53 lines
1.6 KiB
Java
53 lines
1.6 KiB
Java
import java.util.*;
|
|
|
|
public class InvertedIndex {
|
|
public static void main(String[] args) {
|
|
List<String> docs = new ArrayList<>();
|
|
docs.add("Raiders of the Lost Ark");
|
|
docs.add("The Temple of Doom");
|
|
docs.add("The Last Crusade");
|
|
|
|
Map<String, Set<String>> result = createIndex(docs);
|
|
System.out.println(docs);
|
|
System.out.println();
|
|
System.out.println(result);
|
|
}
|
|
|
|
// TODO: Write and document your createIndex method here
|
|
|
|
public static Map<String, Set<String>> createIndex(List<String> docs) {
|
|
Map<String, Set<String>> index = new TreeMap<>();
|
|
Set<String> uniqueWords = getUniqueWords(docs);
|
|
|
|
for (String uniqueWord : uniqueWords) {
|
|
index.put(uniqueWord.toLowerCase(), new HashSet<String>());
|
|
}
|
|
|
|
for (String word : index.keySet()) {
|
|
for (int i = 0; i < docs.size(); i++) {
|
|
Scanner wordScanner = new Scanner(docs.get(i));
|
|
while (wordScanner.hasNext()) {
|
|
if (wordScanner.next().equalsIgnoreCase(word)) {
|
|
index.get(word).add(docs.get(i));
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return index;
|
|
}
|
|
|
|
public static Set<String> getUniqueWords(List<String> docs) {
|
|
Set<String> uniqueWords = new HashSet<>();
|
|
for (String title : docs) {
|
|
Scanner titleScanner = new Scanner(title);
|
|
while (titleScanner.hasNext()) {
|
|
uniqueWords.add(titleScanner.next());
|
|
}
|
|
titleScanner.close();
|
|
}
|
|
return uniqueWords;
|
|
}
|
|
|
|
|
|
}
|