1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
|
// Copyright 2013 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
// Functions for canonicalizing "mailto:" URLs.
#include "url/url_canon.h"
#include "url/url_canon_internal.h"
#include "url/url_file.h"
#include "url/url_parse_internal.h"
namespace url_canon {
namespace {
template<typename CHAR, typename UCHAR>
bool DoCanonicalizeMailtoURL(const URLComponentSource<CHAR>& source,
const url_parse::Parsed& parsed,
CanonOutput* output,
url_parse::Parsed* new_parsed) {
// mailto: only uses {scheme, path, query} -- clear the rest.
new_parsed->username = url_parse::Component();
new_parsed->password = url_parse::Component();
new_parsed->host = url_parse::Component();
new_parsed->port = url_parse::Component();
new_parsed->ref = url_parse::Component();
// Scheme (known, so we don't bother running it through the more
// complicated scheme canonicalizer).
new_parsed->scheme.begin = output->length();
output->Append("mailto:", 7);
new_parsed->scheme.len = 6;
bool success = true;
// Path
if (parsed.path.is_valid()) {
new_parsed->path.begin = output->length();
// Copy the path using path URL's more lax escaping rules.
// We convert to UTF-8 and escape non-ASCII, but leave all
// ASCII characters alone.
int end = parsed.path.end();
for (int i = parsed.path.begin; i < end; ++i) {
UCHAR uch = static_cast<UCHAR>(source.path[i]);
if (uch < 0x20 || uch >= 0x80)
success &= AppendUTF8EscapedChar(source.path, &i, end, output);
else
output->push_back(static_cast<char>(uch));
}
new_parsed->path.len = output->length() - new_parsed->path.begin;
} else {
// No path at all
new_parsed->path.reset();
}
// Query -- always use the default utf8 charset converter.
CanonicalizeQuery(source.query, parsed.query, NULL,
output, &new_parsed->query);
return success;
}
} // namespace
bool CanonicalizeMailtoURL(const char* spec,
int spec_len,
const url_parse::Parsed& parsed,
CanonOutput* output,
url_parse::Parsed* new_parsed) {
return DoCanonicalizeMailtoURL<char, unsigned char>(
URLComponentSource<char>(spec), parsed, output, new_parsed);
}
bool CanonicalizeMailtoURL(const char16* spec,
int spec_len,
const url_parse::Parsed& parsed,
CanonOutput* output,
url_parse::Parsed* new_parsed) {
return DoCanonicalizeMailtoURL<char16, char16>(
URLComponentSource<char16>(spec), parsed, output, new_parsed);
}
bool ReplaceMailtoURL(const char* base,
const url_parse::Parsed& base_parsed,
const Replacements<char>& replacements,
CanonOutput* output,
url_parse::Parsed* new_parsed) {
URLComponentSource<char> source(base);
url_parse::Parsed parsed(base_parsed);
SetupOverrideComponents(base, replacements, &source, &parsed);
return DoCanonicalizeMailtoURL<char, unsigned char>(
source, parsed, output, new_parsed);
}
bool ReplaceMailtoURL(const char* base,
const url_parse::Parsed& base_parsed,
const Replacements<char16>& replacements,
CanonOutput* output,
url_parse::Parsed* new_parsed) {
RawCanonOutput<1024> utf8;
URLComponentSource<char> source(base);
url_parse::Parsed parsed(base_parsed);
SetupUTF16OverrideComponents(base, replacements, &utf8, &source, &parsed);
return DoCanonicalizeMailtoURL<char, unsigned char>(
source, parsed, output, new_parsed);
}
} // namespace url_canon
|
