关于字符串处理的一些工具类

import java.io.File;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.text.NumberFormat;
import java.util.ArrayList;
import java.util.Collection;
import java.util.List;
import java.util.Locale;
import java.util.Map;
import java.util.regex.Pattern;

import javax.servlet.http.HttpServletRequest;

import org.apache.commons.io.FilenameUtils;
import org.apache.commons.lang.StringUtils;

import com.seeyon.v3x.common.authenticate.domain.User;
import com.seeyon.v3x.common.parser.StrExtractor;
import com.seeyon.v3x.common.web.login.CurrentUser;

/**
*
* @author <a href="mailto:tanmf@seeyon.com">Tanmf</a>
* @version 1.0 2006-9-8
*/
public final class Strings {
/**
* The number of bytes in a kilobyte.
*/
public static final long ONE_KB = 1024;

/**
* The number of bytes in a megabyte.
*/
public static final long ONE_MB = ONE_KB * ONE_KB;

/**
* The number of bytes in a gigabyte.
*/
public static final long ONE_GB = ONE_KB * ONE_MB;

/**
* 得到截取后的字符串
*
* @param str
*            需要截取的字符串
* @param length
*            要得到的长度，以byte为单位, 此长度包括symbol的长度
* @param symbol
*            用来代替被省略的信息，如“...”、“>>>”等
* @return
* @throws UnsupportedEncodingException
*/
public static String getLimitLengthString(String content, int len,
String symbol) {
if(len < 0){
return content;
}

try {
return getLimitLengthString(content, null, len, symbol);
}
catch (UnsupportedEncodingException e) {
return content;
}
}

/**
* 得到截取后的字符串
*
* @param str
*            需要截取的字符串
* @param charsetName
*            指定的编码
* @param length
*            要得到的长度，以byte为单位, 此长度包括symbol的长度
* @param symbol
*            用来代替被省略的信息，如“...”、“>>>”等
* @return
* @throws UnsupportedEncodingException
*/
public static String getLimitLengthString(String content,
String charsetName, int len, String symbol)
throws UnsupportedEncodingException {
if (content == null || content.length() == 0) {
return content;
}

if (symbol == null) {
symbol = "";
}

int counterOfDoubleByte = 0;
byte[] b;
if (charsetName == null) {
b = content.getBytes("GBK");
}
else {
b = content.getBytes(charsetName);
}

if (b.length <= len) {
return content;
}
// 减去symbol占用的位置
if (len > symbol.length()) {
len -= symbol.length();
}
for (int i = 0; i < len; i++) {
if (b[i] < 0) {
counterOfDoubleByte++;
}
}
if (counterOfDoubleByte % 2 != 0) {
len--;
}
byte[] newBytes = new byte[len];
System.arraycopy(b, 0, newBytes, 0, len);
if (charsetName == null) {
return new String(newBytes,"GBK") + symbol;
}
else {
return new String(newBytes, charsetName) + symbol;
}
}

/**
* Filter the specified message string for characters that are sensitive in
* HTML. This avoids potential attacks caused by including JavaScript codes
* in the request URL that is often reported in error messages.
*
* @param message
*            The message string to be filtered
*/
public static String toHTML(String text) {
return toHTML(text, true);
}

/**
*
* @param text
* @param isEscapeSpace 是否转换空格
* @return
*/
public static String toHTML(String text, boolean isEscapeSpace) {
if (text == null || text.equals("")) {
return "";
}

char content[] = new char[text.length()];
text.getChars(0, text.length(), content, 0);
StringBuffer result = new StringBuffer();
for (int i = 0; i < content.length; i++) {
switch (content[i]) {
case '\n':
result.append("<br/>");
break;
case '\r':
result.append("");
break;
case '<':
result.append("<");
break;
case '>':
result.append(">");
break;
case '&':
result.append("&");
break;
case '\'':
result.append("'");
break;
case '"':
result.append(""");
break;
case ' ':
if(isEscapeSpace){
result.append(" ");
}
else{
result.append(content[i]);
}
break;
default:
result.append(content[i]);
}
}

return result.toString();
}

/**
* 把带有\r\n\t等字符的清理掉，只保留文字；但不转换HTML的标签<br>
* 只适合于textarea输入的文本，如果是正文编辑器输入的文本请用全文检索的工具  {@link StrExtractor#getHTMLContent(String)}
* @param text
* @return
*/
public static String toText(String text) {
if (text == null || text.equals("")) {
return "";
}

char content[] = new char[text.length()];
text.getChars(0, text.length(), content, 0);
StringBuffer result = new StringBuffer();
for (int i = 0; i < content.length; i++) {
switch (content[i]) {
case '\n':
break;
case '\r':
break;
case '\t':
break;
case '\b':
break;
case '\f':
break;
default:
result.append(content[i]);
}
}

return result.toString();
}

public static String toHTMLAlt(String text) {
if (text == null || text.equals("")) {
return "";
}

char content[] = new char[text.length()];
text.getChars(0, text.length(), content, 0);
StringBuffer result = new StringBuffer();
for (int i = 0; i < content.length; i++) {
switch (content[i]) {
case '\r':
result.append("");
break;
case '<':
result.append("<");
break;
case '>':
result.append(">");
break;
case '&':
result.append("&");
break;
case '\'':
result.append("'");
break;
case '"':
result.append(""");
break;
case ' ':
result.append(" ");
break;
default:
result.append(content[i]);
}
}

return result.toString();
}

/**
* 对null处理
*
* @param <T>
* @param str
* @param defaultValue
* @return
*/
public static <T extends Object> T escapeNULL(T str, T defaultValue) {
return str == null ? defaultValue : str;
}

/**
* 将文件大小格式化输出<br>
* 如： Strings.formatFileSize(123456L, false) --> 120.47 KB<br>
* Strings.formatFileSize(12345678L, false) --> 11.77 MB<br>
* Strings.formatFileSize(18L, true) --> 1 KB<br>
* Strings.formatFileSize(18L, false) --> 18 B<br>
*
* 前端显示采用<code>${v3x:formatFileSize(21433L, true)}</code>
*
* @param fileSize
*            单位为字节
* @param isUseMinValue
*            是否采用最小值显示，即：最小显示1KB
* @return
* @throws ArithmeticException
*             fileSize less than zero
* @author Lucas
*/
public static String formatFileSize(long fileSize, boolean isUseMinValue) {
if (fileSize < 0) {
throw new ArithmeticException("fileSize less than zero");
}

Locale locale = Locale.getDefault();

User user = CurrentUser.get();
if (user != null) {
locale = user.getLocale();
}

NumberFormat format = NumberFormat.getInstance(locale);
format.setMaximumFractionDigits(2);
format.setMinimumFractionDigits(0);

if (fileSize >= ONE_GB) {
float filesize = fileSize / new Long(ONE_GB).floatValue();

return format.format(filesize) + " GB";
}
else if (fileSize >= ONE_MB) {
float filesize = fileSize / new Long(ONE_MB).floatValue();

return format.format(filesize) + " MB";
}
else if (fileSize >= ONE_KB) {
float filesize = fileSize / new Long(ONE_KB).floatValue();
return format.format(filesize) + " KB";
}
else if (fileSize == 0) {
return "0 KB";
}
else {
if (isUseMinValue) {
return "1 KB";
}
else {
return format.format(fileSize) + " B";
}
}
}

public static String join(String separator, String... strings) {
StringBuilder sb = new StringBuilder();
int i = 0;
for(String str : strings) {
if(i > 0){
sb.append(separator);
}
sb.append(str);
i++;
}

return sb.toString();
}
/**
* 串联字符串，屏蔽参数中的null，''字符
* @param separator
* @param strings
* @return
*/
public static String joinDelNull(String separator, String... strings) {
StringBuilder sb=new StringBuilder();
boolean hasValue=false;
for(String str:strings)
{
hasValue=(str!=null && !"".equals(str));
if(hasValue && sb.length()>0)
{
sb.append(separator);
}
if(hasValue)
{
sb.append(str);
}
}
return sb.toString();
}

/**
* 配合选人界面，对选择的人员进行分解 <code>
* <pre>
* //授权信息
* String authInfo = request.getParameter("authInfo");
* String[][] authInfos = Strings.getSelectPeopleElements(authInfo);
* if (authInfos != null) {
* 	int i = 0;
* 	for (String[] strings : authInfos) {
* 		TempleteAuth auth = new TempleteAuth();
*
* 		auth.setIdIfNew();
* 		auth.setAuthType(strings[0]);
* 		auth.setAuthId(Long.parseLong(strings[1]));
* 		auth.setSort(i++);
* 		auth.setTempleteId(templeteId);
*
* 		templete.getTempleteAuths().add(auth);
* 	}
* }
* </pre>
* </code>
*
* @param selectPeopleStr
*            选人后的字符串，如Department|123|4352345,Member|234|23452
* @return String[][] 第一列是类型，第二列是Id
*/
public static String[][] getSelectPeopleElements(String selectPeopleStr) {
String[][] results = null;
if (StringUtils.isNotBlank(selectPeopleStr)) {
String[] entities = selectPeopleStr.split(",");

results = new String[entities.length][2];

int i = 0;
for (String entity : entities) {
String[] items = entity.split("[|]");
results[i][0] = items[0];
results[i][1] = items[1];

i++;
}
}

return results;
}
/**
* 将字符串转换成Javascript，将对\r \n < > & 空格进行转换
*
* @param text
* @return
*/
public static String escapeJavascript(String str) {

if (str == null) {
return str;
}

StringBuffer out = new StringBuffer();

int sz;
sz = str.length();
for (int i = 0; i < sz; i++) {
char ch = str.charAt(i);

if (ch < 32) {
switch (ch) {
case '\b':
out.append('\\');
out.append('b');
break;
case '\n':
out.append('\\');
out.append('n');
break;
case '\t':
out.append('\\');
out.append('t');
break;
case '\f':
out.append('\\');
out.append('f');
break;
case '\r':
out.append('\\');
out.append('r');
break;
default:
if (ch > 0xf) {
out.append("\\u00" + hex(ch));
}
else {
out.append("\\u000" + hex(ch));
}
break;
}
}
else {
switch (ch) {
case '\'':
out.append('\\');
out.append('\'');
break;
case '"':
out.append("\\\"");
break;
case '\\':
out.append('\\');
out.append('\\');
break;
case '/':
out.append("\\/");
break;
default:
out.append(ch);
break;
}
}
}

return out.toString();
}
public static String escapeQuot(String str) {

if (str == null) {
return str;
}

StringBuffer out = new StringBuffer();

int sz;
sz = str.length();
for (int i = 0; i < sz; i++) {
char ch = str.charAt(i);

if (ch < 32) {
switch (ch) {
case '\b':
out.append('\\');
out.append('b');
break;
case '\n':
out.append('\\');
out.append('n');
break;
case '\t':
out.append('\\');
out.append('t');
break;
case '\f':
out.append('\\');
out.append('f');
break;
case '\r':
out.append('\\');
out.append('r');
break;
default:
if (ch > 0xf) {
out.append("\\u00" + hex(ch));
}
else {
out.append("\\u000" + hex(ch));
}
break;
}
}
else {
switch (ch) {
case '\'':
out.append("'");
break;
case '"':
out.append(""");
break;
case '<':
out.append("<");
break;
case '>':
out.append(">");
break;
case '\\':
out.append('\\');
out.append('\\');
break;
default:
out.append(ch);
break;
}
}
}

return out.toString();
}
private static String hex(char ch) {
return Integer.toHexString(ch).toUpperCase();
}

/**
* 检测是否是null字符串, 允许空格
*
* <pre>
* Strings.isEmpty(null)      = true
* Strings.isEmpty("")        = true
* Strings.isEmpty(" ")       = false
* Strings.isEmpty("bob")     = false
* Strings.isEmpty("  bob  ") = false
* </pre>
*
* @param str
* @return
*/
public static boolean isEmpty(String str){
return StringUtils.isEmpty(str);
}

/**
* 检测是否不是null字符串, 允许空格
*
* <pre>
* Strings.isNotEmpty(null)      = false
* Strings.isNotEmpty("")
3ff0
= false
* Strings.isNotEmpty(" ")       = true
* Strings.isNotEmpty("bob")     = true
* Strings.isNotEmpty("  bob  ") = true
* </pre>
*
* @param str
* @return
*/
public static boolean isNotEmpty(String str){
return StringUtils.isNotEmpty(str);
}

/**
* 检测是否是空字符串, 不允许空格
*
* <pre>
* Strings.isBlank(null)      = true
* Strings.isBlank("")        = true
* Strings.isBlank(" ")       = true
* Strings.isBlank("bob")     = false
* Strings.isBlank("  bob  ") = false
* </pre>
*
* @param str
* @return
*/
public static boolean isBlank(String str){
return StringUtils.isBlank(str);
}

/**
* 检测集合是否有数据
*
* @param c
* @return
*/
public static boolean isEmpty(Collection c){
return c == null || c.isEmpty();
}

public static boolean isNotEmpty(Collection c){
return !isEmpty(c);
}

/**
* 检测是否不是空字符串, 不允许空格
*
* <pre>
* Strings.isNotBlank(null)      = false
* Strings.isNotBlank("")        = false
* Strings.isNotBlank(" ")       = false
* Strings.isNotBlank("bob")     = true
* Strings.isNotBlank("  bob  ") = true
* </pre>
*
* @param str
* @return
*/
public static boolean isNotBlank(String str){
return StringUtils.isNotBlank(str);
}

//  public static final String REGEX_DIGIT = "(^-|[\\d])[\\d]+$";
public static final String REGEX_DIGIT ="^([-]?[\\d]*)[\\d]+$";
public static final String REGEX_WORD  = "^[\\w]+$";
public static final String REGEX_I18NKey  = "^[\\w.-]+$";
public static final String REGEX_NOTCHARACTER = "[\\x00-\\xff]*[^\\x00-\\xff]+[\\x00-\\xff]*";
public static final String REGEX_DECIMAL_EXCLUDEPLUS ="^([-]?)([\\d]*)([.]?)(\\d+)$";

/**
* 检测是否为整形数字
*
* <pre>
* Strings.isDigits("1234")    = true
* Strings.isDigits("a123")    = false
* Strings.isDigits(" 123")    = false
* </pre>
*
* @param str
* @return
*/
public static boolean isDigits(String str){
return Pattern.matches(REGEX_DIGIT, str);
}

public static boolean isTrue(Boolean b){
return Boolean.TRUE.equals(b);
}

/**
* 检测是否为纯单词，只有数字、字母、下划线
*
* @param str
* @return
*/
public static boolean isWord(String str){
return Pattern.matches(REGEX_WORD, str);
}

/**
* 是否是标准的国际化资源的key，有数字/字母/下划线/点／横线组成
*
* @param key
* @return
*/
public static boolean isI18NKey(String key){
if(isBlank(key)){
return false;
}

return Pattern.matches(REGEX_I18NKey, key);
}

/**
* 转换成标准的路径
* <pre>
* C:/a/b/c           -->  C:\a\b\c
* C:/a/b/c/..        -->  C:\a\b
* C:/a/b/c/../..     -->  C:\a
* C:/a/b/../c        -->  C:\a\c
* C:/../a/b/../c     -->  C:\a\c
* </pre>
*
* @param filepath
* @return
*/
public static String getCanonicalPath(String filepath){
return getCanonicalPath(filepath, false);
}

/**
* 转换成标准的路径，同时创建文件夹
*
* @param filepath
* @return
* @see getCanonicalPath(String)
*/
public static String getCanonicalPathAndCreate(String filepath){
return getCanonicalPath(filepath, true);
}

private static String getCanonicalPath(String filepath, boolean isCreate){
if(isBlank(filepath)){
return null;
}
String path = FilenameUtils.normalize(filepath);
File f = new File(path);
try {
File fc = f.getCanonicalFile();

if(isCreate){
fc.mkdirs();
}

return fc.getAbsolutePath();
}
catch (IOException e) {
}

return filepath;
}

/**
* 得到站点的基础路径：http://office.seeyon.com:80
*
* @param request
* @return
*/
public static String getBaseHref(HttpServletRequest request){
return request.getScheme() + "://" + request.getServerName() + ":" + request.getServerPort();
}

/**
* 得到站点的基础路径+contextPath：http://office.seeyon.com:80/seeyon
*
* @param request
* @return
*/
public static String getBaseContext(HttpServletRequest request){
return getBaseHref(request) + request.getContextPath();
}

public static String toXmlStr(String srcStr)
{
String xml=srcStr;
xml=xml.replaceAll("&","&");
xml=xml.replaceAll("<","<");
xml=xml.replaceAll(">",">");
xml=xml.replaceAll("'","'");
xml=xml.replaceAll("\"",""");
return xml;
}

/**
* 判断是否包括汉字等非字符
* isIncludeNotCharacter("234ds,提供电所")=true
* isIncludeNotCharacter("234ds, ?\\ff3")=false
* @param str
* @return
*/
public static boolean isIncludeNotCharacter(String str) {
if(str==null)
return false;
return Pattern.matches(REGEX_NOTCHARACTER, str);
}

/**
* 判断是否是数字，包括-号开始，小数点，小数部分；
* 整数部分能以0开始，小数部分能以0结尾，整个数字不能以.结尾；
* 主要用于表单数据校验
* 34342.02   true
* 02425.6    true
* 232.60     true
* 0.2323     true
* 00.325     true
* +656.32    false
* -233       true
* -.32       true
* .32        true
* @param str
* @return
*/
public static boolean isDecimalExcludePlus(String str){
if(str == null)
return false;
return Pattern.matches(REGEX_DECIMAL_EXCLUDEPLUS, str);
}

/**
*
* @param <K>
* @param <V>
* @param map
* @param k
* @param v
*/
public static <K, V> void  addToMap1(Map<K, ArrayList<V>> map, K k, V v){
ArrayList<V> list = map.get(k);
if(list == null){
list = new ArrayList<V>();
map.put(k, list);
}

list.add(v);
}
public  static <K, V> void  addToMap(Map<K, List<V>> map, K k, V v){
List<V> list = map.get(k);
if(list == null){
list = new ArrayList<V>();
map.put(k, list);
}

list.add(v);
}

/**
* 将不换行空格（NO-BREAK SPACE，Unicode 0x00a0，UTF-8编码：0xC2A0）替换为普通空格。
* 用于避免因数据库字符集不兼容导致这个字符变为问号“?”的情况。
*/
public static String nobreakSpaceToSpace(String str) {
if (str == null) {
return null;
}
char nbsp = 0x00a0;
return str.replace(nbsp, ' ');
}

public static void main(String[] args) {
String t = "asdf''''\nsadf</br>";
String temp = Strings.toHTMLAlt(t);
System.out.println(temp);

System.out.println(Strings.join("|", "a","b","c"));
System.out.println(Strings.hex('A'));
}
}