OLD | NEW |
(Empty) | |
| 1 // Copyright 2008, 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 // Functions for canonicalizing "mailto:" URLs. |
| 31 |
| 32 #include "googleurl/src/url_canon.h" |
| 33 #include "googleurl/src/url_canon_internal.h" |
| 34 #include "googleurl/src/url_file.h" |
| 35 #include "googleurl/src/url_parse_internal.h" |
| 36 |
| 37 namespace url_canon { |
| 38 |
| 39 namespace { |
| 40 |
| 41 |
| 42 template<typename CHAR, typename UCHAR> |
| 43 bool DoCanonicalizeMailtoURL(const URLComponentSource<CHAR>& source, |
| 44 const url_parse::Parsed& parsed, |
| 45 CanonOutput* output, |
| 46 url_parse::Parsed* new_parsed) { |
| 47 |
| 48 // mailto: only uses {scheme, path, query} -- clear the rest. |
| 49 new_parsed->username = url_parse::Component(); |
| 50 new_parsed->password = url_parse::Component(); |
| 51 new_parsed->host = url_parse::Component(); |
| 52 new_parsed->port = url_parse::Component(); |
| 53 new_parsed->ref = url_parse::Component(); |
| 54 |
| 55 // Scheme (known, so we don't bother running it through the more |
| 56 // complicated scheme canonicalizer). |
| 57 new_parsed->scheme.begin = output->length(); |
| 58 output->Append("mailto:", 7); |
| 59 new_parsed->scheme.len = 6; |
| 60 |
| 61 bool success = true; |
| 62 |
| 63 // Path |
| 64 if (parsed.path.is_valid()) { |
| 65 new_parsed->path.begin = output->length(); |
| 66 |
| 67 // Copy the path using path URL's more lax escaping rules. |
| 68 // We convert to UTF-8 and escape non-ASCII, but leave all |
| 69 // ASCII characters alone. |
| 70 int end = parsed.path.end(); |
| 71 for (int i = parsed.path.begin; i < end; ++i) { |
| 72 UCHAR uch = static_cast<UCHAR>(source.path[i]); |
| 73 if (uch < 0x20 || uch >= 0x80) |
| 74 success &= AppendUTF8EscapedChar(source.path, &i, end, output); |
| 75 else |
| 76 output->push_back(static_cast<char>(uch)); |
| 77 } |
| 78 |
| 79 new_parsed->path.len = output->length() - new_parsed->path.begin; |
| 80 } else { |
| 81 // No path at all |
| 82 new_parsed->path.reset(); |
| 83 } |
| 84 |
| 85 // Query -- always use the default utf8 charset converter. |
| 86 CanonicalizeQuery(source.query, parsed.query, NULL, |
| 87 output, &new_parsed->query); |
| 88 |
| 89 return success; |
| 90 } |
| 91 |
| 92 } // namespace |
| 93 |
| 94 bool CanonicalizeMailtoURL(const char* spec, |
| 95 int spec_len, |
| 96 const url_parse::Parsed& parsed, |
| 97 CanonOutput* output, |
| 98 url_parse::Parsed* new_parsed) { |
| 99 return DoCanonicalizeMailtoURL<char, unsigned char>( |
| 100 URLComponentSource<char>(spec), parsed, output, new_parsed); |
| 101 } |
| 102 |
| 103 bool CanonicalizeMailtoURL(const char16* spec, |
| 104 int spec_len, |
| 105 const url_parse::Parsed& parsed, |
| 106 CanonOutput* output, |
| 107 url_parse::Parsed* new_parsed) { |
| 108 return DoCanonicalizeMailtoURL<char16, char16>( |
| 109 URLComponentSource<char16>(spec), parsed, output, new_parsed); |
| 110 } |
| 111 |
| 112 bool ReplaceMailtoURL(const char* base, |
| 113 const url_parse::Parsed& base_parsed, |
| 114 const Replacements<char>& replacements, |
| 115 CanonOutput* output, |
| 116 url_parse::Parsed* new_parsed) { |
| 117 URLComponentSource<char> source(base); |
| 118 url_parse::Parsed parsed(base_parsed); |
| 119 SetupOverrideComponents(base, replacements, &source, &parsed); |
| 120 return DoCanonicalizeMailtoURL<char, unsigned char>( |
| 121 source, parsed, output, new_parsed); |
| 122 } |
| 123 |
| 124 bool ReplaceMailtoURL(const char* base, |
| 125 const url_parse::Parsed& base_parsed, |
| 126 const Replacements<char16>& replacements, |
| 127 CanonOutput* output, |
| 128 url_parse::Parsed* new_parsed) { |
| 129 RawCanonOutput<1024> utf8; |
| 130 URLComponentSource<char> source(base); |
| 131 url_parse::Parsed parsed(base_parsed); |
| 132 SetupUTF16OverrideComponents(base, replacements, &utf8, &source, &parsed); |
| 133 return DoCanonicalizeMailtoURL<char, unsigned char>( |
| 134 source, parsed, output, new_parsed); |
| 135 } |
| 136 |
| 137 } // namespace url_canon |
OLD | NEW |