com.itextpdf.styledxmlparser.jsoup.parser.XmlTreeBuilder Maven / Gradle / Ivy
Show all versions of styled-xml-parser Show documentation
/*
This file is part of the iText (R) project.
Copyright (c) 1998-2024 Apryse Group NV
Authors: Apryse Software.
This program is offered under a commercial and under the AGPL license.
For commercial licensing, contact us at https://itextpdf.com/sales. For AGPL licensing, see below.
AGPL licensing:
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see
* Usage example: {@code Document xmlDoc = Jsoup.parse(html, baseUrl, Parser.xmlParser());}
*/
public class XmlTreeBuilder extends TreeBuilder {
ParseSettings defaultSettings() {
return ParseSettings.preserveCase;
}
@Override
protected void initialiseParse(Reader input, String baseUri, Parser parser) {
super.initialiseParse(input, baseUri, parser);
stack.add(doc); // place the document onto the stack. differs from HtmlTreeBuilder (not on stack)
doc.outputSettings()
.syntax(Document.OutputSettings.Syntax.xml)
.escapeMode(Entities.EscapeMode.xhtml)
.prettyPrint(false); // as XML, we don't understand what whitespace is significant or not
}
Document parse(Reader input, String baseUri) {
return parse(input, baseUri, new Parser(this));
}
Document parse(String input, String baseUri) {
return parse(new StringReader(input), baseUri, new Parser(this));
}
@Override
TreeBuilder newInstance() {
return new XmlTreeBuilder();
}
@Override
protected boolean process(Token token) {
// start tag, end tag, doctype, comment, character, eof
switch (token.type) {
case StartTag:
insert(token.asStartTag());
break;
case EndTag:
popStackToClose(token.asEndTag());
break;
case Comment:
insert(token.asComment());
break;
case Character:
insert(token.asCharacter());
break;
case Doctype:
insert(token.asDoctype());
break;
case EOF: // could put some normalisation here if desired
break;
default:
Validate.fail("Unexpected token type: " + token.type);
}
return true;
}
private void insertNode(Node node) {
currentElement().appendChild(node);
}
Element insert(Token.StartTag startTag) {
Tag tag = Tag.valueOf(startTag.name(), settings);
if (startTag.hasAttributes())
startTag.attributes.deduplicate(settings);
Element el = new Element(tag, null, settings.normalizeAttributes(startTag.attributes));
insertNode(el);
if (startTag.isSelfClosing()) {
if (!tag.isKnownTag()) // unknown tag, remember this is self closing for output. see above.
tag.setSelfClosing();
} else {
stack.add(el);
}
return el;
}
void insert(Token.Comment commentToken) {
Comment comment = new Comment(commentToken.getData());
Node insert = comment;
if (commentToken.bogus && comment.isXmlDeclaration()) {
// xml declarations are emitted as bogus comments (which is right for html, but not xml)
// so we do a bit of a hack and parse the data as an element to pull the attributes out
XmlDeclaration decl = comment.asXmlDeclaration(); // else, we couldn't parse it as a decl, so leave as a comment
if (decl != null)
insert = decl;
}
insertNode(insert);
}
void insert(Token.Character token) {
final String data = token.getData();
insertNode(token.isCData() ? new CDataNode(data) : new TextNode(data));
}
void insert(Token.Doctype d) {
DocumentType doctypeNode = new DocumentType(settings.normalizeTag(d.getName()), d.getPublicIdentifier(), d.getSystemIdentifier());
doctypeNode.setPubSysKey(d.getPubSysKey());
insertNode(doctypeNode);
}
/**
* If the stack contains an element with this tag's name, pop up the stack to remove the first occurrence. If not
* found, skips.
*
* @param endTag tag to close
*/
private void popStackToClose(Token.EndTag endTag) {
String elName = settings.normalizeTag(endTag.tagName);
Element firstFound = null;
for (int pos = stack.size() -1; pos >= 0; pos--) {
Element next = stack.get(pos);
if (next.nodeName().equals(elName)) {
firstFound = next;
break;
}
}
if (firstFound == null)
return; // not found, skip
for (int pos = stack.size() -1; pos >= 0; pos--) {
Element next = stack.get(pos);
stack.remove(pos);
if (next == firstFound)
break;
}
}
List parseFragment(String inputFragment, String baseUri, Parser parser) {
initialiseParse(new StringReader(inputFragment), baseUri, parser);
runParser();
return doc.childNodes();
}
List parseFragment(String inputFragment, Element context, String baseUri, Parser parser) {
return parseFragment(inputFragment, baseUri, parser);
}
}