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 // Functions for canonicalizing "path" URLs. Not to be confused with the path
31 // of a URL, these are URLs that have no authority section, only a path. For
32 // example, "javascript:" and "data:".
33
34 #include "googleurl/src/url_canon.h"
35 #include "googleurl/src/url_canon_internal.h"
36
37 namespace url_canon {
38
39 namespace {
40
41 template<typename CHAR, typename UCHAR>
DoCanonicalizePathURL(const URLComponentSource<CHAR> & source,const url_parse::Parsed & parsed,CanonOutput * output,url_parse::Parsed * new_parsed)42 bool DoCanonicalizePathURL(const URLComponentSource<CHAR>& source,
43 const url_parse::Parsed& parsed,
44 CanonOutput* output,
45 url_parse::Parsed* new_parsed) {
46 // Scheme: this will append the colon.
47 bool success = CanonicalizeScheme(source.scheme, parsed.scheme,
48 output, &new_parsed->scheme);
49
50 // We assume there's no authority for path URLs. Note that hosts should never
51 // have -1 length.
52 new_parsed->username.reset();
53 new_parsed->password.reset();
54 new_parsed->host.reset();
55 new_parsed->port.reset();
56
57 if (parsed.path.is_valid()) {
58 // Copy the path using path URL's more lax escaping rules (think for
59 // javascript:). We convert to UTF-8 and escape non-ASCII, but leave all
60 // ASCII characters alone. This helps readability of JavaStript.
61 new_parsed->path.begin = output->length();
62 int end = parsed.path.end();
63 for (int i = parsed.path.begin; i < end; i++) {
64 UCHAR uch = static_cast<UCHAR>(source.path[i]);
65 if (uch < 0x20 || uch >= 0x80)
66 success &= AppendUTF8EscapedChar(source.path, &i, end, output);
67 else
68 output->push_back(static_cast<char>(uch));
69 }
70 new_parsed->path.len = output->length() - new_parsed->path.begin;
71 } else {
72 // Empty path.
73 new_parsed->path.reset();
74 }
75
76 // Assume there's no query or ref.
77 new_parsed->query.reset();
78 new_parsed->ref.reset();
79
80 return success;
81 }
82
83 } // namespace
84
CanonicalizePathURL(const char * spec,int spec_len,const url_parse::Parsed & parsed,CanonOutput * output,url_parse::Parsed * new_parsed)85 bool CanonicalizePathURL(const char* spec,
86 int spec_len,
87 const url_parse::Parsed& parsed,
88 CanonOutput* output,
89 url_parse::Parsed* new_parsed) {
90 return DoCanonicalizePathURL<char, unsigned char>(
91 URLComponentSource<char>(spec), parsed, output, new_parsed);
92 }
93
CanonicalizePathURL(const char16 * spec,int spec_len,const url_parse::Parsed & parsed,CanonOutput * output,url_parse::Parsed * new_parsed)94 bool CanonicalizePathURL(const char16* spec,
95 int spec_len,
96 const url_parse::Parsed& parsed,
97 CanonOutput* output,
98 url_parse::Parsed* new_parsed) {
99 return DoCanonicalizePathURL<char16, char16>(
100 URLComponentSource<char16>(spec), parsed, output, new_parsed);
101 }
102
ReplacePathURL(const char * base,const url_parse::Parsed & base_parsed,const Replacements<char> & replacements,CanonOutput * output,url_parse::Parsed * new_parsed)103 bool ReplacePathURL(const char* base,
104 const url_parse::Parsed& base_parsed,
105 const Replacements<char>& replacements,
106 CanonOutput* output,
107 url_parse::Parsed* new_parsed) {
108 URLComponentSource<char> source(base);
109 url_parse::Parsed parsed(base_parsed);
110 SetupOverrideComponents(base, replacements, &source, &parsed);
111 return DoCanonicalizePathURL<char, unsigned char>(
112 source, parsed, output, new_parsed);
113 }
114
ReplacePathURL(const char * base,const url_parse::Parsed & base_parsed,const Replacements<char16> & replacements,CanonOutput * output,url_parse::Parsed * new_parsed)115 bool ReplacePathURL(const char* base,
116 const url_parse::Parsed& base_parsed,
117 const Replacements<char16>& replacements,
118 CanonOutput* output,
119 url_parse::Parsed* new_parsed) {
120 RawCanonOutput<1024> utf8;
121 URLComponentSource<char> source(base);
122 url_parse::Parsed parsed(base_parsed);
123 SetupUTF16OverrideComponents(base, replacements, &utf8, &source, &parsed);
124 return DoCanonicalizePathURL<char, unsigned char>(
125 source, parsed, output, new_parsed);
126 }
127
128 } // namespace url_canon
129