lsm/hutool
1
0
Fork 0
mirror of https://gitee.com/dromara/hutool.git synced 2025-07-15 23:13:33 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix：避免调用方 显示调用API 触发查找树 优化；并通过内置锁，避免因并行树优化 可能造成的不可预知结果 和 无效重复的 树优化操作

Browse Source
This commit is contained in:
renyp 2023-03-16 20:40:36 +08:00
parent 6cd998f648
commit 00e9af4ffb
2 changed files with 164 additions and 128 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
hutool-core/src/main/java/cn/hutool/core/text/dfa/Automaton.java
View File

@ -4,19 +4,33 @@ 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 Automaton {
/**
* 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 lock;
/**
* 默认构造
*/
public Automaton() {
this.root = new Node();
this.needBuildAC = true;
this.lock = new Object();
}
/**
@ -35,6 +49,7 @@ public class Automaton {
* @param word 添加的新词
*/
public void insert(String word) {
needBuildAC = true;
Node p = root;
for (char curr : word.toCharArray()) {
int ind = curr;
@ -61,7 +76,7 @@ public class Automaton {
/**
* 构建基于NFA模型的 AC自动机
*/
public void buildAc() {
private void buildAc() {
Queue<Node> queue = new LinkedList<>();
Node p = root;
for (Integer key : p.next.keySet()) {
@ -86,6 +101,7 @@ public class Automaton {
queue.offer(curr.next.get(key));
}
}
needBuildAC = false;
}
/**
@ -100,6 +116,14 @@ public class Automaton {
* @param isDensityMatch 是否密集匹配
*/
public List<FoundWord> find(String text, boolean isDensityMatch) {
// double check，防止重复无用的 buildAC
if (needBuildAC) {
synchronized (lock) {
if (needBuildAC) {
this.buildAc();
}
}
}
List<FoundWord> ans = new ArrayList<>();
Node p = root, k = null;
for (int i = 0, len = text.length(); i < len; i++) {
@ -131,9 +155,21 @@ public class Automaton {
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() {

12
hutool-core/src/test/java/cn/hutool/core/text/dfa/AutomatonTest.java
View File

@ -17,7 +17,7 @@ public class AutomatonTest extends TestCase {
Automaton automaton = new Automaton();
WordTree wordTree = new WordTree();
automaton.insert("say", "her", "he", "she", "shr");
automaton.buildAc();
// automaton.buildAc();
wordTree.addWords("say", "her", "he", "she", "shr");
StopWatch stopWatch = new StopWatch();
@ -51,7 +51,7 @@ public class AutomatonTest extends TestCase {
Automaton automaton = new Automaton();
WordTree wordTree = new WordTree();
automaton.insert("say", "her", "he", "she", "shr");
automaton.buildAc();
// automaton.buildAc();
wordTree.addWords("say", "her", "he", "she", "shr");
StopWatch stopWatch = new StopWatch();
@ -84,7 +84,7 @@ public class AutomatonTest extends TestCase {
stopWatch.start("automaton_char_buid_find");
Automaton automatonLocal = new Automaton();
automatonLocal.insert("say", "her", "he", "she", "shr");
automatonLocal.buildAc();
// automatonLocal.buildAc();
List<FoundWord> ans1 = automatonLocal.find(input);
stopWatch.stop();
assertEquals("she,he,her,say", ans1.stream().map(FoundWord::getWord).collect(Collectors.joining(",")));
@ -118,7 +118,7 @@ public class AutomatonTest extends TestCase {
stopWatch.start("automaton_cn_build_find");
Automaton automatonLocal = new Automaton();
automatonLocal.insert("赵", "赵啊", "赵啊三");
automatonLocal.buildAc();
// automatonLocal.buildAc();
final List<FoundWord> result = automatonLocal.find(input);
stopWatch.stop();
@ -156,7 +156,7 @@ public class AutomatonTest extends TestCase {
Automaton automatonLocal = new Automaton();
automatonLocal.insert("赵", "赵啊", "赵啊三");
automatonLocal.buildAc();
// automatonLocal.buildAc();
stopWatch.start("automaton_cn_find");
final List<FoundWord> result = automatonLocal.find(input);
@ -196,7 +196,7 @@ public class AutomatonTest extends TestCase {
Automaton automatonLocal = new Automaton();
automatonLocal.insert("赵", "赵啊", "赵啊三");
automatonLocal.buildAc();
// automatonLocal.buildAc();
stopWatch.start("automaton_cn_find_not_density");
final List<FoundWord> result = automatonLocal.find(input, false);