jodd.util.CharUtil Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of xml-stream-css Show documentation
Show all versions of xml-stream-css Show documentation
Stream Xml using StAX and Css matcher
The newest version!
package jodd.util;
import java.io.UnsupportedEncodingException;
/**
* Various character and character sequence utilities, including char[] - byte[] conversions.
*/
public class CharUtil {
// ---------------------------------------------------------------- simple
/**
* Converts (signed) byte to (unsigned) char.
*/
public static char toChar(byte b) {
return (char) (b & 0xFF);
}
/**
* Converts char array into byte array by stripping the high byte of each character.
*/
public static byte[] toSimpleByteArray(char[] carr) {
byte[] barr = new byte[carr.length];
for (int i = 0; i < carr.length; i++) {
barr[i] = (byte) carr[i];
}
return barr;
}
/**
* Converts char sequence into byte array.
* @see #toSimpleByteArray(char[])
*/
public static byte[] toSimpleByteArray(CharSequence charSequence) {
byte[] barr = new byte[charSequence.length()];
for (int i = 0; i < barr.length; i++) {
barr[i] = (byte) charSequence.charAt(i);
}
return barr;
}
/**
* Converts byte array to char array by simply extending bytes to chars.
*/
public static char[] toSimpleCharArray(byte[] barr) {
char[] carr = new char[barr.length];
for (int i = 0; i < barr.length; i++) {
carr[i] = (char) (barr[i] & 0xFF);
}
return carr;
}
// ---------------------------------------------------------------- ascii
/**
* Returns ASCII value of a char. In case of overload, 0x3F is returned.
*/
public static int toAscii(char c) {
if (c <= 0xFF) {
return c;
} else {
return 0x3F;
}
}
/**
* Converts char array into {@link #toAscii(char) ASCII} array.
*/
public static byte[] toAsciiByteArray(char[] carr) {
byte[] barr = new byte[carr.length];
for (int i = 0; i < carr.length; i++) {
barr[i] = (byte) ((int) (carr[i] <= 0xFF ? carr[i] : 0x3F));
}
return barr;
}
/**
* Converts char sequence into ASCII byte array.
*/
public static byte[] toAsciiByteArray(CharSequence charSequence) {
byte[] barr = new byte[charSequence.length()];
for (int i = 0; i < barr.length; i++) {
char c = charSequence.charAt(i);
barr[i] = (byte) ((int) (c <= 0xFF ? c : 0x3F));
}
return barr;
}
// ---------------------------------------------------------------- raw arrays
/**
* Converts char array into byte array by replacing each character with two bytes.
*/
public static byte[] toRawByteArray(char[] carr) {
byte[] barr = new byte[carr.length << 1];
for (int i = 0, bpos = 0; i < carr.length; i++) {
char c = carr[i];
barr[bpos++] = (byte) ((c & 0xFF00) >> 8);
barr[bpos++] = (byte) (c & 0x00FF);
}
return barr;
}
public static char[] toRawCharArray(byte[] barr) {
int carrLen = barr.length >> 1;
if (carrLen << 1 < barr.length) {
carrLen++;
}
char[] carr = new char[carrLen];
int i = 0, j = 0;
while (i < barr.length) {
char c = (char) (barr[i] << 8);
i++;
if (i != barr.length) {
c += barr[i] & 0xFF;
i++;
}
carr[j++] = c;
}
return carr;
}
// ---------------------------------------------------------------- encoding
/**
* Converts byte array of specific encoding to char array.
*/
public static char[] toCharArray(byte[] barr, String charset) throws UnsupportedEncodingException {
return new String(barr, charset).toCharArray();
}
// ---------------------------------------------------------------- find
/**
* Match if one character equals to any of the given character.
*
* @return true if characters match any character from given array,
* otherwise false
*/
public static boolean equalsOne(char c, char[] match) {
for (char aMatch : match) {
if (c == aMatch) {
return true;
}
}
return false;
}
/**
* Finds index of the first character in given array the matches any from the
* given set of characters.
*
* @return index of matched character or -1
*/
public static int findFirstEqual(char[] source, int index, char[] match) {
for (int i = index; i < source.length; i++) {
if (equalsOne(source[i], match) == true) {
return i;
}
}
return -1;
}
/**
* Finds index of the first character in given array the matches any from the
* given set of characters.
*
* @return index of matched character or -1
*/
public static int findFirstEqual(char[] source, int index, char match) {
for (int i = index; i < source.length; i++) {
if (source[i] == match) {
return i;
}
}
return -1;
}
/**
* Finds index of the first character in given array the differs from the
* given set of characters.
*
* @return index of matched character or -1
*/
public static int findFirstDiff(char[] source, int index, char[] match) {
for (int i = index; i < source.length; i++) {
if (equalsOne(source[i], match) == false) {
return i;
}
}
return -1;
}
/**
* Finds index of the first character in given array the differs from the
* given set of characters.
*
* @return index of matched character or -1
*/
public static int findFirstDiff(char[] source, int index, char match) {
for (int i = index; i < source.length; i++) {
if (source[i] != match) {
return i;
}
}
return -1;
}
// ---------------------------------------------------------------- is
/**
* Returns true if character is a white space ({@code <= ' '}).
* White space definition is taken from String class (see: trim()).
*/
public static boolean isWhitespace(char c) {
return c <= ' ';
}
/**
* Returns true if specified character is lowercase ASCII.
* If user uses only ASCIIs, it is much much faster.
*/
public static boolean isLowercaseAlpha(char c) {
return (c >= 'a') && (c <= 'z');
}
/**
* Returns true if specified character is uppercase ASCII.
* If user uses only ASCIIs, it is much much faster.
*/
public static boolean isUppercaseAlpha(char c) {
return (c >= 'A') && (c <= 'Z');
}
public static boolean isAlphaOrDigit(char c) {
return isDigit(c) || isAlpha(c);
}
public static boolean isWordChar(char c) {
return isDigit(c) || isAlpha(c) || (c == '_');
}
public static boolean isPropertyNameChar(char c) {
return isDigit(c) || isAlpha(c) || (c == '_') || (c == '.') || (c == '[') || (c == ']');
}
// ---------------------------------------------------------------- RFC
/**
* Indicates whether the given character is in the {@code ALPHA} set.
*
* @see RFC 3986, appendix A
*/
public static boolean isAlpha(char c) {
return ((c >= 'a') && (c <= 'z')) || ((c >= 'A') && (c <= 'Z'));
}
/**
* Indicates whether the given character is in the {@code DIGIT} set.
*
* @see RFC 3986, appendix A
*/
public static boolean isDigit(char c) {
return c >= '0' && c <= '9';
}
/**
* Indicates whether the given character is the hexadecimal digit.
*/
public static boolean isHexDigit(char c) {
return (c >= '0' && c <= '9') || ((c >= 'a') && (c <= 'f')) || ((c >= 'A') && (c <= 'F'));
}
/**
* Indicates whether the given character is in the gen-delims set.
*
* @see RFC 3986, appendix A
*/
public static boolean isGenericDelimiter(int c) {
switch (c) {
case ':':
case '/':
case '?':
case '#':
case '[':
case ']':
case '@':
return true;
default:
return false;
}
}
/**
* Indicates whether the given character is in the sub-delims set.
*
* @see RFC 3986, appendix A
*/
protected static boolean isSubDelimiter(int c) {
switch (c) {
case '!':
case '$':
case '&':
case '\'':
case '(':
case ')':
case '*':
case '+':
case ',':
case ';':
case '=':
return true;
default:
return false;
}
}
/**
* Indicates whether the given character is in the reserved set.
*
* @see RFC 3986, appendix A
*/
protected static boolean isReserved(char c) {
return isGenericDelimiter(c) || isSubDelimiter(c);
}
/**
* Indicates whether the given character is in the unreserved set.
*
* @see RFC 3986, appendix A
*/
protected static boolean isUnreserved(char c) {
return isAlpha(c) || isDigit(c) || c == '-' || c == '.' || c == '_' || c == '~';
}
/**
* Indicates whether the given character is in the pchar set.
*
* @see RFC 3986, appendix A
*/
protected static boolean isPchar(char c) {
return isUnreserved(c) || isSubDelimiter(c) || c == ':' || c == '@';
}
// ---------------------------------------------------------------- conversions
/**
* Uppers lowercase ASCII char.
*/
public static char toUpperAscii(char c) {
if (isLowercaseAlpha(c)) {
c -= (char) 0x20;
}
return c;
}
/**
* Lowers uppercase ASCII char.
*/
public static char toLowerAscii(char c) {
if (isUppercaseAlpha(c)) {
c += (char) 0x20;
}
return c;
}
/**
* Converts hex char to int value.
*/
public static int hex2int(char c) {
switch (c) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
return c - '0';
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
return c - 55;
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
return c - 87;
default:
throw new IllegalArgumentException("Not a hex: " + c);
}
}
/**
* Converts integer digit to heck char.
*/
public static char int2hex(int i) {
return HEX_CHARS[i];
}
public static final char[] HEX_CHARS = new char[] {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'};
}