Merge branch 'houbb:master' into master

CHANGE_LOG.md

@@ -393,3 +393,30 @@
 |:---|:-----|----------------|:--------------------|:--------------|
 | 1  | A    | 内置支持多个单词标签实现策略 | 2024-12-22 14:08:20 | 强化单词标签能力，方便复用 |
 | 2  | O    | 升级 heaven 依赖   | 2024-12-22 14:08:20 |  |
+
+# release_0.24.1
+
+| 序号 | 变更类型 | 说明         | 时间                | 备注             |
+|:---|:-----|------------|:------------------|:---------------|
+| 1  | F    | 删除时添加同步锁优化 | 2025-2-2 15:30:26 | 涉及到接口调整 PR-100 |
+
+# release_0.24.2
+
+| 序号 | 变更类型 | 说明                  | 时间                | 备注                 |
+|:---|:-----|---------------------|:------------------|:-------------------|
+| 1  | O    | findFirst 真实实现，性能优化 | 2025-2-2 15:30:26 | PR-99              |
+| 2  | O    | 黑白名单遍历统一优化，性能优化     | 2025-2-2 15:30:26 | PR-99 涉及到原始结果返回值调整 |
+
+# release_0.25.0
+
+| 序号 | 变更类型 | 说明                   | 时间                 | 备注   |
+|:---|:-----|----------------------|:-------------------|:-----|
+| 1  | A    | wordCheck 策略支持用户自定义  | 2025-2-17 12:06:45 | https://github.com/houbb/sensitive-word/issues/101 |
+| 2  | A    | wordCheckUrlNoPrefix | 2025-2-17 12:06:45 | https://github.com/houbb/sensitive-word/issues/101 |
+
+# release_0.25.0
+
+| 序号 | 变更类型 | 说明                   | 时间                 | 备注   |
+|:---|:-----|----------------------|:-------------------|:-----|
+| 1  | A    | wordCheck 策略支持用户自定义  | 2025-2-17 12:06:45 | https://github.com/houbb/sensitive-word/issues/101 |
+| 2  | A    | wordCheckUrlNoPrefix | 2025-2-17 12:06:45 | https://github.com/houbb/sensitive-word/issues/101 |

README.md

@@ -58,14 +58,6 @@ v0.24.0 开始内置支持对敏感词的分类细化，不过工作量比较大
 
 [CHANGE_LOG.md](https://github.com/houbb/sensitive-word/blob/master/CHANGE_LOG.md)
 
-### V0.23.0
-
-- 结果条件拓展支持 wordTags 和 chains 
-
-### V0.24.0
-
-- 初步内置实现单词标签，丰富单词标签内置策略
-
 ## 更多资料
 
 ### 敏感词控台
@@ -104,7 +96,7 @@ v0.24.0 开始内置支持对敏感词的分类细化，不过工作量比较大
 <dependency>
     <groupId>com.github.houbb</groupId>
     <artifactId>sensitive-word</artifactId>
-    <version>0.24.0</version>
+    <version>0.25.0</version>
 </dependency>
 ```
 
@@ -370,6 +362,22 @@ Assert.assertEquals("[ⒻⒻⒻfⓤuⓤ⒰cⓒ⒦]", wordList.toString());
 
 ## 更多检测策略
 
+### 说明
+
+v0.25.0 目前的几个策略，也支持用户引导类自定义。所有的策略都是接口，支持用户自定义实现。
+
+| 序号 | 方法                   | 说明                                         | 默认值   |
+|:---|:---------------------|:-------------------------------------------|:------|
+| 16 | wordCheckNum          | 数字检测策略(v0.25.0开始支持)                        | `WordChecks.num()`   |
+| 17 | wordCheckEmail          | 邮箱检测策略(v0.25.0开始支持)                        | `WordChecks.email()`   |
+| 18 | wordCheckUrl          | URL检测策略(v0.25.0开始支持)，内置还是实现了 `urlNoPrefix()` | `(WordChecks.url()`   |
+| 19 | wordCheckIpv4          | ipv4检测策略(v0.25.0开始支持)                      | `WordChecks.ipv4()`   |
+| 20 | wordCheckWord          | 敏感词检测策略(v0.25.0开始支持)                       | `WordChecks.word()`   |
+
+内置实现：
+
+a) `WordChecks.urlNoPrefix()` 作为 url 的额外实现，可以不需要 `https://` 和 `http://` 前缀。 
+
 ### 邮箱检测
 
 邮箱等个人信息，默认未启用。
@@ -418,6 +426,21 @@ Assert.assertEquals("[https://www.baidu.com]", wordList.toString());
 Assert.assertEquals("点击链接 ********************* 查看答案", sensitiveWordBs.replace(text));
 ```
 
+v0.25.0 内置支持不需要 http 协议的前缀检测：
+
+```java
+final String text = "点击链接 https://www.baidu.com 查看答案，当然也可以是 baidu.com、www.baidu.com";
+
+final SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance()
+        .enableUrlCheck(true) // 启用URL检测
+        .wordCheckUrl(WordChecks.urlNoPrefix()) //指定检测的方式
+        .init();
+List<String> wordList = sensitiveWordBs.findAll(text);
+Assert.assertEquals("[www.baidu.com, baidu.com, www.baidu.com]", wordList.toString());
+
+Assert.assertEquals("点击链接 https://************* 查看答案，当然也可以是 *********、*************", sensitiveWordBs.replace(text));
+```
+
 ### IPV4 检测
 
 v0.17.0 支持
@@ -460,6 +483,11 @@ SensitiveWordBs wordBs = SensitiveWordBs.newInstance()
         .enableUrlCheck(false)
         .enableIpv4Check(false)
         .enableWordCheck(true)
+        .wordCheckNum(WordChecks.num())
+        .wordCheckEmail(WordChecks.email())
+        .wordCheckUrl(WordChecks.url())
+        .wordCheckIpv4(WordChecks.ipv4())
+        .wordCheckWord(WordChecks.word())
         .numCheckLen(8)
         .wordTag(WordTags.none())
         .charIgnore(SensitiveWordCharIgnores.defaults())
@@ -474,7 +502,7 @@ 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  |
@@ -490,6 +518,12 @@ Assert.assertTrue(wordBs.contains(text));
 | 13 | wordTag             | 词对应的标签                       | none  |
 | 14 | charIgnore          | 忽略的字符                        | none  |
 | 15 | 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   |
+| 16 | wordCheckNum        | 数字检测策略(v0.25.0开始支持)          | `WordChecks.num()`   |
+| 17 | wordCheckEmail      | 邮箱检测策略(v0.25.0开始支持)          | `WordChecks.email()`   |
+| 18 | wordCheckUrl        | URL检测策略(v0.25.0开始支持)         | `(WordChecks.url()`   |
+| 19 | wordCheckIpv4       | ipv4检测策略(v0.25.0开始支持)        | `WordChecks.ipv4()`   |
+| 20 | wordCheckWord       | 敏感词检测策略(v0.25.0开始支持)         | `WordChecks.word()`   |
+| 21 | wordReplace         | 替换策略                         | `WordReplaces.defaults()`   |
 
 ## 内存资源的释放
 

pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.github.houbb</groupId>
     <artifactId>sensitive-word</artifactId>
-    <version>0.24.0</version>
+    <version>0.25.0</version>
 
     <properties>
         <!--============================== All Plugins START ==============================-->

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=0.24.0
+SET version=0.25.0
 :::: 新版本名称
-SET newVersion=0.25.0
+SET newVersion=0.26.0
 :::: 组织名称
 SET groupName=com.github.houbb
 :::: 项目名称

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

@@ -31,6 +31,7 @@ public interface IWordCheck {
      * @param context       执行上下文
      * @return 敏感信息对应的长度
      * @since 0.0.5
+     * @since 0.24.2 为了黑白名单统一，调整了对应的返回值
      */
     WordCheckResult sensitiveCheck(final int beginIndex,
                                    final InnerSensitiveWordContext context);

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

@@ -275,4 +275,23 @@ public interface IWordContext {
 
     SensitiveWordContext wordResultCondition(IWordResultCondition wordResultCondition);
 
+    IWordCheck wordCheckWord();
+
+    SensitiveWordContext wordCheckWord(IWordCheck wordCheckWord);
+
+    IWordCheck wordCheckNum();
+
+    SensitiveWordContext wordCheckNum(IWordCheck wordCheckNum);
+
+    IWordCheck wordCheckEmail();
+
+    SensitiveWordContext wordCheckEmail(IWordCheck wordCheckEmail);
+
+    IWordCheck wordCheckUrl();
+
+    SensitiveWordContext wordCheckUrl(IWordCheck wordCheckUrl);
+
+    IWordCheck wordCheckIpv4();
+
+    SensitiveWordContext wordCheckIpv4(IWordCheck wordCheckIpv4);
 }

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

@@ -22,10 +22,10 @@ public interface IWordData extends ISensitiveWordDestroy {
 
     /**
      * 删除敏感词
-     * @param word 单词
+     * @param collection 单词
      * @since 0.19.0
      */
-    void removeWord(String word);
+    void removeWord(Collection<String> collection);
 
     /**
      * 新增敏感词

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

@@ -10,6 +10,7 @@ import com.github.houbb.sensitive.word.api.combine.IWordCheckCombine;
 import com.github.houbb.sensitive.word.api.combine.IWordFormatCombine;
 import com.github.houbb.sensitive.word.core.SensitiveWords;
 import com.github.houbb.sensitive.word.support.allow.WordAllows;
+import com.github.houbb.sensitive.word.support.check.WordChecks;
 import com.github.houbb.sensitive.word.support.combine.allowdeny.WordAllowDenyCombines;
 import com.github.houbb.sensitive.word.support.combine.check.WordCheckCombines;
 import com.github.houbb.sensitive.word.support.combine.format.WordFormatCombines;
@@ -182,6 +183,36 @@ public class SensitiveWordBs implements ISensitiveWordDestroy {
      */
     private IWordResultCondition wordResultCondition = WordResultConditions.alwaysTrue();
 
+    /**
+     * 单词检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckWord = WordChecks.word();
+
+    /**
+     * 数字检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckNum = WordChecks.num();
+
+    /**
+     * email 检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckEmail = WordChecks.email();
+
+    /**
+     * URL 检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckUrl = WordChecks.url();
+
+    /**
+     * ipv4 检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckIpv4 = WordChecks.ipv4();
+
     /**
      * 新建验证实例
      * <p>
@@ -255,6 +286,13 @@ public class SensitiveWordBs implements ISensitiveWordDestroy {
         context.enableWordCheck(enableWordCheck);
         context.enableIpv4Check(enableIpv4Check);
 
+        // 校验策略实现配置
+        context.wordCheckWord(wordCheckWord);
+        context.wordCheckEmail(wordCheckEmail);
+        context.wordCheckNum(wordCheckNum);
+        context.wordCheckUrl(wordCheckUrl);
+        context.wordCheckIpv4(wordCheckIpv4);
+
         // 额外配置
         context.sensitiveCheckNumLen(numCheckLen);
         context.wordReplace(wordReplace);
@@ -370,6 +408,41 @@ public class SensitiveWordBs implements ISensitiveWordDestroy {
         return this;
     }
 
+    public SensitiveWordBs wordCheckWord(IWordCheck wordCheckWord) {
+        ArgUtil.notNull(wordCheckWord, "wordCheckWord");
+
+        this.wordCheckWord = wordCheckWord;
+        return this;
+    }
+
+    public SensitiveWordBs wordCheckNum(IWordCheck wordCheckNum) {
+        ArgUtil.notNull(wordCheckNum, "wordCheckNum");
+
+        this.wordCheckNum = wordCheckNum;
+        return this;
+    }
+
+    public SensitiveWordBs wordCheckEmail(IWordCheck wordCheckEmail) {
+        ArgUtil.notNull(wordCheckEmail, "wordCheckEmail");
+
+        this.wordCheckEmail = wordCheckEmail;
+        return this;
+    }
+
+    public SensitiveWordBs wordCheckUrl(IWordCheck wordCheckUrl) {
+        ArgUtil.notNull(wordCheckUrl, "wordCheckUrl");
+
+        this.wordCheckUrl = wordCheckUrl;
+        return this;
+    }
+
+    public SensitiveWordBs wordCheckIpv4(IWordCheck wordCheckIpv4) {
+        ArgUtil.notNull(wordCheckIpv4, "wordCheckIpv4");
+
+        this.wordCheckIpv4 = wordCheckIpv4;
+        return this;
+    }
+
     //-------------------------------------------------------- 基础属性设置
     /**
      * 是否启用 ipv4 校验
@@ -642,9 +715,7 @@ public class SensitiveWordBs implements ISensitiveWordDestroy {
         // 主要原因是二者没有保持一致，初始化的数据和插入的数据没有做相同的格式化
         List<String> formatList = InnerWordFormatUtils.formatWordList(collection, context);
 
-        for(String word : formatList) {
+        this.wordData.removeWord(formatList);
-            this.wordData.removeWord(word);
-        }
     }
 
     /**
@@ -701,9 +772,8 @@ public class SensitiveWordBs implements ISensitiveWordDestroy {
         // 主要原因是二者没有保持一致，初始化的数据和插入的数据没有做相同的格式化
         List<String> formatList = InnerWordFormatUtils.formatWordList(collection, context);
 
-        for(String word : formatList) {
+        this.wordDataAllow.removeWord(formatList);
-            this.wordDataAllow.removeWord(word);
+
-        }
     }
     /**
      * 新增敏感词白名单

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

@@ -1,6 +1,7 @@
 package com.github.houbb.sensitive.word.bs;
 
 import com.github.houbb.sensitive.word.api.*;
+import com.github.houbb.sensitive.word.support.check.WordChecks;
 
 /**
  * 上下文
@@ -133,6 +134,36 @@ public class SensitiveWordContext implements IWordContext {
      */
     private IWordResultCondition wordResultCondition;
 
+    /**
+     * 单词检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckWord;
+
+    /**
+     * 数字检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckNum;
+
+    /**
+     * email 检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckEmail;
+
+    /**
+     * URL 检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckUrl;
+
+    /**
+     * ipv4 检测策略
+     * @since 0.25.0
+     */
+    private IWordCheck wordCheckIpv4;
+
     public IWordData wordData() {
         return wordData;
     }
@@ -355,4 +386,49 @@ public class SensitiveWordContext implements IWordContext {
         this.wordResultCondition = wordResultCondition;
         return this;
     }
+
+    public IWordCheck wordCheckWord() {
+        return wordCheckWord;
+    }
+
+    public SensitiveWordContext wordCheckWord(IWordCheck wordCheckWord) {
+        this.wordCheckWord = wordCheckWord;
+        return this;
+    }
+
+    public IWordCheck wordCheckNum() {
+        return wordCheckNum;
+    }
+
+    public SensitiveWordContext wordCheckNum(IWordCheck wordCheckNum) {
+        this.wordCheckNum = wordCheckNum;
+        return this;
+    }
+
+    public IWordCheck wordCheckEmail() {
+        return wordCheckEmail;
+    }
+
+    public SensitiveWordContext wordCheckEmail(IWordCheck wordCheckEmail) {
+        this.wordCheckEmail = wordCheckEmail;
+        return this;
+    }
+
+    public IWordCheck wordCheckUrl() {
+        return wordCheckUrl;
+    }
+
+    public SensitiveWordContext wordCheckUrl(IWordCheck wordCheckUrl) {
+        this.wordCheckUrl = wordCheckUrl;
+        return this;
+    }
+
+    public IWordCheck wordCheckIpv4() {
+        return wordCheckIpv4;
+    }
+
+    public SensitiveWordContext wordCheckIpv4(IWordCheck wordCheckIpv4) {
+        this.wordCheckIpv4 = wordCheckIpv4;
+        return this;
+    }
 }

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

@@ -60,7 +60,17 @@ public class WordCheckUrl extends AbstractConditionWordCheck {
 
         // 改为 http:// 或者 https:// 开头
         String string = stringBuilder.toString();
-        return RegexUtil.isUrl(string);
+        return isUrl(string);
+    }
+
+    /**
+     * 是否为 URL
+     * @param text 原始文本
+     * @return 结果
+     * @since 0.25.0
+     */
+    protected boolean isUrl(final String text) {
+        return RegexUtil.isUrl(text);
     }
 
 }

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

@@ -0,0 +1,32 @@
+package com.github.houbb.sensitive.word.support.check;
+
+import com.github.houbb.heaven.util.util.regex.RegexUtil;
+import com.github.houbb.sensitive.word.api.IWordCheck;
+
+/**
+ * （1）暂时先粗略的处理 web-site
+ * （2）如果网址的最后为图片类型，则跳过。
+ * （3）长度超过 70，直接结束。
+ *
+ * 不包含前缀的实现策略
+ *
+ * @author binbin.hou
+ * @since 0.25.0
+ */
+public class WordCheckUrlNoPrefix extends WordCheckUrl {
+
+    /**
+     * @since 0.3.0
+     */
+    private static final IWordCheck INSTANCE = new WordCheckUrlNoPrefix();
+
+    public static IWordCheck getInstance() {
+        return INSTANCE;
+    }
+
+    @Override
+    protected boolean isUrl(String text) {
+        return RegexUtil.isWebSite(text);
+    }
+
+}

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

@@ -0,0 +1,96 @@
+package com.github.houbb.sensitive.word.support.check;
+
+import com.github.houbb.heaven.annotation.ThreadSafe;
+import com.github.houbb.sensitive.word.api.ISensitiveWordCharIgnore;
+import com.github.houbb.sensitive.word.api.IWordCheck;
+import com.github.houbb.sensitive.word.api.IWordContext;
+import com.github.houbb.sensitive.word.api.IWordData;
+import com.github.houbb.sensitive.word.api.context.InnerSensitiveWordContext;
+import com.github.houbb.sensitive.word.constant.enums.WordContainsTypeEnum;
+import com.github.houbb.sensitive.word.constant.enums.WordTypeEnum;
+import com.github.houbb.sensitive.word.support.result.WordLengthResult;
+
+import java.util.Map;
+
+/**
+ * 敏感词监测实现
+ * @author binbin.hou
+ * @since 0.26.0
+ */
+@Deprecated
+public class WordCheckWordMaxLen extends AbstractWordCheck {
+
+    @Override
+    protected Class<? extends IWordCheck> getSensitiveCheckClass() {
+        return WordCheckWordMaxLen.class;
+    }
+
+    @Override
+    protected WordLengthResult getActualLength(int beginIndex, InnerSensitiveWordContext innerContext) {
+        final String txt = innerContext.originalText();
+        final Map<Character, Character> formatCharMapping = innerContext.formatCharMapping();
+        final IWordContext context = innerContext.wordContext();
+        final IWordData wordData = context.wordData();
+        final IWordData wordDataAllow = context.wordDataAllow();
+        final ISensitiveWordCharIgnore wordCharIgnore = context.charIgnore();
+
+        // 前一个条件
+        StringBuilder stringBuilder = new StringBuilder();
+        char[] rawChars = txt.toCharArray();
+
+        int tempLen = 0;
+        int maxWhite = 0;
+        int maxBlack = 0;
+        boolean firstCheck = true;
+
+        WordContainsTypeEnum wordContainsTypeEnumAllow = wordDataAllow.contains(stringBuilder, innerContext);
+        WordContainsTypeEnum wordContainsTypeEnumDeny = wordData.contains(stringBuilder, innerContext);
+
+        for (int i = beginIndex; i < rawChars.length; i++) {
+            if (wordCharIgnore.ignore(i, rawChars, innerContext) && tempLen != 0) {
+                tempLen++;
+                continue;
+            }
+
+            char mappingChar = formatCharMapping.get(rawChars[i]);
+            stringBuilder.append(mappingChar);
+            tempLen++;
+
+            if (firstCheck || !WordContainsTypeEnum.NOT_FOUND.equals(wordContainsTypeEnumAllow)) {
+                wordContainsTypeEnumAllow = wordDataAllow.contains(stringBuilder, innerContext);
+                if (WordContainsTypeEnum.CONTAINS_END.equals(wordContainsTypeEnumAllow)) {
+                    maxWhite += tempLen;
+                    wordContainsTypeEnumAllow = WordContainsTypeEnum.NOT_FOUND;
+                }
+            }
+
+            // 黑名单命中
+            if (firstCheck || !WordContainsTypeEnum.NOT_FOUND.equals(wordContainsTypeEnumDeny)) {
+                wordContainsTypeEnumDeny = wordData.contains(stringBuilder, innerContext);
+                if (WordContainsTypeEnum.CONTAINS_END.equals(wordContainsTypeEnumDeny)) {
+                    maxBlack += tempLen;
+                    wordContainsTypeEnumDeny = WordContainsTypeEnum.NOT_FOUND;
+                }
+            }
+
+            // 不再是第一次检测
+            firstCheck = false;
+
+            // 黑白名单都未匹配
+            if (WordContainsTypeEnum.NOT_FOUND.equals(wordContainsTypeEnumAllow) &&
+                    WordContainsTypeEnum.NOT_FOUND.equals(wordContainsTypeEnumDeny)) {
+                break;
+            }
+        }
+
+        return WordLengthResult.newInstance()
+                .wordAllowLen(maxWhite)
+                .wordDenyLen(maxBlack);
+    }
+
+    @Override
+    protected String getType() {
+        return WordTypeEnum.WORD.getCode();
+    }
+
+}

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

@@ -77,4 +77,15 @@ public final class WordChecks {
         return WordCheckIPV4.getInstance();
     }
 
+    /**
+     * 不需要前缀的 urlPrefix
+     * 注意：这种检测方法可能会和代码中的包名称冲突
+     *
+     * @return 实现
+     * @since 0.25.0
+     */
+    public static IWordCheck urlNoPrefix() {
+        return WordCheckUrlNoPrefix.getInstance();
+    }
+
 }

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

@@ -18,19 +18,19 @@ public class WordCheckCombine extends AbstractWordCheckCombine {
         List<IWordCheck> wordCheckList = new ArrayList<>();
 
         if(context.enableWordCheck()) {
-            wordCheckList.add(WordChecks.word());
+            wordCheckList.add(context.wordCheckWord());
         }
         if(context.enableNumCheck()) {
-            wordCheckList.add(WordChecks.num());
+            wordCheckList.add(context.wordCheckNum());
         }
         if(context.enableEmailCheck()) {
-            wordCheckList.add(WordChecks.email());
+            wordCheckList.add(context.wordCheckEmail());
         }
         if(context.enableUrlCheck()) {
-            wordCheckList.add(WordChecks.url());
+            wordCheckList.add(context.wordCheckUrl());
         }
         if(context.enableIpv4Check()) {
-            wordCheckList.add(WordChecks.ipv4());
+            wordCheckList.add(context.wordCheckIpv4());
         }
 
         return wordCheckList;

src/main/java/com/github/houbb/sensitive/word/support/data/AbstractWordData.java

@@ -1,6 +1,5 @@
 package com.github.houbb.sensitive.word.support.data;
 
-import com.github.houbb.heaven.util.lang.StringUtil;
 import com.github.houbb.heaven.util.util.CollectionUtil;
 import com.github.houbb.sensitive.word.api.IWordData;
 import com.github.houbb.sensitive.word.api.context.InnerSensitiveWordContext;
@@ -31,9 +30,9 @@ public abstract class AbstractWordData implements IWordData {
 
     /**
      * 删除敏感词
-     * @param word 敏感词
+     * @param collection 集合
      */
-    protected abstract void doRemoveWord(String word);
+    protected abstract void doRemoveWord(Collection<String> collection);
 
     /**
      * 新增敏感词
@@ -49,12 +48,12 @@ public abstract class AbstractWordData implements IWordData {
     }
 
     @Override
-    public void removeWord(String word) {
+    public void removeWord(Collection<String> collection) {
-        if(StringUtil.isEmpty(word)) {
+        if(CollectionUtil.isEmpty(collection)) {
             return;
         }
 
-        doRemoveWord(word);
+        doRemoveWord(collection);
     }
 
     @Override

src/main/java/com/github/houbb/sensitive/word/support/data/WordDataHashMap.java

@@ -89,7 +89,7 @@ public class WordDataHashMap extends AbstractWordData {
     }
 
     @Override
-    protected void doRemoveWord(String word) {
+    protected void doRemoveWord(Collection<String> collection) {
 
     }
 

src/main/java/com/github/houbb/sensitive/word/support/data/WordDataTree.java

@@ -4,7 +4,6 @@ import com.github.houbb.heaven.annotation.ThreadSafe;
 import com.github.houbb.heaven.util.lang.ObjectUtil;
 import com.github.houbb.heaven.util.lang.StringUtil;
 import com.github.houbb.sensitive.word.api.IWordContext;
-import com.github.houbb.sensitive.word.api.IWordData;
 import com.github.houbb.sensitive.word.api.context.InnerSensitiveWordContext;
 import com.github.houbb.sensitive.word.constant.enums.WordContainsTypeEnum;
 
@@ -84,49 +83,7 @@ public class WordDataTree extends AbstractWordData {
         this.root = newRoot;
     }
 
-    @Override
-    protected void doRemoveWord(String word) {
-        WordDataTreeNode tempNode = root;
-        //需要删除的
-        Map<Character, WordDataTreeNode> map = new HashMap<>();
-        char[] chars = word.toCharArray();
-        int length = chars.length;
-        for (int i = 0; i < length; i++) {
-            //不存在第一个词
-            WordDataTreeNode subNode = tempNode.getSubNode(chars[i]);
-            if (subNode == null) {
-                return;
-            }
-            if (i == (length - 1)) {
-                //尾字符判断是否结束
-                if (!subNode.end()) {
-                    return;
-                }
-                if (subNode.getNodeSize() > 0) {
-                    //尾字符下还存在字符,即标识即可
-                    subNode.end(false);
-                    return;
-                }
-            }
-            if (subNode.end()) {
-                map.clear();
-            }
-            map.put(chars[i], tempNode);
 
-            tempNode = subNode;
-        }
-
-        for (Map.Entry<Character, WordDataTreeNode> entry : map.entrySet()) {
-            WordDataTreeNode value = entry.getValue();
-            //节点只有一个就置空
-            if (value.getNodeSize() == 1) {
-                value.clearNode();
-                return;
-            }
-            //多个就删除
-            value.removeNode(entry.getKey());
-        }
-    }
 
     /**
      * 新增敏感词
@@ -143,6 +100,21 @@ public class WordDataTree extends AbstractWordData {
         }
     }
 
+    @Override
+    protected synchronized void doRemoveWord(Collection<String> collection) {
+        for (String word : collection) {
+            if (StringUtil.isEmpty(word)) {
+                continue;
+            }
+            removeWord(this.root, word);
+        }
+    }
+
+
+
+
+
+
     /**
      * 获取当前的 Map
      * @param nowNode 当前节点
@@ -211,4 +183,48 @@ public class WordDataTree extends AbstractWordData {
         tempNode.end(true);
     }
 
+
+    private void removeWord(WordDataTreeNode root, String word){
+        WordDataTreeNode tempNode = root;
+        //需要删除的
+        Map<Character, WordDataTreeNode> map = new HashMap<>();
+        char[] chars = word.toCharArray();
+        int length = chars.length;
+        for (int i = 0; i < length; i++) {
+            //不存在第一个词
+            WordDataTreeNode subNode = tempNode.getSubNode(chars[i]);
+            if (subNode == null) {
+                return;
+            }
+            if (i == (length - 1)) {
+                //尾字符判断是否结束
+                if (!subNode.end()) {
+                    return;
+                }
+                if (subNode.getNodeSize() > 0) {
+                    //尾字符下还存在字符,即标识即可
+                    subNode.end(false);
+                    return;
+                }
+            }
+            if (subNode.end()) {
+                map.clear();
+            }
+            map.put(chars[i], tempNode);
+
+            tempNode = subNode;
+        }
+
+        for (Map.Entry<Character, WordDataTreeNode> entry : map.entrySet()) {
+            WordDataTreeNode value = entry.getValue();
+            //节点只有一个就置空
+            if (value.getNodeSize() == 1) {
+                value.clearNode();
+                return;
+            }
+            //多个就删除
+            value.removeNode(entry.getKey());
+        }
+    }
+
 }

src/main/java/com/github/houbb/sensitive/word/support/result/WordLengthResult.java

@@ -1,20 +1,28 @@
 package com.github.houbb.sensitive.word.support.result;
 
+/**
+ * 说明：统一让黑白名单一次遍历，性能优化
+ *
+ * @since 0.24.2
+ */
 public class WordLengthResult {
+    /**
+     * 白名单长度
+     */
     private int wordAllowLen;
+    /**
+     * 黑名单长度
+     */
     private int wordDenyLen;
 
-
-    private WordLengthResult(){}
-
     public static WordLengthResult newInstance() {
         return new WordLengthResult();
     }
 
-
     public int wordAllowLen() {
         return this.wordAllowLen;
     }
+
     public WordLengthResult wordAllowLen(int wordAllowLen) {
         this.wordAllowLen = wordAllowLen;
         return this;
@@ -23,10 +31,18 @@ public class WordLengthResult {
     public int wordDenyLen() {
         return this.wordDenyLen;
     }
+
     public WordLengthResult wordDenyLen(int wordDenyLen) {
         this.wordDenyLen = wordDenyLen;
         return this;
     }
 
+    @Override
+    public String toString() {
+        return "WordLengthResult{" +
+                "wordAllowLen=" + wordAllowLen +
+                ", wordDenyLen=" + wordDenyLen +
+                '}';
+    }
 
 }

src/main/java/com/github/houbb/sensitive/word/support/tag/WordTags.java

@@ -71,6 +71,8 @@ public class WordTags {
     /**
      * 根据标准的约定行处理
      * @param lines 行信息
+     * @param wordSplit 单词分割
+     * @param tagSplit 标签分割
      * @return 结果
      */
     public static IWordTag lines(final Collection<String> lines, final String wordSplit, final String tagSplit) {

src/test/java/com/github/houbb/sensitive/word/benchmark/BenchmarkBasicTest.java

@@ -72,9 +72,9 @@ public class BenchmarkBasicTest {
     }
 
     /**
-     *      * 黑白名单一次遍历 优化前：300*他们在地铁口交易，查10000次，26183
+     * 黑白名单一次遍历 优化前：300*他们在地铁口交易，查10000次，26183
-     *      * 黑白名单一次遍历 优化后：300*他们在地铁口交易，查10000次，15705
+     * 黑白名单一次遍历 优化后：300*他们在地铁口交易，查10000次，15705
-     *
+     * @since 0.24.2
      */
     @Test
     public void costTimeOneTraceTest() {
@@ -86,24 +86,17 @@ public class BenchmarkBasicTest {
 
         // 1W 次
         long start = System.currentTimeMillis();
-        SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance()
+        SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance().wordDeny(new IWordDeny() {
-                .wordDeny(new IWordDeny() {
             @Override
             public List<String> deny() {
                 return Collections.singletonList("口交");
             }
-                })
+        }).wordAllow(new IWordAllow() {
-                .wordAllow(new IWordAllow() {
             @Override
             public List<String> allow() {
                 return Collections.singletonList("地铁口交易");
             }
-                })
+        }).enableWordCheck(true).enableNumCheck(false).enableUrlCheck(false).enableEmailCheck(false).init();
-                .enableWordCheck(true)
-                .enableNumCheck(false)
-                .enableUrlCheck(false)
-                .enableEmailCheck(false)
-                .init();
 
         for (int i = 0; i < 10000; i++) {
             sensitiveWordBs.findAll(text);

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

@@ -4,8 +4,10 @@ import com.github.houbb.heaven.util.io.FileUtil;
 import com.github.houbb.heaven.util.util.CollectionUtil;
 import com.github.houbb.sensitive.word.data.WordCountDto;
 import com.github.houbb.sensitive.word.support.allow.WordAllows;
+import com.github.houbb.sensitive.word.support.check.WordChecks;
 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.resultcondition.WordResultConditions;
 import com.github.houbb.sensitive.word.support.tag.WordTags;
 import org.junit.Assert;
@@ -39,46 +41,19 @@ public class SensitiveWordBsConfigTest {
                 .enableUrlCheck(false)
                 .enableIpv4Check(false)
                 .enableWordCheck(true)
+                .wordCheckNum(WordChecks.num())
+                .wordCheckEmail(WordChecks.email())
+                .wordCheckUrl(WordChecks.url())
+                .wordCheckIpv4(WordChecks.ipv4())
+                .wordCheckWord(WordChecks.word())
                 .numCheckLen(8)
                 .wordTag(WordTags.none())
                 .charIgnore(SensitiveWordCharIgnores.defaults())
                 .wordResultCondition(WordResultConditions.alwaysTrue())
                 .wordAllow(WordAllows.defaults())
                 .wordDeny(WordDenys.defaults())
+                .wordReplace(WordReplaces.defaults())
                 .init();
-
-//        String dir = "D:\\code\\github\\houbb.github.io\\_posts";
-//        File[] files = new File(dir).listFiles();
-//
-//        Set<String> wordSet = new HashSet<>();
-//
-//        Map<String, Integer> wordCountMap = new HashMap<>();
-//        for(File file : files) {
-//            String content = FileUtil.getFileContent(file);
-//            List<String> allWords = wordBs.findAll(content);
-//
-//            for(String word : allWords) {
-//                Integer integer = wordCountMap.get(word);
-//                if(integer == null) {
-//                    integer = 0;
-//                }
-//
-//                integer++;
-//                wordCountMap.put(word, integer);
-//            }
-//
-//            System.out.println(file.getName());
-//        }
-//
-////        List<WordCountDto> wordCountDtoList = new ArrayList<>();
-//        for(Map.Entry<String, Integer> entry : wordCountMap.entrySet()) {
-//            if(entry.getValue() >= 3) {
-//                System.out.println(entry.getKey() + " : " + entry.getValue());
-//            }
-//        }
-
-//        Collections.sort(wordCountDtoList);
-//        System.out.println(wordCountDtoList);
     }
 
     @Test

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

@@ -0,0 +1,37 @@
+package com.github.houbb.sensitive.word.bs;
+
+import com.github.houbb.sensitive.word.support.check.WordChecks;
+import org.junit.Assert;
+import org.junit.Test;
+
+import java.util.List;
+
+/**
+ * <p> project: sensitive-word-SensitiveWordBsTest </p>
+ * <p> create on 2020/1/7 23:43 </p>
+ *
+ * @author Administrator
+ * @since 0.25.0
+ */
+public class SensitiveWordBsUrlNoPrefixTest {
+
+    /**
+     * URL 检测
+     *
+     * @since 0.25.0
+     */
+    @Test
+    public void urlNoPrefixTest() {
+        final String text = "点击链接 https://www.baidu.com 查看答案，当然也可以是 baidu.com、www.baidu.com";
+
+        final SensitiveWordBs sensitiveWordBs = SensitiveWordBs.newInstance()
+                .enableUrlCheck(true) // 启用URL检测
+                .wordCheckUrl(WordChecks.urlNoPrefix()) //指定检测的方式
+                .init();
+        List<String> wordList = sensitiveWordBs.findAll(text);
+        Assert.assertEquals("[www.baidu.com, baidu.com, www.baidu.com]", wordList.toString());
+
+        Assert.assertEquals("点击链接 https://************* 查看答案，当然也可以是 *********、*************", sensitiveWordBs.replace(text));
+    }
+
+}

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

@@ -0,0 +1,28 @@
+package com.github.houbb.sensitive.word.bs;
+
+import com.github.houbb.sensitive.word.api.IWordDeny;
+import org.junit.Assert;
+import org.junit.Test;
+
+import java.util.Arrays;
+import java.util.List;
+
+public class SensitiveWordMaxFirstTest {
+
+    @Test
+    public void maxFirstTest() {
+        SensitiveWordBs bs = SensitiveWordBs.newInstance()
+                .wordDeny(new IWordDeny() {
+                    @Override
+                    public List<String> deny() {
+                        return Arrays.asList("我的世界", "我的");
+                    }
+                }).init();
+
+        String text = "我的世界我的好玩";
+
+        List<String> textList = bs.findAll(text);
+//        Assert.assertEquals("", textList.toString());
+    }
+
+}