honeymoose
/
ik-analyzer-solr
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

代码格式化；

This commit is contained in:
Magese 2021-12-31 17:11:52 +08:00
parent 3ec8076730
commit df29bdc4df
1 changed files with 51 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
src/main/java/org/wltea/analyzer/core/CharacterUtil.java
View File

@ -28,7 +28,6 @@
package org.wltea.analyzer.core;
/**
*
* 字符集识别工具类
*/
class CharacterUtil {
@ -46,27 +45,28 @@ class CharacterUtil {
/**
* 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'){
static int identifyCharType(char input) {
if (input >= '0' && input <= '9') {
return CHAR_ARABIC;
}else if((input >= 'a' && input <= 'z')
|| (input >= 'A' && input <= 'Z')){
} else if ((input >= 'a' && input <= 'z')
|| (input >= 'A' && input <= 'Z')) {
return CHAR_ENGLISH;
}else {
} else {
Character.UnicodeBlock ub = Character.UnicodeBlock.of(input);
if(ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A){
|| 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
} 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
@ -74,7 +74,7 @@ class CharacterUtil {
//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){
|| ub == Character.UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS) {
return CHAR_OTHER_CJK;
}
@ -85,17 +85,18 @@ class CharacterUtil {
/**
* 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){
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') {
} else if (input >= 'A' && input <= 'Z') {
input += 32;
}