OLD | NEW |
1 // Copyright 2007, Google Inc. | 1 // Copyright 2007, Google Inc. |
2 // All rights reserved. | 2 // All rights reserved. |
3 // | 3 // |
4 // Redistribution and use in source and binary forms, with or without | 4 // Redistribution and use in source and binary forms, with or without |
5 // modification, are permitted provided that the following conditions are | 5 // modification, are permitted provided that the following conditions are |
6 // met: | 6 // met: |
7 // | 7 // |
8 // * Redistributions of source code must retain the above copyright | 8 // * Redistributions of source code must retain the above copyright |
9 // notice, this list of conditions and the following disclaimer. | 9 // notice, this list of conditions and the following disclaimer. |
10 // * Redistributions in binary form must reproduce the above | 10 // * Redistributions in binary form must reproduce the above |
(...skipping 15 matching lines...) Expand all Loading... |
26 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | 26 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
27 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | 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. | 28 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
29 | 29 |
30 #ifndef GOOGLEURL_SRC_URL_UTIL_H__ | 30 #ifndef GOOGLEURL_SRC_URL_UTIL_H__ |
31 #define GOOGLEURL_SRC_URL_UTIL_H__ | 31 #define GOOGLEURL_SRC_URL_UTIL_H__ |
32 | 32 |
33 #include <string> | 33 #include <string> |
34 | 34 |
35 #include "base/string16.h" | 35 #include "base/string16.h" |
| 36 #include "googleurl/src/url_common.h" |
36 #include "googleurl/src/url_parse.h" | 37 #include "googleurl/src/url_parse.h" |
37 #include "googleurl/src/url_canon.h" | 38 #include "googleurl/src/url_canon.h" |
38 | 39 |
39 namespace url_util { | 40 namespace url_util { |
40 | 41 |
41 // Init ------------------------------------------------------------------------ | 42 // Init ------------------------------------------------------------------------ |
42 | 43 |
43 // Initialization is NOT required, it will be implicitly initialized when first | 44 // Initialization is NOT required, it will be implicitly initialized when first |
44 // used. However, this implicit initialization is NOT threadsafe. If you are | 45 // used. However, this implicit initialization is NOT threadsafe. If you are |
45 // using this library in a threaded environment and don't have a consistent | 46 // using this library in a threaded environment and don't have a consistent |
46 // "first call" (an example might be calling "AddStandardScheme" with your | 47 // "first call" (an example might be calling "AddStandardScheme" with your |
47 // special application-specific schemes) then you will want to call initialize | 48 // special application-specific schemes) then you will want to call initialize |
48 // before spawning any threads. | 49 // before spawning any threads. |
49 // | 50 // |
50 // It is OK to call this function more than once, subsequent calls will simply | 51 // It is OK to call this function more than once, subsequent calls will simply |
51 // "noop", unless Shutdown() was called in the mean time. This will also be a | 52 // "noop", unless Shutdown() was called in the mean time. This will also be a |
52 // "noop" if other calls to the library have forced an initialization | 53 // "noop" if other calls to the library have forced an initialization |
53 // beforehand. | 54 // beforehand. |
54 void Initialize(); | 55 GURL_API void Initialize(); |
55 | 56 |
56 // Cleanup is not required, except some strings may leak. For most user | 57 // Cleanup is not required, except some strings may leak. For most user |
57 // applications, this is fine. If you're using it in a library that may get | 58 // applications, this is fine. If you're using it in a library that may get |
58 // loaded and unloaded, you'll want to unload to properly clean up your | 59 // loaded and unloaded, you'll want to unload to properly clean up your |
59 // library. | 60 // library. |
60 void Shutdown(); | 61 GURL_API void Shutdown(); |
61 | 62 |
62 // Schemes -------------------------------------------------------------------- | 63 // Schemes -------------------------------------------------------------------- |
63 | 64 |
64 // Adds an application-defined scheme to the internal list of "standard" URL | 65 // Adds an application-defined scheme to the internal list of "standard" URL |
65 // schemes. This function is not threadsafe and can not be called concurrently | 66 // schemes. This function is not threadsafe and can not be called concurrently |
66 // with any other url_util function. It will assert if the list of standard | 67 // with any other url_util function. It will assert if the list of standard |
67 // schemes has been locked (see LockStandardSchemes). | 68 // schemes has been locked (see LockStandardSchemes). |
68 void AddStandardScheme(const char* new_scheme); | 69 GURL_API void AddStandardScheme(const char* new_scheme); |
69 | 70 |
70 // Sets a flag to prevent future calls to AddStandardScheme from succeeding. | 71 // Sets a flag to prevent future calls to AddStandardScheme from succeeding. |
71 // | 72 // |
72 // This is designed to help prevent errors for multithreaded applications. | 73 // This is designed to help prevent errors for multithreaded applications. |
73 // Normal usage would be to call AddStandardScheme for your custom schemes at | 74 // Normal usage would be to call AddStandardScheme for your custom schemes at |
74 // the beginning of program initialization, and then LockStandardSchemes. This | 75 // the beginning of program initialization, and then LockStandardSchemes. This |
75 // prevents future callers from mistakenly calling AddStandardScheme when the | 76 // prevents future callers from mistakenly calling AddStandardScheme when the |
76 // program is running with multiple threads, where such usage would be | 77 // program is running with multiple threads, where such usage would be |
77 // dangerous. | 78 // dangerous. |
78 // | 79 // |
79 // We could have had AddStandardScheme use a lock instead, but that would add | 80 // We could have had AddStandardScheme use a lock instead, but that would add |
80 // some platform-specific dependencies we don't otherwise have now, and is | 81 // some platform-specific dependencies we don't otherwise have now, and is |
81 // overkill considering the normal usage is so simple. | 82 // overkill considering the normal usage is so simple. |
82 void LockStandardSchemes(); | 83 GURL_API void LockStandardSchemes(); |
83 | 84 |
84 // Locates the scheme in the given string and places it into |found_scheme|, | 85 // Locates the scheme in the given string and places it into |found_scheme|, |
85 // which may be NULL to indicate the caller does not care about the range. | 86 // which may be NULL to indicate the caller does not care about the range. |
86 // | 87 // |
87 // Returns whether the given |compare| scheme matches the scheme found in the | 88 // Returns whether the given |compare| scheme matches the scheme found in the |
88 // input (if any). The |compare| scheme must be a valid canonical scheme or | 89 // input (if any). The |compare| scheme must be a valid canonical scheme or |
89 // the result of the comparison is undefined. | 90 // the result of the comparison is undefined. |
90 bool FindAndCompareScheme(const char* str, | 91 GURL_API bool FindAndCompareScheme(const char* str, |
91 int str_len, | 92 int str_len, |
92 const char* compare, | 93 const char* compare, |
93 url_parse::Component* found_scheme); | 94 url_parse::Component* found_scheme); |
94 bool FindAndCompareScheme(const char16* str, | 95 GURL_API bool FindAndCompareScheme(const char16* str, |
95 int str_len, | 96 int str_len, |
96 const char* compare, | 97 const char* compare, |
97 url_parse::Component* found_scheme); | 98 url_parse::Component* found_scheme); |
98 inline bool FindAndCompareScheme(const std::string& str, | 99 inline bool FindAndCompareScheme(const std::string& str, |
99 const char* compare, | 100 const char* compare, |
100 url_parse::Component* found_scheme) { | 101 url_parse::Component* found_scheme) { |
101 return FindAndCompareScheme(str.data(), static_cast<int>(str.size()), | 102 return FindAndCompareScheme(str.data(), static_cast<int>(str.size()), |
102 compare, found_scheme); | 103 compare, found_scheme); |
103 } | 104 } |
104 inline bool FindAndCompareScheme(const string16& str, | 105 inline bool FindAndCompareScheme(const string16& str, |
105 const char* compare, | 106 const char* compare, |
106 url_parse::Component* found_scheme) { | 107 url_parse::Component* found_scheme) { |
107 return FindAndCompareScheme(str.data(), static_cast<int>(str.size()), | 108 return FindAndCompareScheme(str.data(), static_cast<int>(str.size()), |
108 compare, found_scheme); | 109 compare, found_scheme); |
109 } | 110 } |
110 | 111 |
111 // Returns true if the given string represents a standard URL. This means that | 112 // Returns true if the given string represents a standard URL. This means that |
112 // either the scheme is in the list of known standard schemes. | 113 // either the scheme is in the list of known standard schemes. |
113 bool IsStandard(const char* spec, const url_parse::Component& scheme); | 114 GURL_API bool IsStandard(const char* spec, |
114 bool IsStandard(const char16* spec, const url_parse::Component& scheme); | 115 const url_parse::Component& scheme); |
| 116 GURL_API bool IsStandard(const char16* spec, |
| 117 const url_parse::Component& scheme); |
115 | 118 |
116 // TODO(brettw) remove this. This is a temporary compatibility hack to avoid | 119 // TODO(brettw) remove this. This is a temporary compatibility hack to avoid |
117 // breaking the WebKit build when this version is synced via Chrome. | 120 // breaking the WebKit build when this version is synced via Chrome. |
118 inline bool IsStandard(const char* spec, int spec_len, | 121 inline bool IsStandard(const char* spec, int spec_len, |
119 const url_parse::Component& scheme) { | 122 const url_parse::Component& scheme) { |
120 return IsStandard(spec, scheme); | 123 return IsStandard(spec, scheme); |
121 } | 124 } |
122 | 125 |
123 // URL library wrappers ------------------------------------------------------- | 126 // URL library wrappers ------------------------------------------------------- |
124 | 127 |
125 // Parses the given spec according to the extracted scheme type. Normal users | 128 // Parses the given spec according to the extracted scheme type. Normal users |
126 // should use the URL object, although this may be useful if performance is | 129 // should use the URL object, although this may be useful if performance is |
127 // critical and you don't want to do the heap allocation for the std::string. | 130 // critical and you don't want to do the heap allocation for the std::string. |
128 // | 131 // |
129 // As with the url_canon::Canonicalize* functions, the charset converter can | 132 // As with the url_canon::Canonicalize* functions, the charset converter can |
130 // be NULL to use UTF-8 (it will be faster in this case). | 133 // be NULL to use UTF-8 (it will be faster in this case). |
131 // | 134 // |
132 // Returns true if a valid URL was produced, false if not. On failure, the | 135 // Returns true if a valid URL was produced, false if not. On failure, the |
133 // output and parsed structures will still be filled and will be consistent, | 136 // output and parsed structures will still be filled and will be consistent, |
134 // but they will not represent a loadable URL. | 137 // but they will not represent a loadable URL. |
135 bool Canonicalize(const char* spec, | 138 GURL_API bool Canonicalize(const char* spec, |
136 int spec_len, | 139 int spec_len, |
137 url_canon::CharsetConverter* charset_converter, | 140 url_canon::CharsetConverter* charset_converter, |
138 url_canon::CanonOutput* output, | 141 url_canon::CanonOutput* output, |
139 url_parse::Parsed* output_parsed); | 142 url_parse::Parsed* output_parsed); |
140 bool Canonicalize(const char16* spec, | 143 GURL_API bool Canonicalize(const char16* spec, |
141 int spec_len, | 144 int spec_len, |
142 url_canon::CharsetConverter* charset_converter, | 145 url_canon::CharsetConverter* charset_converter, |
143 url_canon::CanonOutput* output, | 146 url_canon::CanonOutput* output, |
144 url_parse::Parsed* output_parsed); | 147 url_parse::Parsed* output_parsed); |
145 | 148 |
146 // Resolves a potentially relative URL relative to the given parsed base URL. | 149 // Resolves a potentially relative URL relative to the given parsed base URL. |
147 // The base MUST be valid. The resulting canonical URL and parsed information | 150 // The base MUST be valid. The resulting canonical URL and parsed information |
148 // will be placed in to the given out variables. | 151 // will be placed in to the given out variables. |
149 // | 152 // |
150 // The relative need not be relative. If we discover that it's absolute, this | 153 // The relative need not be relative. If we discover that it's absolute, this |
151 // will produce a canonical version of that URL. See Canonicalize() for more | 154 // will produce a canonical version of that URL. See Canonicalize() for more |
152 // about the charset_converter. | 155 // about the charset_converter. |
153 // | 156 // |
154 // Returns true if the output is valid, false if the input could not produce | 157 // Returns true if the output is valid, false if the input could not produce |
155 // a valid URL. | 158 // a valid URL. |
156 bool ResolveRelative(const char* base_spec, | 159 GURL_API bool ResolveRelative(const char* base_spec, |
157 int base_spec_len, | 160 int base_spec_len, |
158 const url_parse::Parsed& base_parsed, | 161 const url_parse::Parsed& base_parsed, |
159 const char* relative, | 162 const char* relative, |
160 int relative_length, | 163 int relative_length, |
161 url_canon::CharsetConverter* charset_converter, | 164 url_canon::CharsetConverter* charset_converter, |
162 url_canon::CanonOutput* output, | 165 url_canon::CanonOutput* output, |
163 url_parse::Parsed* output_parsed); | 166 url_parse::Parsed* output_parsed); |
164 bool ResolveRelative(const char* base_spec, | 167 GURL_API bool ResolveRelative(const char* base_spec, |
165 int base_spec_len, | 168 int base_spec_len, |
166 const url_parse::Parsed& base_parsed, | 169 const url_parse::Parsed& base_parsed, |
167 const char16* relative, | 170 const char16* relative, |
168 int relative_length, | 171 int relative_length, |
169 url_canon::CharsetConverter* charset_converter, | 172 url_canon::CharsetConverter* charset_converter, |
170 url_canon::CanonOutput* output, | 173 url_canon::CanonOutput* output, |
171 url_parse::Parsed* output_parsed); | 174 url_parse::Parsed* output_parsed); |
172 | 175 |
173 // Replaces components in the given VALID input url. The new canonical URL info | 176 // Replaces components in the given VALID input url. The new canonical URL info |
174 // is written to output and out_parsed. | 177 // is written to output and out_parsed. |
175 // | 178 // |
176 // Returns true if the resulting URL is valid. | 179 // Returns true if the resulting URL is valid. |
177 bool ReplaceComponents(const char* spec, | 180 GURL_API bool ReplaceComponents( |
178 int spec_len, | 181 const char* spec, |
179 const url_parse::Parsed& parsed, | 182 int spec_len, |
180 const url_canon::Replacements<char>& replacements, | 183 const url_parse::Parsed& parsed, |
181 url_canon::CharsetConverter* charset_converter, | 184 const url_canon::Replacements<char>& replacements, |
182 url_canon::CanonOutput* output, | 185 url_canon::CharsetConverter* charset_converter, |
183 url_parse::Parsed* out_parsed); | 186 url_canon::CanonOutput* output, |
184 bool ReplaceComponents(const char* spec, | 187 url_parse::Parsed* out_parsed); |
185 int spec_len, | 188 GURL_API bool ReplaceComponents( |
186 const url_parse::Parsed& parsed, | 189 const char* spec, |
187 const url_canon::Replacements<char16>& replacements, | 190 int spec_len, |
188 url_canon::CharsetConverter* charset_converter, | 191 const url_parse::Parsed& parsed, |
189 url_canon::CanonOutput* output, | 192 const url_canon::Replacements<char16>& replacements, |
190 url_parse::Parsed* out_parsed); | 193 url_canon::CharsetConverter* charset_converter, |
| 194 url_canon::CanonOutput* output, |
| 195 url_parse::Parsed* out_parsed); |
191 | 196 |
192 // String helper functions ---------------------------------------------------- | 197 // String helper functions ---------------------------------------------------- |
193 | 198 |
194 // Compare the lower-case form of the given string against the given ASCII | 199 // Compare the lower-case form of the given string against the given ASCII |
195 // string. This is useful for doing checking if an input string matches some | 200 // string. This is useful for doing checking if an input string matches some |
196 // token, and it is optimized to avoid intermediate string copies. | 201 // token, and it is optimized to avoid intermediate string copies. |
197 // | 202 // |
198 // The versions of this function that don't take a b_end assume that the b | 203 // The versions of this function that don't take a b_end assume that the b |
199 // string is NULL terminated. | 204 // string is NULL terminated. |
200 bool LowerCaseEqualsASCII(const char* a_begin, | 205 GURL_API bool LowerCaseEqualsASCII(const char* a_begin, |
201 const char* a_end, | 206 const char* a_end, |
202 const char* b); | 207 const char* b); |
203 bool LowerCaseEqualsASCII(const char* a_begin, | 208 GURL_API bool LowerCaseEqualsASCII(const char* a_begin, |
204 const char* a_end, | 209 const char* a_end, |
205 const char* b_begin, | 210 const char* b_begin, |
206 const char* b_end); | 211 const char* b_end); |
207 bool LowerCaseEqualsASCII(const char16* a_begin, | 212 GURL_API bool LowerCaseEqualsASCII(const char16* a_begin, |
208 const char16* a_end, | 213 const char16* a_end, |
209 const char* b); | 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); |
210 | 219 |
211 } // namespace url_util | 220 } // namespace url_util |
212 | 221 |
213 #endif // GOOGLEURL_SRC_URL_UTIL_H__ | 222 #endif // GOOGLEURL_SRC_URL_UTIL_H__ |
OLD | NEW |