com.itextpdf.styledxmlparser.jsoup.parser.Parser 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 iText modules to parse HTML and XML
/*
This file is part of the iText (R) project.
Copyright (c) 1998-2023 iText Group NV
Authors: iText 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 parseFragmentInput(String fragment, Element context, String baseUri) {
return treeBuilder.parseFragment(fragment, context, baseUri, this);
}
// gets & sets
/**
* Get the TreeBuilder currently in use.
* @return current TreeBuilder.
*/
public TreeBuilder getTreeBuilder() {
return treeBuilder;
}
/**
* Update the TreeBuilder used when parsing content.
* @param treeBuilder current TreeBuilder
* @return this, for chaining
*/
public Parser setTreeBuilder(TreeBuilder treeBuilder) {
this.treeBuilder = treeBuilder;
treeBuilder.parser = this;
return this;
}
/**
* Check if parse error tracking is enabled.
* @return current track error state.
*/
public boolean isTrackErrors() {
return errors.getMaxSize() > 0;
}
/**
* Enable or disable parse error tracking for the next parse.
* @param maxErrors the maximum number of errors to track. Set to 0 to disable.
* @return this, for chaining
*/
public Parser setTrackErrors(int maxErrors) {
errors = maxErrors > 0 ? ParseErrorList.tracking(maxErrors) : ParseErrorList.noTracking();
return this;
}
/**
* Retrieve the parse errors, if any, from the last parse.
* @return list of parse errors, up to the size of the maximum errors tracked.
*/
public ParseErrorList getErrors() {
return errors;
}
public Parser settings(ParseSettings settings) {
this.settings = settings;
return this;
}
public ParseSettings settings() {
return settings;
}
/**
(An internal method, visible for Element. For HTML parse, signals that script and style text should be treated as
Data Nodes).
*/
public boolean isContentForTagData(String normalName) {
return getTreeBuilder().isContentForTagData(normalName);
}
// static parse functions below
/**
* Parse HTML into a Document.
*
* @param html HTML to parse
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
*
* @return parsed Document
*/
public static Document parse(String html, String baseUri) {
TreeBuilder treeBuilder = new HtmlTreeBuilder();
return treeBuilder.parse(new StringReader(html), baseUri, new Parser(treeBuilder));
}
/**
* Parse a fragment of HTML into a list of nodes. The context element, if supplied, supplies parsing context.
*
* @param fragmentHtml the fragment of HTML to parse
* @param context (optional) the element that this HTML fragment is being parsed for (i.e. for inner HTML). This
* provides stack context (for implicit element creation).
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
*
* @return list of nodes parsed from the input HTML. Note that the context element, if supplied, is not modified.
*/
public static List parseFragment(String fragmentHtml, Element context, String baseUri) {
HtmlTreeBuilder treeBuilder = new HtmlTreeBuilder();
return treeBuilder.parseFragment(fragmentHtml, context, baseUri, new Parser(treeBuilder));
}
/**
* Parse a fragment of HTML into a list of nodes. The context element, if supplied, supplies parsing context.
*
* @param fragmentHtml the fragment of HTML to parse
* @param context (optional) the element that this HTML fragment is being parsed for (i.e. for inner HTML). This
* provides stack context (for implicit element creation).
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
* @param errorList list to add errors to
*
* @return list of nodes parsed from the input HTML. Note that the context element, if supplied, is not modified.
*/
public static List parseFragment(String fragmentHtml, Element context, String baseUri, ParseErrorList errorList) {
HtmlTreeBuilder treeBuilder = new HtmlTreeBuilder();
Parser parser = new Parser(treeBuilder);
parser.errors = errorList;
return treeBuilder.parseFragment(fragmentHtml, context, baseUri, parser);
}
/**
* Parse a fragment of XML into a list of nodes.
*
* @param fragmentXml the fragment of XML to parse
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
* @return list of nodes parsed from the input XML.
*/
public static List parseXmlFragment(String fragmentXml, String baseUri) {
XmlTreeBuilder treeBuilder = new XmlTreeBuilder();
return treeBuilder.parseFragment(fragmentXml, baseUri, new Parser(treeBuilder));
}
/**
* Parse a fragment of HTML into the {@code body} of a Document.
*
* @param bodyHtml fragment of HTML
* @param baseUri base URI of document (i.e. original fetch location), for resolving relative URLs.
*
* @return Document, with empty head, and HTML parsed into body
*/
public static Document parseBodyFragment(String bodyHtml, String baseUri) {
Document doc = Document.createShell(baseUri);
Element body = doc.body();
List nodeList = parseFragment(bodyHtml, body, baseUri);
Node[] nodes = nodeList.toArray(new Node[0]); // the node list gets modified when re-parented
for (int i = nodes.length - 1; i > 0; i--) {
nodes[i].remove();
}
for (Node node : nodes) {
body.appendChild(node);
}
return doc;
}
/**
* Utility method to unescape HTML entities from a string
* @param string HTML escaped string
* @param inAttribute if the string is to be escaped in strict mode (as attributes are)
* @return an unescaped string
*/
public static String unescapeEntities(String string, boolean inAttribute) {
Tokeniser tokeniser = new Tokeniser(new CharacterReader(string), ParseErrorList.noTracking());
return tokeniser.unescapeEntities(inAttribute);
}
// builders
/**
* Create a new HTML parser. This parser treats input as HTML5, and enforces the creation of a normalised document,
* based on a knowledge of the semantics of the incoming tags.
* @return a new HTML parser.
*/
public static Parser htmlParser() {
return new Parser(new HtmlTreeBuilder());
}
/**
* Create a new XML parser. This parser assumes no knowledge of the incoming tags and does not treat it as HTML,
* rather creates a simple tree directly from the input.
* @return a new simple XML parser.
*/
public static Parser xmlParser() {
return new Parser(new XmlTreeBuilder());
}
}