com.itextpdf.styledxmlparser.jsoup.safety.Cleaner 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) 1998-2018 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.safety;
import com.itextpdf.styledxmlparser.jsoup.Jsoup;
import com.itextpdf.styledxmlparser.jsoup.helper.Validate;
import com.itextpdf.styledxmlparser.jsoup.nodes.Attribute;
import com.itextpdf.styledxmlparser.jsoup.nodes.Attributes;
import com.itextpdf.styledxmlparser.jsoup.nodes.DataNode;
import com.itextpdf.styledxmlparser.jsoup.nodes.Document;
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.parser.Tag;
import com.itextpdf.styledxmlparser.jsoup.select.NodeTraversor;
import com.itextpdf.styledxmlparser.jsoup.select.NodeVisitor;
/**
The whitelist based HTML cleaner. Use to ensure that end-user provided HTML contains only the elements and attributes
that you are expecting; no junk, and no cross-site scripting attacks!
The HTML cleaner parses the input as HTML and then runs it through a white-list, so the output HTML can only contain
HTML that is allowed by the whitelist.
It is assumed that the input HTML is a body fragment; the clean methods only pull from the source's body, and the
canned white-lists only allow body contained tags.
Rather than interacting directly with a Cleaner object, generally see the {@code clean} methods in {@link Jsoup}.
*/
public class Cleaner {
private Whitelist whitelist;
/**
Create a new cleaner, that sanitizes documents using the supplied whitelist.
@param whitelist white-list to clean with
*/
public Cleaner(Whitelist whitelist) {
Validate.notNull(whitelist);
this.whitelist = whitelist;
}
/**
Creates a new, clean document, from the original dirty document, containing only elements allowed by the whitelist.
The original document is not modified. Only elements from the dirt document's body are used.
@param dirtyDocument Untrusted base document to clean.
@return cleaned document.
*/
public Document clean(Document dirtyDocument) {
Validate.notNull(dirtyDocument);
Document clean = Document.createShell(dirtyDocument.baseUri());
if (dirtyDocument.body() != null) // frameset documents won't have a body. the clean doc will have empty body.
copySafeNodes(dirtyDocument.body(), clean.body());
return clean;
}
/**
Determines if the input document is valid, against the whitelist. It is considered valid if all the tags and attributes
in the input HTML are allowed by the whitelist.
This method can be used as a validator for user input forms. An invalid document will still be cleaned successfully
using the {@link #clean(Document)} document. If using as a validator, it is recommended to still clean the document
to ensure enforced attributes are set correctly, and that the output is tidied.
@param dirtyDocument document to test
@return true if no tags or attributes need to be removed; false if they do
*/
public boolean isValid(Document dirtyDocument) {
Validate.notNull(dirtyDocument);
Document clean = Document.createShell(dirtyDocument.baseUri());
int numDiscarded = copySafeNodes(dirtyDocument.body(), clean.body());
return numDiscarded == 0;
}
/**
Iterates the input and copies trusted nodes (tags, attributes, text) into the destination.
*/
private final class CleaningVisitor implements NodeVisitor {
int numDiscarded = 0;
final Element root;
Element destination; // current element to append nodes to
CleaningVisitor(Element root, Element destination) {
this.root = root;
this.destination = destination;
}
public void head(Node source, int depth) {
if (source instanceof Element) {
Element sourceEl = (Element) source;
if (whitelist.isSafeTag(sourceEl.tagName())) { // safe, clone and copy safe attrs
ElementMeta meta = createSafeElement(sourceEl);
Element destChild = meta.el;
destination.appendChild(destChild);
numDiscarded += meta.numAttribsDiscarded;
destination = destChild;
} else if (source != root) { // not a safe tag, so don't add. don't count root against discarded.
numDiscarded++;
}
} else if (source instanceof TextNode) {
TextNode sourceText = (TextNode) source;
TextNode destText = new TextNode(sourceText.getWholeText(), source.baseUri());
destination.appendChild(destText);
} else if (source instanceof DataNode && whitelist.isSafeTag(source.parent().nodeName())) {
DataNode sourceData = (DataNode) source;
DataNode destData = new DataNode(sourceData.getWholeData(), source.baseUri());
destination.appendChild(destData);
} else { // else, we don't care about comments, xml proc instructions, etc
numDiscarded++;
}
}
public void tail(Node source, int depth) {
if (source instanceof Element && whitelist.isSafeTag(source.nodeName())) {
destination = (Element) destination.parent(); // would have descended, so pop destination stack
}
}
}
private int copySafeNodes(Element source, Element dest) {
CleaningVisitor cleaningVisitor = new CleaningVisitor(source, dest);
NodeTraversor traversor = new NodeTraversor(cleaningVisitor);
traversor.traverse(source);
return cleaningVisitor.numDiscarded;
}
private ElementMeta createSafeElement(Element sourceEl) {
String sourceTag = sourceEl.tagName();
Attributes destAttrs = new Attributes();
Element dest = new Element(Tag.valueOf(sourceTag), sourceEl.baseUri(), destAttrs);
int numDiscarded = 0;
Attributes sourceAttrs = sourceEl.attributes();
for (Attribute sourceAttr : sourceAttrs) {
if (whitelist.isSafeAttribute(sourceTag, sourceEl, sourceAttr))
destAttrs.put(sourceAttr);
else
numDiscarded++;
}
Attributes enforcedAttrs = whitelist.getEnforcedAttributes(sourceTag);
destAttrs.addAll(enforcedAttrs);
return new ElementMeta(dest, numDiscarded);
}
private static class ElementMeta {
Element el;
int numAttribsDiscarded;
ElementMeta(Element el, int numAttribsDiscarded) {
this.el = el;
this.numAttribsDiscarded = numAttribsDiscarded;
}
}
}