com.itextpdf.styledxmlparser.jsoup.parser.XmlTreeBuilder Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of styled-xml-parser Show documentation
Show all versions of styled-xml-parser Show documentation
Styled XML parser is used by iText7 modules to parse HTML and XML
/*
This file is part of the iText (R) project.
Copyright (c) 1998-2019 iText Group NV
Authors: iText Software.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License version 3
as published by the Free Software Foundation with the addition of the
following permission added to Section 15 as permitted in Section 7(a):
FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
ITEXT GROUP. ITEXT GROUP DISCLAIMS THE WARRANTY OF NON INFRINGEMENT
OF THIRD PARTY RIGHTS
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 http://www.gnu.org/licenses or write to
the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
Boston, MA, 02110-1301 USA, or download the license from the following URL:
http://itextpdf.com/terms-of-use/
The interactive user interfaces in modified source and object code versions
of this program must display Appropriate Legal Notices, as required under
Section 5 of the GNU Affero General Public License.
In accordance with Section 7(b) of the GNU Affero General Public License,
a covered work must retain the producer line in every PDF that is created
or manipulated using iText.
You can be released from the requirements of the license by purchasing
a commercial license. Buying such a license is mandatory as soon as you
develop commercial activities involving the iText software without
disclosing the source code of your own applications.
These activities include: offering paid services to customers as an ASP,
serving PDFs on the fly in a web application, shipping iText with a closed
source product.
For more information, please contact iText Software Corp. at this
address: [email protected]
*/
package com.itextpdf.styledxmlparser.jsoup.parser;
import com.itextpdf.styledxmlparser.jsoup.Jsoup;
import com.itextpdf.styledxmlparser.jsoup.helper.Validate;
import com.itextpdf.styledxmlparser.jsoup.nodes.Comment;
import com.itextpdf.styledxmlparser.jsoup.nodes.Document;
import com.itextpdf.styledxmlparser.jsoup.nodes.DocumentType;
import com.itextpdf.styledxmlparser.jsoup.nodes.Element;
import com.itextpdf.styledxmlparser.jsoup.nodes.Node;
import com.itextpdf.styledxmlparser.jsoup.nodes.TextNode;
import com.itextpdf.styledxmlparser.jsoup.nodes.XmlDeclaration;
import java.util.List;
/**
* Use the {@code XmlTreeBuilder} when you want to parse XML without any of the HTML DOM rules being applied to the
* document.
* Usage example: {@code Document xmlDoc = Jsoup.parse(html, baseUrl, Parser.xmlParser());}
*
* @author Jonathan Hedley
*/
public class XmlTreeBuilder extends TreeBuilder {
@Override
protected void initialiseParse(String input, String baseUri, ParseErrorList errors) {
super.initialiseParse(input, baseUri, errors);
stack.add(doc); // place the document onto the stack. differs from HtmlTreeBuilder (not on stack)
doc.outputSettings().syntax(Document.OutputSettings.Syntax.xml);
}
@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());
// todo: wonder if for xml parsing, should treat all tags as unknown? because it's not html.
Element el = new Element(tag, baseUri, startTag.attributes);
insertNode(el);
if (startTag.isSelfClosing()) {
tokeniser.acknowledgeSelfClosingFlag();
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(), baseUri);
Node insert = comment;
if (commentToken.bogus) { // 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
String data = comment.getData();
if (data.length() > 1 && (data.startsWith("!") || data.startsWith("?"))) {
Document doc = Jsoup.parse("<" + data.substring(1, data.length() -1) + ">", baseUri, Parser.xmlParser());
Element el = doc.child(0);
insert = new XmlDeclaration(el.tagName(), comment.baseUri(), data.startsWith("!"));
insert.attributes().addAll(el.attributes());
}
}
insertNode(insert);
}
void insert(Token.Character characterToken) {
Node node = new TextNode(characterToken.getData(), baseUri);
insertNode(node);
}
void insert(Token.Doctype d) {
DocumentType doctypeNode = new DocumentType(d.getName(), d.getPublicIdentifier(), d.getSystemIdentifier(), baseUri);
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
*/
private void popStackToClose(Token.EndTag endTag) {
String elName = endTag.name();
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, ParseErrorList errors) {
initialiseParse(inputFragment, baseUri, errors);
runParser();
return doc.childNodes();
}
}