github/sensitive-word
1
0
Fork 0
mirror of https://github.com/houbb/sensitive-word.git synced 2026-03-22 00:17:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

release branch 0.20.0

Browse Source
This commit is contained in:
binbin.hou
2024-09-18 16:51:04 +08:00
parent 482384ef85
commit 2e7cf1a380
7 changed files with 132 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CHANGE_LOG.md
View File

@@ -355,3 +355,9 @@
| 序号 | 变更类型 | 说明 | 时间 | 备注 |
|:---|:-----|--------------------------------------------------------|:-------------------|:--------------------------------------------------|
| 1 | F | 修正 #68 SensitiveWordCharIgnores.specialChars() 误判命中开始的问题 | 2024-8-28 15:02:25 | https://github.com/houbb/sensitive-word/issues/68 |
# release_0.20.0
| 序号 | 变更类型 | 说明 | 时间 | 备注 |
|:---|:-----|-----------|:-------------------|:--------------------------------------------------|
| 1 | A | 支持数字的全词匹配 | 2024-9-18 16:39:40 | https://github.com/houbb/sensitive-word/issues/77 |

20
README.md
View File

@@ -59,13 +59,9 @@
- 针对单个词的新增/删除，无需全量初始化
- 新增 allow/deny 空实现
### V0.19.1
### V0.20.0
- 修正 englishWordMatch #69 单个英文字符命中错误问题
### V0.19.2
- 修正 #68 `SensitiveWordCharIgnores.specialChars()` 误判命中开始的问题
- 新增数字+英文的全词匹配实现
## 更多资料
@@ -557,7 +553,17 @@ Assert.assertEquals("[]", sensitiveWordBs.findAll(text).toString());
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
## 内置策略
WordResultConditions 工具类可以获取匹配策略
| 实现 | 说明 | 支持版本 |
|:----|:------------|:--------|
| alwaysTrue | 恒为真 | |
| englishWordMatch | 英文单词全词匹配 | v0.13.0 |
| englishWordNumMatch | 英文单词/数字全词匹配 | v0.20.0 |
## 使用例子
原始的默认情况：

2
pom.xml
View File

@@ -6,7 +6,7 @@
<groupId>com.github.houbb</groupId>
<artifactId>sensitive-word</artifactId>
<version>0.19.2</version>
<version>0.20.0</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=0.19.2
SET version=0.20.0
:::: 新版本名称
SET newVersion=0.20.0
SET newVersion=0.21.0
:::: 组织名称
SET groupName=com.github.houbb
:::: 项目名称

50
src/main/java/com/github/houbb/sensitive/word/support/resultcondition/WordResultConditionEnglishWordNumMatch.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.sensitive.word.api.IWordContext;
import com.github.houbb.sensitive.word.api.IWordResult;
import com.github.houbb.sensitive.word.constant.enums.WordValidModeEnum;
/**
* 英文单词和数字必须要全词匹配
*
* https://github.com/houbb/sensitive-word/issues/77
*
* @since 0.20.0
*/
public class WordResultConditionEnglishWordNumMatch 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.isDigitOrLetter(preC)) {
return false;
}
}
// 判断后一个字符是否为英文
// v0.19.1 修正 cp cpm 单个字符错误命中问题
if(endIndex < text.length()) {
char afterC = text.charAt(endIndex);
if(CharUtil.isDigitOrLetter(afterC)) {
return false;
}
}
// 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.isDigitOrLetter(c)) {
return true;
}
}
return true;
}
}

9
src/main/java/com/github/houbb/sensitive/word/support/resultcondition/WordResultConditions.java
View File

@@ -26,4 +26,13 @@ public final class WordResultConditions {
return new WordResultConditionEnglishWordMatch();
}
/**
* 如果是英文或者数字，则必须全词匹匹配
* @return 结果
* @since 0.20.0
*/
public static IWordResultCondition englishWordNumMatch() {
return new WordResultConditionEnglishWordNumMatch();
}
}

51
src/test/java/com/github/houbb/sensitive/word/bs/SensitiveWordBsResultConditionTest.java
View File

@@ -137,4 +137,55 @@ public class SensitiveWordBsResultConditionTest {
Assert.assertEquals("[cp]", wordList.toString());
}
@Test
public void englishWordNumMatchTest1() {
final String text = "cp cpm trade deficit totaled 695 billion yen, or $4.9 billion";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Arrays.asList("cp", "69");
}
})
.wordResultCondition(WordResultConditions.englishWordMatch())
.init()
.findAll(text);
Assert.assertEquals("[cp, 69]", wordList.toString());
}
@Test
public void englishWordNumMatchTest2() {
final String text = "cp cpm trade deficit totaled 695 billion yen, or $4.9 billion";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Arrays.asList("cp", "69");
}
})
.wordResultCondition(WordResultConditions.englishWordNumMatch())
.init()
.findAll(text);
Assert.assertEquals("[cp]", wordList.toString());
}
@Test
public void englishWordNumMatchTest3() {
final String text = "cp cpm trade deficit totaled 695 billion yen, or $4.9 billion 69";
List<String> wordList = SensitiveWordBs.newInstance()
.wordDeny(new IWordDeny() {
@Override
public List<String> deny() {
return Arrays.asList("cp", "69");
}
})
.wordResultCondition(WordResultConditions.englishWordNumMatch())
.init()
.findAll(text);
Assert.assertEquals("[cp, 69]", wordList.toString());
}
}