From df29bdc4df73e865d9e6f571ebd58fc4ad0aa1bf Mon Sep 17 00:00:00 2001
From: Magese <magese@live.cn>
Date: Fri, 31 Dec 2021 17:11:52 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BB=A3=E7=A0=81=E6=A0=BC=E5=BC=8F=E5=8C=96?=
 =?UTF-8?q?=EF=BC=9B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../wltea/analyzer/core/CharacterUtil.java    | 101 +++++++++---------
 1 file changed, 51 insertions(+), 50 deletions(-)

diff --git a/src/main/java/org/wltea/analyzer/core/CharacterUtil.java b/src/main/java/org/wltea/analyzer/core/CharacterUtil.java
index f7d157e..795058b 100644
--- a/src/main/java/org/wltea/analyzer/core/CharacterUtil.java
+++ b/src/main/java/org/wltea/analyzer/core/CharacterUtil.java
@@ -28,77 +28,78 @@
 package org.wltea.analyzer.core;
 
 /**
- *
  * 字符集识别工具类
  */
 class CharacterUtil {
 
-	static final int CHAR_USELESS = 0;
+    static final int CHAR_USELESS = 0;
 
-	static final int CHAR_ARABIC = 0X00000001;
+    static final int CHAR_ARABIC = 0X00000001;
 
-	static final int CHAR_ENGLISH = 0X00000002;
+    static final int CHAR_ENGLISH = 0X00000002;
 
-	static final int CHAR_CHINESE = 0X00000004;
+    static final int CHAR_CHINESE = 0X00000004;
 
-	static final int CHAR_OTHER_CJK = 0X00000008;
+    static final int CHAR_OTHER_CJK = 0X00000008;
 
 
-	/**
-	 * 识别字符类型
-	 * @param input 需要识别的字符
-	 * @return int CharacterUtil定义的字符类型常量
-	 */
-	static int identifyCharType(char input){
-		if(input >= '0' && input <= '9'){
-			return CHAR_ARABIC;
+    /**
+     * 识别字符类型
+     *
+     * @param input 需要识别的字符
+     * @return int CharacterUtil定义的字符类型常量
+     */
+    static int identifyCharType(char input) {
+        if (input >= '0' && input <= '9') {
+            return CHAR_ARABIC;
 
-		}else if((input >= 'a' && input <= 'z')
-				|| (input >= 'A' && input <= 'Z')){
-			return CHAR_ENGLISH;
+        } else if ((input >= 'a' && input <= 'z')
+                || (input >= 'A' && input <= 'Z')) {
+            return CHAR_ENGLISH;
 
-		}else {
-			Character.UnicodeBlock ub = Character.UnicodeBlock.of(input);
+        } else {
+            Character.UnicodeBlock ub = Character.UnicodeBlock.of(input);
 
-			if(ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
-					|| ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
-					|| ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A){
-				//目前已知的中文字符UTF-8集合
-				return CHAR_CHINESE;
+            if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
+                    || ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
+                    || ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A) {
+                //目前已知的中文字符UTF-8集合
+                return CHAR_CHINESE;
 
-			}else if(ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS //全角数字字符和日韩字符
-					//韩文字符集
-					|| ub == Character.UnicodeBlock.HANGUL_SYLLABLES
-					|| ub == Character.UnicodeBlock.HANGUL_JAMO
-					|| ub == Character.UnicodeBlock.HANGUL_COMPATIBILITY_JAMO
-					//日文字符集
-					|| ub == Character.UnicodeBlock.HIRAGANA //平假名
-					|| ub == Character.UnicodeBlock.KATAKANA //片假名
-					|| ub == Character.UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS){
-				return CHAR_OTHER_CJK;
+            } else if (ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS //全角数字字符和日韩字符
+                    //韩文字符集
+                    || ub == Character.UnicodeBlock.HANGUL_SYLLABLES
+                    || ub == Character.UnicodeBlock.HANGUL_JAMO
+                    || ub == Character.UnicodeBlock.HANGUL_COMPATIBILITY_JAMO
+                    //日文字符集
+                    || ub == Character.UnicodeBlock.HIRAGANA //平假名
+                    || ub == Character.UnicodeBlock.KATAKANA //片假名
+                    || ub == Character.UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS) {
+                return CHAR_OTHER_CJK;
 
-			}
-		}
-		//其他的不做处理的字符
-		return CHAR_USELESS;
-	}
+            }
+        }
+        //其他的不做处理的字符
+        return CHAR_USELESS;
+    }
 
-	/**
-	 * 进行字符规格化（全角转半角，大写转小写处理）
-	 * @param input 需要转换的字符
-	 * @return char
-	 */
-	static char regularize(char input){
+    /**
+     * 进行字符规格化（全角转半角，大写转小写处理）
+     *
+     * @param input 需要转换的字符
+     * @return char
+     */
+    static char regularize(char input) {
         if (input == 12288) {
             input = (char) 32;
 
-        }else if (input > 65280 && input < 65375) {
+        } else if (input > 65280 && input < 65375) {
             input = (char) (input - 65248);
 
-        }else if (input >= 'A' && input <= 'Z') {
-        	input += 32;
-		}
+        } else if (input >= 'A' && input <= 'Z') {
+            input += 32;
+        }
 
         return input;
-	}
+    }
 }