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

代码格式化；

Browse Source
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

101
src/main/java/org/wltea/analyzer/core/CharacterUtil.java
View File

@ -28,77 +28,78 @@
package org.wltea.analyzer.core; package org.wltea.analyzer.core;
/** /**
*
* 字符集识别工具类 * 字符集识别工具类
*/ */
class CharacterUtil { 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 * 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 * @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) {
return CHAR_ARABIC; if (input >= '0' && input <= '9') {
return CHAR_ARABIC;
}else if((input >= 'a' && input <= 'z') } else if ((input >= 'a' && input <= 'z')
|| (input >= 'A' && input <= 'Z')){ || (input >= 'A' && input <= 'Z')) {
return CHAR_ENGLISH; return CHAR_ENGLISH;
}else { } else {
Character.UnicodeBlock ub = Character.UnicodeBlock.of(input); 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_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 //目前已知的中文字符UTF-8集合
return CHAR_CHINESE; 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 //韩文字符集
|| ub == Character.UnicodeBlock.HANGUL_SYLLABLES || ub == Character.UnicodeBlock.HANGUL_SYLLABLES
|| ub == Character.UnicodeBlock.HANGUL_JAMO || ub == Character.UnicodeBlock.HANGUL_JAMO
|| ub == Character.UnicodeBlock.HANGUL_COMPATIBILITY_JAMO || ub == Character.UnicodeBlock.HANGUL_COMPATIBILITY_JAMO
//日文字符集 //日文字符集
|| ub == Character.UnicodeBlock.HIRAGANA //平假名 || ub == Character.UnicodeBlock.HIRAGANA //平假名
|| ub == Character.UnicodeBlock.KATAKANA //片假名 || ub == Character.UnicodeBlock.KATAKANA //片假名
|| ub == Character.UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS){ || ub == Character.UnicodeBlock.KATAKANA_PHONETIC_EXTENSIONS) {
return CHAR_OTHER_CJK; return CHAR_OTHER_CJK;
} }
} }
//其他的不做处理的字符 //其他的不做处理的字符
return CHAR_USELESS; return CHAR_USELESS;
} }
/** /**
* 进行字符规格化（全角转半角，大写转小写处理） * 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 * @param input 需要转换的字符
*/ * @return char
static char regularize(char input){ */
static char regularize(char input) {
if (input == 12288) { if (input == 12288) {
input = (char) 32; input = (char) 32;
}else if (input > 65280 && input < 65375) { } else if (input > 65280 && input < 65375) {
input = (char) (input - 65248); input = (char) (input - 65248);
}else if (input >= 'A' && input <= 'Z') { } else if (input >= 'A' && input <= 'Z') {
input += 32; input += 32;
} }
return input; return input;
} }
} }