RTrie.java

/**
 *  The {@code TrieST} class represents an symbol table of key-value
 *  pairs, with string keys and generic values.
 *  It supports the usual <em>put</em>, <em>get</em>, <em>contains</em>,
 *  <em>delete</em>, <em>size</em>, and <em>is-empty</em> methods.
 *  It also provides character-based methods for finding the string
 *  in the symbol table that is the <em>longest prefix</em> of a given prefix,
 *  finding all strings in the symbol table that <em>start with</em> a given prefix,
 *  and finding all strings in the symbol table that <em>match</em> a given pattern.
 *  A symbol table implements the <em>associative array</em> 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 {@code null}—setting the
 *  value associated with a key to {@code null} is equivalent to deleting the key
 *  from the symbol table.
 *  <p>
 *  This implementation uses a 256-way trie.
 *  The <em>put</em>, <em>contains</em>, <em>delete</em>, and
 *  <em>longest prefix</em> operations take time proportional to the length
 *  of the key (in the worst case). Construction takes constant time.
 *  The <em>size</em>, and <em>is-empty</em> operations take constant time.
 *  Construction takes constant time.
 *  <p>
 *  For additional documentation, see <a href="https://algs4.cs.princeton.edu/52trie">Section 5.2</a> of
 *  <i>Algorithms, 4th Edition</i> by Robert Sedgewick and Kevin Wayne.
 */
public class RTrie<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];
    }

   /**
     * Initializes an empty string symbol table.
     */
    public RTrie() {
    }


    /**
     * 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 {@code null} if the key is not in the symbol table
     * @throws IllegalArgumentException if {@code key} is {@code null}
     */
    @SuppressWarnings("unchecked")
	public Value get(StringBuilder key) {
        if (key == null) throw new IllegalArgumentException("argument to get() is null");
        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 {@code true} if this symbol table contains {@code key} and
     *     {@code false} otherwise
     * @throws IllegalArgumentException if {@code key} is {@code null}
     */
    public boolean contains(StringBuilder key) {
        if (key == null) throw new IllegalArgumentException("argument to contains() is null");
        return get(key) != null;
    }

    private Node get(Node x, StringBuilder 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 {@code null}, this effectively deletes the key from the symbol table.
     * @param key the key
     * @param val the value
     * @throws IllegalArgumentException if {@code key} is {@code null}
     */
    public void put(StringBuilder key, Value val) {
        if (key == null) throw new IllegalArgumentException("first argument to put() is null");
        if (val == null) delete(key);
        else root = put(root, key, val, 0);
    }

    private Node put(Node x, StringBuilder 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 {@code true} if this symbol table is empty and {@code false} otherwise
     */
    public boolean isEmpty() {
        return size() == 0;
    }

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

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

    private void collect(Node x, StringBuilder prefix, Queue<StringBuilder> results) {
        if (x == null) return;
        if (x.val != null) results.enqueue(prefix);
        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 {@code pattern},
     * where . symbol is treated as a wildcard character.
     * @param pattern the pattern
     * @return all of the keys in the symbol table that match {@code pattern},
     *     as an iterable, where . is treated as a wildcard character.
     */
    public Iterable<StringBuilder> keysThatMatch(StringBuilder pattern) {
        Queue<StringBuilder> results = new Queue<StringBuilder>();
        collect(root, new StringBuilder(), pattern, results);
        return results;
    }

    private void collect(Node x, StringBuilder prefix, StringBuilder pattern, Queue<StringBuilder> results) {
        if (x == null) return;
        int d = prefix.length();
        if (d == pattern.length() && x.val != null)
            results.enqueue(prefix);
        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 {@code query},
     * or {@code null}, if no such string.
     * @param query the query string
     * @return the string in the symbol table that is the longest prefix of {@code query},
     *     or {@code null} if no such string
     * @throws IllegalArgumentException if {@code query} is {@code null}
     */
    public StringBuilder longestPrefixOf(StringBuilder query) {
        if (query == null) throw new IllegalArgumentException("argument to longestPrefixOf() is null");
        int length = longestPrefixOf(root, query, 0, -1);
        if (length == -1) return null;
        else return new StringBuilder(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 given length (-1 if no such match)
    private int longestPrefixOf(Node x, StringBuilder 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 IllegalArgumentException if {@code key} is {@code null}
     */
    public void delete(StringBuilder key) {
        if (key == null) throw new IllegalArgumentException("argument to delete() is null");
        root = delete(root, key, 0);
    }

    private Node delete(Node x, StringBuilder 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;
    }
}