Java/HtmlDomParserContext.java at main · Eggy115/Java · GitHub

History

243 lines (222 loc) · 10.3 KB

Raw

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

/**

* (The MIT License)

* * {Aaron Patterson}[http://tenderlovemaking.com]

* * {Mike Dalessio}[http://mike.daless.io]

* * {Charles Nutter}[http://blog.headius.com]

* * {Sergio Arbeo}[http://www.serabe.com]

* * {Patrick Mahoney}[http://polycrystal.org]

* * {Yoko Harada}[http://yokolet.blogspot.com]

* Permission is hereby granted, free of charge, to any person obtaining

* a copy of this software and associated documentation files (the

* 'Software'), to deal in the Software without restriction, including

* without limitation the rights to use, copy, modify, merge, publish,

* distribute, sublicense, and/or sell copies of the Software, and to

* permit persons to whom the Software is furnished to do so, subject to

* the following conditions:

* The above copyright notice and this permission notice shall be

* included in all copies or substantial portions of the Software.

* THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,

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

* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.

* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY

* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,

* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

* SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

package nokogiri.internals;

import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;

import static nokogiri.internals.NokogiriHelpers.isNamespace;

import static nokogiri.internals.NokogiriHelpers.stringOrNil;

import nokogiri.HtmlDocument;

import nokogiri.NokogiriService;

import nokogiri.XmlDocument;

import org.apache.xerces.parsers.DOMParser;

import org.apache.xerces.xni.Augmentations;

import org.apache.xerces.xni.QName;

import org.apache.xerces.xni.XMLAttributes;

import org.apache.xerces.xni.XNIException;

import org.apache.xerces.xni.parser.XMLDocumentFilter;

import org.apache.xerces.xni.parser.XMLParserConfiguration;

import org.cyberneko.html.HTMLConfiguration;

import org.cyberneko.html.filters.DefaultFilter;

import org.jruby.Ruby;

import org.jruby.RubyClass;

import org.jruby.runtime.ThreadContext;

import org.jruby.runtime.builtin.IRubyObject;

import org.w3c.dom.Document;

import org.w3c.dom.NamedNodeMap;

import org.w3c.dom.NodeList;

/**

* Parser for HtmlDocument. This class actually parses HtmlDocument using NekoHtml.

* @author sergio

* @author Patrick Mahoney <pat@polycrystal.org>

* @author Yoko Harada <yokolet@gmail.com>

public class HtmlDomParserContext extends XmlDomParserContext {

public HtmlDomParserContext(Ruby runtime, IRubyObject options) {

super(runtime, options);

}

public HtmlDomParserContext(Ruby runtime, IRubyObject encoding, IRubyObject options) {

super(runtime, encoding, options);

}

@Override

protected void initErrorHandler() {

if (options.strict) {

errorHandler = new NokogiriStrictErrorHandler(options.noError, options.noWarning);

} else {

errorHandler = new NokogiriNonStrictErrorHandler4NekoHtml(options.noError, options.noWarning);

}

@Override

protected void initParser(Ruby runtime) {

XMLParserConfiguration config = new HTMLConfiguration();

XMLDocumentFilter removeNSAttrsFilter = new RemoveNSAttrsFilter();

XMLDocumentFilter elementValidityCheckFilter = new ElementValidityCheckFilter(errorHandler);

//XMLDocumentFilter[] filters = { removeNSAttrsFilter, elementValidityCheckFilter};

XMLDocumentFilter[] filters = { elementValidityCheckFilter};

config.setErrorHandler(this.errorHandler);

parser = new DOMParser(config);

// see http://nekohtml.sourceforge.net/settings.html for details

setProperty("http://cyberneko.org/html/properties/default-encoding", java_encoding);

setProperty("http://cyberneko.org/html/properties/names/elems", "lower");

setProperty("http://cyberneko.org/html/properties/names/attrs", "lower");

setProperty("http://cyberneko.org/html/properties/filters", filters);

setFeature("http://cyberneko.org/html/features/report-errors", true);

setFeature("http://xml.org/sax/features/namespaces", false);

setFeature("http://cyberneko.org/html/features/insert-doctype", true);

}

/**

* Enable NekoHTML feature for balancing tags in a document fragment.

* This method is used in XmlNode#in_context method.

public void enableDocumentFragment() {

setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment", true);

}

@Override

protected XmlDocument getNewEmptyDocument(ThreadContext context) {

IRubyObject[] args = new IRubyObject[0];

return (XmlDocument) XmlDocument.rbNew(context, getNokogiriClass(context.getRuntime(), "Nokogiri::HTML::Document"), args);

}

@Override

protected XmlDocument wrapDocument(ThreadContext context,

RubyClass klazz,

Document document) {

HtmlDocument htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(context.getRuntime(), klazz);

htmlDocument.setDocumentNode(context, document);

if (ruby_encoding.isNil()) {

// ruby_encoding might have detected by HtmlDocument::EncodingReader

if (detected_encoding != null && !detected_encoding.isNil()) {

ruby_encoding = detected_encoding;

} else {

// no encoding given & no encoding detected, then try to get it

String charset = tryGetCharsetFromHtml5MetaTag(document);

ruby_encoding = stringOrNil(context.getRuntime(), charset);

}

htmlDocument.setEncoding(ruby_encoding);

htmlDocument.setParsedEncoding(java_encoding);

return htmlDocument;

}

// NekoHtml doesn't understand HTML5 meta tag format. This fails to detect charset

// from an HTML5 style meta tag. Luckily, the meta tag and charset exists in DOM tree

// so, this method attempts to find the charset.

private String tryGetCharsetFromHtml5MetaTag(Document document) {

if (!"html".equalsIgnoreCase(document.getDocumentElement().getNodeName())) return null;

NodeList list = document.getDocumentElement().getChildNodes();

for (int i = 0; i < list.getLength(); i++) {

if ("head".equalsIgnoreCase(list.item(i).getNodeName())) {

NodeList headers = list.item(i).getChildNodes();

for (int j = 0; j < headers.getLength(); j++) {

if ("meta".equalsIgnoreCase(headers.item(j).getNodeName())) {

NamedNodeMap nodeMap = headers.item(j).getAttributes();

for (int k = 0; k < nodeMap.getLength(); k++) {

if ("charset".equalsIgnoreCase(nodeMap.item(k).getNodeName())) {

return nodeMap.item(k).getNodeValue();

}

return null;

}

/**

* Filter to strip out attributes that pertain to XML namespaces.

public static class RemoveNSAttrsFilter extends DefaultFilter {

@Override

public void startElement(QName element, XMLAttributes attrs,

Augmentations augs) throws XNIException {

int i;

for (i = 0; i < attrs.getLength(); ++i) {

if (isNamespace(attrs.getQName(i))) {

attrs.removeAttributeAt(i);

--i;

}

element.uri = null;

super.startElement(element, attrs, augs);

}

public static class ElementValidityCheckFilter extends DefaultFilter {

private NokogiriErrorHandler errorHandler;

private ElementValidityCheckFilter(NokogiriErrorHandler errorHandler) {

this.errorHandler = errorHandler;

}

// element names from xhtml1-strict.dtd

private static String[][] element_names = {

{"a", "abbr", "acronym", "address", "area"},

{"b", "base", "basefont", "bdo", "big", "blockquote", "body", "br", "button"},

{"caption", "cite", "code", "col", "colgroup"},

{"dd", "del", "dfn", "div", "dl", "dt"},

{"em"},

{"fieldset", "font", "form", "frame", "frameset"},

{}, // g

{"h1", "h2", "h3", "h4", "h5", "h6", "head", "hr", "html"},

{"i", "iframe", "img", "input", "ins"},

{}, // j

{"kbd"},

{"label", "legend", "li", "link"},

{"map", "meta"},

{"noframes", "noscript"},

{"object", "ol", "optgroup", "option"},

{"p", "param", "pre"},

{"q"},

{}, // r

{"s", "samp", "script", "select", "small", "span", "strike", "strong", "style", "sub", "sup"},

{"table", "tbody", "td", "textarea", "tfoot", "th", "thead", "title", "tr", "tt"},

{"u", "ul"},

{"var"},

{}, // w

{}, // x

{}, // y

{} // z

};

private boolean isValid(String testee) {

char[] c = testee.toCharArray();

int index = new Integer(c[0]) - 97;

if (index > 25) return false;

for (int i=0; i<element_names[index].length; i++) {

if (testee.equals(element_names[index][i])) {

return true;

}

return false;

}

@Override

public void startElement(QName name, XMLAttributes attrs, Augmentations augs) throws XNIException {

if (!isValid(name.rawname)) {

errorHandler.getErrors().add(new Exception("Tag " + name.rawname + " invalid"));

}

super.startElement(name, attrs, augs);

}

Java/HtmlDomParserContext.java at main · Eggy115/Java · GitHub

Uh oh!

Expand file tree

Breadcrumbs

HtmlDomParserContext.java

Latest commit

History

Breadcrumbs

HtmlDomParserContext.java

File metadata and controls