third_party/WebKit/Source/web/WebFrameSerializer.cpp - Issue 2538953002: Remove hidden elements from MHTML

Side by Side Diff: third_party/WebKit/Source/web/WebFrameSerializer.cpp

Issue 2538953002: Remove hidden elements from MHTML (Closed)

Patch Set: Address feedback Created 4 years ago

Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.

Jump to:

« no previous file with comments | « third_party/WebKit/Source/core/frame/FrameSerializer.cpp ('k') | third_party/WebKit/Source/web/tests/WebFrameSerializerTest.cpp » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Hide Comments ('s')

OLD	NEW
1 /*	1 /*

2 * Copyright (C) 2009 Google Inc. All rights reserved.	2 * Copyright (C) 2009 Google Inc. All rights reserved.

3 *	3 *

4 * Redistribution and use in source and binary forms, with or without	4 * Redistribution and use in source and binary forms, with or without

5 * modification, are permitted provided that the following conditions are	5 * modification, are permitted provided that the following conditions are

6 * met:	6 * met:

7 *	7 *

8 * * Redistributions of source code must retain the above copyright	8 * * Redistributions of source code must retain the above copyright

9 * notice, this list of conditions and the following disclaimer.	9 * notice, this list of conditions and the following disclaimer.

10 * * Redistributions in binary form must reproduce the above	10 * * Redistributions in binary form must reproduce the above

(...skipping 63 matching lines...) Expand 10 before \| Expand all \| Expand 10 after Loading...
74 namespace blink {	74 namespace blink {

75	75

76 namespace {	76 namespace {

77	77

78 class MHTMLFrameSerializerDelegate final : public FrameSerializer::Delegate {	78 class MHTMLFrameSerializerDelegate final : public FrameSerializer::Delegate {

79 WTF_MAKE_NONCOPYABLE(MHTMLFrameSerializerDelegate);	79 WTF_MAKE_NONCOPYABLE(MHTMLFrameSerializerDelegate);

80	80

81 public:	81 public:

82 explicit MHTMLFrameSerializerDelegate(	82 explicit MHTMLFrameSerializerDelegate(

83 WebFrameSerializer::MHTMLPartsGenerationDelegate&);	83 WebFrameSerializer::MHTMLPartsGenerationDelegate&);

	84 bool shouldIgnoreElement(const Element&) override;

84 bool shouldIgnoreAttribute(const Element&, const Attribute&) override;	85 bool shouldIgnoreAttribute(const Element&, const Attribute&) override;

85 bool rewriteLink(const Element&, String& rewrittenLink) override;	86 bool rewriteLink(const Element&, String& rewrittenLink) override;

86 bool shouldSkipResourceWithURL(const KURL&) override;	87 bool shouldSkipResourceWithURL(const KURL&) override;

87 bool shouldSkipResource(const Resource&) override;	88 bool shouldSkipResource(const Resource&) override;

88	89

89 private:	90 private:

90 WebFrameSerializer::MHTMLPartsGenerationDelegate& m_webDelegate;	91 WebFrameSerializer::MHTMLPartsGenerationDelegate& m_webDelegate;

91 };	92 };

92	93

93 MHTMLFrameSerializerDelegate::MHTMLFrameSerializerDelegate(	94 MHTMLFrameSerializerDelegate::MHTMLFrameSerializerDelegate(

94 WebFrameSerializer::MHTMLPartsGenerationDelegate& webDelegate)	95 WebFrameSerializer::MHTMLPartsGenerationDelegate& webDelegate)

95 : m_webDelegate(webDelegate) {}	96 : m_webDelegate(webDelegate) {}

96	97

	98 bool MHTMLFrameSerializerDelegate::shouldIgnoreElement(const Element& element) {

	99 // Do not include elements that are hidden and affect no layout.

	100 return !element.layoutObject();
	tkent 2016/12/01 14:56:43 Though I suggested this, it drops <head>, <meta>, Though I suggested this, it drops <head>, <meta>, <style>, <link>, <script>, <option>, <datalist>, etc. Is it ok? jianli 2016/12/07 02:21:02 We don't want to drop <head>, <meta>, <style>, <li Show quoted text On 2016/12/01 14:56:43, tkent wrote: > Though I suggested this, it drops <head>, <meta>, <style>, <link>, <script>, > <option>, <datalist>, etc. Is it ok? We don't want to drop <head>, <meta>, <style>, <link>, <datalist> and etc. <script> should have already been dropped by MHTML serializer. Do you know any other way to check for that? It seems that these elements <head>, <meta> and etc are defined as "display: none" in the default stylesheet html.css. Can we call CSSDefaultStyleSheets to get the default display style for the element in order not to drop these elements? How do you think?
	101 }

	102

97 bool MHTMLFrameSerializerDelegate::shouldIgnoreAttribute(	103 bool MHTMLFrameSerializerDelegate::shouldIgnoreAttribute(

98 const Element& element,	104 const Element& element,

99 const Attribute& attribute) {	105 const Attribute& attribute) {

100 // TODO(fgorski): Presence of srcset attribute causes MHTML to not display	106 // TODO(fgorski): Presence of srcset attribute causes MHTML to not display

101 // images, as only the value of src is pulled into the archive. Discarding	107 // images, as only the value of src is pulled into the archive. Discarding

102 // srcset prevents the problem. Long term we should make sure to MHTML plays	108 // srcset prevents the problem. Long term we should make sure to MHTML plays

103 // nicely with srcset.	109 // nicely with srcset.

104 if (attribute.localName() == HTMLNames::srcsetAttr)	110 if (attribute.localName() == HTMLNames::srcsetAttr)

105 return true;	111 return true;

106	112

(...skipping 207 matching lines...) Expand 10 before \| Expand all \| Expand 10 after Loading...
314 const WebString& baseTarget) {	320 const WebString& baseTarget) {

315 // TODO(yosin) We should call \|FrameSerializer::baseTagDeclarationOf()\|.	321 // TODO(yosin) We should call \|FrameSerializer::baseTagDeclarationOf()\|.

316 if (baseTarget.isEmpty())	322 if (baseTarget.isEmpty())

317 return String("<base href=\".\">");	323 return String("<base href=\".\">");

318 String baseString = "<base href=\".\" target=\"" +	324 String baseString = "<base href=\".\" target=\"" +

319 static_cast<const String&>(baseTarget) + "\">";	325 static_cast<const String&>(baseTarget) + "\">";

320 return baseString;	326 return baseString;

321 }	327 }

322	328

323 } // namespace blink	329 } // namespace blink

OLD	NEW