JAVA实现过滤掉文本中的表情
2016-05-09 20:34
417 查看
比如我们要把微信昵称存入数据库,就需要把表情给过滤掉。
package com.zjr.common.utils;
import org.apache.commons.lang3.StringUtils;
public class EmojiFilter {
/**
* 检测是否有emoji字符
*
* @param source
* @return 一旦含有就抛出
*/
public static boolean containsEmoji(String source) {
if (StringUtils.isBlank(source)) {
return false;
}
int len = source.length();
for (int i = 0; i < len; i++) {
char codePoint = source.charAt(i);
if (isEmojiCharacter(codePoint)) {
// do nothing,判断到了这里表明,确认有表情字符
return true;
}
}
return false;
}
private static boolean isEmojiCharacter(char codePoint) {
return (codePoint == 0x0) || (codePoint == 0x9) || (codePoint == 0xA) || (codePoint == 0xD) || ((codePoint >= 0x20) && (codePoint <= 0xD7FF))
|| ((codePoint >= 0xE000) && (codePoint <= 0xFFFD)) || ((codePoint >= 0x10000) && (codePoint <= 0x10FFFF));
}
/**
* 过滤emoji 或者 其他非文字类型的字符
*
* @param source
* @return
*/
public static String filterEmoji(String source) {
if (!containsEmoji(source)) {
return source;// 如果不包含,直接返回
}
// 到这里铁定包含
StringBuilder buf = null;
int len = source.length();
for (int i = 0; i < len; i++) {
char codePoint = source.charAt(i);
if (isEmojiCharacter(codePoint)) {
if (buf == null) {
buf = new StringBuilder(source.length());
}
buf.append(codePoint);
}
}
if (buf == null) {
return source;// 如果没有找到 emoji表情,则返回源字符串
} else {
if (buf.length() == len) {// 这里的意义在于尽可能少的toString,因为会重新生成字符串
buf = null;
return source;
} else {
return buf.toString();
}
}
}
}
package com.zjr.common.utils;
import org.apache.commons.lang3.StringUtils;
public class EmojiFilter {
/**
* 检测是否有emoji字符
*
* @param source
* @return 一旦含有就抛出
*/
public static boolean containsEmoji(String source) {
if (StringUtils.isBlank(source)) {
return false;
}
int len = source.length();
for (int i = 0; i < len; i++) {
char codePoint = source.charAt(i);
if (isEmojiCharacter(codePoint)) {
// do nothing,判断到了这里表明,确认有表情字符
return true;
}
}
return false;
}
private static boolean isEmojiCharacter(char codePoint) {
return (codePoint == 0x0) || (codePoint == 0x9) || (codePoint == 0xA) || (codePoint == 0xD) || ((codePoint >= 0x20) && (codePoint <= 0xD7FF))
|| ((codePoint >= 0xE000) && (codePoint <= 0xFFFD)) || ((codePoint >= 0x10000) && (codePoint <= 0x10FFFF));
}
/**
* 过滤emoji 或者 其他非文字类型的字符
*
* @param source
* @return
*/
public static String filterEmoji(String source) {
if (!containsEmoji(source)) {
return source;// 如果不包含,直接返回
}
// 到这里铁定包含
StringBuilder buf = null;
int len = source.length();
for (int i = 0; i < len; i++) {
char codePoint = source.charAt(i);
if (isEmojiCharacter(codePoint)) {
if (buf == null) {
buf = new StringBuilder(source.length());
}
buf.append(codePoint);
}
}
if (buf == null) {
return source;// 如果没有找到 emoji表情,则返回源字符串
} else {
if (buf.length() == len) {// 这里的意义在于尽可能少的toString,因为会重新生成字符串
buf = null;
return source;
} else {
return buf.toString();
}
}
}
}
相关文章推荐
- struts2页面属性值回显
- java的ExecutorService 实现线程池
- JAVA——泛型类和泛型方法(静态方法泛型)
- 我理解的RxJava
- 重新学javaweb---文件上传1
- eclipse远程debug
- IO流----File类的常用方法
- struts2 捕获404错误的常用方法
- java推荐书籍及下载
- Java中二进制和十进制之间的相互转化
- java8之Lambda表达式 4:MapReduce开发案例
- java比较时间差
- Java 克隆
- java8之Lambda表达式 3:数据流
- java8之Lambda表达式 2:内建函数式接口
- java8之Lambda表达式 1:简介
- 利用Java代码实现把一个文件从一个地方剪切到另一个地方
- spring入门(控制台输出helloworld)
- Spring源码解析—— ClassPathResource类
- Spring源码解析—— ClassPathResource类