release branch 0.18.0

CHANGE_LOG.md

@@ -324,3 +324,9 @@
 | 序号 | 变更类型 | 说明      | 时间                | 备注    |
 |:---|:-----|---------|:------------------|:------|
 | 1  | A    | IPV4 校验 | 2024-6-01 15:02:25 |    https://github.com/houbb/sensitive-word/issues/43   |
+
+# release_0.18.0
+
+| 序号 | 变更类型 | 说明                      | 时间                 | 备注   |
+|:---|:-----|-------------------------|:-------------------|:-----|
+| 1  | A    | 优化网址匹配策略，避免命中 1.jpg 之类的 | 2024-7-07 15:02:25 |   |

README.md

@@ -52,15 +52,14 @@
 
 [CHANGE_LOG.md](https://github.com/houbb/sensitive-word/blob/master/CHANGE_LOG.md)
 
-### V0.16.2: 
-
-- 移除部分敏感词
-- 默认关闭 url/email/num 的校验
-
 ### V0.17.0
 
 - 支持 ipv4
 
+### V0.18.0
+
+- 优化 URL 检测，降低误判率
+
 ## 更多资料
 
 ### 敏感词控台
@@ -91,7 +90,7 @@
 <dependency>
     <groupId>com.github.houbb</groupId>
     <artifactId>sensitive-word</artifactId>
-    <version>0.17.0</version>
+    <version>0.18.0</version>
 </dependency>
 ```
 
@@ -393,15 +392,14 @@ Assert.assertEquals("[]", wordList2.toString());
 
 用于过滤常见的网址信息，默认未启用。
 
-```java
+v0.18.0 优化 URL 检测，更加严格，降低误判率
-final String text = "点击链接 www.baidu.com查看答案";
-final SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance().enableUrlCheck(true).init();
-        
-        '
-List<String> wordList = sensitiveWordBs.findAll(text);
-Assert.assertEquals("[www.baidu.com]", wordList.toString());
 
-Assert.assertEquals("点击链接 *************查看答案", sensitiveWordBs.replace(text));
+```java
+final String text = "点击链接 https://www.baidu.com 查看答案";
+final SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance().enableUrlCheck(true).init();
+List<String> wordList = sensitiveWordBs.findAll(text);
+Assert.assertEquals("[https://www.baidu.com]", wordList.toString());
+Assert.assertEquals("点击链接 ********************* 查看答案", sensitiveWordBs.replace(text));
 ```
 
 ### IPV4 检测

pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.github.houbb</groupId>
     <artifactId>sensitive-word</artifactId>
-    <version>0.17.0</version>
+    <version>0.18.0</version>
 
     <properties>
         <!--============================== All Plugins START ==============================-->
@@ -25,7 +25,7 @@
         <project.compiler.level>1.7</project.compiler.level>
 
         <!--============================== INTER ==============================-->
-        <heaven.version>0.10.0</heaven.version>
+        <heaven.version>0.11.0</heaven.version>
         <opencc4j.version>1.8.1</opencc4j.version>
 
         <!--============================== OTHER ==============================-->

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=0.17.0
+SET version=0.18.0
 :::: 新版本名称
-SET newVersion=0.18.0
+SET newVersion=0.19.0
 :::: 组织名称
 SET groupName=com.github.houbb
 :::: 项目名称

src/main/java/com/github/houbb/sensitive/word/support/check/WordCheckUrl.java

@@ -44,7 +44,7 @@ public class WordCheckUrl extends AbstractConditionWordCheck {
 
     @Override
     protected boolean isCharCondition(char mappingChar, int index, InnerSensitiveWordContext checkContext) {
-        return CharUtil.isWebSiteChar(mappingChar);
+        return CharUtil.isWebSiteChar(mappingChar) || mappingChar == ':' || mappingChar == '/';
     }
 
     @Override
@@ -58,8 +58,9 @@ public class WordCheckUrl extends AbstractConditionWordCheck {
             return false;
         }
 
+        // 改为 http:// 或者 https:// 开头
         String string = stringBuilder.toString();
-        return RegexUtil.isWebSite(string);
+        return RegexUtil.isUrl(string);
     }
 
 }

src/test/java/com/github/houbb/sensitive/word/bs/SensitiveWordBsUrlTest.java

@@ -20,13 +20,13 @@ public class SensitiveWordBsUrlTest {
      */
     @Test
     public void commonUrlTest() {
-        final String text = "点击链接 www.baidu.com查看答案";
+        final String text = "点击链接 https://www.baidu.com 查看答案";
 
         final SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance().enableUrlCheck(true).init();
         List<String> wordList = sensitiveWordBs.findAll(text);
-        Assert.assertEquals("[www.baidu.com]", wordList.toString());
+        Assert.assertEquals("[https://www.baidu.com]", wordList.toString());
 
-        Assert.assertEquals("点击链接 *************查看答案", sensitiveWordBs.replace(text));
+        Assert.assertEquals("点击链接 ********************* 查看答案", sensitiveWordBs.replace(text));
     }
 
     /**
@@ -39,15 +39,15 @@ public class SensitiveWordBsUrlTest {
      */
     @Test
     public void imageUrlTest() {
-        final String text = "双击查看大图 www.big-image.png查看";
+        final String text = "双击查看大图 http://www.big-image.png 查看";
 
         final SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance()
                 .enableUrlCheck(true)
                 .init();
         List<String> wordList = sensitiveWordBs.findAll(text);
-        Assert.assertEquals("[www.big-image.png]", wordList.toString());
+        Assert.assertEquals("[http://www.big-image.png]", wordList.toString());
 
-        Assert.assertEquals("双击查看大图 *****************查看", sensitiveWordBs.replace(text));
+        Assert.assertEquals("双击查看大图 ************************ 查看", sensitiveWordBs.replace(text));
     }
 
 }