本文目录导读：
我来详细介绍Java字符串匹配的几种常见开发案例：
基础字符串匹配方法
public class StringMatchExample {
public static void main(String[] args) {
String text = "Hello World, Welcome to Java Programming";
String pattern = "Java";
// 1. contains() - 是否包含
System.out.println("Contains 'Java': " + text.contains("Java"));
// 2. indexOf() - 查找首次出现位置
int index = text.indexOf("World");
System.out.println("Index of 'World': " + index);
// 3. lastIndexOf() - 查找最后出现位置
int lastIndex = text.lastIndexOf("o");
System.out.println("Last index of 'o': " + lastIndex);
// 4. startsWith() / endsWith()
System.out.println("Starts with 'Hello': " + text.startsWith("Hello"));
System.out.println("Ends with 'Programming': " + text.endsWith("Programming"));
// 5. 使用matches()进行正则匹配
boolean isMatch = text.matches(".*Java.*");
System.out.println("Matches pattern '.*Java.*': " + isMatch);
}
}
正则表达式匹配
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class RegexMatchExample {
public static void main(String[] args) {
String text = "我的邮箱是user@example.com，电话是138-1234-5678";
// 1. 匹配邮箱
String emailPattern = "\\w+@\\w+\\.\\w+";
Pattern pattern = Pattern.compile(emailPattern);
Matcher matcher = pattern.matcher(text);
if (matcher.find()) {
System.out.println("找到邮箱: " + matcher.group());
}
// 2. 匹配电话号码
String phonePattern = "\\d{3}-\\d{4}-\\d{4}";
Pattern phonePatternCompiled = Pattern.compile(phonePattern);
Matcher phoneMatcher = phonePatternCompiled.matcher(text);
if (phoneMatcher.find()) {
System.out.println("找到电话: " + phoneMatcher.group());
}
// 3. 多模式匹配
String multiPattern = "(邮箱|电话|地址)";
Pattern multiPatternCompiled = Pattern.compile(multiPattern);
Matcher multiMatcher = multiPatternCompiled.matcher(text);
while (multiMatcher.find()) {
System.out.println("匹配到关键词: " + multiMatcher.group() +
" 位置: " + multiMatcher.start());
}
}
}
KMP算法实现
public class KMPAlgorithm {
// 构建部分匹配表
private static int[] buildPMT(String pattern) {
int[] pmt = new int[pattern.length()];
int j = 0;
for (int i = 1; i < pattern.length(); i++) {
while (j > 0 && pattern.charAt(i) != pattern.charAt(j)) {
j = pmt[j - 1];
}
if (pattern.charAt(i) == pattern.charAt(j)) {
j++;
}
pmt[i] = j;
}
return pmt;
}
// KMP搜索
public static int kmpSearch(String text, String pattern) {
if (pattern.isEmpty()) return 0;
int[] pmt = buildPMT(pattern);
int j = 0;
for (int i = 0; i < text.length(); i++) {
while (j > 0 && text.charAt(i) != pattern.charAt(j)) {
j = pmt[j - 1];
}
if (text.charAt(i) == pattern.charAt(j)) {
j++;
}
if (j == pattern.length()) {
return i - j + 1; // 返回匹配起始位置
}
}
return -1; // 未找到
}
public static void main(String[] args) {
String text = "ABCABCABD";
String pattern = "ABCABD";
int index = kmpSearch(text, pattern);
if (index != -1) {
System.out.println("找到模式 '" + pattern + "' 在文本中的位置: " + index);
System.out.println("匹配子串: '" + text.substring(index, index + pattern.length()) + "'");
} else {
System.out.println("未找到模式 '" + pattern + "'");
}
}
}
实用字符串匹配工具类
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class StringMatchUtils {
// 查找所有匹配位置
public static List<Integer> findAllMatches(String text, String pattern) {
List<Integer> positions = new ArrayList<>();
Pattern p = Pattern.compile(Pattern.quote(pattern));
Matcher m = p.matcher(text);
while (m.find()) {
positions.add(m.start());
}
return positions;
}
// 模糊匹配（忽略大小写）
public static boolean fuzzyMatch(String text, String pattern) {
return text.toLowerCase().contains(pattern.toLowerCase());
}
// 通配符匹配 (* 和 ?)
public static boolean wildcardMatch(String text, String pattern) {
String regex = pattern
.replace(".", "\\.")
.replace("*", ".*")
.replace("?", ".");
return text.matches(regex);
}
// 提取匹配内容
public static List<String> extractMatches(String text, String regex) {
List<String> matches = new ArrayList<>();
Pattern pattern = Pattern.compile(regex);
Matcher matcher = pattern.matcher(text);
while (matcher.find()) {
matches.add(matcher.group());
}
return matches;
}
// 测试
public static void main(String[] args) {
String text = "Hello Java, hello Python, Hello JavaScript";
// 查找所有"hello"位置（忽略大小写）
List<Integer> positions = findAllMatches(text.toLowerCase(), "hello");
System.out.println("'hello'的所有位置: " + positions);
// 模糊搜索
System.out.println("包含'java': " + fuzzyMatch(text, "java"));
// 通配符匹配
System.out.println("通配符匹配 'H*llo': " + wildcardMatch(text, "H*llo"));
// 提取单词
List<String> words = extractMatches(text, "\\w+");
System.out.println("提取的单词: " + words);
}
}
性能测试与比较
public class PerformanceTest {
public static void main(String[] args) {
// 准备测试数据
StringBuilder sb = new StringBuilder();
for (int i = 0; i < 100000; i++) {
sb.append("test" + i + " ");
}
String text = sb.toString();
String pattern = "test99999";
// 测试不同方法
long startTime, endTime;
// 1. contains()
startTime = System.nanoTime();
boolean result1 = text.contains(pattern);
endTime = System.nanoTime();
System.out.println("contains() 耗时: " + (endTime - startTime) + " ns");
// 2. indexOf()
startTime = System.nanoTime();
int index = text.indexOf(pattern);
endTime = System.nanoTime();
System.out.println("indexOf() 耗时: " + (endTime - startTime) + " ns");
// 3. matches()
startTime = System.nanoTime();
boolean result3 = text.matches(".*" + Pattern.quote(pattern) + ".*");
endTime = System.nanoTime();
System.out.println("matches() 耗时: " + (endTime - startTime) + " ns");
// 4. 使用Pattern
startTime = System.nanoTime();
Pattern p = Pattern.compile(Pattern.quote(pattern));
Matcher m = p.matcher(text);
boolean result4 = m.find();
endTime = System.nanoTime();
System.out.println("Pattern.find() 耗时: " + (endTime - startTime) + " ns");
}
}
最佳实践建议
- 简单匹配：优先使用
contains(),indexOf()等基础方法 - 复杂模式：使用正则表达式，但注意预编译Pattern对象提升性能
- 大量数据：考虑使用KMP等高效算法
- 错误处理：添加null检查和异常处理
- 国际化：注意字符编码和Unicode支持
这些案例涵盖了Java字符串匹配的常用场景和实现方法,你可以根据实际需求选择合适的方案。
