1 /*

     2  * Copyright (C) 2008 Apple Inc. All Rights Reserved.

     3  * Copyright (C) 2009 Torch Mobile, Inc. http://www.torchmobile.com/

     4  * Copyright (C) 2010 Google Inc. All Rights Reserved.

     5  *

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

     7  * modification, are permitted provided that the following conditions

     8  * are met:

     9  * 1. Redistributions of source code must retain the above copyright

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

    11  * 2. Redistributions in binary form must reproduce the above copyright

    12  *    notice, this list of conditions and the following disclaimer in the

    13  *    documentation and/or other materials provided with the distribution.

    14  *

    15  * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY

    16  * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE

    17  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR

    18  * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR

    19  * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,

    20  * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,

    21  * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR

    22  * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY

    23  * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

    24  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

    25  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 

    26  */

    27 

    28 #include "config.h"

    29 #include "HTMLPreloadScanner.h"

    30 

    31 #include "CSSHelper.h"

    32 #include "DocLoader.h"

    33 #include "Document.h"

    34 #include "HTMLTreeBuilder.h"

    35 #include "HTMLLinkElement.h"

    36 #include "HTMLNames.h"

    37 

    38 namespace WebCore {

    39 

    40 using namespace HTMLNames;

    41 

    42 namespace {

    43 

    44 class PreloadTask {

    45 public:

    46     PreloadTask(const HTMLToken& token)

    47         : m_tagName(token.name().data(), token.name().size())

    48         , m_linkIsStyleSheet(false)

    49     {

    50         processAttributes(token.attributes());

    51     }

    52 

    53     void processAttributes(const HTMLToken::AttributeList& attributes)

    54     {

    55         if (m_tagName != scriptTag && m_tagName != imgTag && m_tagName != linkTag)

    56             return;

    57 

    58         for (HTMLToken::AttributeList::const_iterator iter = attributes.begin();

    59              iter != attributes.end(); ++iter) {

    60             AtomicString attributeName(iter->m_name.data(), iter->m_name.size());

    61             String attributeValue(iter->m_value.data(), iter->m_value.size());

    62 

    63             if (attributeName == charsetAttr)

    64                 m_charset = attributeValue;

    65 

    66             if (m_tagName == scriptTag || m_tagName == imgTag) {

    67                 if (attributeName == srcAttr)

    68                     setUrlToLoad(attributeValue);

    69             } else if (m_tagName == linkTag) {

    70                 if (attributeName == hrefAttr)

    71                     setUrlToLoad(attributeValue);

    72                 else if (attributeName == relAttr)

    73                     m_linkIsStyleSheet = relAttributeIsStyleSheet(attributeValue);

    74             }

    75         }

    76     }

    77 

    78     bool relAttributeIsStyleSheet(const String& attributeValue)

    79     {

    80         ASSERT(m_tagName == linkTag);

    81         HTMLLinkElement::RelAttribute rel;

    82         HTMLLinkElement::tokenizeRelAttribute(attributeValue, rel);

    83         return rel.m_isStyleSheet && !rel.m_isAlternate && !rel.m_isIcon && !rel.m_isDNSPrefetch;

    84     }

    85 

    86     void setUrlToLoad(const String& attributeValue)

    87     {

    88         // We only respect the first src/href, per HTML5:

    89         // http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html#attribute-name-state

    90         if (!m_urlToLoad.isEmpty())

    91             return;

    92         m_urlToLoad = deprecatedParseURL(attributeValue);

    93     }

    94 

    95     void preload(Document* document, bool scanningBody)

    96     {

    97         if (m_urlToLoad.isEmpty())

    98             return;

    99 

   100         DocLoader* docLoader = document->docLoader();

   101         if (m_tagName == scriptTag)

   102             docLoader->preload(CachedResource::Script, m_urlToLoad, m_charset, scanningBody);

   103         else if (m_tagName == imgTag) 

   104             docLoader->preload(CachedResource::ImageResource, m_urlToLoad, String(), scanningBody);

   105         else if (m_tagName == linkTag && m_linkIsStyleSheet) 

   106             docLoader->preload(CachedResource::CSSStyleSheet, m_urlToLoad, m_charset, scanningBody);

   107     }

   108 

   109     const AtomicString& tagName() const { return m_tagName; }

   110 

   111 private:

   112     AtomicString m_tagName;

   113     String m_urlToLoad;

   114     String m_charset;

   115     bool m_linkIsStyleSheet;

   116 };

   117 

   118 } // namespace

   119 

   120 HTMLPreloadScanner::HTMLPreloadScanner(Document* document)

   121     : m_document(document)

   122     , m_cssScanner(document)

   123     , m_bodySeen(false)

   124     , m_inStyle(false)

   125 {

   126 }

   127 

   128 void HTMLPreloadScanner::appendToEnd(const SegmentedString& source)

   129 {

   130     m_source.append(source);

   131 }

   132 

   133 void HTMLPreloadScanner::scan()

   134 {

   135     // FIXME: We should save and re-use these tokens in HTMLDocumentParser if

   136     // the pending script doesn't end up calling document.write.

   137     while (m_tokenizer.nextToken(m_source, m_token)) {

   138         processToken();

   139         m_token.clear();

   140     }

   141 }

   142 

   143 void HTMLPreloadScanner::processToken()

   144 {

   145     if (m_inStyle) {

   146         if (m_token.type() == HTMLToken::Character)

   147             m_cssScanner.scan(m_token, scanningBody());

   148         else if (m_token.type() == HTMLToken::EndTag) {

   149             m_inStyle = false;

   150             m_cssScanner.reset();

   151         }

   152     }

   153 

   154     if (m_token.type() != HTMLToken::StartTag)

   155         return;

   156 

   157     PreloadTask task(m_token);

   158     m_tokenizer.setState(HTMLTreeBuilder::adjustedLexerState(m_tokenizer.state(), task.tagName(), m_document->frame()));

   159     if (task.tagName() == scriptTag) {

   160         // The tree builder handles scriptTag separately from the other tokenizer

   161         // state adjustments, so we need to handle it separately too.

   162         ASSERT(m_tokenizer.state() == HTMLTokenizer::DataState);

   163         m_tokenizer.setState(HTMLTokenizer::ScriptDataState);

   164     }

   165 

   166     if (task.tagName() == bodyTag)

   167         m_bodySeen = true;

   168 

   169     if (task.tagName() == styleTag)

   170         m_inStyle = true;

   171 

   172     task.preload(m_document, scanningBody());

   173 }

   174 

   175 bool HTMLPreloadScanner::scanningBody() const

   176 {

   177     return m_document->body() || m_bodySeen;

   178 }

   179 

   180 }