadsafe and can not be called concurrently 67 // with any other url_util function. It will assert if the list of standard 68 // schemes has been locked (see LockStandardSchemes). 69 GURL_API void AddStandardScheme(const char* new_scheme); 70 71 // Sets a flag to prevent future calls to AddStandardScheme from succeeding. 72 // 73 // This is designed to help prevent errors for multithreaded applications. 74 // Normal usage would be to call AddStandardScheme for your custom schemes at 75 // the beginning of program initialization, and then LockStandardSchemes. This 76 // prevents future callers from mistakenly calling AddStandardScheme when the 77 // program is running with multiple threads, where such usage would be 78 // dangerous. 79 // 80 // We could have had AddStandardScheme use a lock instead, but that would add 81 // some platform-specific dependencies we don't otherwise have now, and is 82 // overkill considering the normal usage is so simple. 83 GURL_API void LockStandardSchemes(); 84 85 // Locates the scheme in the given string and places it into |found_scheme|, 86 // which may be NULL to indicate the caller does not care about the range. 87 // 88 // Returns whether the given |compare| scheme matches the scheme found in the 89 // input (if any). The |compare| scheme must be a valid canonical scheme or 90 // the result of the comparison is undefined. 91 GURL_API bool FindAndCompareScheme(const char* str, 92 int str_len, 93 const char* compare, 94 url_parse::Component* found_scheme); 95 GURL_API bool FindAndCompareScheme(const char16* str, 96 int str_len, 97 const char* compare, 98 url_parse::Component* found_scheme); 99 inline bool FindAndCompareScheme(const std::string& str, 100 const char* compare, 101 url_parse::Component* found_scheme) { 102 return FindAndCompareScheme(str.data(), static_cast<int>(str.size()), 103 compare, found_scheme); 104 } 105 inline bool FindAndCompareScheme(const string16& str, 106 const char* compare, 107 url_parse::Component* found_scheme) { 108 return FindAndCompareScheme(str.data(), static_cast<int>(str.size()), 109 compare, found_scheme); 110 } 111 112 // Returns true if the given string represents a standard URL. This means that 113 // either the scheme is in the list of known standard schemes. 114 GURL_API bool IsStandard(const char* spec, 115 const url_parse::Component& scheme); 116 GURL_API bool IsStandard(const char16* spec, 117 const url_parse::Component& scheme); 118 119 // TODO(brettw) remove this. This is a temporary compatibility hack to avoid 120 // breaking the WebKit build when this version is synced via Chrome. 121 inline bool IsStandard(const char* spec, int spec_len, 122 const url_parse::Component& scheme) { 123 return IsStandard(spec, scheme); 124 } 125 126 // URL library wrappers ------------------------------------------------------- 127 128 // Parses the given spec according to the extracted scheme type. Normal users 129 // should use the URL object, although this may be useful if performance is 130 // critical and you don't want to do the heap allocation for the std::string. 131 // 132 // As with the url_canon::Canonicalize* functions, the charset converter can 133 // be NULL to use UTF-8 (it will be faster in this case). 134 // 135 // Returns true if a valid URL was produced, false if not. On failure, the 136 // output and parsed structures will still be filled and will be consistent, 137 // but they will not represent a loadable URL. 138 GURL_API bool Canonicalize(const char* spec, 139 int spec_len, 140 url_canon::CharsetConverter* charset_converter, 141 url_canon::CanonOutput* output, 142 url_parse::Parsed* output_parsed); 143 GURL_API bool Canonicalize(const char16* spec, 144 int spec_len, 145 url_canon::CharsetConverter* charset_converter, 146 url_canon::CanonOutput* output, 147 url_parse::Parsed* output_parsed); 148 149 // Resolves a potentially relative URL relative to the given parsed base URL. 150 // The base MUST be valid. The resulting canonical URL and parsed information 151 // will be placed in to the given out variables. 152 // 153 // The relative need not be relative. If we discover that it's absolute, this 154 // will produce a canonical version of that URL. See Canonicalize() for more 155 // about the charset_converter. 156 // 157 // Returns true if the output is valid, false if the input could not produce 158 // a valid URL. 159 GURL_API bool ResolveRelative(const char* base_spec, 160 int base_spec_len, 161 const url_parse::Parsed& base_parsed, 162 const char* relative, 163 int relative_length, 164 url_canon::CharsetConverter* charset_converter, 165 url_canon::CanonOutput* output, 166 url_parse::Parsed* output_parsed); 167 GURL_API bool ResolveRelative(const char* base_spec, 168 int base_spec_len, 169 const url_parse::Parsed& base_parsed, 170 const char16* relative, 171 int relative_length, 172 url_canon::CharsetConverter* charset_converter, 173 url_canon::CanonOutput* output, 174 url_parse::Parsed* output_parsed); 175 176 // Replaces components in the given VALID input url. The new canonical URL info 177 // is written to output and out_parsed. 178 // 179 // Returns true if the resulting URL is valid. 180 GURL_API bool ReplaceComponents( 181 const char* spec, 182 int spec_len, 183 const url_parse::Parsed& parsed, 184 const url_canon::Replacements<char>& replacements, 185 url_canon::CharsetConverter* charset_converter, 186 url_canon::CanonOutput* output, 187 url_parse::Parsed* out_parsed); 188 GURL_API bool ReplaceComponents( 189 const char* spec, 190 int spec_len, 191 const url_parse::Parsed& parsed, 192 const url_canon::Replacements<char16>& replacements, 193 url_canon::CharsetConverter* charset_converter, 194 url_canon::CanonOutput* output, 195 url_parse::Parsed* out_parsed); 196 197 // String helper functions ---------------------------------------------------- 198 199 // Compare the lower-case form of the given string against the given ASCII 200 // string. This is useful for doing checking if an input string matches some 201 // token, and it is optimized to avoid intermediate string copies. 202 // 203 // The versions of this function that don't take a b_end assume that the b 204 // string is NULL terminated. 205 GURL_API bool LowerCaseEqualsASCII(const char* a_begin, 206 const char* a_end, 207 const char* b); 208 GURL_API bool LowerCaseEqualsASCII(const char* a_begin, 209 const char* a_end, 210 const char* b_begin, 211 const char* b_end); 212 GURL_API bool LowerCaseEqualsASCII(const char16* a_begin, 213 const char16* a_end, 214 const char* b); 215 216 // Unescapes the given string using URL escaping rules. 217 GURL_API void DecodeURLEscapeSequences(const char* input, int length, 218 url_canon::CanonOutputW* output); 219 220 } // namespace url_util 221 222 #endif // GOOGLEURL_SRC_URL_UTIL_H__ 223