initial feed url canonicalizer setup (requires java 1.7)

README.md

@@ -36,7 +36,7 @@ Deployment on your own server
 -----------------------------
 
 For storage, you can either use an embedded HSQLDB database or an external MySQL or PostgreSQL database.
-You also need Maven 3.x (and a Java JDK) installed in order to build the application.
+You also need Maven 3.x (and a Java 1.7+ JDK) installed in order to build the application.
 
 To install maven and openjdk on Ubuntu, issue the following commands
 

pom.xml

@@ -60,8 +60,8 @@
 				<artifactId>maven-compiler-plugin</artifactId>
 				<version>3.1</version>
 				<configuration>
-					<source>1.6</source>
+					<source>1.7</source>
-					<target>1.6</target>
+					<target>1.7</target>
 					<compilerArgument>-proc:none</compilerArgument>
 				</configuration>
 			</plugin>
@@ -267,6 +267,11 @@
 				</exclusion>
 			</exclusions>
 		</dependency>
+		<dependency>
+			<groupId>edu.uci.ics</groupId>
+			<artifactId>crawler4j</artifactId>
+			<version>3.5</version>
+		</dependency>
 		<dependency>
 			<groupId>org.jdom</groupId>
 			<artifactId>jdom</artifactId>

src/main/java/com/commafeed/backend/feeds/FeedUtils.java

@@ -36,6 +36,8 @@ import com.google.gwt.i18n.client.HasDirection.Direction;
 import com.google.gwt.i18n.shared.BidiUtils;
 import com.steadystate.css.parser.CSSOMParser;
 
+import edu.uci.ics.crawler4j.url.URLCanonicalizer;
+
 public class FeedUtils {
 
 	protected static Logger log = LoggerFactory.getLogger(FeedUtils.class);
@@ -85,6 +87,13 @@ public class FeedUtils {
 		return encoding;
 	}
 
+	public static String normalizeURL(String url) {
+		if (url == null) {
+			return null;
+		}
+		return URLCanonicalizer.getCanonicalURL(url);
+	}
+
 	/**
 	 * Extract the declared encoding from the xml
 	 */

src/test/java/com/commafeed/backend/feeds/FeedUtilsTest.java

@@ -0,0 +1,23 @@
+package com.commafeed.backend.feeds;
+
+import org.junit.Assert;
+import org.junit.Test;
+
+public class FeedUtilsTest {
+
+	@Test
+	public void testNormalization() {
+		String urla1 = "http://example.com/hello?a=1&b=2";
+		String urla2 = "http://EXAmPLe.com/hello?a=1&b=2";
+		String urla3 = "http://example.com/hello?b=2&a=1";
+
+		String urlb1 = "http://ftr.fivefilters.org/makefulltextfeed.php?url=http%3A%2F%2Ffeeds.howtogeek.com%2FHowToGeek&max=10&summary=1";
+		String urlb2 = "http://ftr.fivefilters.org/makefulltextfeed.php?url=http://feeds.howtogeek.com/HowToGeek&max=10&summary=1";
+
+		Assert.assertEquals(FeedUtils.normalizeURL(urla1), FeedUtils.normalizeURL(urla2));
+		Assert.assertEquals(FeedUtils.normalizeURL(urla1), FeedUtils.normalizeURL(urla3));
+
+		Assert.assertEquals(FeedUtils.normalizeURL(urlb1), FeedUtils.normalizeURL(urlb2));
+
+	}
+}