算法4第5章单词查找树和三向单词查找树讲解-CSDN博客

本文链接：https://blog.csdn.net/cyj88jyc/article/details/97021257

单词查找树

//跟排序一样，对字符串有更高效的查找算法可以实现以字符串作为key的符号表
//这种符号表通过一种叫单词查找树的数据结构来实现，示意图如下：

//根节点无字母，每个节点都可能有0-R个子节点，某节点的值不为空则表示从根节点到该节点的字符构成的字符串key在符号表中有对应的value.
//代码实现如下：
public class TrieST<Value> {
private static final int R = 256; // extended ASCII，字母表的大小

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; //节点的值
        private Node[] next = new Node[R];//节点的子节点，以字母表中的每个字母为索引
    }

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

    /**
     * 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}
     */
    public Value get(String 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(String key) {
        if (key == null) throw new IllegalArgumentException("argument to contains() is null");
        return get(key) != null;
    }
//以节点x做为根节点，递归查找从key的第d个字母开始匹配的键，直到d == key.length()
    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 {@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(String 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);
    }
//以x做为跟节点，存入key的第d个字母，如果d==key.length,则把val存入x节点
    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 {@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<String> keys() {
        return keysWithPrefix("");
    }

    /**
     * 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<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);
        }
    }

    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 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, 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 IllegalArgumentException if {@code key} is {@code null}
     */
    public void delete(String key) {
        if (key == null) throw new IllegalArgumentException("argument to delete() is null");
        root = delete(root, key, 0);
    }
    //以节点x做为根节点，递归查找从key的第d个字母开始匹配的键，直到d == key.length()删除键对应的value
    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);
        }
        //递归删除所有无效的节点，如果某节点所有子节点的值都为空，则这些子节点都要删除
        // 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 {@code TrieST} data type.
     *
     * @param args the command-line arguments
     */
    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("longestPrefixOf(\"quicksort\"):");
        StdOut.println(st.longestPrefixOf("quicksort"));
        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);
    }
}

//三向单词查找树
//普通单词查找树一个节点占据字母表大小的空间，如果字母表比较大就不太现实了，
//三向单词查找树每个节点只含有一个字符,三条链接和一个值，三条链接分别对应小于,等于,大于节点字母的所有节点，示意图如下

//代码实现如下：
public class TST<Value> {
private int n; // size
private Node<Value> root; // root of TST

    private static class Node<Value> {
        private char c;                        // character
        private Node<Value> left, mid, right; // left, middle, and right subtries
        private Value val;                     // value associated with string
    }

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

    /**
     * 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;
    }

    /**
     * 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}
     */
    public Value get(String key) {
        if (key == null) {
            throw new IllegalArgumentException("calls get() with null argument");
        }
        if (key.length() == 0) throw new IllegalArgumentException("key must have length >= 1");
        Node<Value> x = get(root, key, 0);
        if (x == null) return null;
        return x.val;
    }

    // return subtrie corresponding to given key
    private Node<Value> get(Node<Value> x, String key, int d) {
        if (x == null) return null;
        if (key.length() == 0) throw new IllegalArgumentException("key must have length >= 1");
        char c = key.charAt(d);
        if      (c < x.c)              return get(x.left, key, d);
        else if (c > x.c)              return get(x.right, key, d);
        else if (d < key.length() - 1) return get(x.mid,   key, d+1);
        else                           return x;
    }

    private Node<Value> put(Node<Value> x, String key, Value val, int d) {
        char c = key.charAt(d);
        if (x == null) {
            x = new Node<Value>();
            x.c = c;
        }
        if      (c < x.c)               x.left = put(x.left, key, val, d);
        else if (c > x.c)               x.right = put(x.right, key, val, d);
        else if (d < key.length() - 1) x.mid   = put(x.mid,   key, val, d+1);
        else                            x.val   = val;
        return x;
    }

    /**
     * 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 String longestPrefixOf(String query) {
        if (query == null) {
            throw new IllegalArgumentException("calls longestPrefixOf() with null argument");
        }
        if (query.length() == 0) return null;
        int length = 0;
        Node<Value> x = root;
        int i = 0;
        while (x != null && i < query.length()) {
            char c = query.charAt(i);
            if      (c < x.c) x = x.left;
            else if (c > x.c) x = x.right;
            else {
                i++;
                if (x.val != null) length = i;
                x = x.mid;
            }
        }
        return query.substring(0, length);
    }

    /**
     * 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
     * @throws IllegalArgumentException if {@code prefix} is {@code null}
     */
    public Iterable<String> keysWithPrefix(String prefix) {
        if (prefix == null) {
            throw new IllegalArgumentException("calls keysWithPrefix() with null argument");
        }
        Queue<String> queue = new Queue<String>();
        Node<Value> x = get(root, prefix, 0);
        if (x == null) return queue;
        if (x.val != null) queue.enqueue(prefix);
        collect(x.mid, new StringBuilder(prefix), queue);
        return queue;
    }

    // all keys in subtrie rooted at x with given prefix
    private void collect(Node<Value> x, StringBuilder prefix, Queue<String> queue) {
        if (x == null) return;
        collect(x.left, prefix, queue);
        if (x.val != null) queue.enqueue(prefix.toString() + x.c);
        collect(x.mid,   prefix.append(x.c), queue);
        prefix.deleteCharAt(prefix.length() - 1);
        collect(x.right, prefix, queue);
    }

    /**
     * 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<String> keysThatMatch(String pattern) {
        Queue<String> queue = new Queue<String>();
        collect(root, new StringBuilder(), 0, pattern, queue);
        return queue;
    }

    private void collect(Node<Value> x, StringBuilder prefix, int i, String pattern, Queue<String> queue) {
        if (x == null) return;
        char c = pattern.charAt(i);
        if (c == '.' || c < x.c) collect(x.left, prefix, i, pattern, queue);
        if (c == '.' || c == x.c) {
            if (i == pattern.length() - 1 && x.val != null) queue.enqueue(prefix.toString() + x.c);
            if (i < pattern.length() - 1) {
                collect(x.mid, prefix.append(x.c), i+1, pattern, queue);
                prefix.deleteCharAt(prefix.length() - 1);
            }
        }
        if (c == '.' || c > x.c) collect(x.right, prefix, i, pattern, queue);
    }

    /**
     * Unit tests the {@code TST} data type.
     *
     * @param args the command-line arguments
     */
    public static void main(String[] args) {

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

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

        StdOut.println("longestPrefixOf(\"shell\"):");
        StdOut.println(st.longestPrefixOf("shell"));
        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);
    }
}