github/sensitive-word
1
0
Fork 0
mirror of https://github.com/houbb/sensitive-word.git synced 2026-03-22 08:27:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

release branch 0.13.0

Browse Source
This commit is contained in:
houbb
2024-02-19 20:04:46 +08:00
parent f745bc49cf
commit 8772b1b810
15 changed files with 374 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
CHANGE_LOG.md
View File

@@ -224,4 +224,10 @@
| 序号 | 变更类型 | 说明 | 时间 | 备注 |
|:---|:-----|----------------------------------------------|:--------------------|:------|
| 1 | A | 添加 wordTags 标签结果处理类 | 2023-12-18 23:51:58 | |
| 2 | A | 添加 AbstractWordResultHandler 处理类，便于后续拓展和统一管理 | 2023-12-18 23:51:58 | |
| 2 | A | 添加 AbstractWordResultHandler 处理类，便于后续拓展和统一管理 | 2023-12-18 23:51:58 | |
# release_0.13.0
| 序号 | 变更类型 | 说明 | 时间 | 备注 |
|:---|:-----|-----------------------------------|:--------------------|:------|
| 1 | A | 对匹配后的单词，额外可以做一次校验，比如做一次英文全词匹配的验证。 | 2024-02-19 23:51:58 | |

85
README.md
View File

@@ -82,7 +82,7 @@
<dependency>
<groupId>com.github.houbb</groupId>
<artifactId>sensitive-word</artifactId>
<version>0.12.0</version>
<version>0.13.0</version>
</dependency>
```
@@ -429,6 +429,7 @@ SensitiveWordBs wordBs = SensitiveWordBs.newInstance()
.numCheckLen(8)
.wordTag(WordTags.none())
.charIgnore(SensitiveWordCharIgnores.defaults())
.wordResultCondition(WordResultConditions.alwaysTrue())
.init();
final String text = "五星红旗迎风飘扬，毛主席的画像屹立在天安门前。";
@@ -438,22 +439,74 @@ Assert.assertTrue(wordBs.contains(text));
其中各项配置的说明如下：
| 序号 | 方法 | 说明 | 默认值 |
|:---|:---------------------|:--------------|:------|
| 1 | ignoreCase | 忽略大小写 | true |
| 2 | ignoreWidth | 忽略半角圆角 | true |
| 3 | ignoreNumStyle | 忽略数字的写法 | true |
| 4 | ignoreChineseStyle | 忽略中文的书写格式 | true |
| 5 | ignoreEnglishStyle | 忽略英文的书写格式 | true |
| 6 | ignoreRepeat | 忽略重复词 | false |
| 7 | enableNumCheck | 是否启用数字检测。 | true |
| 8 | enableEmailCheck | 是有启用邮箱检测 | true |
| 9 | enableUrlCheck | 是否启用链接检测 | true |
| 10 | enableWordCheck | 是否启用敏感单词检测 | true |
| 11 | numCheckLen | 数字检测，自定义指定长度。 | 8 |
| 12 | wordTag | 词对应的标签 | none |
| 13 | charIgnore | 忽略的字符 | none |
| 序号 | 方法 | 说明 | 默认值 |
|:---|:---------------------|:-----------------------------|:------|
| 1 | ignoreCase | 忽略大小写 | true |
| 2 | ignoreWidth | 忽略半角圆角 | true |
| 3 | ignoreNumStyle | 忽略数字的写法 | true |
| 4 | ignoreChineseStyle | 忽略中文的书写格式 | true |
| 5 | ignoreEnglishStyle | 忽略英文的书写格式 | true |
| 6 | ignoreRepeat | 忽略重复词 | false |
| 7 | enableNumCheck | 是否启用数字检测。 | true |
| 8 | enableEmailCheck | 是有启用邮箱检测 | true |
| 9 | enableUrlCheck | 是否启用链接检测 | true |
| 10 | enableWordCheck | 是否启用敏感单词检测 | true |
| 11 | numCheckLen | 数字检测，自定义指定长度。 | 8 |
| 12 | wordTag | 词对应的标签 | none |
| 13 | charIgnore | 忽略的字符 | none |
| 14 | wordResultCondition | 针对匹配的敏感词额外加工，比如可以限制英文单词必须全匹配 | 恒为真 |
# wordResultCondition-针对匹配词进一步判断
## 说明
支持版本：v0.13.0
有时候我们可能希望对匹配的敏感词进一步限制，比如虽然我们定义了【av】作为敏感词，但是不希望【have】被匹配。
就可以自定义实现 wordResultCondition 接口，实现自己的策略。
系统内置的策略在 WordResultConditions#alwaysTrue() 恒为真，WordResultConditions#englishWordMatch() 则要求英文必须全词匹配。
## 入门例子
原始的默认情况：
```java
final String text = "I have a nice day。";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Collections.singletonList("av");
}
})
.wordResultCondition(WordResultConditions.alwaysTrue())
.init()
.findAll(text);
Assert.assertEquals("[av]", wordList.toString());
```
我们可以指定为英文必须全词匹配。
```java
final String text = "I have a nice day。";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Collections.singletonList("av");
}
})
.wordResultCondition(WordResultConditions.englishWordMatch())
.init()
.findAll(text);
Assert.assertEquals("[]", wordList.toString());
```
当然可以根据需要实现更加复杂的策略。
# 忽略字符

2
pom.xml
View File

@@ -6,7 +6,7 @@
<groupId>com.github.houbb</groupId>
<artifactId>sensitive-word</artifactId>
<version>0.12.0</version>
<version>0.13.0</version>
<properties>
<!--============================== All Plugins START ==============================-->

4
release.bat
View File

@@ -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=0.12.0
SET version=0.13.0
:::: 新版本名称
SET newVersion=0.13.0
SET newVersion=0.14.0
:::: 组织名称
SET groupName=com.github.houbb
:::: 项目名称

4
src/main/java/com/github/houbb/sensitive/word/api/IWordContext.java
View File

@@ -241,4 +241,8 @@ public interface IWordContext {
SensitiveWordContext charIgnore(ISensitiveWordCharIgnore charIgnore);
IWordResultCondition wordResultCondition();
SensitiveWordContext wordResultCondition(IWordResultCondition wordResultCondition);
}

26
src/main/java/com/github/houbb/sensitive/word/api/IWordResultCondition.java Normal file
View File

@@ -0,0 +1,26 @@
package com.github.houbb.sensitive.word.api;
import com.github.houbb.sensitive.word.constant.enums.WordValidModeEnum;
/**
* 敏感词的结果是否匹配
* @author binbin.hou
* @since 0.13.0
*/
public interface IWordResultCondition {
/**
* 是否匹配
* @param wordResult 根据词匹配的结果
* @param text 原始文本
* @param modeEnum 枚举类别
* @param context 上下文
* @return 是否匹配
* @since 0.13.0
*/
boolean match(final IWordResult wordResult,
final String text,
final WordValidModeEnum modeEnum,
final IWordContext context);
}

15
src/main/java/com/github/houbb/sensitive/word/bs/SensitiveWordBs.java
View File

@@ -18,6 +18,7 @@ import com.github.houbb.sensitive.word.support.deny.WordDenys;
import com.github.houbb.sensitive.word.support.ignore.SensitiveWordCharIgnores;
import com.github.houbb.sensitive.word.support.replace.WordReplaces;
import com.github.houbb.sensitive.word.support.result.WordResultHandlers;
import com.github.houbb.sensitive.word.support.resultcondition.WordResultConditions;
import com.github.houbb.sensitive.word.support.tag.WordTags;
import java.util.Collection;
@@ -163,6 +164,12 @@ public class SensitiveWordBs {
*/
private ISensitiveWordCharIgnore charIgnore = SensitiveWordCharIgnores.defaults();
/**
* 敏感词结果匹配策略
* @since 0.13.0
*/
private IWordResultCondition wordResultCondition = WordResultConditions.alwaysTrue();
/**
* 新建验证实例
* <p>
@@ -233,10 +240,18 @@ public class SensitiveWordBs {
context.wordData(wordData);
context.wordTag(wordTag);
context.charIgnore(charIgnore);
context.wordResultCondition(wordResultCondition);
return context;
}
public SensitiveWordBs wordResultCondition(IWordResultCondition wordResultCondition) {
ArgUtil.notNull(wordResultCondition, "wordResultCondition");
this.wordResultCondition = wordResultCondition;
return this;
}
public SensitiveWordBs charIgnore(ISensitiveWordCharIgnore charIgnore) {
ArgUtil.notNull(charIgnore, "charIgnore");

16
src/main/java/com/github/houbb/sensitive/word/bs/SensitiveWordContext.java
View File

@@ -113,6 +113,13 @@ public class SensitiveWordContext implements IWordContext {
*/
private ISensitiveWordCharIgnore charIgnore;
/**
* 敏感词结果匹配
*
* @since 0.13.0
*/
private IWordResultCondition wordResultCondition;
public IWordData wordData() {
return wordData;
}
@@ -304,4 +311,13 @@ public class SensitiveWordContext implements IWordContext {
this.charIgnore = charIgnore;
return this;
}
public IWordResultCondition wordResultCondition() {
return wordResultCondition;
}
public SensitiveWordContext wordResultCondition(IWordResultCondition wordResultCondition) {
this.wordResultCondition = wordResultCondition;
return this;
}
}

11
src/main/java/com/github/houbb/sensitive/word/core/SensitiveWord.java
View File

@@ -1,10 +1,7 @@
package com.github.houbb.sensitive.word.core;
import com.github.houbb.heaven.util.guava.Guavas;
import com.github.houbb.sensitive.word.api.IWordCheck;
import com.github.houbb.sensitive.word.api.ISensitiveWord;
import com.github.houbb.sensitive.word.api.IWordContext;
import com.github.houbb.sensitive.word.api.IWordResult;
import com.github.houbb.sensitive.word.api.*;
import com.github.houbb.sensitive.word.api.context.InnerSensitiveWordContext;
import com.github.houbb.sensitive.word.constant.enums.WordValidModeEnum;
import com.github.houbb.sensitive.word.support.check.WordCheckResult;
@@ -59,6 +56,7 @@ public class SensitiveWord extends AbstractSensitiveWord {
.wordContext(context)
.modeEnum(WordValidModeEnum.FAIL_OVER)
.formatCharMapping(characterCharacterMap);
final IWordResultCondition wordResultCondition = context.wordResultCondition();
for (int i = 0; i < text.length(); i++) {
WordCheckResult checkResult = sensitiveCheck.sensitiveCheck(i, checkContext);
@@ -70,7 +68,10 @@ public class SensitiveWord extends AbstractSensitiveWord {
WordResult wordResult = WordResult.newInstance()
.startIndex(i)
.endIndex(i+wordLength);
resultList.add(wordResult);
//v0.13.0 添加判断
if(wordResultCondition.match(wordResult, text, modeEnum, context)) {
resultList.add(wordResult);
}
// 快速返回
if (WordValidModeEnum.FAIL_FAST.equals(modeEnum)) {

22
src/main/java/com/github/houbb/sensitive/word/support/resultcondition/AbstractWordResultCondition.java Normal file
View File

@@ -0,0 +1,22 @@
package com.github.houbb.sensitive.word.support.resultcondition;
import com.github.houbb.sensitive.word.api.IWordContext;
import com.github.houbb.sensitive.word.api.IWordResult;
import com.github.houbb.sensitive.word.api.IWordResultCondition;
import com.github.houbb.sensitive.word.constant.enums.WordValidModeEnum;
/**
* 抽象实现
*
* @since 0.13.0
*/
public abstract class AbstractWordResultCondition implements IWordResultCondition {
protected abstract boolean doMatch(IWordResult wordResult, String text, WordValidModeEnum modeEnum, IWordContext context);
@Override
public boolean match(IWordResult wordResult, String text, WordValidModeEnum modeEnum, IWordContext context) {
return doMatch(wordResult, text, modeEnum, context);
}
}

19
src/main/java/com/github/houbb/sensitive/word/support/resultcondition/WordResultConditionAlwaysTrue.java Normal file
View File

@@ -0,0 +1,19 @@
package com.github.houbb.sensitive.word.support.resultcondition;
import com.github.houbb.sensitive.word.api.IWordContext;
import com.github.houbb.sensitive.word.api.IWordResult;
import com.github.houbb.sensitive.word.constant.enums.WordValidModeEnum;
/**
* 恒为真
*
* @since 0.13.0
*/
public class WordResultConditionAlwaysTrue extends AbstractWordResultCondition {
@Override
protected boolean doMatch(IWordResult wordResult, String text, WordValidModeEnum modeEnum, IWordContext context) {
return true;
}
}

50
src/main/java/com/github/houbb/sensitive/word/support/resultcondition/WordResultConditionEnglishWordMatch.java Normal file
View File

@@ -0,0 +1,50 @@
package com.github.houbb.sensitive.word.support.resultcondition;
import com.github.houbb.heaven.util.lang.CharUtil;
import com.github.houbb.heaven.util.util.CharsetUtil;
import com.github.houbb.sensitive.word.api.IWordContext;
import com.github.houbb.sensitive.word.api.IWordResult;
import com.github.houbb.sensitive.word.constant.enums.WordValidModeEnum;
/**
* 英文单词必须要全词匹配
*
* https://github.com/houbb/sensitive-word/issues/45
*
* @since 0.13.0
*/
public class WordResultConditionEnglishWordMatch extends AbstractWordResultCondition {
@Override
protected boolean doMatch(IWordResult wordResult, String text, WordValidModeEnum modeEnum, IWordContext context) {
final int startIndex = wordResult.startIndex();
final int endIndex = wordResult.endIndex();
// 判断当前是否为英文单词
for(int i = startIndex; i < endIndex; i++) {
char c = text.charAt(i);
if(!CharUtil.isEnglish(c)) {
return true;
}
}
// 判断处理，判断前一个字符是否为英文。如果是，则不满足
if(startIndex > 0) {
char preC = text.charAt(startIndex-1);
if(CharUtil.isEnglish(preC)) {
return false;
}
}
// 判断后一个字符是否为英文
if(endIndex < text.length() - 1) {
char afterC = text.charAt(endIndex+1);
if(CharUtil.isEnglish(afterC)) {
return false;
}
}
return true;
}
}

29
src/main/java/com/github/houbb/sensitive/word/support/resultcondition/WordResultConditions.java Normal file
View File

@@ -0,0 +1,29 @@
package com.github.houbb.sensitive.word.support.resultcondition;
import com.github.houbb.sensitive.word.api.IWordResultCondition;
/**
* 匹配结果工具类
*
* @since 0.13.0
*/
public final class WordResultConditions {
/**
* 恒为真
* @return 结果
*/
public static IWordResultCondition alwaysTrue() {
return new WordResultConditionAlwaysTrue();
}
/**
* 如果是英文，则必须全词匹匹配
* @return 结果
* @since 0.13.0
*/
public static IWordResultCondition englishWordMatch() {
return new WordResultConditionEnglishWordMatch();
}
}

2
src/test/java/com/github/houbb/sensitive/word/bs/SensitiveWordBsConfigTest.java
View File

@@ -3,6 +3,7 @@ package com.github.houbb.sensitive.word.bs;
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.ignore.SensitiveWordCharIgnores;
import com.github.houbb.sensitive.word.support.resultcondition.WordResultConditions;
import com.github.houbb.sensitive.word.support.tag.WordTags;
import org.junit.Assert;
import org.junit.Test;
@@ -31,6 +32,7 @@ public class SensitiveWordBsConfigTest {
.numCheckLen(8)
.wordTag(WordTags.none())
.charIgnore(SensitiveWordCharIgnores.defaults())
.wordResultCondition(WordResultConditions.alwaysTrue())
.init();
final String text = "五星红旗迎风飘扬，毛主席的画像屹立在天安门前。";

106
src/test/java/com/github/houbb/sensitive/word/bs/SensitiveWordBsResultConditionTest.java Normal file
View File

@@ -0,0 +1,106 @@
package com.github.houbb.sensitive.word.bs;
import com.github.houbb.sensitive.word.api.IWordDeny;
import com.github.houbb.sensitive.word.support.resultcondition.WordResultConditions;
import org.junit.Assert;
import org.junit.Test;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
/**
* <p> project: sensitive-word-SensitiveWordBsTest </p>
* <p> create on 2020/1/7 23:43 </p>
*
* @author Administrator
* @since 0.13.0
*/
public class SensitiveWordBsResultConditionTest {
@Test
public void alwaysTrueTest() {
final String text = "I have a nice day。";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Collections.singletonList("av");
}
})
.wordResultCondition(WordResultConditions.alwaysTrue())
.init()
.findAll(text);
Assert.assertEquals("[av]", wordList.toString());
}
@Test
public void englishWordMatchTest() {
final String text = "I have a nice day。";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Collections.singletonList("av");
}
})
.wordResultCondition(WordResultConditions.englishWordMatch())
.init()
.findAll(text);
Assert.assertEquals("[]", wordList.toString());
}
@Test
public void englishWordMatchTest2() {
final String text = "I hav";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Arrays.asList("av");
}
})
.wordResultCondition(WordResultConditions.englishWordMatch())
.init()
.findAll(text);
Assert.assertEquals("[]", wordList.toString());
}
@Test
public void englishWordMatchTest3() {
final String text = "av";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Arrays.asList("av");
}
})
.wordResultCondition(WordResultConditions.englishWordMatch())
.init()
.findAll(text);
Assert.assertEquals("[av]", wordList.toString());
}
@Test
public void englishWordMatchTest4() {
final String text = "I have a nice day";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Arrays.asList("av", "day");
}
})
.wordResultCondition(WordResultConditions.englishWordMatch())
.init()
.findAll(text);
Assert.assertEquals("[day]", wordList.toString());
}
}