cn.hutool.dfa.SensitiveUtil Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of hutool-all Show documentation
Show all versions of hutool-all Show documentation
Hutool是一个小而全的Java工具类库,通过静态方法封装,降低相关API的学习成本,提高工作效率,使Java拥有函数式语言般的优雅,让Java语言也可以“甜甜的”。
package cn.hutool.dfa;
import cn.hutool.core.collection.CollUtil;
import cn.hutool.core.lang.Filter;
import cn.hutool.core.thread.ThreadUtil;
import cn.hutool.core.util.StrUtil;
import cn.hutool.json.JSONUtil;
import java.util.Collection;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
/**
* 敏感词工具类
*
* @author Looly
*/
public final class SensitiveUtil {
public static final char DEFAULT_SEPARATOR = StrUtil.C_COMMA;
private static final WordTree sensitiveTree = new WordTree();
/**
* @return 是否已经被初始化
*/
public static boolean isInited() {
return false == sensitiveTree.isEmpty();
}
/**
* 初始化敏感词树
*
* @param isAsync 是否异步初始化
* @param sensitiveWords 敏感词列表
*/
public static void init(final Collection sensitiveWords, boolean isAsync) {
if (isAsync) {
ThreadUtil.execAsync(() -> {
init(sensitiveWords);
return true;
});
} else {
init(sensitiveWords);
}
}
/**
* 初始化敏感词树
*
* @param sensitiveWords 敏感词列表
*/
public static void init(Collection sensitiveWords) {
sensitiveTree.clear();
sensitiveTree.addWords(sensitiveWords);
// log.debug("Sensitive init finished, sensitives: {}", sensitiveWords);
}
/**
* 初始化敏感词树
*
* @param sensitiveWords 敏感词列表组成的字符串
* @param isAsync 是否异步初始化
* @param separator 分隔符
*/
public static void init(String sensitiveWords, char separator, boolean isAsync) {
if (StrUtil.isNotBlank(sensitiveWords)) {
init(StrUtil.split(sensitiveWords, separator), isAsync);
}
}
/**
* 初始化敏感词树,使用逗号分隔每个单词
*
* @param sensitiveWords 敏感词列表组成的字符串
* @param isAsync 是否异步初始化
*/
public static void init(String sensitiveWords, boolean isAsync) {
init(sensitiveWords, DEFAULT_SEPARATOR, isAsync);
}
/**
* 设置字符过滤规则,通过定义字符串过滤规则,过滤不需要的字符
* 当accept为false时,此字符不参与匹配
*
* @param charFilter 过滤函数
* @since 5.4.4
*/
public static void setCharFilter(Filter charFilter) {
if (charFilter != null) {
sensitiveTree.setCharFilter(charFilter);
}
}
/**
* 是否包含敏感词
*
* @param text 文本
* @return 是否包含
*/
public static boolean containsSensitive(String text) {
return sensitiveTree.isMatch(text);
}
/**
* 是否包含敏感词
*
* @param obj bean,会被转为JSON字符串
* @return 是否包含
*/
public static boolean containsSensitive(Object obj) {
return sensitiveTree.isMatch(JSONUtil.toJsonStr(obj));
}
/**
* 查找敏感词,返回找到的第一个敏感词
*
* @param text 文本
* @return 敏感词
* @since 5.5.3
*/
public static FoundWord getFoundFirstSensitive(String text) {
return sensitiveTree.matchWord(text);
}
/**
* 查找敏感词,返回找到的第一个敏感词
*
* @param obj bean,会被转为JSON字符串
* @return 敏感词
*/
public static FoundWord getFoundFirstSensitive(Object obj) {
return sensitiveTree.matchWord(JSONUtil.toJsonStr(obj));
}
/**
* 查找敏感词,返回找到的所有敏感词
*
* @param text 文本
* @return 敏感词
* @since 5.5.3
*/
public static List getFoundAllSensitive(String text) {
return sensitiveTree.matchAllWords(text);
}
/**
* 查找敏感词,返回找到的所有敏感词
* 密集匹配原则:假如关键词有 ab,b,文本是abab,将匹配 [ab,b,ab]
* 贪婪匹配(最长匹配)原则:假如关键字a,ab,最长匹配将匹配[a, ab]
*
* @param text 文本
* @param isDensityMatch 是否使用密集匹配原则
* @param isGreedMatch 是否使用贪婪匹配(最长匹配)原则
* @return 敏感词
*/
public static List getFoundAllSensitive(String text, boolean isDensityMatch, boolean isGreedMatch) {
return sensitiveTree.matchAllWords(text, -1, isDensityMatch, isGreedMatch);
}
/**
* 查找敏感词,返回找到的所有敏感词
*
* @param bean 对象,会被转为JSON
* @return 敏感词
* @since 5.5.3
*/
public static List getFoundAllSensitive(Object bean) {
return sensitiveTree.matchAllWords(JSONUtil.toJsonStr(bean));
}
/**
* 查找敏感词,返回找到的所有敏感词
* 密集匹配原则:假如关键词有 ab,b,文本是abab,将匹配 [ab,b,ab]
* 贪婪匹配(最长匹配)原则:假如关键字a,ab,最长匹配将匹配[a, ab]
*
* @param bean 对象,会被转为JSON
* @param isDensityMatch 是否使用密集匹配原则
* @param isGreedMatch 是否使用贪婪匹配(最长匹配)原则
* @return 敏感词
* @since 5.5.3
*/
public static List getFoundAllSensitive(Object bean, boolean isDensityMatch, boolean isGreedMatch) {
return getFoundAllSensitive(JSONUtil.toJsonStr(bean), isDensityMatch, isGreedMatch);
}
/**
* 敏感词过滤
*
* @param bean 对象,会被转为JSON
* @param isGreedMatch 贪婪匹配(最长匹配)原则:假如关键字a,ab,最长匹配将匹配[a, ab]
* @param sensitiveProcessor 敏感词处理器,默认按匹配内容的字符数替换成*
* @param bean的class类型
* @return 敏感词过滤处理后的bean对象
*/
public static T sensitiveFilter(T bean, boolean isGreedMatch, SensitiveProcessor sensitiveProcessor) {
final String jsonText = JSONUtil.toJsonStr(bean);
@SuppressWarnings("unchecked") final Class c = (Class) bean.getClass();
return JSONUtil.toBean(sensitiveFilter(jsonText, isGreedMatch, sensitiveProcessor), c);
}
/**
* 处理过滤文本中的敏感词,默认替换成*
*
* @param text 文本
* @return 敏感词过滤处理后的文本
* @since 5.7.21
*/
public static String sensitiveFilter(String text) {
return sensitiveFilter(text, true, null);
}
/**
* 处理过滤文本中的敏感词,默认替换成*
*
* @param text 文本
* @param isGreedMatch 贪婪匹配(最长匹配)原则:假如关键字a,ab,最长匹配将匹配[a, ab]
* @param sensitiveProcessor 敏感词处理器,默认按匹配内容的字符数替换成*
* @return 敏感词过滤处理后的文本
*/
public static String sensitiveFilter(String text, boolean isGreedMatch, SensitiveProcessor sensitiveProcessor) {
if (StrUtil.isEmpty(text)) {
return text;
}
//敏感词过滤场景下,不需要密集匹配
final List foundWordList = getFoundAllSensitive(text, true, isGreedMatch);
if (CollUtil.isEmpty(foundWordList)) {
return text;
}
sensitiveProcessor = sensitiveProcessor == null ? new SensitiveProcessor() {
} : sensitiveProcessor;
final Map foundWordMap = new HashMap<>(foundWordList.size(), 1);
foundWordList.forEach(foundWord -> foundWordMap.put(foundWord.getStartIndex(), foundWord));
final int length = text.length();
final StringBuilder textStringBuilder = new StringBuilder();
for (int i = 0; i < length; i++) {
final FoundWord fw = foundWordMap.get(i);
if (fw != null) {
textStringBuilder.append(sensitiveProcessor.process(fw));
i = fw.getEndIndex();
} else {
textStringBuilder.append(text.charAt(i));
}
}
return textStringBuilder.toString();
}
}
© 2015 - 2024 Weber Informatics LLC | Privacy Policy