import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* path路径过滤字符串帮助类
*/
public class CleanPathUtil {
public static String cleanString(String path) {
if (path == null){
return null;
}
StringBuilder cleanString = new StringBuilder();
for (int i = 0; i < path.length(); ++i) {
cleanString.append(cleanChar(path.charAt(i)));
}
return cleanString.toString();
}
private static char cleanChar(char aChar) {
// 判断验证是否是汉字或者0-9、a-z、A-Z
if (isRightChar(aChar)){
return aChar;
}
// 其他字符
switch (aChar) {
case '/':
return '/';
case '\\':
return '\\';
case ':':
return ':';
case '.':
return '.';
case '-':
return '-';
case '_':
return '_';
case '%':
return '%';
case '&':
return '&';
case '=':
return '=';
case '?':
return '?';
default:
return ' ';
}
}
/**
* 判断字符串中是否包含中文
* 不能校验是否为中文标点符号
* @param str 待校验字符串
* @return 是否为中文
*/
public static boolean isContainChinese(String str) {
Pattern p = Pattern.compile("[\u4e00-\u9fa5]");
Matcher m = p.matcher(str);
return m.find();
}
/**
* 过滤掉中文
* @param str 待过滤中文的字符串
* @return 过滤掉中文后字符串
*/
public static String filterChinese(String str) {
// 用于返回结果
String result = str;
boolean flag = isContainChinese(str);
if (flag) {// 包含中文
// 用于拼接过滤中文后的字符
StringBuffer sb = new StringBuffer();
// 用于校验是否为中文
boolean flag2 = false;
// 用于临时存储单字符
char chinese = 0;
// 5.去除掉文件名中的中文
// 将字符串转换成char[]
char[] charArray = str.toCharArray();
// 过滤到中文及中文字符
for (char c : charArray) {
chinese = c;
flag2 = isChinese(chinese);
if (!flag2) {// 不是中日韩文字及标点符号
sb.append(chinese);
}
}
result = sb.toString();
}
return result;
}
/**
* 校验一个字符是否是汉字
* @param c 被校验的字符
* @return true代表是汉字
*/
public static boolean isChineseChar(char c) {
try {
return String.valueOf(c).getBytes("UTF-8").length > 1;
} catch (Exception e) {
e.printStackTrace();
return false;
}
}
/**
* 验证字符串内容是否包含下列非法字符<br>
* `~!#%^&*=+\\|{};:'\",<>/?○●★☆☉♀♂※¤╬の〆
* @param content 字符串内容
* @return 't'代表不包含非法字符，otherwise代表包含非法字符。
*/
public static char validateLegalString(String content) {
String illegal = "`~!#%^&*=+\\|{};:'\",<>/?○●★☆☉♀♂※¤╬の〆";
char isLegalChar = 't';
L1: for (int i = 0; i < content.length(); i++) {
for (int j = 0; j < illegal.length(); j++) {
if (content.charAt(i) == illegal.charAt(j)) {
isLegalChar = content.charAt(i);
break L1;
}
}
}
return isLegalChar;
}
/**
* 验证是否是汉字或者0-9、a-z、A-Z
* @param c 被验证的char
* @return true代表符合条件
*/
public static boolean isRightChar(char c) {
return isChinese(c) || isWord(c);
}
/**
* 校验某个字符是否是a-z、A-Z、_、0-9
* @param c 被校验的字符
* @return true代表符合条件
*/
public static boolean isWord(char c) {
String regEx = "[\\w]";
Pattern p = Pattern.compile(regEx);
Matcher m = p.matcher("" + c);
return m.matches();
}
/**
* 判定输入的是否是汉字
* @param c 被校验的字符
* @return true代表是汉字
*/
public static boolean isChinese(char c) {
Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
return ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
|| ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
|| ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
|| ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS;
}
/**
* 校验String是否全是中文
* @param name 被校验的字符串
* @return true代表全是汉字
*/
public static boolean checkNameChese(String name) {
boolean res = true;
char[] cTemp = name.toCharArray();
for (int i = 0; i < name.length(); i++) {
if (!isChinese(cTemp[i])) {
res = false;
break;
}
}
return res;
}
/**
* main方法测试
* @param args 入参
*/
public static void main(String[] args) {
String path = "https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=baidu&wd=%E6%B1%89%E5%AD%97%20%E8%B7%AF%E5%BE%84%E8%BF%87%E6%BB%A4&fenlei=256&oq=%25E8%25B7%25AF%25E5%25BE%2584%25E8%25BF%2587%25E6%25BB%25A4&rsv_pq=b04d9420000bb9bc&rsv_t=9b21H1kF8kegeLOXb7XmsQuwLpD0XMpZ6vyocQ2HhUVNfysvg5TI6p0s2Xk&rqlang=cn&rsv_enter=0&rsv_dl=tb&rsv_btype=t&inputT=202&rsv_sug3=60&rsv_sug1=26&rsv_sug7=100&rsv_sug2=0&rsv_sug4=25744&rsv_sug=1";
String cleanString = CleanPathUtil.cleanString(path);
System.out.println(cleanString);
}
}
