Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 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 | // How we handle the base tag better. |
| 32 | // Current status: |
| 33 | // At now the normal way we use to handling base tag is |
| 34 | // a) For those links which have corresponding local saved files, such as |
| 35 | // savable CSS, JavaScript files, they will be written to relative URLs which |
| 36 | // point to local saved file. Why those links can not be resolved as absolute |
| 37 | // file URLs, because if they are resolved as absolute URLs, after moving the |
| 38 | // file location from one directory to another directory, the file URLs will |
| 39 | // be dead links. |
| 40 | // b) For those links which have not corresponding local saved files, such as |
| 41 | // links in A, AREA tags, they will be resolved as absolute URLs. |
| 42 | // c) We comment all base tags when serialzing DOM for the page. |
| 43 | // FireFox also uses above way to handle base tag. |
| 44 | // |
| 45 | // Problem: |
| 46 | // This way can not handle the following situation: |
| 47 | // the base tag is written by JavaScript. |
| 48 | // For example. The page "www.yahoo.com" use |
| 49 | // "document.write('<base href="http://www.yahoo.com/"...');" to setup base URL |
| 50 | // of page when loading page. So when saving page as completed-HTML, we assume |
| 51 | // that we save "www.yahoo.com" to "c:\yahoo.htm". After then we load the saved |
| 52 | // completed-HTML page, then the JavaScript will insert a base tag |
| 53 | // <base href="http://www.yahoo.com/"...> to DOM, so all URLs which point to |
| 54 | // local saved resource files will be resolved as |
| 55 | // "http://www.yahoo.com/yahoo_files/...", which will cause all saved resource |
| 56 | // files can not be loaded correctly. Also the page will be rendered ugly since |
| 57 | // all saved sub-resource files (such as CSS, JavaScript files) and sub-frame |
| 58 | // files can not be fetched. |
| 59 | // Now FireFox, IE and WebKit based Browser all have this problem. |
| 60 | // |
| 61 | // Solution: |
| 62 | // My solution is that we comment old base tag and write new base tag: |
| 63 | // <base href="." ...> after the previous commented base tag. In WebKit, it |
| 64 | // always uses the latest "href" attribute of base tag to set document's base |
| 65 | // URL. Based on this behavior, when we encounter a base tag, we comment it and |
| 66 | // write a new base tag <base href="."> after the previous commented base tag. |
| 67 | // The new added base tag can help engine to locate correct base URL for |
| 68 | // correctly loading local saved resource files. Also I think we need to inherit |
| 69 | // the base target value from document object when appending new base tag. |
| 70 | // If there are multiple base tags in original document, we will comment all old |
| 71 | // base tags and append new base tag after each old base tag because we do not |
| 72 | // know those old base tags are original content or added by JavaScript. If |
| 73 | // they are added by JavaScript, it means when loading saved page, the script(s) |
| 74 | // will still insert base tag(s) to DOM, so the new added base tag(s) can |
| 75 | // override the incorrect base URL and make sure we alway load correct local |
| 76 | // saved resource files. |
| 77 | |
| 78 | #include "config.h" |
| 79 | #include "WebPageSerializerImpl.h" |
| 80 | |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 81 | #include "HTMLNames.h" |
| 82 | #include "WebFrameImpl.h" |
| 83 | #include "core/dom/Document.h" |
| 84 | #include "core/dom/DocumentType.h" |
| 85 | #include "core/dom/Element.h" |
| 86 | #include "core/editing/markup.h" |
| 87 | #include "core/html/HTMLAllCollection.h" |
| 88 | #include "core/html/HTMLElement.h" |
| 89 | #include "core/html/HTMLFormElement.h" |
| 90 | #include "core/html/HTMLHtmlElement.h" |
| 91 | #include "core/html/HTMLMetaElement.h" |
| 92 | #include "core/loader/DocumentLoader.h" |
| 93 | #include "core/loader/FrameLoader.h" |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 94 | #include "public/platform/WebVector.h" |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 95 | #include "wtf/text/TextEncoding.h" |
| 96 | |
| 97 | using namespace WebCore; |
| 98 | |
Torne (Richard Coles) | 51b2906 | 2013-11-28 11:56:03 +0000 | [diff] [blame] | 99 | namespace blink { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 100 | |
| 101 | // Maximum length of data buffer which is used to temporary save generated |
| 102 | // html content data. This is a soft limit which might be passed if a very large |
| 103 | // contegious string is found in the page. |
| 104 | static const unsigned dataBufferCapacity = 65536; |
| 105 | |
| 106 | WebPageSerializerImpl::SerializeDomParam::SerializeDomParam(const KURL& url, |
| 107 | const WTF::TextEncoding& textEncoding, |
| 108 | Document* document, |
| 109 | const String& directoryName) |
| 110 | : url(url) |
| 111 | , textEncoding(textEncoding) |
| 112 | , document(document) |
| 113 | , directoryName(directoryName) |
| 114 | , isHTMLDocument(document->isHTMLDocument()) |
| 115 | , haveSeenDocType(false) |
| 116 | , haveAddedCharsetDeclaration(false) |
| 117 | , skipMetaElement(0) |
| 118 | , isInScriptOrStyleTag(false) |
| 119 | , haveAddedXMLProcessingDirective(false) |
| 120 | , haveAddedContentsBeforeEnd(false) |
| 121 | { |
| 122 | } |
| 123 | |
| 124 | String WebPageSerializerImpl::preActionBeforeSerializeOpenTag( |
| 125 | const Element* element, SerializeDomParam* param, bool* needSkip) |
| 126 | { |
| 127 | StringBuilder result; |
| 128 | |
| 129 | *needSkip = false; |
| 130 | if (param->isHTMLDocument) { |
| 131 | // Skip the open tag of original META tag which declare charset since we |
| 132 | // have overrided the META which have correct charset declaration after |
| 133 | // serializing open tag of HEAD element. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 134 | ASSERT(element); |
| 135 | if (isHTMLMetaElement(*element)) { |
| 136 | const HTMLMetaElement& meta = toHTMLMetaElement(*element); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 137 | // Check whether the META tag has declared charset or not. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 138 | String equiv = meta.httpEquiv(); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 139 | if (equalIgnoringCase(equiv, "content-type")) { |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 140 | String content = meta.content(); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 141 | if (content.length() && content.contains("charset", false)) { |
| 142 | // Find META tag declared charset, we need to skip it when |
| 143 | // serializing DOM. |
| 144 | param->skipMetaElement = element; |
| 145 | *needSkip = true; |
| 146 | } |
| 147 | } |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 148 | } else if (isHTMLHtmlElement(*element)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 149 | // Check something before processing the open tag of HEAD element. |
| 150 | // First we add doc type declaration if original document has it. |
| 151 | if (!param->haveSeenDocType) { |
| 152 | param->haveSeenDocType = true; |
| 153 | result.append(createMarkup(param->document->doctype())); |
| 154 | } |
| 155 | |
| 156 | // Add MOTW declaration before html tag. |
| 157 | // See http://msdn2.microsoft.com/en-us/library/ms537628(VS.85).aspx. |
| 158 | result.append(WebPageSerializer::generateMarkOfTheWebDeclaration(param->url)); |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 159 | } else if (isHTMLBaseElement(*element)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 160 | // Comment the BASE tag when serializing dom. |
| 161 | result.append("<!--"); |
| 162 | } |
| 163 | } else { |
| 164 | // Write XML declaration. |
| 165 | if (!param->haveAddedXMLProcessingDirective) { |
| 166 | param->haveAddedXMLProcessingDirective = true; |
| 167 | // Get encoding info. |
| 168 | String xmlEncoding = param->document->xmlEncoding(); |
| 169 | if (xmlEncoding.isEmpty()) |
Torne (Richard Coles) | c0e19a6 | 2013-08-30 15:15:11 +0100 | [diff] [blame] | 170 | xmlEncoding = param->document->encodingName(); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 171 | if (xmlEncoding.isEmpty()) |
| 172 | xmlEncoding = UTF8Encoding().name(); |
| 173 | result.append("<?xml version=\""); |
| 174 | result.append(param->document->xmlVersion()); |
| 175 | result.append("\" encoding=\""); |
| 176 | result.append(xmlEncoding); |
| 177 | if (param->document->xmlStandalone()) |
| 178 | result.append("\" standalone=\"yes"); |
| 179 | result.append("\"?>\n"); |
| 180 | } |
| 181 | // Add doc type declaration if original document has it. |
| 182 | if (!param->haveSeenDocType) { |
| 183 | param->haveSeenDocType = true; |
| 184 | result.append(createMarkup(param->document->doctype())); |
| 185 | } |
| 186 | } |
| 187 | return result.toString(); |
| 188 | } |
| 189 | |
| 190 | String WebPageSerializerImpl::postActionAfterSerializeOpenTag( |
| 191 | const Element* element, SerializeDomParam* param) |
| 192 | { |
| 193 | StringBuilder result; |
| 194 | |
| 195 | param->haveAddedContentsBeforeEnd = false; |
| 196 | if (!param->isHTMLDocument) |
| 197 | return result.toString(); |
| 198 | // Check after processing the open tag of HEAD element |
| 199 | if (!param->haveAddedCharsetDeclaration |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 200 | && isHTMLHeadElement(*element)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 201 | param->haveAddedCharsetDeclaration = true; |
| 202 | // Check meta element. WebKit only pre-parse the first 512 bytes |
| 203 | // of the document. If the whole <HEAD> is larger and meta is the |
| 204 | // end of head part, then this kind of pages aren't decoded correctly |
| 205 | // because of this issue. So when we serialize the DOM, we need to |
| 206 | // make sure the meta will in first child of head tag. |
| 207 | // See http://bugs.webkit.org/show_bug.cgi?id=16621. |
| 208 | // First we generate new content for writing correct META element. |
| 209 | result.append(WebPageSerializer::generateMetaCharsetDeclaration( |
| 210 | String(param->textEncoding.name()))); |
| 211 | |
| 212 | param->haveAddedContentsBeforeEnd = true; |
| 213 | // Will search each META which has charset declaration, and skip them all |
| 214 | // in PreActionBeforeSerializeOpenTag. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 215 | } else if (isHTMLScriptElement(*element) || isHTMLScriptElement(*element)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 216 | param->isInScriptOrStyleTag = true; |
| 217 | } |
| 218 | |
| 219 | return result.toString(); |
| 220 | } |
| 221 | |
| 222 | String WebPageSerializerImpl::preActionBeforeSerializeEndTag( |
| 223 | const Element* element, SerializeDomParam* param, bool* needSkip) |
| 224 | { |
| 225 | String result; |
| 226 | |
| 227 | *needSkip = false; |
| 228 | if (!param->isHTMLDocument) |
| 229 | return result; |
| 230 | // Skip the end tag of original META tag which declare charset. |
| 231 | // Need not to check whether it's META tag since we guarantee |
| 232 | // skipMetaElement is definitely META tag if it's not 0. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 233 | if (param->skipMetaElement == element) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 234 | *needSkip = true; |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 235 | } else if (isHTMLScriptElement(*element) || isHTMLScriptElement(*element)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 236 | ASSERT(param->isInScriptOrStyleTag); |
| 237 | param->isInScriptOrStyleTag = false; |
| 238 | } |
| 239 | |
| 240 | return result; |
| 241 | } |
| 242 | |
| 243 | // After we finish serializing end tag of a element, we give the target |
| 244 | // element a chance to do some post work to add some additional data. |
| 245 | String WebPageSerializerImpl::postActionAfterSerializeEndTag( |
| 246 | const Element* element, SerializeDomParam* param) |
| 247 | { |
| 248 | StringBuilder result; |
| 249 | |
| 250 | if (!param->isHTMLDocument) |
| 251 | return result.toString(); |
| 252 | // Comment the BASE tag when serializing DOM. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 253 | if (isHTMLBaseElement(*element)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 254 | result.append("-->"); |
| 255 | // Append a new base tag declaration. |
| 256 | result.append(WebPageSerializer::generateBaseTagDeclaration( |
| 257 | param->document->baseTarget())); |
| 258 | } |
| 259 | |
| 260 | return result.toString(); |
| 261 | } |
| 262 | |
| 263 | void WebPageSerializerImpl::saveHTMLContentToBuffer( |
| 264 | const String& result, SerializeDomParam* param) |
| 265 | { |
| 266 | m_dataBuffer.append(result); |
| 267 | encodeAndFlushBuffer(WebPageSerializerClient::CurrentFrameIsNotFinished, |
| 268 | param, |
| 269 | DoNotForceFlush); |
| 270 | } |
| 271 | |
| 272 | void WebPageSerializerImpl::encodeAndFlushBuffer( |
| 273 | WebPageSerializerClient::PageSerializationStatus status, |
| 274 | SerializeDomParam* param, |
| 275 | FlushOption flushOption) |
| 276 | { |
| 277 | // Data buffer is not full nor do we want to force flush. |
| 278 | if (flushOption != ForceFlush && m_dataBuffer.length() <= dataBufferCapacity) |
| 279 | return; |
| 280 | |
| 281 | String content = m_dataBuffer.toString(); |
| 282 | m_dataBuffer.clear(); |
| 283 | |
Ben Murdoch | 02772c6 | 2013-07-26 10:21:05 +0100 | [diff] [blame] | 284 | CString encodedContent = param->textEncoding.normalizeAndEncode(content, WTF::EntitiesForUnencodables); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 285 | |
| 286 | // Send result to the client. |
| 287 | m_client->didSerializeDataForFrame(param->url, |
| 288 | WebCString(encodedContent.data(), encodedContent.length()), |
| 289 | status); |
| 290 | } |
| 291 | |
| 292 | void WebPageSerializerImpl::openTagToString(Element* element, |
| 293 | SerializeDomParam* param) |
| 294 | { |
| 295 | bool needSkip; |
| 296 | StringBuilder result; |
| 297 | // Do pre action for open tag. |
| 298 | result.append(preActionBeforeSerializeOpenTag(element, param, &needSkip)); |
| 299 | if (needSkip) |
| 300 | return; |
| 301 | // Add open tag |
| 302 | result.append('<'); |
| 303 | result.append(element->nodeName().lower()); |
| 304 | // Go through all attributes and serialize them. |
| 305 | if (element->hasAttributes()) { |
| 306 | unsigned numAttrs = element->attributeCount(); |
| 307 | for (unsigned i = 0; i < numAttrs; i++) { |
| 308 | result.append(' '); |
| 309 | // Add attribute pair |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 310 | const Attribute& attribute = element->attributeItem(i); |
| 311 | result.append(attribute.name().toString()); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 312 | result.appendLiteral("=\""); |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 313 | if (!attribute.value().isEmpty()) { |
| 314 | const String& attrValue = attribute.value(); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 315 | |
| 316 | // Check whether we need to replace some resource links |
| 317 | // with local resource paths. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 318 | const QualifiedName& attrName = attribute.name(); |
Torne (Richard Coles) | 43e7502 | 2014-03-21 14:26:12 +0000 | [diff] [blame] | 319 | if (element->hasLegalLinkAttribute(attrName)) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 320 | // For links start with "javascript:", we do not change it. |
| 321 | if (attrValue.startsWith("javascript:", false)) |
| 322 | result.append(attrValue); |
| 323 | else { |
| 324 | // Get the absolute link |
| 325 | WebFrameImpl* subFrame = WebFrameImpl::fromFrameOwnerElement(element); |
Ben Murdoch | 02772c6 | 2013-07-26 10:21:05 +0100 | [diff] [blame] | 326 | String completeURL = subFrame ? subFrame->frame()->document()->url() : |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 327 | param->document->completeURL(attrValue); |
| 328 | // Check whether we have local files for those link. |
| 329 | if (m_localLinks.contains(completeURL)) { |
| 330 | if (!param->directoryName.isEmpty()) { |
| 331 | result.appendLiteral("./"); |
| 332 | result.append(param->directoryName); |
| 333 | result.append('/'); |
| 334 | } |
| 335 | result.append(m_localLinks.get(completeURL)); |
| 336 | } else |
| 337 | result.append(completeURL); |
| 338 | } |
| 339 | } else { |
| 340 | if (param->isHTMLDocument) |
| 341 | result.append(m_htmlEntities.convertEntitiesInString(attrValue)); |
| 342 | else |
| 343 | result.append(m_xmlEntities.convertEntitiesInString(attrValue)); |
| 344 | } |
| 345 | } |
| 346 | result.append('\"'); |
| 347 | } |
| 348 | } |
| 349 | |
| 350 | // Do post action for open tag. |
| 351 | String addedContents = postActionAfterSerializeOpenTag(element, param); |
| 352 | // Complete the open tag for element when it has child/children. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 353 | if (element->hasChildren() || param->haveAddedContentsBeforeEnd) |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 354 | result.append('>'); |
| 355 | // Append the added contents generate in post action of open tag. |
| 356 | result.append(addedContents); |
| 357 | // Save the result to data buffer. |
| 358 | saveHTMLContentToBuffer(result.toString(), param); |
| 359 | } |
| 360 | |
| 361 | // Serialize end tag of an specified element. |
| 362 | void WebPageSerializerImpl::endTagToString(Element* element, |
| 363 | SerializeDomParam* param) |
| 364 | { |
| 365 | bool needSkip; |
| 366 | StringBuilder result; |
| 367 | // Do pre action for end tag. |
| 368 | result.append(preActionBeforeSerializeEndTag(element, param, &needSkip)); |
| 369 | if (needSkip) |
| 370 | return; |
| 371 | // Write end tag when element has child/children. |
Torne (Richard Coles) | d5428f3 | 2014-03-18 10:21:16 +0000 | [diff] [blame] | 372 | if (element->hasChildren() || param->haveAddedContentsBeforeEnd) { |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 373 | result.appendLiteral("</"); |
| 374 | result.append(element->nodeName().lower()); |
| 375 | result.append('>'); |
| 376 | } else { |
| 377 | // Check whether we have to write end tag for empty element. |
| 378 | if (param->isHTMLDocument) { |
| 379 | result.append('>'); |
| 380 | // FIXME: This code is horribly wrong. WebPageSerializerImpl must die. |
| 381 | if (!element->isHTMLElement() || !toHTMLElement(element)->ieForbidsInsertHTML()) { |
| 382 | // We need to write end tag when it is required. |
| 383 | result.appendLiteral("</"); |
| 384 | result.append(element->nodeName().lower()); |
| 385 | result.append('>'); |
| 386 | } |
| 387 | } else { |
| 388 | // For xml base document. |
| 389 | result.appendLiteral(" />"); |
| 390 | } |
| 391 | } |
| 392 | // Do post action for end tag. |
| 393 | result.append(postActionAfterSerializeEndTag(element, param)); |
| 394 | // Save the result to data buffer. |
| 395 | saveHTMLContentToBuffer(result.toString(), param); |
| 396 | } |
| 397 | |
| 398 | void WebPageSerializerImpl::buildContentForNode(Node* node, |
| 399 | SerializeDomParam* param) |
| 400 | { |
| 401 | switch (node->nodeType()) { |
| 402 | case Node::ELEMENT_NODE: |
| 403 | // Process open tag of element. |
| 404 | openTagToString(toElement(node), param); |
| 405 | // Walk through the children nodes and process it. |
| 406 | for (Node *child = node->firstChild(); child; child = child->nextSibling()) |
| 407 | buildContentForNode(child, param); |
| 408 | // Process end tag of element. |
| 409 | endTagToString(toElement(node), param); |
| 410 | break; |
| 411 | case Node::TEXT_NODE: |
| 412 | saveHTMLContentToBuffer(createMarkup(node), param); |
| 413 | break; |
| 414 | case Node::ATTRIBUTE_NODE: |
| 415 | case Node::DOCUMENT_NODE: |
| 416 | case Node::DOCUMENT_FRAGMENT_NODE: |
| 417 | // Should not exist. |
| 418 | ASSERT_NOT_REACHED(); |
| 419 | break; |
| 420 | // Document type node can be in DOM? |
| 421 | case Node::DOCUMENT_TYPE_NODE: |
| 422 | param->haveSeenDocType = true; |
| 423 | default: |
| 424 | // For other type node, call default action. |
| 425 | saveHTMLContentToBuffer(createMarkup(node), param); |
| 426 | break; |
| 427 | } |
| 428 | } |
| 429 | |
| 430 | WebPageSerializerImpl::WebPageSerializerImpl(WebFrame* frame, |
| 431 | bool recursiveSerialization, |
| 432 | WebPageSerializerClient* client, |
| 433 | const WebVector<WebURL>& links, |
| 434 | const WebVector<WebString>& localPaths, |
| 435 | const WebString& localDirectoryName) |
| 436 | : m_client(client) |
| 437 | , m_recursiveSerialization(recursiveSerialization) |
| 438 | , m_framesCollected(false) |
| 439 | , m_localDirectoryName(localDirectoryName) |
| 440 | , m_htmlEntities(false) |
| 441 | , m_xmlEntities(true) |
| 442 | { |
| 443 | // Must specify available webframe. |
| 444 | ASSERT(frame); |
Torne (Richard Coles) | c0e19a6 | 2013-08-30 15:15:11 +0100 | [diff] [blame] | 445 | m_specifiedWebFrameImpl = toWebFrameImpl(frame); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 446 | // Make sure we have non 0 client. |
| 447 | ASSERT(client); |
| 448 | // Build local resources map. |
| 449 | ASSERT(links.size() == localPaths.size()); |
| 450 | for (size_t i = 0; i < links.size(); i++) { |
| 451 | KURL url = links[i]; |
| 452 | ASSERT(!m_localLinks.contains(url.string())); |
| 453 | m_localLinks.set(url.string(), localPaths[i]); |
| 454 | } |
| 455 | |
| 456 | ASSERT(m_dataBuffer.isEmpty()); |
| 457 | } |
| 458 | |
| 459 | void WebPageSerializerImpl::collectTargetFrames() |
| 460 | { |
| 461 | ASSERT(!m_framesCollected); |
| 462 | m_framesCollected = true; |
| 463 | |
| 464 | // First, process main frame. |
| 465 | m_frames.append(m_specifiedWebFrameImpl); |
| 466 | // Return now if user only needs to serialize specified frame, not including |
| 467 | // all sub-frames. |
| 468 | if (!m_recursiveSerialization) |
| 469 | return; |
| 470 | // Collect all frames inside the specified frame. |
| 471 | for (int i = 0; i < static_cast<int>(m_frames.size()); ++i) { |
| 472 | WebFrameImpl* currentFrame = m_frames[i]; |
| 473 | // Get current using document. |
| 474 | Document* currentDoc = currentFrame->frame()->document(); |
| 475 | // Go through sub-frames. |
| 476 | RefPtr<HTMLCollection> all = currentDoc->all(); |
| 477 | |
Torne (Richard Coles) | 0938029 | 2014-02-21 12:17:33 +0000 | [diff] [blame] | 478 | for (unsigned i = 0; Element* element = all->item(i); i++) { |
| 479 | if (!element->isHTMLElement()) |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 480 | continue; |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 481 | WebFrameImpl* webFrame = |
| 482 | WebFrameImpl::fromFrameOwnerElement(element); |
| 483 | if (webFrame) |
| 484 | m_frames.append(webFrame); |
| 485 | } |
| 486 | } |
| 487 | } |
| 488 | |
| 489 | bool WebPageSerializerImpl::serialize() |
| 490 | { |
| 491 | if (!m_framesCollected) |
| 492 | collectTargetFrames(); |
| 493 | |
| 494 | bool didSerialization = false; |
| 495 | KURL mainURL = m_specifiedWebFrameImpl->frame()->document()->url(); |
| 496 | |
| 497 | for (unsigned i = 0; i < m_frames.size(); ++i) { |
| 498 | WebFrameImpl* webFrame = m_frames[i]; |
| 499 | Document* document = webFrame->frame()->document(); |
| 500 | const KURL& url = document->url(); |
| 501 | |
| 502 | if (!url.isValid() || !m_localLinks.contains(url.string())) |
| 503 | continue; |
| 504 | |
| 505 | didSerialization = true; |
| 506 | |
Torne (Richard Coles) | c0e19a6 | 2013-08-30 15:15:11 +0100 | [diff] [blame] | 507 | const WTF::TextEncoding& textEncoding = document->encoding().isValid() ? document->encoding() : UTF8Encoding(); |
Ben Murdoch | e69819b | 2013-07-17 14:56:49 +0100 | [diff] [blame] | 508 | String directoryName = url == mainURL ? m_localDirectoryName : ""; |
| 509 | |
| 510 | SerializeDomParam param(url, textEncoding, document, directoryName); |
| 511 | |
| 512 | Element* documentElement = document->documentElement(); |
| 513 | if (documentElement) |
| 514 | buildContentForNode(documentElement, ¶m); |
| 515 | |
| 516 | encodeAndFlushBuffer(WebPageSerializerClient::CurrentFrameIsFinished, ¶m, ForceFlush); |
| 517 | } |
| 518 | |
| 519 | ASSERT(m_dataBuffer.isEmpty()); |
| 520 | m_client->didSerializeDataForFrame(KURL(), WebCString("", 0), WebPageSerializerClient::AllFramesAreFinished); |
| 521 | return didSerialization; |
| 522 | } |
| 523 | |
Torne (Richard Coles) | 51b2906 | 2013-11-28 11:56:03 +0000 | [diff] [blame] | 524 | } // namespace blink |