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));
    }
}