Merge pull request #36 from gerhardgossen/master

Escape redirect URLs in RealCDXExtractorOutput

CHANGES.md

@@ -1,5 +1,6 @@
 1.1.5
 -----
+* [Escape redirect URLs in RealCDXExtractorOutput](https://github.com/iipc/webarchive-commons/pull/36)
 * [Tests fail on Windows](https://github.com/iipc/webarchive-commons/issues/2)
 * [Test fails on Java 8](https://github.com/iipc/webarchive-commons/issues/31)
 

src/main/java/org/archive/extract/RealCDXExtractorOutput.java

@@ -4,6 +4,7 @@
 import java.io.OutputStream;
 import java.io.PrintWriter;
 import java.net.MalformedURLException;
+import java.net.URI;
 import java.net.URISyntaxException;
 import java.net.URL;
 import java.util.List;
@@ -307,12 +308,14 @@ private String extractHTMLMetaRefresh(String origUrl, MetaData m) {
 		return "-";
 	}
 
-	private String resolve(String context, String spec) {
+	static String resolve(String context, String spec) {
 		// TODO: test!
 		try {
 			URL cUrl = new URL(context);
-			URL resolved = new URL(cUrl,spec);
-			return resolved.toURI().toASCIIString();
+			URL url = new URL(cUrl, spec);
+			// this constructor escapes its arguments, if necessary
+			URI uri = new URI(url.getProtocol(), url.getHost(), url.getPath(), url.getQuery(), url.getRef());
+			return uri.toASCIIString();
 
 		} catch (URISyntaxException e) {			
 		} catch (MalformedURLException e) {

src/test/java/org/archive/extract/RealCDXExtractorOutputTest.java

@@ -0,0 +1,28 @@
+package org.archive.extract;
+
+import java.net.MalformedURLException;
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.net.URL;
+import java.net.URLEncoder;
+
+import junit.framework.TestCase;
+
+
+public class RealCDXExtractorOutputTest extends TestCase {
+
+    public void testEscapeResolvedUrl() throws Exception {
+	String context ="http://www.uni-giessen.de/cms/studium/dateien/informationberatung/merkblattpdf";
+	String spec = "http://fss.plone.uni-giessen.de/fß/studium/dateien/informationberatung/merkblattpdf/file/Mérkblatt zur Gestaltung von Nachteilsausgleichen.pdf?föo=bar#änchor";
+	String escaped = RealCDXExtractorOutput.resolve(context, spec);
+	assertTrue(escaped.indexOf(" ") < 0);
+	URI parsed = new URI(escaped);
+	assertEquals("änchor", parsed.getFragment());
+    }
+
+    public void testNoDoubleEscaping() throws Exception {
+	String spec = "https://www.google.com/search?q=java+escape+url+spaces&ie=utf-8&oe=utf-8";
+	String resolved = RealCDXExtractorOutput.resolve(spec, spec);
+	assertTrue(spec.equals(resolved));
+    }
+}