Extract languages from wiki page #3

baudoliver7 · Dec 9, 2021 · 822b15f · 822b15f
1 parent fd36aa2
commit 822b15f
Show file tree

Hide file tree

Showing 3 changed files with 30 additions and 12 deletions.
diff --git a/README.md b/README.md
@@ -26,12 +26,12 @@ You can run it by these commands :
 
 ### From Maven
 ``` cmd
-mvn clean pre-integration-test -Pstart-app
+mvn clean integration-test -Pstart-app
 ```
 
 ### From JAR file
 ``` cmd
-java -Dfile.encoding=utf-8 -cp ool-survey-X.X.X-jar-with-dependencies.jar com.ool.survey.Main
+java -jar ool-survey-X.X.X-jar-with-dependencies.jar
 ``` 
 
 ## How to contribute

diff --git a/pom.xml b/pom.xml
@@ -84,24 +84,33 @@ SOFTWARE.
       <artifactId>hamcrest-core</artifactId>
       <version>2.2</version>
     </dependency>
+    <dependency>
+      <groupId>com.jcabi</groupId>
+      <artifactId>jcabi-xml</artifactId>
+      <version>0.23.1</version>
+    </dependency>
   </dependencies>
   <build>
     <plugins>
       <plugin>
-        <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-assembly-plugin</artifactId>
-        <configuration>
-          <descriptorRefs>
-            <descriptorRef>jar-with-dependencies</descriptorRef>
-          </descriptorRefs>
-        </configuration>
         <executions>
           <execution>
             <id>make-assembly</id>
             <phase>package</phase>
             <goals>
               <goal>single</goal>
             </goals>
+            <configuration>
+              <archive>
+                <manifest>
+                  <mainClass>com.ool.survey.Main</mainClass>
+                </manifest>
+              </archive>
+              <descriptorRefs>
+                <descriptorRef>jar-with-dependencies</descriptorRef>
+              </descriptorRefs>
+            </configuration>
           </execution>
         </executions>
       </plugin>

diff --git a/src/main/java/com/ool/survey/Main.java b/src/main/java/com/ool/survey/Main.java
@@ -25,17 +25,17 @@
 
 import com.jcabi.http.Request;
 import com.jcabi.http.request.JdkRequest;
+import com.jcabi.xml.XML;
+import com.jcabi.xml.XMLDocument;
 import java.io.IOException;
+import java.util.List;
 import javax.ws.rs.core.HttpHeaders;
 import javax.ws.rs.core.MediaType;
 
 /**
  * Class Entrance.
  *
  * @since 0.1
- * @todo #1:30min Extract languages from loaded wiki page.
- *  We have loaded the entire page of wiki. Now, we want to extract
- *  all languages present in its content.
  * @checkstyle HideUtilityClassConstructorCheck (100 lines)
  */
 @SuppressWarnings({"PMD.SystemPrintln", "PMD.UseUtilityClass"})
@@ -47,6 +47,12 @@ public final class Main {
     private static final String WIKI_PAGE =
         "https://en.wikipedia.org/wiki/List_of_programming_languages";
 
+    /**
+     * Xpath query for retrieve languages in Wiki page.
+     */
+    private static final String QUERY_WIKI_PAGE =
+        "//div[@id='mw-content-text']/div/div/ul/li/a/text()";
+
     /**
      * Entrance.
      * @param args Arguments
@@ -59,6 +65,9 @@ public static void main(final String... args) throws IOException {
             .header(HttpHeaders.ACCEPT, MediaType.TEXT_HTML)
             .fetch()
             .body();
-        System.out.println(html);
+        final XML xml = new XMLDocument(html);
+        final List<String> languages = xml.xpath(Main.QUERY_WIKI_PAGE);
+        System.out.println(languages);
+        System.out.println(languages.size());
     }
 }