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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
|
/*
* Copyright (C) 2011 Google Inc. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
*
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following disclaimer
* in the documentation and/or other materials provided with the
* distribution.
* * Neither the name of Google Inc. nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "config.h"
#if ENABLE(MHTML)
#include "MHTMLArchive.h"
#include "Document.h"
#include "Frame.h"
#include "MHTMLParser.h"
#include "MIMETypeRegistry.h"
#include "Page.h"
#include "PageSerializer.h"
#include "QuotedPrintable.h"
#include "SchemeRegistry.h"
#include "SharedBuffer.h"
#include <wtf/CryptographicallyRandomNumber.h>
#include <wtf/DateMath.h>
#include <wtf/StdLibExtras.h>
#include <wtf/text/Base64.h>
#include <wtf/text/StringBuilder.h>
#if HAVE(SYS_TIME_H)
#include <sys/time.h>
#endif
#include <time.h>
namespace WebCore {
const char* const quotedPrintable = "quoted-printable";
const char* const base64 = "base64";
const char* const binary = "binary";
static String generateRandomBoundary()
{
// Trying to generate random boundaries similar to IE/UnMHT (ex: ----=_NextPart_000_001B_01CC157B.96F808A0).
const size_t randomValuesLength = 10;
char randomValues[randomValuesLength];
cryptographicallyRandomValues(&randomValues, randomValuesLength);
StringBuilder stringBuilder;
stringBuilder.append("----=_NextPart_000_");
for (size_t i = 0; i < randomValuesLength; ++i) {
if (i == 2)
stringBuilder.append('_');
else if (i == 6)
stringBuilder.append('.');
stringBuilder.append(lowerNibbleToASCIIHexDigit(randomValues[i]));
stringBuilder.append(upperNibbleToASCIIHexDigit(randomValues[i]));
}
return stringBuilder.toString();
}
static String replaceNonPrintableCharacters(const String& text)
{
StringBuilder stringBuilder;
for (size_t i = 0; i < text.length(); ++i) {
if (isASCIIPrintable(text[i]))
stringBuilder.append(text[i]);
else
stringBuilder.append('?');
}
return stringBuilder.toString();
}
MHTMLArchive::MHTMLArchive()
{
}
MHTMLArchive::~MHTMLArchive()
{
// Because all frames know about each other we need to perform a deep clearing of the archives graph.
clearAllSubframeArchives();
}
PassRefPtr<MHTMLArchive> MHTMLArchive::create()
{
return adoptRef(new MHTMLArchive);
}
PassRefPtr<MHTMLArchive> MHTMLArchive::create(const KURL& url, SharedBuffer* data)
{
// For security reasons we only load MHTML pages from local URLs.
if (!SchemeRegistry::shouldTreatURLSchemeAsLocal(url.protocol()))
return 0;
MHTMLParser parser(data);
RefPtr<MHTMLArchive> mainArchive = parser.parseArchive();
if (!mainArchive)
return 0; // Invalid MHTML file.
// Since MHTML is a flat format, we need to make all frames aware of all resources.
for (size_t i = 0; i < parser.frameCount(); ++i) {
RefPtr<MHTMLArchive> archive = parser.frameAt(i);
for (size_t j = 1; j < parser.frameCount(); ++j) {
if (i != j)
archive->addSubframeArchive(parser.frameAt(j));
}
for (size_t j = 0; j < parser.subResourceCount(); ++j)
archive->addSubresource(parser.subResourceAt(j));
}
return mainArchive.release();
}
PassRefPtr<SharedBuffer> MHTMLArchive::generateMHTMLData(Page* page)
{
return generateMHTMLData(page, false);
}
PassRefPtr<SharedBuffer> MHTMLArchive::generateMHTMLDataUsingBinaryEncoding(Page* page)
{
return generateMHTMLData(page, true);
}
PassRefPtr<SharedBuffer> MHTMLArchive::generateMHTMLData(Page* page, bool useBinaryEncoding)
{
Vector<PageSerializer::Resource> resources;
PageSerializer pageSerializer(&resources);
pageSerializer.serialize(page);
String boundary = generateRandomBoundary();
String endOfResourceBoundary = makeString("--", boundary, "\r\n");
tm localTM;
getCurrentLocalTime(&localTM);
String dateString = makeRFC2822DateString(localTM.tm_wday, localTM.tm_mday, localTM.tm_mon, 1900 + localTM.tm_year, localTM.tm_hour, localTM.tm_min, localTM.tm_sec, calculateUTCOffset() / (1000 * 60));
StringBuilder stringBuilder;
stringBuilder.append("From: <Saved by WebKit>\r\n");
stringBuilder.append("Subject: ");
// We replace non ASCII characters with '?' characters to match IE's behavior.
stringBuilder.append(replaceNonPrintableCharacters(page->mainFrame()->document()->title()));
stringBuilder.append("\r\nDate: ");
stringBuilder.append(dateString);
stringBuilder.append("\r\nMIME-Version: 1.0\r\n");
stringBuilder.append("Content-Type: multipart/related;\r\n");
stringBuilder.append("\ttype=\"");
stringBuilder.append(page->mainFrame()->document()->suggestedMIMEType());
stringBuilder.append("\";\r\n");
stringBuilder.append("\tboundary=\"");
stringBuilder.append(boundary);
stringBuilder.append("\"\r\n\r\n");
// We use utf8() below instead of ascii() as ascii() replaces CRLFs with ?? (we still only have put ASCII characters in it).
ASSERT(stringBuilder.toString().containsOnlyASCII());
CString asciiString = stringBuilder.toString().utf8();
RefPtr<SharedBuffer> mhtmlData = SharedBuffer::create();
mhtmlData->append(asciiString.data(), asciiString.length());
for (size_t i = 0; i < resources.size(); ++i) {
const PageSerializer::Resource& resource = resources[i];
stringBuilder.clear();
stringBuilder.append(endOfResourceBoundary);
stringBuilder.append("Content-Type: ");
stringBuilder.append(resource.mimeType);
const char* contentEncoding = 0;
if (useBinaryEncoding)
contentEncoding = binary;
else if (MIMETypeRegistry::isSupportedJavaScriptMIMEType(resource.mimeType) || MIMETypeRegistry::isSupportedNonImageMIMEType(resource.mimeType))
contentEncoding = quotedPrintable;
else
contentEncoding = base64;
stringBuilder.append("\r\nContent-Transfer-Encoding: ");
stringBuilder.append(contentEncoding);
stringBuilder.append("\r\nContent-Location: ");
stringBuilder.append(resource.url);
stringBuilder.append("\r\n\r\n");
asciiString = stringBuilder.toString().utf8();
mhtmlData->append(asciiString.data(), asciiString.length());
if (!strcmp(contentEncoding, binary)) {
const char* data;
size_t position = 0;
while (size_t length = resource.data->getSomeData(data, position)) {
mhtmlData->append(data, length);
position += length;
}
} else {
// FIXME: ideally we would encode the content as a stream without having to fetch it all.
const char* data = resource.data->data();
size_t dataLength = resource.data->size();
Vector<char> encodedData;
if (!strcmp(contentEncoding, quotedPrintable)) {
quotedPrintableEncode(data, dataLength, encodedData);
mhtmlData->append(encodedData.data(), encodedData.size());
mhtmlData->append("\r\n", 2);
} else {
ASSERT(!strcmp(contentEncoding, base64));
// We are not specifying insertLFs = true below as it would cut the lines with LFs and MHTML requires CRLFs.
base64Encode(data, dataLength, encodedData);
const size_t maximumLineLength = 76;
size_t index = 0;
size_t encodedDataLength = encodedData.size();
do {
size_t lineLength = std::min(encodedDataLength - index, maximumLineLength);
mhtmlData->append(encodedData.data() + index, lineLength);
mhtmlData->append("\r\n", 2);
index += maximumLineLength;
} while (index < encodedDataLength);
}
}
}
asciiString = makeString("--", boundary, "--\r\n").utf8();
mhtmlData->append(asciiString.data(), asciiString.length());
return mhtmlData.release();
}
}
#endif
|
