forked from jhy/jsoup
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathCleaner.java
More file actions
176 lines (152 loc) · 7.15 KB
/
Copy pathCleaner.java
File metadata and controls
176 lines (152 loc) · 7.15 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
package org.jsoup.safety;
import org.jsoup.helper.Validate;
import org.jsoup.nodes.Attribute;
import org.jsoup.nodes.Attributes;
import org.jsoup.nodes.DataNode;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import org.jsoup.parser.ParseErrorList;
import org.jsoup.parser.Parser;
import org.jsoup.parser.Tag;
import org.jsoup.select.NodeTraversor;
import org.jsoup.select.NodeVisitor;
import java.util.List;
/**
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!
<p>
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.
</p>
<p>
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.
</p>
<p>
Rather than interacting directly with a Cleaner object, generally see the {@code clean} methods in {@link org.jsoup.Jsoup}.
</p>
*/
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 <code>body</code> 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 <b>body</b>is valid, against the whitelist. It is considered valid if all the tags and attributes
in the input HTML are allowed by the whitelist, and that there is no content in the <code>head</code>.
<p>
This method can be used as a validator for user input. 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.
</p>
@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
&& dirtyDocument.head().childNodes().size() == 0; // because we only look at the body, but we start from a shell, make sure there's nothing in the head
}
public boolean isValidBodyHtml(String bodyHtml) {
Document clean = Document.createShell("");
Document dirty = Document.createShell("");
ParseErrorList errorList = ParseErrorList.tracking(1);
List<Node> nodes = Parser.parseFragment(bodyHtml, dirty.body(), "", errorList);
dirty.body().insertChildren(0, nodes);
int numDiscarded = copySafeNodes(dirty.body(), clean.body());
return numDiscarded == 0 && errorList.size() == 0;
}
/**
Iterates the input and copies trusted nodes (tags, attributes, text) into the destination.
*/
private final class CleaningVisitor implements NodeVisitor {
private int numDiscarded = 0;
private final Element root;
private Element destination; // current element to append nodes to
private 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 = 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;
}
}
}