Java独立关键词查找：精确匹配与避免嵌入式字符串的策略

public class KeywordFinder {

    /**
     * 查找作为独立词汇出现的关键词，基于空格进行判断。
     * 注意：此方法对标点符号等非空格边界支持有限。
     *
     * @param s       源字符串
     * @param keyword 待查找的关键词
     * @return 关键词在源字符串中的起始索引，如果未找到则返回 -1。
     */
    public static int indexOfKeywordSimple(String s, String keyword) {
        // 转换为小写以实现不区分大小写的匹配
        String source = s.toLowerCase();
        String key = " " + keyword.toLowerCase() + " ";

        // 在源字符串前后添加空格，以便处理关键词在字符串开头或结尾的情况
        String paddedSource = " " + source + " ";

        int foundIdx = paddedSource.indexOf(key);

        // 如果找到，需要调整索引，因为我们在源字符串前添加了一个空格
        return (foundIdx != -1) ? (foundIdx - 1) : -1;
    }

    public static void main(String[] args) {
        String s1 = "She sells seashells by the seashore.";
        String keyword1 = "sea";
        System.out.println("Test Case 1: '" + s1 + "', keyword '" + keyword1 + "' -> " + indexOfKeywordSimple(s1, keyword1)); // 预期: -1

        String s2 = "Carolyn has a car that is scary fast.";
        String keyword2 = "car";
        System.out.println("Test Case 2: '" + s2 + "', keyword '" + keyword2 + "' -> " + indexOfKeywordSimple(s2, keyword2)); // 预期: 14 (实际返回14)

        String s3 = "Sea is beautiful.";
        String keyword3 = "sea";
        System.out.println("Test Case 3: '" + s3 + "', keyword '" + keyword3 + "' -> " + indexOfKeywordSimple(s3, keyword3)); // 预期: 0 (实际返回0)

        String s4 = "The sea is vast.";
        String keyword4 = "sea";
        System.out.println("Test Case 4: '" + s4 + "', keyword '" + keyword4 + "' -> " + indexOfKeywordSimple(s4, keyword4)); // 预期: 4 (实际返回4)
    }
}

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class KeywordFinder {

    /**
     * 查找作为独立词汇出现的关键词，使用正则表达式的词边界()。
     * 此方法对各种边界情况（空格、标点、字符串开头/结尾）支持更全面。
     *
     * @param s       源字符串
     * @param keyword 待查找的关键词
     * @return 关键词在源字符串中的起始索引，如果未找到则返回 -1。
     */
    public static int indexOfKeywordRegex(String s, String keyword) {
        // 使用 Pattern.quote() 转义关键词，防止其被解释为正则表达式元字符
        // 使用  匹配词边界，确保关键词作为独立词汇出现
        // Pattern.CASE_INSENSITIVE 使得匹配不区分大小写
        Pattern pattern = Pattern.compile("\b" + Pattern.quote(keyword) + "\b", Pattern.CASE_INSENSITIVE);
        Matcher matcher = pattern.matcher(s);

        // 查找第一个匹配项
        if (matcher.find()) {
            return matcher.start(); // 返回匹配到的起始索引
        }
        return -1; // 未找到
    }

    public static void main(String[] args) {
        String s1 = "She sells seashells by the seashore.";
        String keyword1 = "sea";
        System.out.println("Test Case 1: '" + s1 + "', keyword '" + keyword1 + "' -> " + indexOfKeywordRegex(s1, keyword1)); // 预期: -1

        String s2 = "Carolyn has a car that is scary fast.";
        String keyword2 = "car";
        System.out.println("Test Case 2: '" + s2 + "', keyword '" + keyword2 + "' -> " + indexOfKeywordRegex(s2, keyword2)); // 预期: 14

        String s3 = "Sea is beautiful.";
        String keyword3 = "sea";
        System.out.println("Test Case 3: '" + s3 + "', keyword '" + keyword3 + "' -> " + indexOfKeywordRegex(s3, keyword3)); // 预期: 0

        String s4 = "The sea is vast.";
        String keyword4 = "sea";
        System.out.println("Test Case 4: '" + s4 + "', keyword '" + keyword4 + "' -> " + indexOfKeywordRegex(s4, keyword4)); // 预期: 4

        String s5 = "Hello, world! This is a test.";
        String keyword5 = "world";
        System.out.println("Test Case 5: '" + s5 + "', keyword '" + keyword5 + "' -> " + indexOfKeywordRegex(s5, keyword5)); // 预期: 7 (正确处理标点)

        String s6 = "Test. The test is complete.";
        String keyword6 = "test";
        System.out.println("Test Case 6: '" + s6 + "', keyword '" + keyword6 + "' -> " + indexOfKeywordRegex(s6, keyword6)); // 预期: 0 (正确处理句号)

        String s7 = "book";
        String keyword7 = "book";
        System.out.println("Test Case 7: '" + s7 + "', keyword '" + keyword7 + "' -> " + indexOfKeywordRegex(s7, keyword7)); // 预期: 0 (正确处理字符串本身就是关键词)
    }
}