OLD | NEW |
(Empty) | |
| 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 // As with url_canon_internal.h, this file is intended to be included in |
| 31 // another C++ file where the template types are defined. This allows the |
| 32 // programmer to use this to use these functions for their own strings |
| 33 // types, without bloating the code by having inline templates used in |
| 34 // every call site. |
| 35 // |
| 36 // *** This file must be included after url_canon_internal as we depend on some |
| 37 // functions in it. *** |
| 38 |
| 39 #ifndef GOOGLEURL_SRC_URL_CANON_INTERNAL_FILE_H__ |
| 40 #define GOOGLEURL_SRC_URL_CANON_INTERNAL_FILE_H__ |
| 41 |
| 42 #include "googleurl/src/url_file.h" |
| 43 #include "googleurl/src/url_parse_internal.h" |
| 44 |
| 45 using namespace url_canon; |
| 46 |
| 47 // Given a pointer into the spec, this copies and canonicalizes the drive |
| 48 // letter and colon to the output, if one is found. If there is not a drive |
| 49 // spec, it won't do anything. The index of the next character in the input |
| 50 // spec is returned (after the colon when a drive spec is found, the begin |
| 51 // offset if one is not). |
| 52 template<typename CHAR> |
| 53 static int FileDoDriveSpec(const CHAR* spec, int begin, int end, |
| 54 CanonOutput* output) { |
| 55 // The path could be one of several things: /foo/bar, c:/foo/bar, /c:/foo, |
| 56 // (with backslashes instead of slashes as well). |
| 57 int num_slashes = CountConsecutiveSlashes(spec, begin, end); |
| 58 int after_slashes = begin + num_slashes; |
| 59 |
| 60 if (!DoesBeginWindowsDriveSpec(spec, after_slashes, end)) |
| 61 return begin; // Haven't consumed any characters |
| 62 |
| 63 // DoesBeginWindowsDriveSpec will ensure that the drive letter is valid |
| 64 // and that it is followed by a colon/pipe. |
| 65 |
| 66 // Normalize Windows drive letters to uppercase |
| 67 if (spec[after_slashes] >= 'a' && spec[after_slashes] <= 'z') |
| 68 output->push_back(spec[after_slashes] - 'a' + 'A'); |
| 69 else |
| 70 output->push_back(static_cast<char>(spec[after_slashes])); |
| 71 |
| 72 // Normalize the character following it to a colon rather than pipe. |
| 73 output->push_back(':'); |
| 74 output->push_back('/'); |
| 75 return after_slashes + 2; |
| 76 } |
| 77 |
| 78 // FileDoDriveSpec will have already added the first backslash, so we need to |
| 79 // write everything following the slashes using the path canonicalizer. |
| 80 template<typename CHAR, typename UCHAR> |
| 81 static void FileDoPath(const CHAR* spec, int begin, int end, |
| 82 CanonOutput* output) { |
| 83 // Normalize the number of slashes after the drive letter. The path |
| 84 // canonicalizer expects the input to begin in a slash already so |
| 85 // doesn't check. We want to handle no-slashes |
| 86 int num_slashes = CountConsecutiveSlashes(spec, begin, end); |
| 87 int after_slashes = begin + num_slashes; |
| 88 |
| 89 // Now use the regular path canonicalizer to canonicalize the rest of the |
| 90 // path. We supply it with the path following the slashes. It won't prepend |
| 91 // a slash because it assumes any nonempty path already starts with one. |
| 92 // We explicitly filter out calls with no path here to prevent that case. |
| 93 ParsedURL::Component sub_path(after_slashes, end - after_slashes); |
| 94 if (sub_path.len > 0) { |
| 95 // Give it a fake output component to write into. DoCanonicalizeFile will |
| 96 // compute the full path component. |
| 97 ParsedURL::Component fake_output_path; |
| 98 URLCanonInternal<CHAR, UCHAR>::DoPath( |
| 99 spec, sub_path, output, &fake_output_path); |
| 100 } |
| 101 } |
| 102 |
| 103 template<typename CHAR, typename UCHAR> |
| 104 static bool DoCanonicalizeFileURL(const URLComponentSource<CHAR>& source, |
| 105 const ParsedURL& parsed, |
| 106 CanonOutput* output, |
| 107 ParsedURL* new_parsed) { |
| 108 // Things we don't set in file: URLs. |
| 109 new_parsed->username = ParsedURL::Component(0, -1); |
| 110 new_parsed->password = ParsedURL::Component(0, -1); |
| 111 new_parsed->port = ParsedURL::Component(0, -1); |
| 112 |
| 113 // Scheme (known, so we don't bother running it through the more |
| 114 // complicated scheme canonicalizer). |
| 115 new_parsed->scheme.begin = output->length(); |
| 116 output->push_back('f'); |
| 117 output->push_back('i'); |
| 118 output->push_back('l'); |
| 119 output->push_back('e'); |
| 120 new_parsed->scheme.len = output->length() - new_parsed->scheme.begin; |
| 121 output->push_back(':'); |
| 122 |
| 123 // Write the separator for the host. |
| 124 output->push_back('/'); |
| 125 output->push_back('/'); |
| 126 |
| 127 // Append the host. For many file URLs, this will be empty. For UNC, this |
| 128 // will be present. |
| 129 // TODO(brettw) This doesn't do any checking for host name validity. We |
| 130 // should probably handle validity checking of UNC hosts differently than |
| 131 // for regular IP hosts. |
| 132 bool success = URLCanonInternal<CHAR, UCHAR>::DoHost( |
| 133 source.host, parsed.host, output, &new_parsed->host); |
| 134 |
| 135 // Write a separator for the start of the path. We'll ignore any slashes |
| 136 // already at the beginning of the path. |
| 137 new_parsed->path.begin = output->length(); |
| 138 output->push_back('/'); |
| 139 |
| 140 // Copies and normalizes the "c:" at the beginning, if present. |
| 141 int after_drive = FileDoDriveSpec(source.path, parsed.path.begin, |
| 142 parsed.path.end(), output); |
| 143 |
| 144 // Copies the rest of the path |
| 145 FileDoPath<CHAR, UCHAR>(source.path, after_drive, parsed.path.end(), output); |
| 146 new_parsed->path.len = output->length() - new_parsed->path.begin; |
| 147 |
| 148 // Things following the path we can use the standard canonicalizers for. |
| 149 success &= URLCanonInternal<CHAR, UCHAR>::DoQuery( |
| 150 source.query, parsed.query, output, &new_parsed->query); |
| 151 success &= URLCanonInternal<CHAR, UCHAR>::DoRef( |
| 152 source.ref, parsed.ref, output, &new_parsed->ref); |
| 153 |
| 154 return success; |
| 155 } |
| 156 |
| 157 #endif // GOOGLEURL_SRC_URL_CANON_INTERNAL_FILE_H__ |
OLD | NEW |