└── Drill07.java


/Drill07.java:
--------------------------------------------------------------------------------
 1 | import java.util.HashSet;
 2 | import java.util.Set;
 3 | import java.util.regex.Matcher;
 4 | import java.util.regex.Pattern;
 5 | 
 6 | public class Drill07 {
 7 | 
 8 | 	/*
 9 | 	 * Takes in a string of the HTML source for a webPage.
10 | 	 * Returns a Set<String> containing all of the valid wiki link
11 | 	 * titles found in the HTML source.
12 | 	 * 
13 | 	 * In order for a link to be a valid wikiLink for our case, it must
14 | 	 * match the pattern:
15 | 	 * <a href="/wiki/Marine_mammal">
16 | 	 * and NOT contain the character '#' nor ':'. From the above match, you
17 | 	 * would then extract the link name which in this case is:
18 | 	 * Marine_mammal
19 | 	 * Refer to the testcases for more examples.
20 | 	 * 
21 | 	 * The fact that the input to this parameter is HTML is largely
22 | 	 * irrelevant to this function. It is just a string processing function.
23 | 	 * You take in a string, and need to search for matches to a specific
24 | 	 * pattern in that string. We will go through a brief description of HTML
25 | 	 * in class this week if you are curious.
26 | 	 * 
27 | 	 * Your first job is to pass all of the tests. This means you either have
28 | 	 * a functionally correct algorithm, or are close to one. However, performance
29 | 	 * and efficiency will be very important for this PA. After finding a functionally
30 | 	 * correct algorithm, spend time designing other approaches to see if
31 | 	 * you can determine a more efficient approach. It will pay off when
32 | 	 * writing the PA! i.e. do not do anything inefficient, for
33 | 	 * instance, you should only go through the string once.
34 | 	 */
35 | 	public static Set<String> findWikiLinks(String html) {
36 | 		Set<String> result = new HashSet<String>();
37 | 		String regex = "<a href=\"/wiki/(.*?)\">";
38 | 		Pattern pattern = Pattern.compile(regex);
39 | 		Matcher matcher = pattern.matcher(html);
40 | 		while (matcher.find()) {
41 | 			String name = matcher.group(1);
42 | 			if (name.contains(Character.toString('"'))) {
43 | 				int end = name.indexOf('"');
44 | 				name = name.substring(0, end);
45 | 			}
46 | 			if (!(name.contains(":") || name.contains("#"))) {
47 | 				result.add(name);
48 | 			}
49 | 		}
50 | 		return result;
51 | 	}
52 | 
53 | }
54 | 


--------------------------------------------------------------------------------