Merge pull request #2992 from veteran2018/v6-dev

fix： （基于NFA模型 实现的AC自动机）优化 调用方 需要显示触发API 完成树优化 的问题

hutool-core/src/main/java/cn/hutool/core/text/dfa/NFA.java

@@ -4,19 +4,39 @@ import java.util.*;
 
 /**
  * <p>
- *
  * 基于非确定性有穷自动机（NFA） 实现的多模匹配工具
+ * </p>
  *
  * @author renyp
  */
 public class NFA {
+    /**
+     * AC树的根节点
+     */
     private final Node root;
+    /**
+     * 标记是否需要构建AC自动机，做树优化
+     */
+    private volatile boolean needBuildAc;
+
+    /**
+     * 内置锁，防止并发场景，并行建AC树，造成不可预知结果
+     */
+    private final Object buildAcLock;
+
+    /**
+     * 内置锁，防止并行插入，新节点建立后，被挂载到树上前 被篡改
+     */
+    private final Object insertTreeLock;
 
     /**
      * 默认构造
      */
     public NFA() {
         this.root = new Node();
+        this.needBuildAc = true;
+        this.buildAcLock = new Object();
+        this.insertTreeLock = new Object();
     }
 
     /**
@@ -24,7 +44,7 @@ public class NFA {
      *
      * @param words 添加的新词
      */
-	public NFA(final String... words) {
+    public NFA(String... words) {
         this();
         this.insert(words);
     }
@@ -34,25 +54,29 @@ public class NFA {
      *
      * @param word 添加的新词
      */
-	public void insert(final String word) {
+    public void insert(String word) {
+        synchronized (insertTreeLock) {
+            needBuildAc = true;
             Node p = root;
-		for (final char curr : word.toCharArray()) {
+            for (char curr : word.toCharArray()) {
-			if (p.next.get((int) curr) == null) {
+                int ind = curr;
-				p.next.put((int) curr, new Node());
+                if (p.next.get(ind) == null) {
+                    p.next.put(ind, new Node());
                 }
-			p = p.next.get((int) curr);
+                p = p.next.get(ind);
             }
             p.flag = true;
             p.str = word;
         }
+    }
 
     /**
      * 词库批量添加新词，初始化查找树
      *
      * @param words 添加的新词
      */
-	public void insert(final String... words) {
+    public void insert(String... words) {
-		for (final String word : words) {
+        for (String word : words) {
             this.insert(word);
         }
     }
@@ -60,16 +84,16 @@ public class NFA {
     /**
      * 构建基于NFA模型的 AC自动机
      */
-	public void buildAc() {
+    private void buildAc() {
-		final Queue<Node> queue = new LinkedList<>();
+        Queue<Node> queue = new LinkedList<>();
-		final Node p = root;
+        Node p = root;
-		for (final Integer key : p.next.keySet()) {
+        for (Integer key : p.next.keySet()) {
             p.next.get(key).fail = root;
             queue.offer(p.next.get(key));
         }
         while (!queue.isEmpty()) {
-			final Node curr = queue.poll();
+            Node curr = queue.poll();
-			for (final Integer key : curr.next.keySet()) {
+            for (Integer key : curr.next.keySet()) {
                 Node fail = curr.fail;
                 // 查找当前节点匹配失败，他对应等效匹配的节点是哪个
                 while (fail != null && fail.next.get(key) == null) {
@@ -85,26 +109,33 @@ public class NFA {
                 queue.offer(curr.next.get(key));
             }
         }
+        needBuildAc = false;
     }
 
     /**
      * @param text 查询的文本（母串）
-	 * @return 关键字列表
      */
-	public List<FoundWord> find(final String text) {
+    public List<FoundWord> find(String text) {
         return this.find(text, true);
     }
 
     /**
      * @param text           查找的文本（母串）
      * @param isDensityMatch 是否密集匹配
-	 * @return 关键字列表
      */
-	public List<FoundWord> find(final String text, final boolean isDensityMatch) {
+    public List<FoundWord> find(String text, boolean isDensityMatch) {
-		final List<FoundWord> ans = new ArrayList<>();
+        // double check，防止重复无用的 buildAC
-		Node p = root, k;
+        if (needBuildAc) {
+            synchronized (buildAcLock) {
+                if (needBuildAc) {
+                    this.buildAc();
+                }
+            }
+        }
+        List<FoundWord> ans = new ArrayList<>();
+        Node p = root, k = null;
         for (int i = 0, len = text.length(); i < len; i++) {
-			final int ind = text.charAt(i);
+            int ind = text.charAt(i);
             // 状态转移(沿着fail指针链接的链表，此处区别于DFA模型)
             while (p != null && p.next.get(ind) == null) {
                 p = p.fail;
@@ -130,11 +161,24 @@ public class NFA {
         return ans;
     }
 
+
     private static class Node {
 
+        /**
+         * 当前节点是否是一个单词的结尾
+         */
         boolean flag;
+        /**
+         * 指向 当前节点匹配失败应该跳转的下个节点
+         */
         Node fail;
+        /**
+         * 以当前节点结尾的单词
+         */
         String str;
+        /**
+         * 当前节点的子节点
+         */
         Map<Integer, Node> next;
 
         public Node() {

hutool-core/src/test/java/cn/hutool/core/text/dfa/NFATest.java

@@ -16,7 +16,7 @@ public class NFATest {
 	public void testFind() {
 		final NFA NFA = new NFA();
 		NFA.insert("say", "her", "he", "she", "shr");
-		NFA.buildAc();
+//		NFA.buildAc();
 
 		final WordTree wordTree = new WordTree();
 		wordTree.addWords("say", "her", "he", "she", "shr");
@@ -53,7 +53,7 @@ public class NFATest {
 	public void testFindNotDensity() {
 		final NFA NFA = new NFA();
 		NFA.insert("say", "her", "he", "she", "shr");
-		NFA.buildAc();
+//		NFA.buildAc();
 
 		final WordTree wordTree = new WordTree();
 		wordTree.addWords("say", "her", "he", "she", "shr");
@@ -89,7 +89,7 @@ public class NFATest {
 		stopWatch.start("automaton_char_buid_find");
 		final NFA NFALocal = new NFA();
 		NFALocal.insert("say", "her", "he", "she", "shr");
-		NFALocal.buildAc();
+//		NFALocal.buildAc();
 		final List<FoundWord> ans1 = NFALocal.find(input);
 		stopWatch.stop();
 
@@ -124,7 +124,7 @@ public class NFATest {
 		stopWatch.start("automaton_cn_build_find");
 		final NFA NFALocal = new NFA();
 		NFALocal.insert("赵", "赵啊", "赵啊三");
-		NFALocal.buildAc();
+//		NFALocal.buildAc();
 
 		final List<FoundWord> result = NFALocal.find(input);
 		stopWatch.stop();
@@ -161,7 +161,7 @@ public class NFATest {
 
 		final NFA NFALocal = new NFA();
 		NFALocal.insert("赵", "赵啊", "赵啊三");
-		NFALocal.buildAc();
+//		NFALocal.buildAc();
 
 		stopWatch.start("automaton_cn_find");
 		final List<FoundWord> result = NFALocal.find(input);
@@ -200,7 +200,7 @@ public class NFATest {
 
 		final NFA NFALocal = new NFA();
 		NFALocal.insert("赵", "赵啊", "赵啊三");
-		NFALocal.buildAc();
+//		NFALocal.buildAc();
 
 		stopWatch.start("automaton_cn_find_not_density");
 		final List<FoundWord> result = NFALocal.find(input, false);