wtf/url/src/URLSegments.h

   1 // Copyright 2007, 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 #ifndef URLSegments_h
  30 #define URLSegments_h
  31
  32 #include "URLComponent.h"
  33
  34 namespace WTF {
  35
  36 // A structure that holds the identified parts of an input URL. This structure
  37 // does NOT store the URL itself. The caller will have to store the URL text
  38 // and its corresponding Parsed structure separately.
  39 class URLSegments {
  40 public:
  41     // Identifies different components.
  42     enum ComponentType {
  43         Scheme,
  44         Username,
  45         Password,
  46         Host,
  47         Port,
  48         Path,
  49         Query,
  50         Fragment,
  51     };
  52
  53     URLSegments() { }
  54
  55     // Returns the length of the URL (the end of the last component).
  56     //
  57     // Note that for some invalid, non-canonical URLs, this may not be the length
  58     // of the string. For example "http://": the parsed structure will only
  59     // contain an entry for the four-character scheme, and it doesn't know about
  60     // the "://". For all other last-components, it will return the real length.
  61     int length() const;
  62
  63     // Returns the number of characters before the given component if it exists,
  64     // or where the component would be if it did exist. This will return the
  65     // string length if the component would be appended to the end.
  66     //
  67     // Note that this can get a little funny for the port, query, and fragment
  68     // components which have a delimiter that is not counted as part of the
  69     // component. The |includeDelimiter| flag controls if you want this counted
  70     // as part of the component or not when the component exists.
  71     //
  72     // This example shows the difference between the two flags for two of these
  73     // delimited components that is present (the port and query) and one that
  74     // isn't (the reference). The components that this flag affects are marked
  75     // with a *.
  76     //                 0         1         2
  77     //                 012345678901234567890
  78     // Example input:  http://foo:80/?query
  79     //              include_delim=true,  ...=false  ("<-" indicates different)
  80     //      Scheme: 0                    0
  81     //    Username: 5                    5
  82     //    Password: 5                    5
  83     //        Host: 7                    7
  84     //       *Port: 10                   11 <-
  85     //        Path: 13                   13
  86     //      *Query: 14                   15 <-
  87     //        *Fragment: 20                   20
  88     //
  89     int charactersBefore(ComponentType, bool includeDelimiter) const;
  90
  91     // Each component excludes the related delimiters and has a length of -1
  92     // if that component is absent but 0 if the component exists but is empty.
  93     URLComponent scheme;
  94     URLComponent username;
  95     URLComponent password;
  96     URLComponent host;
  97     URLComponent port;
  98     URLComponent path;
  99     URLComponent query;
 100     URLComponent fragment;
 101 };
 102
 103 } // namespace WTF
 104
 105 #endif // URLSegments_h