springboot集成sensitive-word实现敏感词过滤的两种方案

public static void main(String[] args) {
        String text = "这是一个包含敏感词汇的文本，例如色情、赌博等。";
        String[] sensitiveWords = {"色情", "赌博"};
        for (String word : sensitiveWords) {
            text = filterSensitiveWords(text, word);
        }
        System.out.println("过滤后的文本： " + text);
        testSensitiveWordFrame();
    }
    /**
     * 方案一：正则表达式实现敏感词过滤.只适合于敏感词较少、文本量较少的场合，并且无法处理同音字、错别字等.
     *
     * @param text
     * @param sensitiveWord
     * @return
     */
    public static String filterSensitiveWords(String text, String sensitiveWord) {
        Pattern pattern = Pattern.compile(sensitiveWord);
        Matcher matcher = pattern.matcher(text);
        return matcher.replaceAll("***");
    }

<dependency>
	<groupId>com.github.houbb</groupId>
	<artifactId>sensitive-word</artifactId>
	<version>0.2.0</version>
</dependency>

@Configuration
public class MySensitiveWordBs {
    @Autowired
    private MyWordAllow myWordAllow;
    @Autowired
    private MyWordDeny myWordDeny;
    @Autowired
    private MyWordReplace myWordReplace;
    /**
     * 初始化引导类
     *
     * @return 初始化引导类
     * @since 1.0.0
     */
    @Bean
    public SensitiveWordBs sensitiveWordBs() {
        SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance()
//                .wordAllow(WordAllows.chains(WordAllows.defaults(), myWordAllow)) // 设置多个敏感词，系统默认和自定义
//                .wordDeny(WordDenys.chains(WordDenys.defaults(), myWordDeny))     // 设置多个敏感词，系统默认和自定义
                .wordAllow(WordAllows.chains(myWordAllow))  // 自定义
                .wordDeny(WordDenys.chains(myWordDeny))     // 自定义
                .wordReplace(myWordReplace)                                        // 自定义替换规则
                .ignoreCase(true)           // 忽略大小写
                .ignoreWidth(true)          // 忽略半角圆角
                .ignoreNumStyle(true)       // 忽略数字的写法
                .ignoreChineseStyle(true)   // 忽略中文的书写格式
                .ignoreEnglishStyle(true)   // 忽略英文的书写格式
                .ignoreRepeat(true)         // 忽略重复词
                .enableNumCheck(true)       // 是否启用数字检测。默认连续 8 位数字认为是敏感词
                .enableEmailCheck(true)     // 是有启用邮箱检测
                .enableUrlCheck(true)       // 是否启用链接检测
                .init();
        return sensitiveWordBs;
    }
}

/**
 * 自定义非敏感词
 * 注意每一行为一个非敏感词，单行不能只包括空格，否则，也会把空格识别为非敏感词
 */
@Component
@Slf4j
public class MyWordAllow implements IWordAllow {
    @Override
    public List<String> allow() {
        List<String> allowWords = new ArrayList<>();
        try {
            ClassPathResource resource = new ClassPathResource("myAllowWords.txt");
            Path myAllowWordsPath = Paths.get(resource.getUrl().toURI());
            allowWords = Files.readAllLines(myAllowWordsPath, StandardCharsets.UTF_8);
        } catch (IOException ioException) {
            log.error("读取非敏感词文件错误：{}", ioException);
        } catch (URISyntaxException e) {
            throw new RuntimeException(e);
        }
        return allowWords;
    }
}

@Component
@Slf4j
public class MyWordDeny implements IWordDeny {
    @Override
    public List<String> deny() {
        List<String> denyWords = new ArrayList<>();
        try {
            ClassPathResource resource = new ClassPathResource("myDenyWords.txt");
            Path myAllowWordsPath = Paths.get(resource.getUrl().toURI());
            denyWords = Files.readAllLines(myAllowWordsPath, StandardCharsets.UTF_8);
        } catch (
                IOException ioException) {
            log.error("读取敏感词文件错误：{}", ioException);
        } catch (URISyntaxException e) {
            throw new RuntimeException(e);
        }
        return denyWords;
    }
}

/**
 * 自定义敏感词对应的替换值.
 * 场景说明：有时候我们希望不同的敏感词有不同的替换结果。比如【游戏】替换为【电子竞技】，【失业】替换为【灵活就业】。
 */
@Configuration
public class MyWordReplace implements IWordReplace {
    @Override
    public void replace(StringBuilder stringBuilder, final char[] rawChars, IWordResult wordResult, IWordContext wordContext) {
        String sensitiveWord = InnerWordCharUtils.getString(rawChars, wordResult);
        if ("zhupeng".equals(sensitiveWord)) {
            stringBuilder.append("朱鹏");
        } else {
            // 其他默认使用 * 代替
            int wordLength = wordResult.endIndex() - wordResult.startIndex();
            for (int i = 0; i < wordLength; i++) {
                stringBuilder.append('-');
            }
        }
    }
}

public class SensitiveWordController {
    @Autowired
    private MyWordReplace myWordReplace;
    @Autowired
    private SensitiveWordBs sensitiveWordBs;
    private static final String text = "五星红旗迎风飘扬，毛主席的画像屹立在天安门前,zhuzhuhzu";
    @GetMapping("/pattern")
    public void testSensitiveWord2() {
        String text = "这是一个包含敏感词汇的文本，例如色情、赌博等。";
        String[] sensitiveWords = {"色情", "赌博"};
        for (String word : sensitiveWords) {
            text = filterSensitiveWords(text, word);
        }
        System.out.println("过滤后的文本： " + text);
    }
    /**
     * 方案二：基于DFA算法的敏感词过滤工具框架-sensitive-word:https://github.com/houbb/sensitive-word
     * 6W+ 词库，且不断优化更新
     * 基于 DFA 算法，性能较好
     * 基于 fluent-api 实现，使用优雅简洁
     * 支持敏感词的判断、返回、脱敏等常见操作
     * 支持全角半角互换
     * 支持英文大小写互换
     * 支持数字常见形式的互换
     * 支持中文繁简体互换
     * 支持英文常见形式的互换
     * 支持用户自定义敏感词和白名单
     * 支持数据的数据动态更新，实时生效
     */
    @GetMapping("/filter")
    public void testSensitiveWord() {
        System.out.println("SensitiveWordHelper.contains(text) = " + SensitiveWordHelper.contains(text));
        System.out.println("SensitiveWordHelper.findAll(text) = " + SensitiveWordHelper.findAll(text));
        System.out.println("SensitiveWordHelper.replace(text,myWordReplace) = " + SensitiveWordHelper.replace(text, myWordReplace));
        // 如果自定义敏感词，不要使用SensitiveWordHelper的方法，要使用SensitiveWordBs
        System.out.println("sensitiveWordBs.contains(text) = " + sensitiveWordBs.contains(text));
        System.out.println("sensitiveWordBs.findAll(text) = " + sensitiveWordBs.findAll(text));
        System.out.println("sensitiveWordBs.replace(text) = " + sensitiveWordBs.replace(text));
    }
}