| OLD | NEW |
|---|
| (Empty) |
| 1 /* | |
| 2 * Copyright (C) 2009 Google Inc. 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 | |
| 31 #include "public/web/WebPageSerializer.h" | |
| 32 | |
| 33 #include "core/HTMLNames.h" | |
| 34 #include "core/dom/Document.h" | |
| 35 #include "core/dom/Element.h" | |
| 36 #include "core/frame/Frame.h" | |
| 37 #include "core/frame/LocalFrame.h" | |
| 38 #include "core/frame/RemoteFrame.h" | |
| 39 #include "core/html/HTMLAllCollection.h" | |
| 40 #include "core/html/HTMLFrameElementBase.h" | |
| 41 #include "core/html/HTMLFrameOwnerElement.h" | |
| 42 #include "core/html/HTMLInputElement.h" | |
| 43 #include "core/html/HTMLTableElement.h" | |
| 44 #include "core/loader/DocumentLoader.h" | |
| 45 #include "core/page/PageSerializer.h" | |
| 46 #include "platform/SerializedResource.h" | |
| 47 #include "platform/SharedBuffer.h" | |
| 48 #include "platform/mhtml/MHTMLArchive.h" | |
| 49 #include "platform/mhtml/MHTMLParser.h" | |
| 50 #include "platform/weborigin/KURL.h" | |
| 51 #include "public/platform/WebCString.h" | |
| 52 #include "public/platform/WebString.h" | |
| 53 #include "public/platform/WebURL.h" | |
| 54 #include "public/platform/WebVector.h" | |
| 55 #include "public/web/WebDocument.h" | |
| 56 #include "public/web/WebFrame.h" | |
| 57 #include "public/web/WebPageSerializerClient.h" | |
| 58 #include "web/WebLocalFrameImpl.h" | |
| 59 #include "web/WebPageSerializerImpl.h" | |
| 60 #include "web/WebRemoteFrameImpl.h" | |
| 61 #include "wtf/Assertions.h" | |
| 62 #include "wtf/HashMap.h" | |
| 63 #include "wtf/HashSet.h" | |
| 64 #include "wtf/Noncopyable.h" | |
| 65 #include "wtf/Vector.h" | |
| 66 #include "wtf/text/StringConcatenate.h" | |
| 67 | |
| 68 namespace blink { | |
| 69 | |
| 70 namespace { | |
| 71 | |
| 72 class MHTMLPageSerializerDelegate final : public PageSerializer::Delegate { | |
| 73 WTF_MAKE_NONCOPYABLE(MHTMLPageSerializerDelegate); | |
| 74 public: | |
| 75 explicit MHTMLPageSerializerDelegate(WebPageSerializer::MHTMLPartsGeneration
Delegate&); | |
| 76 bool shouldIgnoreAttribute(const Attribute&) override; | |
| 77 bool rewriteLink(const Element&, String& rewrittenLink) override; | |
| 78 bool shouldSkipResource(const KURL&) override; | |
| 79 | |
| 80 private: | |
| 81 WebPageSerializer::MHTMLPartsGenerationDelegate& m_webDelegate; | |
| 82 }; | |
| 83 | |
| 84 MHTMLPageSerializerDelegate::MHTMLPageSerializerDelegate( | |
| 85 WebPageSerializer::MHTMLPartsGenerationDelegate& webDelegate) | |
| 86 : m_webDelegate(webDelegate) | |
| 87 { | |
| 88 } | |
| 89 | |
| 90 bool MHTMLPageSerializerDelegate::shouldIgnoreAttribute(const Attribute& attribu
te) | |
| 91 { | |
| 92 // TODO(fgorski): Presence of srcset attribute causes MHTML to not display i
mages, as only the value of src | |
| 93 // is pulled into the archive. Discarding srcset prevents the problem. Long
term we should make sure to MHTML | |
| 94 // plays nicely with srcset. | |
| 95 return attribute.localName() == HTMLNames::srcsetAttr; | |
| 96 } | |
| 97 | |
| 98 bool MHTMLPageSerializerDelegate::rewriteLink( | |
| 99 const Element& element, | |
| 100 String& rewrittenLink) | |
| 101 { | |
| 102 if (!element.isFrameOwnerElement()) | |
| 103 return false; | |
| 104 | |
| 105 auto* frameOwnerElement = toHTMLFrameOwnerElement(&element); | |
| 106 Frame* frame = frameOwnerElement->contentFrame(); | |
| 107 if (!frame) | |
| 108 return false; | |
| 109 | |
| 110 WebString contentID = m_webDelegate.getContentID(*WebFrame::fromFrame(frame)
); | |
| 111 KURL cidURI = MHTMLParser::convertContentIDToURI(contentID); | |
| 112 ASSERT(cidURI.isValid()); | |
| 113 | |
| 114 if (isHTMLFrameElementBase(&element)) { | |
| 115 rewrittenLink = cidURI.string(); | |
| 116 return true; | |
| 117 } | |
| 118 | |
| 119 if (isHTMLObjectElement(&element)) { | |
| 120 Document* doc = frameOwnerElement->contentDocument(); | |
| 121 bool isHandledBySerializer = doc->isHTMLDocument() | |
| 122 || doc->isXHTMLDocument() || doc->isImageDocument(); | |
| 123 if (isHandledBySerializer) { | |
| 124 rewrittenLink = cidURI.string(); | |
| 125 return true; | |
| 126 } | |
| 127 } | |
| 128 | |
| 129 return false; | |
| 130 } | |
| 131 | |
| 132 bool MHTMLPageSerializerDelegate::shouldSkipResource(const KURL& url) | |
| 133 { | |
| 134 return m_webDelegate.shouldSkipResource(url); | |
| 135 } | |
| 136 | |
| 137 } // namespace | |
| 138 | |
| 139 WebData WebPageSerializer::generateMHTMLHeader( | |
| 140 const WebString& boundary, WebLocalFrame* frame) | |
| 141 { | |
| 142 Document* document = toWebLocalFrameImpl(frame)->frame()->document(); | |
| 143 | |
| 144 RefPtr<SharedBuffer> buffer = SharedBuffer::create(); | |
| 145 MHTMLArchive::generateMHTMLHeader( | |
| 146 boundary, document->title(), document->suggestedMIMEType(), | |
| 147 *buffer); | |
| 148 return buffer.release(); | |
| 149 } | |
| 150 | |
| 151 WebData WebPageSerializer::generateMHTMLParts( | |
| 152 const WebString& boundary, WebLocalFrame* webFrame, bool useBinaryEncoding, | |
| 153 MHTMLPartsGenerationDelegate* webDelegate) | |
| 154 { | |
| 155 ASSERT(webFrame); | |
| 156 ASSERT(webDelegate); | |
| 157 | |
| 158 // Translate arguments from public to internal blink APIs. | |
| 159 LocalFrame* frame = toWebLocalFrameImpl(webFrame)->frame(); | |
| 160 MHTMLArchive::EncodingPolicy encodingPolicy = useBinaryEncoding | |
| 161 ? MHTMLArchive::EncodingPolicy::UseBinaryEncoding | |
| 162 : MHTMLArchive::EncodingPolicy::UseDefaultEncoding; | |
| 163 | |
| 164 // Serialize. | |
| 165 Vector<SerializedResource> resources; | |
| 166 MHTMLPageSerializerDelegate coreDelegate(*webDelegate); | |
| 167 PageSerializer serializer(resources, coreDelegate); | |
| 168 serializer.serializeFrame(*frame); | |
| 169 | |
| 170 // Get Content-ID for the frame being serialized. | |
| 171 String frameContentID = webDelegate->getContentID(*webFrame); | |
| 172 ASSERT(!frameContentID.isEmpty()); | |
| 173 | |
| 174 // Encode serializer's output as MHTML. | |
| 175 RefPtr<SharedBuffer> output = SharedBuffer::create(); | |
| 176 bool isFirstResource = true; | |
| 177 for (const SerializedResource& resource : resources) { | |
| 178 // Frame is the 1st resource (see PageSerializer::serializeFrame doc | |
| 179 // comment). Frames get a Content-ID header. | |
| 180 String contentID = isFirstResource ? frameContentID : String(); | |
| 181 | |
| 182 MHTMLArchive::generateMHTMLPart( | |
| 183 boundary, contentID, encodingPolicy, resource, *output); | |
| 184 | |
| 185 isFirstResource = false; | |
| 186 } | |
| 187 return output.release(); | |
| 188 } | |
| 189 | |
| 190 WebData WebPageSerializer::generateMHTMLFooter(const WebString& boundary) | |
| 191 { | |
| 192 RefPtr<SharedBuffer> buffer = SharedBuffer::create(); | |
| 193 MHTMLArchive::generateMHTMLFooter(boundary, *buffer); | |
| 194 return buffer.release(); | |
| 195 } | |
| 196 | |
| 197 bool WebPageSerializer::serialize( | |
| 198 WebLocalFrame* frame, | |
| 199 WebPageSerializerClient* client, | |
| 200 const WebVector<std::pair<WebURL, WebString>>& urlsToLocalPaths) | |
| 201 { | |
| 202 WebPageSerializerImpl serializerImpl(frame, client, urlsToLocalPaths); | |
| 203 return serializerImpl.serialize(); | |
| 204 } | |
| 205 | |
| 206 WebString WebPageSerializer::generateMetaCharsetDeclaration(const WebString& cha
rset) | |
| 207 { | |
| 208 // TODO(yosin) We should call |PageSerializer::metaCharsetDeclarationOf()|. | |
| 209 String charsetString = "<meta http-equiv=\"Content-Type\" content=\"text/htm
l; charset=" + static_cast<const String&>(charset) + "\">"; | |
| 210 return charsetString; | |
| 211 } | |
| 212 | |
| 213 WebString WebPageSerializer::generateMarkOfTheWebDeclaration(const WebURL& url) | |
| 214 { | |
| 215 StringBuilder builder; | |
| 216 builder.append("\n<!-- "); | |
| 217 builder.append(PageSerializer::markOfTheWebDeclaration(url)); | |
| 218 builder.append(" -->\n"); | |
| 219 return builder.toString(); | |
| 220 } | |
| 221 | |
| 222 WebString WebPageSerializer::generateBaseTagDeclaration(const WebString& baseTar
get) | |
| 223 { | |
| 224 // TODO(yosin) We should call |PageSerializer::baseTagDeclarationOf()|. | |
| 225 if (baseTarget.isEmpty()) | |
| 226 return String("<base href=\".\">"); | |
| 227 String baseString = "<base href=\".\" target=\"" + static_cast<const String&
>(baseTarget) + "\">"; | |
| 228 return baseString; | |
| 229 } | |
| 230 | |
| 231 } // namespace blink | |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 1541463002:
Rename [Web]PageSerializer[Test|Client|Impl] to ...FrameSerializer... (Closed)
Base URL: https://chromium.googlesource.com/chromium/src.git@mhtml-deduplication-of-resources