release branch 0.2.0

CHANGE_LOG.md

@@ -126,3 +126,10 @@
 | 序号 | 变更类型 | 说明 | 时间 | 备注 |
 |:---|:---|:---|:---|:--|
 | 1 | F | 自定义敏感词 allow/deny 进行格式化处理 | 2021-12-11 23:51:58 | |
+
+# release_0.2.0
+
+| 序号 | 变更类型 | 说明 | 时间 | 备注 |
+|:---|:---|:---|:---|:--|
+| 1 | A | 允许用户自定义替换策略 | 2022-01-15 23:51:58 | |
+| 2 | U | 升级二方数据库依赖 | 2022-01-15 23:51:58 | |

README.md

@@ -44,9 +44,9 @@
 
 [CHANGE_LOG.md](https://github.com/houbb/sensitive-word/blob/master/doc/CHANGE_LOG.md)
 
-v0.1.1 变更：
+v0.2.0 变更：
 
-- 敏感词自定义 Allow/Deny 进行格式化处理
+- 支持用户自定义替换策略
 
 # 快速开始
 
@@ -62,7 +62,7 @@ v0.1.1 变更：
 <dependency>
     <groupId>com.github.houbb</groupId>
     <artifactId>sensitive-word</artifactId>
-    <version>0.1.1</version>
+    <version>0.2.0</version>
 </dependency>
 ```
 
@@ -73,6 +73,7 @@ v0.1.1 变更：
 | 方法 | 参数 | 返回值| 说明 |
 |:---|:---|:---|:---|
 | contains(String) | 待验证的字符串 | 布尔值 | 验证字符串是否包含敏感词 |
+| replace(String, ISensitiveWordReplace) | 使用指定的替换策略替换敏感词 | 字符串 | 返回脱敏后的字符串 |
 | replace(String, char) | 使用指定的 char 替换敏感词 | 字符串 | 返回脱敏后的字符串 |
 | replace(String) | 使用 `*` 替换敏感词 | 字符串 | 返回脱敏后的字符串 |
 | findAll(String) | 待验证的字符串 | 字符串列表 | 返回字符串中所有敏感词 |
@@ -170,6 +171,58 @@ String result = SensitiveWordHelper.replace(text, '0');
 Assert.assertEquals("0000迎风飘扬，000的画像屹立在000前。", result);
 ```
 
+### 自定义替换策略
+
+V0.2.0 支持该特性。
+
+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】。
+
+诚然，提前使用字符串的正则替换也可以，不过性能一般。
+
+使用例子：
+
+```java
+/**
+ * 自定替换策略
+ * @since 0.2.0
+ */
+@Test
+public void defineReplaceTest() {
+    final String text = "五星红旗迎风飘扬，毛主席的画像屹立在天安门前。";
+
+    ISensitiveWordReplace replace = new MySensitiveWordReplace();
+    String result = SensitiveWordHelper.replace(text, replace);
+
+    Assert.assertEquals("国家旗帜迎风飘扬，教员的画像屹立在***前。", result);
+}
+```
+
+其中 `MySensitiveWordReplace` 是我们自定义的替换策略，实现如下：
+
+```java
+public class MySensitiveWordReplace implements ISensitiveWordReplace {
+
+    @Override
+    public String replace(ISensitiveWordReplaceContext context) {
+        String sensitiveWord = context.sensitiveWord();
+        // 自定义不同的敏感词替换策略，可以从数据库等地方读取
+        if("五星红旗".equals(sensitiveWord)) {
+            return "国家旗帜";
+        }
+        if("毛主席".equals(sensitiveWord)) {
+            return "教员";
+        }
+
+        // 其他默认使用 * 代替
+        int wordLength = context.wordLength();
+        return CharUtil.repeat('*', wordLength);
+    }
+
+}
+```
+
+我们针对其中的部分词做固定映射处理，其他的默认转换为 `*`。
+
 # 更多特性
 
 后续的诸多特性，主要是针对各种针对各种情况的处理，尽可能的提升敏感词命中率。
@@ -530,8 +583,6 @@ public class SensitiveWordService {
 
 # 后期 road-map
 
-- 停顿词
-
 - 同音字处理
 
 - 形近字处理
@@ -542,7 +593,7 @@ public class SensitiveWordService {
 
 - 敏感词标签支持
 
-- 邮箱后缀检测
+- [ ] DFA 数据结构的另一种实现
 
 # 拓展阅读
 
@@ -552,4 +603,16 @@ public class SensitiveWordService {
 
 [敏感词库优化流程](https://houbb.github.io/2020/01/07/sensitive-word-slim)
 
-[停止词的思考记录](https://houbb.github.io/2020/01/07/sensitive-word-stopword)
+[java 如何实现开箱即用的敏感词控台服务？](https://mp.weixin.qq.com/s/rQo75cfMU_OEbTJa0JGMGg)
+
+![WECHAT](WECHAT.png)
+
+# 相关开源库
+
+[heaven 基础工具包](https://github.com/houbb/heaven)
+
+[opencc4j 繁简体转换](https://github.com/houbb/opencc4j)
+
+[pinyin 拼音工具](https://github.com/houbb/pinyin)
+
+[nlp-hanzi-similar 汉字相似度工具](https://github.com/houbb/nlp-hanzi-similar)

pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.github.houbb</groupId>
     <artifactId>sensitive-word</artifactId>
-    <version>0.1.1</version>
+    <version>0.2.0</version>
 
     <properties>
         <!--============================== All Plugins START ==============================-->
@@ -25,8 +25,8 @@
         <project.compiler.level>1.7</project.compiler.level>
 
         <!--============================== INTER ==============================-->
-        <heaven.version>0.1.148</heaven.version>
-        <opencc4j.version>1.7.1</opencc4j.version>
+        <heaven.version>0.1.154</heaven.version>
+        <opencc4j.version>1.7.2</opencc4j.version>
 
         <!--============================== OTHER ==============================-->
         <junit.version>4.13.1</junit.version>
@@ -104,7 +104,7 @@
                     <source>${project.compiler.level}</source>
                     <target>${project.compiler.level}</target>
                     <encoding>${project.build.sourceEncoding}</encoding>
-                    <compilerArgument>-proc:none</compilerArgument>
+<!--                    <compilerArgument>-proc:none</compilerArgument>-->
                 </configuration>
             </plugin>
 

release.bat

@@ -10,9 +10,9 @@ ECHO "============================= RELEASE START..."
 
 :: 版本号信息(需要手动指定)
 :::: 旧版本名称
-SET version=0.1.1
+SET version=0.2.0
 :::: 新版本名称
-SET newVersion=0.1.2
+SET newVersion=0.2.1
 :::: 组织名称
 SET groupName=com.github.houbb
 :::: 项目名称

src/main/java/com/github/houbb/sensitive/word/api/ISensitiveWordReplace.java

@@ -0,0 +1,19 @@
+package com.github.houbb.sensitive.word.api;
+
+/**
+ * 敏感词替换策略
+ *
+ * @author binbin.hou
+ * @since 0.2.0
+ */
+public interface ISensitiveWordReplace {
+
+    /**
+     * 替换
+     * @param context 上下文
+     * @return 结果
+     * @since 0.2.0
+     */
+    String replace(ISensitiveWordReplaceContext context);
+
+}

src/main/java/com/github/houbb/sensitive/word/api/ISensitiveWordReplaceContext.java

@@ -0,0 +1,25 @@
+package com.github.houbb.sensitive.word.api;
+
+/**
+ * 敏感词替换策略上下文
+ *
+ * @author binbin.hou
+ * @since 0.2.0
+ */
+public interface ISensitiveWordReplaceContext {
+
+    /**
+     * 敏感词
+     * @return 敏感词
+     * @since 0.2.0
+     */
+    String sensitiveWord();
+
+    /**
+     * 单词长度
+     * @return 单词长度
+     * @since 0.2.0
+     */
+    int wordLength();
+
+}

src/main/java/com/github/houbb/sensitive/word/api/IWordMap.java

@@ -59,12 +59,13 @@ public interface IWordMap extends ISensitiveCheck {
      * ps: 这里可以添加优化。
      *
      * @param target 目标字符串
-     * @param replaceChar 替换为的 char
+     * @param replace 替换策略
      * @param context 上下文
      * @return 替换后结果
      * @since 0.0.2
      */
-    String replace(final String target, final char replaceChar,
+    String replace(final String target,
+                   final ISensitiveWordReplace replace,
                    final IWordContext context);
 
 }

src/main/java/com/github/houbb/sensitive/word/bs/SensitiveWordBs.java

@@ -8,6 +8,7 @@ import com.github.houbb.sensitive.word.api.*;
 import com.github.houbb.sensitive.word.support.allow.WordAllows;
 import com.github.houbb.sensitive.word.support.deny.WordDenys;
 import com.github.houbb.sensitive.word.support.map.SensitiveWordMap;
+import com.github.houbb.sensitive.word.support.replace.SensitiveWordReplaceChar;
 import com.github.houbb.sensitive.word.support.result.WordResultHandlers;
 import com.github.houbb.sensitive.word.utils.InnerFormatUtils;
 
@@ -393,9 +394,23 @@ public class SensitiveWordBs {
      * @since 0.0.2
      */
     public String replace(final String target, final char replaceChar) {
+        ISensitiveWordReplace replace = new SensitiveWordReplaceChar(replaceChar);
+
+        return replace(target, replace);
+    }
+
+    /**
+     * 替换所有内容
+     *
+     * @param target      目标字符串
+     * @param replace 替换策略
+     * @return 替换后结果
+     * @since 0.2.0
+     */
+    public String replace(final String target, final ISensitiveWordReplace replace) {
         statusCheck();
 
-        return sensitiveWordMap.replace(target, replaceChar, context);
+        return sensitiveWordMap.replace(target, replace, context);
     }
 
     /**

src/main/java/com/github/houbb/sensitive/word/core/SensitiveWordHelper.java

@@ -1,5 +1,6 @@
 package com.github.houbb.sensitive.word.core;
 
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplace;
 import com.github.houbb.sensitive.word.api.IWordResultHandler;
 import com.github.houbb.sensitive.word.bs.SensitiveWordBs;
 
@@ -59,6 +60,18 @@ public final class SensitiveWordHelper {
         return WORD_BS.findFirst(target);
     }
 
+    /**
+     * 替换所有内容
+     *
+     * @param target      目标字符串
+     * @param replace 替换策略
+     * @return 替换后结果
+     * @since 0.2.0
+     */
+    public static String replace(final String target, final ISensitiveWordReplace replace) {
+        return WORD_BS.replace(target, replace);
+    }
+
     /**
      * 替换所有内容
      *

src/main/java/com/github/houbb/sensitive/word/support/map/SensitiveWordMap.java

@@ -9,14 +9,13 @@ import com.github.houbb.heaven.util.lang.ObjectUtil;
 import com.github.houbb.heaven.util.lang.StringUtil;
 import com.github.houbb.heaven.util.util.CollectionUtil;
 import com.github.houbb.heaven.util.util.MapUtil;
-import com.github.houbb.sensitive.word.api.IWordContext;
-import com.github.houbb.sensitive.word.api.IWordMap;
-import com.github.houbb.sensitive.word.api.IWordResult;
+import com.github.houbb.sensitive.word.api.*;
 import com.github.houbb.sensitive.word.constant.AppConst;
 import com.github.houbb.sensitive.word.constant.enums.ValidModeEnum;
 import com.github.houbb.sensitive.word.support.check.SensitiveCheckResult;
 import com.github.houbb.sensitive.word.support.check.impl.SensitiveCheckChain;
 import com.github.houbb.sensitive.word.support.check.impl.SensitiveCheckUrl;
+import com.github.houbb.sensitive.word.support.replace.SensitiveWordReplaceContext;
 import com.github.houbb.sensitive.word.support.result.WordResult;
 
 import java.util.Collection;
@@ -156,12 +155,12 @@ public class SensitiveWordMap implements IWordMap {
     }
 
     @Override
-    public String replace(String target, char replaceChar, final IWordContext context) {
+    public String replace(String target, final ISensitiveWordReplace replace, final IWordContext context) {
         if(StringUtil.isEmpty(target)) {
             return target;
         }
 
-        return this.replaceSensitiveWord(target, replaceChar, context);
+        return this.replaceSensitiveWord(target, replace, context);
     }
 
     /**
@@ -213,11 +212,13 @@ public class SensitiveWordMap implements IWordMap {
     /**
      * 直接替换敏感词，返回替换后的结果
      * @param target           文本信息
+     * @param replace 替换策略
+     * @param context 上下文
      * @return 脱敏后的字符串
      * @since 0.0.2
      */
     private String replaceSensitiveWord(final String target,
-                                        final char replaceChar,
+                                        final ISensitiveWordReplace replace,
                                         final IWordContext context) {
         if(StringUtil.isEmpty(target)) {
             return target;
@@ -241,7 +242,12 @@ public class SensitiveWordMap implements IWordMap {
                     // 直接使用原始内容，避免 markdown 图片转换失败
                     resultBuilder.append(string);
                 } else {
-                    String replaceStr = CharUtil.repeat(replaceChar, wordLength);
+                    // 创建上下文
+                    ISensitiveWordReplaceContext replaceContext = SensitiveWordReplaceContext.newInstance()
+                            .sensitiveWord(string)
+                            .wordLength(wordLength);
+                    String replaceStr = replace.replace(replaceContext);
+
                     resultBuilder.append(replaceStr);
                 }
 

src/main/java/com/github/houbb/sensitive/word/support/replace/SensitiveWordReplaceChar.java

@@ -0,0 +1,29 @@
+package com.github.houbb.sensitive.word.support.replace;
+
+import com.github.houbb.heaven.annotation.ThreadSafe;
+import com.github.houbb.heaven.util.lang.CharUtil;
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplace;
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplaceContext;
+
+/**
+ * 指定字符的替换策略
+ * @author binbin.hou
+ * @since 0.2.0
+ */
+@ThreadSafe
+public class SensitiveWordReplaceChar implements ISensitiveWordReplace {
+
+    private final char replaceChar;
+
+    public SensitiveWordReplaceChar(char replaceChar) {
+        this.replaceChar = replaceChar;
+    }
+
+    @Override
+    public String replace(ISensitiveWordReplaceContext context) {
+        int wordLength = context.wordLength();
+
+        return CharUtil.repeat(replaceChar, wordLength);
+    }
+
+}

src/main/java/com/github/houbb/sensitive/word/support/replace/SensitiveWordReplaceContext.java

@@ -0,0 +1,57 @@
+package com.github.houbb.sensitive.word.support.replace;
+
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplaceContext;
+
+/**
+ * 敏感词替换上下文
+ *
+ * @author binbin.hou
+ * @since 0.2.0
+ */
+public class SensitiveWordReplaceContext implements ISensitiveWordReplaceContext {
+
+    public static SensitiveWordReplaceContext newInstance() {
+        return new SensitiveWordReplaceContext();
+    }
+
+    /**
+     * 敏感词
+     * @since 0.2.0
+     */
+    private String sensitiveWord;
+
+    /**
+     * 单词长度
+     * @since 0.2.0
+     */
+    private int wordLength;
+
+    @Override
+    public String sensitiveWord() {
+        return sensitiveWord;
+    }
+
+    public SensitiveWordReplaceContext sensitiveWord(String sensitiveWord) {
+        this.sensitiveWord = sensitiveWord;
+        return this;
+    }
+
+    @Override
+    public int wordLength() {
+        return wordLength;
+    }
+
+    public SensitiveWordReplaceContext wordLength(int wordLength) {
+        this.wordLength = wordLength;
+        return this;
+    }
+
+    @Override
+    public String toString() {
+        return "SensitiveWordReplaceContext{" +
+                "sensitiveWord='" + sensitiveWord + '\'' +
+                ", wordLength=" + wordLength +
+                '}';
+    }
+
+}

src/test/java/com/github/houbb/sensitive/word/core/SensitiveWordHelperTest.java

@@ -1,6 +1,8 @@
 package com.github.houbb.sensitive.word.core;
 
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplace;
 import com.github.houbb.sensitive.word.api.IWordResult;
+import com.github.houbb.sensitive.word.replace.MySensitiveWordReplace;
 import com.github.houbb.sensitive.word.support.result.WordResultHandlers;
 import org.junit.Assert;
 import org.junit.Test;
@@ -148,4 +150,18 @@ public class SensitiveWordHelperTest {
         Assert.assertEquals("ｆｕｃｋ", word);
     }
 
+    /**
+     * 自定替换策略
+     * @since 0.2.0
+     */
+    @Test
+    public void defineReplaceTest() {
+        final String text = "五星红旗迎风飘扬，毛主席的画像屹立在天安门前。";
+
+        ISensitiveWordReplace replace = new MySensitiveWordReplace();
+        String result = SensitiveWordHelper.replace(text, replace);
+
+        Assert.assertEquals("国家旗帜迎风飘扬，教员的画像屹立在***前。", result);
+    }
+
 }

src/test/java/com/github/houbb/sensitive/word/replace/MySensitiveWordReplace.java

@@ -0,0 +1,31 @@
+package com.github.houbb.sensitive.word.replace;
+
+import com.github.houbb.heaven.util.lang.CharUtil;
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplace;
+import com.github.houbb.sensitive.word.api.ISensitiveWordReplaceContext;
+
+/**
+ * 自定义敏感词替换策略
+ *
+ * @author binbin.hou
+ * @since 0.2.0
+ */
+public class MySensitiveWordReplace implements ISensitiveWordReplace {
+
+    @Override
+    public String replace(ISensitiveWordReplaceContext context) {
+        String sensitiveWord = context.sensitiveWord();
+        // 自定义不同的敏感词替换策略，可以从数据库等地方读取
+        if("五星红旗".equals(sensitiveWord)) {
+            return "国家旗帜";
+        }
+        if("毛主席".equals(sensitiveWord)) {
+            return "教员";
+        }
+
+        // 其他默认使用 * 代替
+        int wordLength = context.wordLength();
+        return CharUtil.repeat('*', wordLength);
+    }
+
+}