honeymoose/org.hl7.fhir.core
1
0
Fork 0
mirror of https://github.com/hapifhir/org.hl7.fhir.core.git synced 2025-03-09 14:31:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add parsing DTD entity declarations

Browse Source
This commit is contained in:
Grahame Grieve 2020-07-17 09:26:54 +10:00
parent 6707d5a59f
commit 847858c131
2 changed files with 44 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlParser.java
View File

@ -120,6 +120,7 @@ public class XhtmlParser {
private Set<String> elements = new HashSet<String>(); private Set<String> elements = new HashSet<String>();
private Set<String> attributes = new HashSet<String>(); private Set<String> attributes = new HashSet<String>();
private Map<String, String> entities = new HashMap<>();
public XhtmlParser() { public XhtmlParser() {
@ -522,8 +523,9 @@ private boolean elementIsOk(String name) throws FHIRFormatError {
readChar(); readChar();
if (peekChar() == '!') { if (peekChar() == '!') {
String sc = readToCommentEnd(); String sc = readToCommentEnd();
if (sc.startsWith("DOCTYPE")) // moved the validator
throw new FHIRFormatError("Malformed XHTML: Found a DocType declaration, and these are not allowed (XXE security vulnerability protection)"); // if (sc.startsWith("DOCTYPE"))
// throw new FHIRFormatError("Malformed XHTML: Found a DocType declaration, and these are not allowed (XXE security vulnerability protection)");
node.addComment(sc).setLocation(markLocation()); node.addComment(sc).setLocation(markLocation());
} else if (peekChar() == '?') } else if (peekChar() == '?')
node.addComment(readToTagEnd()).setLocation(markLocation()); node.addComment(readToTagEnd()).setLocation(markLocation());
@ -786,6 +788,8 @@ private boolean elementIsOk(String name) throws FHIRFormatError {
readChar(); readChar();
} }
boolean doctypeEntities = false;
boolean done = false; boolean done = false;
while (!done) { while (!done) {
char c = peekChar(); char c = peekChar();
@ -799,8 +803,16 @@ private boolean elementIsOk(String name) throws FHIRFormatError {
s.append("--"); s.append("--");
} else } else
s.append('-'); s.append('-');
} else if (simple && peekChar() == '>') { } else if (doctypeEntities && c == ']') {
s.append(readChar());
if (peekChar() == '>') {
done = true; done = true;
}
} else if (simple && peekChar() == '>' && !doctypeEntities) {
done = true;
} else if (c == '[' && s.toString().startsWith("DOCTYPE ")) {
doctypeEntities = true;
s.append(readChar());
} else if (c != '\0') } else if (c != '\0')
s.append(readChar()); s.append(readChar());
else if (mustBeWellFormed) else if (mustBeWellFormed)
@ -811,9 +823,30 @@ private boolean elementIsOk(String name) throws FHIRFormatError {
readChar(); readChar();
skipWhiteSpace(); skipWhiteSpace();
} }
if (doctypeEntities) {
parseDoctypeEntities(s.toString());
}
return s.toString(); return s.toString();
} }
private void parseDoctypeEntities(String s) {
while (s.contains("<!ENTITY")) {
s = s.substring(s.indexOf("<!ENTITY"));
int e = s.indexOf(">");
String ed = s.substring(0, e+1);
s = s.substring(e+1);
ed = ed.substring(8).trim();
e = ed.indexOf(" ");
String n = ed.substring(0, e).trim();
ed = ed.substring(e).trim();
e = ed.indexOf(" "); // SYSTEM
ed = ed.substring(e).trim();
String v = ed.substring(0, ed.length()-1);
entities.put(n, v);
}
}
private boolean isNameChar(char ch) private boolean isNameChar(char ch)
{ {
return Character.isLetterOrDigit(ch) || ch == '_' || ch == '-' || ch == ':'; return Character.isLetterOrDigit(ch) || ch == '_' || ch == '-' || ch == ':';
@ -1125,6 +1158,8 @@ private boolean elementIsOk(String name) throws FHIRFormatError {
s.append((char) 8221); s.append((char) 8221);
else if (c.equals("rdquo")) else if (c.equals("rdquo"))
s.append((char) 201D); s.append((char) 201D);
else if (entities.containsKey(c))
s.append(entities.get(c));
else else
throw new FHIRFormatError("unable to parse character reference '" + c + "'' (last text = '" + lastText + "'" + descLoc()); throw new FHIRFormatError("unable to parse character reference '" + c + "'' (last text = '" + lastText + "'" + descLoc());
} }

6
org.hl7.fhir.utilities/src/test/java/org/hl7/fhir/utilities/tests/XhtmlNodeTest.java
View File

@ -73,6 +73,12 @@ public class XhtmlNodeTest {
Assertions.assertEquals("<div xmlns=\"http://www.w3.org/1999/xhtml\"><img src=\"http://pbs.twimg.com/profile_images/544507893991485440/r_vo3uj2_bigger.png\" alt=\"Twitter Avatar\"/>@fhirabend</div>", output); Assertions.assertEquals("<div xmlns=\"http://www.w3.org/1999/xhtml\"><img src=\"http://pbs.twimg.com/profile_images/544507893991485440/r_vo3uj2_bigger.png\" alt=\"Twitter Avatar\"/>@fhirabend</div>", output);
} }
@Test
public void testParseXXE() {
XhtmlNode dt = new XhtmlNode();
dt.setValueAsString("<div xmlns=\"http://www.w3.org/1999/xhtml\">\n <!DOCTYPE foo [ <!ENTITY xxe SYSTEM \"file://c:\\temp\\xxe.txt\">]>\n <p>This is some narrative &xxe;</p>\n </div>");
}
@Test @Test
public void testSerializable() throws IOException { public void testSerializable() throws IOException {
XhtmlNode node = new XhtmlNode(); XhtmlNode node = new XhtmlNode();