updated and added test cases

dependency-check-core/src/main/java/org/owasp/dependencycheck/utils/UrlStringUtils.java

@@ -47,8 +47,8 @@ public final class UrlStringUtils {
     private static final Pattern IS_URL_TEST = Pattern.compile("^(ht|f)tps?://.*", Pattern.CASE_INSENSITIVE);
 
     /**
-     * Tests if the text provided contains a URL. This is somewhat limited search in that it only looks for
-     * (ftp|http|https)://
+     * Tests if the text provided contains a URL. This is somewhat limited
+     * search in that it only looks for (ftp|http|https)://
      *
      * @param text the text to search
      * @return true if the text contains a url, otherwise false
@@ -67,14 +67,16 @@ public final class UrlStringUtils {
         return IS_URL_TEST.matcher(text).matches();
     }
     /**
-     * A listing of domain parts that should not be used as evidence. Yes, this is an incomplete list.
+     * A listing of domain parts that should not be used as evidence. Yes, this
+     * is an incomplete list.
      */
     private static final Set<String> IGNORE_LIST = new HashSet<>(
             Arrays.asList("www", "com", "org", "gov", "info", "name", "net", "pro", "tel", "mobi", "xxx"));
 
     /**
      * <p>
-     * Takes a URL, in String format, and adds the important parts of the URL to a list of strings.</p>
+     * Takes a URL, in String format, and adds the important parts of the URL to
+     * a list of strings.</p>
      * <p>
      * Example, given the following input:</p>
      * <code>"https://www.somedomain.com/path1/path2/file.php?id=439"</code>
@@ -99,14 +101,21 @@ public final class UrlStringUtils {
         }
         final String document = url.getPath();
         final String[] pathParts = document.split("[\\//]");
-        for (int i = 0; i < pathParts.length - 2; i++) {
+        for (int i = 0; i < pathParts.length - 1; i++) {
             if (!pathParts[i].isEmpty()) {
                 importantParts.add(pathParts[i]);
             }
         }
         if (pathParts.length > 0 && !pathParts[pathParts.length - 1].isEmpty()) {
-            final String fileNameNoExt = pathParts[pathParts.length - 1].replaceAll("\\..*{0,5}$", "");
-            importantParts.add(fileNameNoExt);
+            final String tmp = pathParts[pathParts.length - 1];
+            final int pos = tmp.lastIndexOf('.');
+            if (pos > 1) {
+                importantParts.add(tmp.substring(0, pos));
+            } else if (pos == 0 && tmp.length()>1) {
+                importantParts.add(tmp.substring(1));
+            } else {
+                importantParts.add(tmp);
+            }
         }
         return importantParts;
     }

dependency-check-core/src/test/java/org/owasp/dependencycheck/utils/UrlStringUtilsTest.java

@@ -0,0 +1,74 @@
+/*
+ * This file is part of dependency-check-core.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ *
+ * Copyright (c) 2017 Jeremy Long. All Rights Reserved.
+ */
+package org.owasp.dependencycheck.utils;
+
+import java.util.Arrays;
+import java.util.List;
+import org.junit.Test;
+import static org.junit.Assert.*;
+
+/**
+ *
+ * @author jeremy long
+ */
+public class UrlStringUtilsTest {
+
+    /**
+     * Test of containsUrl method, of class UrlStringUtils.
+     */
+    @Test
+    public void testContainsUrl() {
+        String text = "Test of https://github.com";
+        assertTrue(UrlStringUtils.containsUrl(text));
+        text = "Test of github.com";
+        assertFalse(UrlStringUtils.containsUrl(text));
+    }
+
+    /**
+     * Test of isUrl method, of class UrlStringUtils.
+     */
+    @Test
+    public void testIsUrl() {
+        String text = "https://github.com";
+        assertTrue(UrlStringUtils.isUrl(text));
+        text = "simple text";
+        assertFalse(UrlStringUtils.isUrl(text));
+    }
+
+    /**
+     * Test of extractImportantUrlData method, of class UrlStringUtils.
+     */
+    @Test
+    public void testExtractImportantUrlData() throws Exception {
+        String text = "http://github.com/jeremylong/DependencyCheck/index.html";
+        List<String> expResult = Arrays.asList("github", "jeremylong", "DependencyCheck", "index");;
+        List<String> result = UrlStringUtils.extractImportantUrlData(text);
+        assertEquals(expResult, result);
+        
+        text = "http://github.com/jeremylong/DependencyCheck/.gitignore";
+        expResult = Arrays.asList("github", "jeremylong", "DependencyCheck", "gitignore");;
+        result = UrlStringUtils.extractImportantUrlData(text);
+        assertEquals(expResult, result);
+        
+        text = "http://github.com/jeremylong/DependencyCheck/something";
+        expResult = Arrays.asList("github", "jeremylong", "DependencyCheck", "something");;
+        result = UrlStringUtils.extractImportantUrlData(text);
+        assertEquals(expResult, result);
+    }
+
+}