programming-examples/java/Data_Structures/TrieST.java

 

import edu.princeton.cs.introcs.StdIn;
import edu.princeton.cs.introcs.StdOut;

/*************************************************************************
 *  Compilation:  javac TrieST.java
 *  Execution:    java TrieST < words.txt
 *  Dependencies: StdIn.java
 *
 *  A string symbol table for extended ASCII strings, implemented
 *  using a 256-way trie.
 *
 *  % java TrieST < shellsST.txt 
 *  by 4
 *  sea 6
 *  sells 1
 *  she 0
 *  shells 3
 *  shore 7
 *  the 5
 *
 *************************************************************************/

/**
 *  The  TrieST  class represents an symbol table of key-value
 *  pairs, with string keys and generic values.
 *  It supports the usual  put ,  get ,  contains ,
 *   delete ,  size , and  is-empty  methods.
 *  It also provides character-based methods for finding the string
 *  in the symbol table that is the  longest prefix  of a given prefix,
 *  finding all strings in the symbol table that  start with  a given prefix,
 *  and finding all strings in the symbol table that  match  a given pattern.
 *  A symbol table implements the  associative array  abstraction:
 *  when associating a value with a key that is already in the symbol table,
 *  the convention is to replace the old value with the new value.
 *  Unlike {@link java.util.Map}, this class uses the convention that
 *  values cannot be  null &mdash;setting the
 *  value associated with a key to  null  is equivalent to deleting the key
 *  from the symbol table.
 *   
 *  This implementation uses a 256-way trie.
 *  The  put ,  contains ,  delete , and
 *   longest prefix  operations take time proportional to the length
 *  of the key (in the worst case). Construction takes constant time.
 *  The  size , and  is-empty  operations take constant time.
 *  Construction takes constant time.
 *   
 *  For additional documentation, see <a href="http://algs4.cs.princeton.edu/52trie">Section 5.2</a> of
 *   Algorithms, 4th Edition  by Robert Sedgewick and Kevin Wayne.
 */
public class TrieST<Value> {
    private static final int R = 256;        // extended ASCII


    private Node root;      // root of trie
    private int N;          // number of keys in trie

    // R-way trie node
    private static class Node {
        private Object val;
        private Node[] next = new Node[R];
    }

    public TrieST() {
    }

   /**
     * Initializes an empty string symbol table.
     */

    /**
     * Returns the value associated with the given key.
     * @param key the key
     * @return the value associated with the given key if the key is in the symbol table
     *     and  null  if the key is not in the symbol table
     * @throws NullPointerException if  key  is  null 
     */
    public Value get(String key) {
        Node x = get(root, key, 0);
        if (x == null) return null;
        return (Value) x.val;
    }

    /**
     * Does this symbol table contain the given key?
     * @param key the key
     * @return  true  if this symbol table contains  key  and
     *      false  otherwise
     * @throws NullPointerException if  key  is  null 
     */
    public boolean contains(String key) {
        return get(key) != null;
    }

    private Node get(Node x, String key, int d) {
        if (x == null) return null;
        if (d == key.length()) return x;
        char c = key.charAt(d);
        return get(x.next[c], key, d+1);
    }

    /**
     * Inserts the key-value pair into the symbol table, overwriting the old value
     * with the new value if the key is already in the symbol table.
     * If the value is  null , this effectively deletes the key from the symbol table.
     * @param key the key
     * @param val the value
     * @throws NullPointerException if  key  is  null 
     */
    public void put(String key, Value val) {
        if (val == null) delete(key);
        else root = put(root, key, val, 0);
    }

    private Node put(Node x, String key, Value val, int d) {
        if (x == null) x = new Node();
        if (d == key.length()) {
            if (x.val == null) N++;
            x.val = val;
            return x;
        }
        char c = key.charAt(d);
        x.next[c] = put(x.next[c], key, val, d+1);
        return x;
    }

    /**
     * Returns the number of key-value pairs in this symbol table.
     * @return the number of key-value pairs in this symbol table
     */
    public int size() {
        return N;
    }

    /**
     * Is this symbol table empty?
     * @return  true  if this symbol table is empty and  false  otherwise
     */
    public boolean isEmpty() {
        return size() == 0;
    }

    /**
     * Returns all keys in the symbol table as an  Iterable .
     * To iterate over all of the keys in the symbol table named  st ,
     * use the foreach notation:  for (Key key : st.keys()) .
     * @return all keys in the sybol table as an  Iterable 
     */
    public Iterable<String> keys() {
        return keysWithPrefix("");
    }

    /**
     * Returns all of the keys in the set that start with  prefix .
     * @param prefix the prefix
     * @return all of the keys in the set that start with  prefix ,
     *     as an iterable
     */
    public Iterable<String> keysWithPrefix(String prefix) {
        Queue<String> results = new Queue<String>();
        Node x = get(root, prefix, 0);
        collect(x, new StringBuilder(prefix), results);
        return results;
    }

    private void collect(Node x, StringBuilder prefix, Queue<String> results) {
        if (x == null) return;
        if (x.val != null) results.enqueue(prefix.toString());
        for (char c = 0; c < R; c++) {
            prefix.append(c);
            collect(x.next[c], prefix, results);
            prefix.deleteCharAt(prefix.length() - 1);
        }
    }

    /**
     * Returns all of the keys in the symbol table that match  pattern ,
     * where . symbol is treated as a wildcard character.
     * @param pattern the pattern
     * @return all of the keys in the symbol table that match  pattern ,
     *     as an iterable, where . is treated as a wildcard character.
     */
    public Iterable<String> keysThatMatch(String pattern) {
        Queue<String> results = new Queue<String>();
        collect(root, new StringBuilder(), pattern, results);
        return results;
    }

    private void collect(Node x, StringBuilder prefix, String pattern, Queue<String> results) {
        if (x == null) return;
        int d = prefix.length();
        if (d == pattern.length() && x.val != null)
            results.enqueue(prefix.toString());
        if (d == pattern.length())
            return;
        char c = pattern.charAt(d);
        if (c == '.') {
            for (char ch = 0; ch < R; ch++) {
                prefix.append(ch);
                collect(x.next[ch], prefix, pattern, results);
                prefix.deleteCharAt(prefix.length() - 1);
            }
        }
        else {
            prefix.append(c);
            collect(x.next[c], prefix, pattern, results);
            prefix.deleteCharAt(prefix.length() - 1);
        }
    }

    /**
     * Returns the string in the symbol table that is the longest prefix of  query ,
     * or  null , if no such string.
     * @param query the query string
     * @throws NullPointerException if  query  is  null 
     * @return the string in the symbol table that is the longest prefix of  query ,
     *     or  null  if no such string
     */
    public String longestPrefixOf(String query) {
        int length = longestPrefixOf(root, query, 0, 0);
        return query.substring(0, length);
    }

    // returns the length of the longest string key in the subtrie
    // rooted at x that is a prefix of the query string,
    // assuming the first d character match and we have already
    // found a prefix match of length length
    private int longestPrefixOf(Node x, String query, int d, int length) {
        if (x == null) return length;
        if (x.val != null) length = d;
        if (d == query.length()) return length;
        char c = query.charAt(d);
        return longestPrefixOf(x.next[c], query, d+1, length);
    }

    /**
     * Removes the key from the set if the key is present.
     * @param key the key
     * @throws NullPointerException if  key  is  null 
     */
    public void delete(String key) {
        root = delete(root, key, 0);
    }

    private Node delete(Node x, String key, int d) {
        if (x == null) return null;
        if (d == key.length()) {
            if (x.val != null) N--;
            x.val = null;
        }
        else {
            char c = key.charAt(d);
            x.next[c] = delete(x.next[c], key, d+1);
        }

        // remove subtrie rooted at x if it is completely empty
        if (x.val != null) return x;
        for (int c = 0; c < R; c++)
            if (x.next[c] != null)
                return x;
        return null;
    }

    /**
     * Unit tests the  TrieSET  data type.
     */
    public static void main(String[] args) {

        // build symbol table from standard input
        TrieST<Integer> st = new TrieST<Integer>();
        for (int i = 0; !StdIn.isEmpty(); i++) {
            String key = StdIn.readString();
            st.put(key, i);
        }

        // print results
        if (st.size() < 100) {
            StdOut.println("keys(\"\"):");
            for (String key : st.keys()) {
                StdOut.println(key + " " + st.get(key));
            }
            StdOut.println();
        }

        StdOut.println("longestPrefixOf(\"shellsort\"):");
        StdOut.println(st.longestPrefixOf("shellsort"));
        StdOut.println();

        StdOut.println("keysWithPrefix(\"shor\"):");
        for (String s : st.keysWithPrefix("shor"))
            StdOut.println(s);
        StdOut.println();

        StdOut.println("keysThatMatch(\".he.l.\"):");
        for (String s : st.keysThatMatch(".he.l."))
            StdOut.println(s);
    }
}