checkstyle fixes

checkstyle.xml

@@ -82,16 +82,6 @@
     <!--
     JavaDoc regexp checks
     -->
-    <module name="RegexpSingleline">
-        <property name="format" value="\* +@return +[^A-Z]"/>
-        <property name="fileExtensions" value="java"/>
-        <property name="message" value="@return tag description should start with capital letter"/>
-    </module>
-    <module name="RegexpSingleline">
-        <property name="format" value="\* +@param +\w+ +[^A-Z]"/>
-        <property name="fileExtensions" value="java"/>
-        <property name="message" value="@param tag description should start with capital letter"/>
-    </module>
     <module name="RegexpSingleline">
         <property name="format" value="/\*\* +[^A-Z\{]"/>
         <property name="fileExtensions" value="java"/>
@@ -167,7 +157,6 @@
         <module name="EmptyStatement"/>
         <module name="EqualsAvoidNull"/>
         <module name="EqualsHashCode"/>
-        <module name="FinalLocalVariable"/>
         <module name="HiddenField">
             <property name="ignoreConstructorParameter" value="true"/>
         </module>
@@ -267,9 +256,6 @@
         <module name="LocalVariableName">
             <property name="format" value="^(id|[A-Za-z]{3,20})$"/>
         </module>
-        <module name="CatchParameterName">
-            <property name="format" value="^(ex|[A-Za-z]{3,20})$"/>
-        </module>
         <module name="MemberName">
             <property name="format" value="^(id|[A-Za-z]{3,20})$"/>
         </module>

src/main/java/com/amihaiemil/charles/AbstractWebCrawl.java

@@ -23,12 +23,14 @@
  * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  * ARISING IN ANY WAY OUT OF THE USE
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */package com.amihaiemil.charles;
+ */
+package com.amihaiemil.charles;
 
 import org.openqa.selenium.WebDriver;
 
 /**
- * An abstract webcrawl - contains the webdriver and other common data of each crawl.
+ * An abstract webcrawl - contains the webdriver and other common data of each
+ * crawl.
  * @author Mihai Andronache (amihaiemil@gmail.com)
  * @version $Id$
  * @since 1.0.0
@@ -39,37 +41,74 @@ public abstract class AbstractWebCrawl implements WebCrawl {
     /**
      * WebDriver.
      */
-    protected WebDriver driver;
+    private final WebDriver driver;
 
     /**
      * Ignored pages patterns.
      */
-    protected IgnoredPatterns ignoredLinks;
+    private final IgnoredPatterns ignoredLinks;
 
     /**
      * Repo to export the pages to.
      */
-    protected Repository repo;
+    private final Repository repo;
 
     /**
      * Pages are crawled and exported in batches in order to avoid flooding
      * the memory if there are many pages on a website. Default value is 100.
      */
-    protected int batchSize;
+    private final int batchSize;
 
     /**
      * Ctor.
      * @param webd Selenium WebDriver.
      * @param igp Ignored patterns.
      * @param repo Repository to export the crawled pages into.
      * @param batch Size of a crawl batch.
+     * @checkstyle ParameterNumber (6 lines)
      */
-    public AbstractWebCrawl(WebDriver webd, IgnoredPatterns igp, Repository repo, int batch) {
+    public AbstractWebCrawl(
+        final WebDriver webd, final IgnoredPatterns igp,
+        final Repository repo, final int batch
+    ) {
         this.driver = webd;
         this.ignoredLinks = igp;
         this.repo = repo;
         this.batchSize = batch;
     }
 
+    @Override
     public abstract void crawl() throws DataExportException;
+
+    /**
+     * Fetch the used WebSriver.
+     * @return driver Webdriver of this crawl
+     */
+    public final WebDriver driver() {
+        return this.driver;
+    }
+
+    /**
+     * Fetch the used Repository.
+     * @return repo Repository where the pages are sent
+     */
+    public final Repository repo() {
+        return this.repo;
+    }
+
+    /**
+     * Fetch the ignored links patterns.
+     * @return ignoredLinks IgnoredPatterns of this crawl
+     */
+    public final IgnoredPatterns ignoredPatterns() {
+        return this.ignoredLinks;
+    }
+
+    /**
+     * Batch size. How many pages will be crawled at once?
+     * @return Integer batch size.
+     */
+    public final int batchSize() {
+        return this.batchSize;
+    }
 }

src/main/java/com/amihaiemil/charles/DataExportException.java

@@ -23,7 +23,8 @@
  * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  * ARISING IN ANY WAY OUT OF THE USE
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */package com.amihaiemil.charles;
+ */
+package com.amihaiemil.charles;
 
 /**
  * Exception thrown if a page cannot be exported properly.

src/main/java/com/amihaiemil/charles/GraphCrawl.java

@@ -98,9 +98,9 @@ public GraphCrawl(
 
     @Override
     public void crawl() throws DataExportException {
-        if(!this.ignoredLinks.contains(this.index.getHref())) {
+        if(!this.ignoredPatterns().contains(this.index.getHref())) {
             List<WebPage> pages = new ArrayList<WebPage>();
-            WebPage indexSnapshot =  new LiveWebPage(this.driver, this.index).snapshot();
+            WebPage indexSnapshot =  new LiveWebPage(this.driver(), this.index).snapshot();
             pages.add(indexSnapshot);
 
             Set<Link> crawledLinks = new HashSet<Link>();
@@ -114,22 +114,22 @@ public void crawl() throws DataExportException {
             if(toCrawl.size() > 0) {
                 Link link = toCrawl.remove(0);
                 while(toCrawl.size() > 0) {
-                    if(this.ignoredLinks.contains(link.getHref())) {
+                    if(this.ignoredPatterns().contains(link.getHref())) {
                         link = toCrawl.remove(0);
                         continue;
                     }
                     boolean notCrawledAlready = crawledLinks.add(link);
                     if(notCrawledAlready) {
-                        WebPage snapshotCrawled = new LiveWebPage(this.driver, link).snapshot();
+                        WebPage snapshotCrawled = new LiveWebPage(this.driver(), link).snapshot();
                         pages.add(snapshotCrawled);
                         this.checkBatchSize(pages);
                         toCrawl.addAll(snapshotCrawled.getLinks());   
                     }
                     link = toCrawl.remove(0);
                 }
             }
-            this.repo.export(pages);
-            this.driver.quit();
+            this.repo().export(pages);
+            this.driver().quit();
         }
     }
 
@@ -140,8 +140,8 @@ public void crawl() throws DataExportException {
      * @throws DataExportException If something goes wrong during processing of crawled pages.
      */
     private void checkBatchSize(List<WebPage> pages) throws DataExportException {
-        if(pages.size() == this.batchSize) {
-            this.repo.export(pages);
+        if(pages.size() == this.batchSize()) {
+            this.repo().export(pages);
             pages.clear();
         }
     }

src/main/java/com/amihaiemil/charles/InMemoryRepository.java

@@ -39,25 +39,25 @@
 * @author Mihai Andronache (amihaiemil@gmail.com)
 *
 */
-public class InMemoryRepository implements Repository {
+public final class InMemoryRepository implements Repository {
 
     /**
      * Holds all the crawled pages.
      */
-    private List<WebPage> pages = new ArrayList<WebPage>();
+    private final List<WebPage> pgs = new ArrayList<WebPage>();
 
     /**
      * Get all the pages from this Repository.
      * @return List of pages.
      */
     public List<WebPage> getCrawledPages() {
-        return this.pages;
+        return this.pgs;
     }
 
     @Override
-    public void export(List<WebPage> pages) throws DataExportException {
-        for(WebPage page : pages) {
-            this.pages.add(page);
+    public void export(final List<WebPage> pages) throws DataExportException {
+        for(final WebPage page : pages) {
+            this.pgs.add(page);
         }
     }
 }

src/main/java/com/amihaiemil/charles/Link.java

@@ -46,7 +46,7 @@ public Link() {
         this("", "");
     }
 
-    public Link(String text, String href) {
+    public Link(final String text, final String href) {
         this.text = text;
         this.href = href;
     }
@@ -55,15 +55,15 @@ public String getText() {
         return text;
     }
 
-    public void setText(String text) {
+    public void setText(final String text) {
         this.text = text;
     }
 
     public String getHref() {
         return href;
     }
 
-    public void setHref(String href) {
+    public void setHref(final String href) {
         this.href = href;
     }
 
@@ -75,8 +75,9 @@ public int hashCode() {
             result = prime * result + 0;
         } else {
             if (this.href.contains("#")) {
-                result = new Link("", href.substring(0, href.indexOf("#")))
-                        .hashCode();
+                result = new Link(
+                	         "", this.href.substring(0, this.href.indexOf("#"))
+                	     ).hashCode();
             } else {
                 if (this.href.endsWith("/")) {
                     result = prime
@@ -103,7 +104,7 @@ public boolean equals(Object obj) {
             return false;
         }
         Link other = (Link) obj;
-        if (href == null) {
+        if (this.href == null) {
             if (other.href != null)
                 return false;
         } else {
@@ -121,7 +122,7 @@ public boolean equals(Object obj) {
             }
 
             if (this.href.endsWith("/") && other.href.endsWith("/")) {
-                return this.href.substring(0, href.length() - 1).equals(
+                return this.href.substring(0, this.href.length() - 1).equals(
                         other.href.substring(0, other.href.length() - 1));
             } else if (this.href.endsWith("/")) {
                 return this.href.substring(0, href.length() - 1).equals(
@@ -144,7 +145,7 @@ public String toString() {
      * 
      * @return ture if valid, false otherwise.
      */
-    public boolean valid(String parentLoc) {
+    public boolean valid(final String parentLoc) {
 
         if (this.href != null && !this.href.startsWith("mailto")) {
             int slashIndex = parentLoc.indexOf("/", 8);// index of the first "/"

src/main/java/com/amihaiemil/charles/LiveWebPage.java

@@ -50,14 +50,14 @@ public final class LiveWebPage implements LivePage {
     /**
      * Visible anchors.
      */
-    @FindBys(@FindBy(tagName=("a")))
+    @FindBys(@FindBy(tagName="a"))
     @CacheLookup
     private List<WebElement> anchors;
 
     /**
      * Text content from the page.
      */
-    @FindBy(tagName=("body"))
+    @FindBy(tagName="body")
     @CacheLookup
     private WebElement body;
 

src/main/java/com/amihaiemil/charles/SitemapXmlCrawl.java

@@ -29,11 +29,9 @@
 import java.util.ArrayList;
 import java.util.List;
 import java.util.Set;
-
 import org.openqa.selenium.WebDriver;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
-
 import com.amihaiemil.charles.sitemap.SitemapXml;
 import com.amihaiemil.charles.sitemap.SitemapXmlLocation;
 import com.amihaiemil.charles.sitemap.Url;
@@ -98,24 +96,24 @@ public void crawl() throws DataExportException {
         List<WebPage> pages = new ArrayList<WebPage>();
         LOG.info("Started crawling the sitemap.xml...");
         for(Url url : this.urlset) {
-            if(this.ignoredLinks.contains(url.getLoc())) {
+            if(this.ignoredPatterns().contains(url.getLoc())) {
                 continue;
             }
             LOG.info("Crawling page " + url.getLoc() + "... ");
-            pages.add(new LiveWebPage(this.driver, url.getLoc()).snapshot());
+            pages.add(new LiveWebPage(this.driver(), url.getLoc()).snapshot());
             LOG.info("Done crawling page " + url.getLoc() + "!");
-            if(pages.size() == this.batchSize) {
-            try {
-                    this.repo.export(pages);
+            if(pages.size() == this.batchSize()) {
+                try {
+                    this.repo().export(pages);
                     pages.clear();
-            } catch (DataExportException e) {
+                } catch (DataExportException e) {
                     e.printStackTrace();
                 }
-        }
+            }
         }
         LOG.info("Finished crawling the sitemap.xml!");
-        this.repo.export(pages);
-        this.driver.quit();
+        this.repo().export(pages);
+        this.driver().quit();
     }
 
 }