AC自动机实现

hutool-core/src/main/java/org/dromara/hutool/core/text/CharSequenceUtil.java

@@ -43,10 +43,7 @@ import java.util.HashSet;
 import java.util.LinkedList;
 import java.util.List;
 import java.util.Set;
-import java.util.function.Function;
+import java.util.function.*;
-import java.util.function.Predicate;
-import java.util.function.Supplier;
-import java.util.function.UnaryOperator;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
@@ -1730,7 +1727,7 @@ public class CharSequenceUtil extends StrValidator {
 
 		final StringBuilder sb = new StringBuilder();
 		final int subLen = toIndex - fromIndex;
-		str.toString().codePoints().skip(fromIndex).limit(subLen).forEach(v -> sb.append(Character.toChars(v)));
+		str.codePoints().skip(fromIndex).limit(subLen).forEach(v -> sb.append(Character.toChars(v)));
 		return sb.toString();
 	}
 
@@ -4131,4 +4128,28 @@ public class CharSequenceUtil extends StrValidator {
 		}
 		return (isCodePoint ? str.codePoints() : str.chars()).toArray();
 	}
+
+	/**
+	 * 遍历字符串的每个字符，并处理
+	 *
+	 * @param str      字符串
+	 * @param consumer 字符处理
+	 */
+	public static void forEach(final CharSequence str, final Consumer<Character> consumer) {
+		forEach(str, false, (cInt)-> consumer.accept((char) cInt));
+	}
+
+	/**
+	 * 遍历字符串的每个字符，并处理
+	 *
+	 * @param str         字符串
+	 * @param isCodePoint 是否为Unicode码点（即支持emoji等多char字符）
+	 * @param consumer    字符处理
+	 */
+	public static void forEach(final CharSequence str, final boolean isCodePoint, final IntConsumer consumer) {
+		if (null == str) {
+			return;
+		}
+		(isCodePoint ? str.codePoints() : str.chars()).forEach(consumer);
+	}
 }

hutool-core/src/main/java/org/dromara/hutool/core/text/finder/MultiStrFinder.java

@@ -1,51 +1,56 @@
 package org.dromara.hutool.core.text.finder;
 
+import org.dromara.hutool.core.text.StrUtil;
+
 import java.util.*;
 
 /**
  * 多字符串查询器 底层思路 使用 AC 自动机实现
+ *
  * @author newshiJ
- * @date 2024/8/2 上午10:07
  */
 public class MultiStrFinder {
 
-	// 字符索引
+	/**
-	protected final Map<Character,Integer> charIndex = new HashMap<>();
+	 * 创建多字符串查询器
+	 * @param source 字符串集合
+	 * @return 多字符串查询器
+	 */
+	public static MultiStrFinder of(final Collection<String> source) {
+		return new MultiStrFinder(source);
+	}
 
+	// 字符索引
+	protected final Map<Character, Integer> charIndexMap = new HashMap<>();
 	// 全部字符数量
 	protected final int allCharSize;
-
 	// 根节点
 	protected final Node root;
-
 	// 全部节点数量
 	int nodeSize;
 
 	/**
 	 * 构建多字符串查询器
-	 * @param source
+	 *
+	 * @param source 字符串集合
 	 */
-	public MultiStrFinder(Collection<String> source){
+	public MultiStrFinder(final Collection<String> source) {
 		// 待匹配的字符串
 		final Set<String> stringSet = new HashSet<>();
 
 		// 所有字符
 		final Set<Character> charSet = new HashSet<>();
-		for (String string : source) {
+		for (final String string : source) {
 			stringSet.add(string);
-			char[] charArray = string.toCharArray();
+			StrUtil.forEach(string, charSet::add);
-			for (char c : charArray) {
-				charSet.add(c);
-			}
 		}
 		allCharSize = charSet.size();
 		int index = 0;
-		for (Character c : charSet) {
+		for (final Character c : charSet) {
-			charIndex.put(c,index);
+			charIndexMap.put(c,index);
 			index ++;
 		}
-
+		this.root = Node.createRoot(index);
-		root = Node.createRoot(allCharSize);
 
 		buildPrefixTree(stringSet);
 		buildFail();
@@ -53,17 +58,16 @@ public class MultiStrFinder {
 
 	/**
 	 * 构建前缀树
+	 *
 	 * @param stringSst 待匹配的字符串
 	 */
-	protected void buildPrefixTree(Collection<String> stringSst){
+	protected void buildPrefixTree(final Collection<String> stringSst) {
 		// 节点编号 根节点已经是0了 所以从 1开始编号
 		int nodeIndex = 1;
-		for (String string : stringSst) {
+		for (final String string : stringSst) {
 			Node node = root;
-			char[] charArray = string.toCharArray();
+			for (final char c : string.toCharArray()) {
-			for (int i = 0; i < charArray.length; i++) {
+				final boolean addValue = node.addValue(c, nodeIndex, charIndexMap);
-				char c = charArray[i];
-				boolean addValue = node.addValue(c, nodeIndex, charIndex);
 				if (addValue) {
 					nodeIndex++;
 				}
@@ -79,9 +83,9 @@ public class MultiStrFinder {
 	 * 构建 directRouter 直接访问路由表 减少跳fail次数 直接跳 router 边
 	 */
 	protected void buildFail() {
-		LinkedList<Node> nodeQueue = new LinkedList<>();
+		final LinkedList<Node> nodeQueue = new LinkedList<>();
 		for (int i = 0; i < root.directRouter.length; i++) {
-			Node nextNode = root.directRouter[i];
+			final Node nextNode = root.directRouter[i];
 			if (nextNode == null) {
 				root.directRouter[i] = root;
 				continue;
@@ -92,10 +96,10 @@ public class MultiStrFinder {
 
 		// 进行广度优先遍历
 		while (!nodeQueue.isEmpty()) {
-			Node parent = nodeQueue.removeFirst();
+			final Node parent = nodeQueue.removeFirst();
 			// 因为 使用了 charIndex 进行字符到下标的映射 i 可以直接认为就是对应字符 char
 			for (int i = 0; i < parent.directRouter.length; i++) {
-				Node child = parent.directRouter[i];
+				final Node child = parent.directRouter[i];
 				// child 为 null 表示没有子节点
 				if (child == null) {
 					parent.directRouter[i] = parent.fail.directRouter[i];
@@ -110,18 +114,19 @@ public class MultiStrFinder {
 
 	/**
 	 * 查询匹配的字符串
+	 *
 	 * @param text 返回每个匹配的 字符串 value是字符首字母地址
-	 * @return
+	 * @return 匹配结果
 	 */
-	public Map<String,List<Integer>> findMatch(String text){
+	public Map<String, List<Integer>> findMatch(final String text) {
 		// 节点经过次数 放在方法内部声明变量 希望可以一个构建对象 进行多次匹配
-		HashMap<String, List<Integer>> resultMap = new HashMap<>();
+		final HashMap<String, List<Integer>> resultMap = new HashMap<>();
 
-		char[] chars = text.toCharArray();
+		final char[] chars = text.toCharArray();
 		Node currentNode = root;
 		for (int i = 0; i < chars.length; i++) {
-			char c = chars[i];
+			final char c = chars[i];
-			Integer index = charIndex.get(c);
+			final Integer index = charIndexMap.get(c);
 			// 找不到字符索引 认为一定不在匹配字符中存在 直接从根节点开始重新计算
 			if (index == null) {
 				currentNode = root;
@@ -143,11 +148,12 @@ public class MultiStrFinder {
 
 	/**
 	 * 获取字符 下标
-	 * @param c
+	 *
-	 * @return
+	 * @param c 字符
+	 * @return 下标
 	 */
-	protected int getIndex(char c){
+	protected int getIndex(final char c) {
-		Integer i = charIndex.get(c);
+		final Integer i = charIndexMap.get(c);
 		if (i == null) {
 			return -1;
 		}
@@ -155,10 +161,6 @@ public class MultiStrFinder {
 	}
 
 
-	public static MultiStrFinder create(Collection<String> source){
-		return new MultiStrFinder(source);
-	}
-
 	/**
 	 * AC 自动机节点
 	 */
@@ -189,17 +191,19 @@ public class MultiStrFinder {
 		// fail指针来源
 		public List<Node> failPre = new ArrayList<>();
 
-		public Node(){}
+		public Node() {
+		}
 
 		/**
 		 * 新增子节点
+		 *
 		 * @param c         字符
 		 * @param nodeIndex 节点编号
 		 * @param charIndex 字符索引
 		 * @return 如果已经存在子节点 false 新增 ture
 		 */
-		public boolean addValue(char c, int nodeIndex ,Map<Character,Integer> charIndex){
+		public boolean addValue(final char c, final int nodeIndex, final Map<Character, Integer> charIndex) {
-			Integer index = charIndex.get(c);
+			final Integer index = charIndex.get(c);
 			Node node = directRouter[index];
 			if (node != null) {
 				return false;
@@ -214,21 +218,23 @@ public class MultiStrFinder {
 
 		/**
 		 * 标记当前节点为 字符串尾节点
+		 *
 		 * @param string
 		 */
-		public void setEnd(String string){
+		public void setEnd(final String string) {
 			tagetString = string;
 			isEnd = true;
 		}
 
 		/**
 		 * 获取下一跳
+		 *
 		 * @param c         字符
 		 * @param charIndex 字符索引
 		 * @return
 		 */
-		public Node getNext(char c,Map<Character,Integer> charIndex){
+		public Node getNext(final char c, final Map<Character, Integer> charIndex) {
-			Integer index = charIndex.get(c);
+			final Integer index = charIndex.get(c);
 			if (index == null) {
 				return null;
 			}
@@ -237,11 +243,12 @@ public class MultiStrFinder {
 
 		/**
 		 * 构建根节点
+		 *
 		 * @param allCharSize 全部字符数量
 		 * @return
 		 */
-		public static Node createRoot(int allCharSize){
+		public static Node createRoot(final int allCharSize) {
-			Node node = new Node();
+			final Node node = new Node();
 			node.nodeIndex = 0;
 			node.fail = node;
 			node.directRouter = new Node[allCharSize];

hutool-core/src/main/java/org/dromara/hutool/core/text/replacer/HighMultiReplacerV2.java

@@ -14,9 +14,9 @@ import java.util.*;
  *  3、"abc", "bc"  会优先替换"abc"
  *
  * @author newshiJ
- * @date 2024/8/2 下午3:41
  */
 public class HighMultiReplacerV2 extends StrReplacer {
+	private static final long serialVersionUID = 1L;
 
 	private final AhoCorasickAutomaton ahoCorasickAutomaton;
 
@@ -49,19 +49,17 @@ public class HighMultiReplacerV2 extends StrReplacer {
 	protected static class AhoCorasickAutomaton extends MultiStrFinder{
 		protected final Map<String,String> replaceMap;
 
-		public AhoCorasickAutomaton(Map<String,String> replaceMap){
+		public AhoCorasickAutomaton(final Map<String,String> replaceMap){
 			super(replaceMap.keySet());
 			this.replaceMap = replaceMap;
 		}
-
-
 		public void replace(final CharSequence text, final StringBuilder stringBuilder){
 			Node currentNode = root;
 			// 临时字符串存储空间
-			StringBuilder temp = new StringBuilder();
+			final StringBuilder temp = new StringBuilder();
 			for (int i = 0; i < text.length(); i++) {
-				char ch = text.charAt(i);
+				final char ch = text.charAt(i);
-				Integer index = charIndex.get(ch);
+				final Integer index = charIndexMap.get(ch);
 				// 下一个字符在候选转换字符串中都不存在 ch字符一定不会被替换
 				if(index < 0){
 					// 临时缓存空间中的数据写入到输出的 StringBuilder
@@ -94,7 +92,7 @@ public class HighMultiReplacerV2 extends StrReplacer {
 
 				// 表示匹配到 现在进行字符串替换工作
 				if(currentNode.isEnd){
-					int length = currentNode.tagetString.length();
+					final int length = currentNode.tagetString.length();
 					// 先清理匹配到的字符 最后一个字符未加入临时空间
 					temp.delete(temp.length() - length + 1,length - 1);
 					if(temp.length() > 0){