Example usage for java.lang String codePointAt

Introduction

In this page you can find the example usage for java.lang String codePointAt.

Prototype

public int codePointAt(int index) 

Source Link

Document

Returns the character (Unicode code point) at the specified index.

Usage

From source file:hm.binkley.util.ServiceBinder.java

private static boolean skip(final String s) {
    if (null == s)
        return true;
    final int len = s.length();
    if (0 == len)
        return true;
    for (int i = 0; i < len;) {
        final int cp = s.codePointAt(i);
        if (!isWhitespace(cp))
            return false;
        i += charCount(cp);/*from   w  w  w. ja  v a 2 s.  co m*/
    }
    return true;
}

---

From source file:com.pfarrell.utils.misc.TextTools.java

/**
 * make a string with no whitespace at all
 * @param arg  string//from w w  w.  ja  v  a  2s  .  c  om
 * @return string with no whitespace
 */
public static String noWhiteSpace(String arg) {
    StringBuilder sb = new StringBuilder();
    for (int i = 0; i < arg.length(); i++) {
        int c = arg.codePointAt(i);
        if (!Character.isWhitespace(c)) {
            sb.appendCodePoint(c);
        }
    }
    return sb.toString();
}

---

From source file:com.pfarrell.utils.misc.TextTools.java

/**
 * make a string with no whitespace at all
 * @param arg  string/*from  www .  ja v a2  s .c  o  m*/
 * @return string with no whitespace
 */
public static String justLettersOrDigits(String arg) {
    StringBuilder sb = new StringBuilder();
    for (int i = 0; i < arg.length(); i++) {
        int c = arg.codePointAt(i);
        if (Character.isLetterOrDigit(c)) {
            sb.appendCodePoint(c);
        }
    }
    return sb.toString();
}

---

From source file:com.pfarrell.utils.misc.TextTools.java

/**
 * make a string with only letters//  w  w  w  .  j av a2  s  .c  om
 * @param arg  string
 * @return string with only letters, no punct, space, digits, etc.
 */
public static String justLetters(String arg) {
    StringBuilder sb = new StringBuilder();
    for (int i = 0; i < arg.length(); i++) {
        int c = arg.codePointAt(i);
        if (Character.isLetter(c)) {
            sb.appendCodePoint(c);
        }
    }
    return sb.toString();
}

---

From source file:com.pfarrell.utils.misc.TextTools.java

/**
 * make a string with only digits/*  ww  w.ja  va 2  s  .  c  o  m*/
 * @param arg  string
 * @return string with only digits
 */
public static String justDigits(String arg) {
    StringBuilder sb = new StringBuilder();
    for (int i = 0; i < arg.length(); i++) {
        int c = arg.codePointAt(i);
        if (Character.isDigit(c)) {
            sb.appendCodePoint(c);
        }
    }
    return sb.toString();
}

---

From source file:org.exoplatform.cms.common.TransformHTML.java

public static String enCodeViewSignature(String s) {
    if (s != null && s.trim().length() > 0) {
        // replace enter key to <br/> tag html
        StringBuffer buffer = new StringBuffer();
        for (int j = 0; j < s.trim().length(); j++) {
            if (s.codePointAt(j) == 10) {
                buffer.append("<br/>");
            } else {
                buffer.append(s.charAt(j));
            }//from  ww  w  .j  a v a  2s  .  c  om
        }
        s = buffer.toString();
    } else
        s = EMPTY_STR;
    return s;
}

---

From source file:com.predic8.membrane.core.interceptor.IndexInterceptor.java

static String fullfillRegexp(String regex) {
    StringBuilder sb = new StringBuilder();
    int p = 0, groupLevel = 0;
    WHILE: while (p < regex.length()) {
        int c = regex.codePointAt(p++);
        switch (c) {
        case '\\':
            if (p == regex.length())
                return null; // illegal
            c = regex.codePointAt(p++);//from   w w w. j a  va  2  s .  c o m
            if (Character.isDigit(c))
                return null; // backreferences are not supported
            if (c == 'Q') {
                while (true) {
                    if (p == regex.length())
                        return null; // 'end of regex' within quote
                    c = regex.codePointAt(p++);
                    if (c == '\\') {
                        if (p == regex.length())
                            return null; // 'end of regex' within quote
                        c = regex.codePointAt(p++);
                        if (c == 'E')
                            break;
                        sb.append('\\');
                    }
                    sb.appendCodePoint(c);
                }
                break;
            }
            if (c == 'E') {
                return null; // 'end of quote' without begin
            }
            sb.appendCodePoint(c);
            break;
        case '[':
        case '?':
        case '*':
        case '+':
        case '{':
            return null; // meaningful characters we do not unterstand
        case '(':
            groupLevel++;
            break;
        case ')':
            if (groupLevel == 0)
                return null; // unbalanced ')'
            else
                groupLevel--;
            break;
        case '|':
            if (groupLevel == 0) {
                break WHILE;
            }
            W2: while (true) {
                if (++p == regex.length())
                    return null; // unbalanced ')'
                switch (regex.charAt(p)) {
                case ')':
                    break W2;
                case '[':
                case '?':
                case '*':
                case '+':
                case '{':
                    return null; // meaningful characters we do not unterstand
                case '\\':
                    return null; // TODO: \) \Q..\E
                }
            }
            groupLevel--;
            p++;
            break;
        case '^':
            if (p == 1)
                break;
            return null;
        case '$':
            if (p == regex.length() || regex.codePointAt(p) == '|')
                break;
            return null;
        case '.':
            int q;
            if (p != regex.length() && isQuantifier(q = regex.codePointAt(p))) {
                if (++p != regex.length() && isModifier(regex.codePointAt(p)))
                    p++;
                if (q == '+')
                    sb.append('a');
            } else {
                sb.append('a');
            }
            break;
        default:
            sb.appendCodePoint(c);
            break;
        }
    }
    if (groupLevel > 0)
        return null;
    return sb.toString();
}

---

From source file:com.marklogic.mapreduce.utilities.InternalUtilities.java

public static String unparse(String s) {
    int len = s.length();
    StringBuilder buf = new StringBuilder(len * 2);
    for (int cp, i = 0; i < s.length(); i += Character.charCount(cp)) {
        cp = s.codePointAt(i);
        // iterate through the codepoints in the string
        if ((cp >= 0x20) && (cp < 0x80)) {
            switch (cp) {
            case '"':
                buf.append("&quot;");
                break;
            case '&':
                buf.append("&amp;");
                break;
            default:
                buf.append(s.charAt(i));
            }//from  w  w  w. j  a  v  a 2  s.  c om
        } else {
            buf.append("&#x");
            buf.append(Long.toString(cp, 16));
            buf.append(';');
        }
    }
    return buf.toString();
}

---

From source file:password.pwm.util.StringUtil.java

public static int[] toCodePointArray(String str) {
    if (str != null) {
        int len = str.length();
        int[] acp = new int[str.codePointCount(0, len)];

        for (int i = 0, j = 0; i < len; i = str.offsetByCodePoints(i, 1)) {
            acp[j++] = str.codePointAt(i);
        }//from   w  w  w . ja v a  2  s . c om

        return acp;
    }

    return new int[0];
}

---

From source file:Main.java

/**
 * This method ensures that the output String has only valid XML unicode
 * characters as specified by the XML 1.0 standard. For reference, please
 * see//from   ww  w .j  a v  a 2s  .c  o  m
 * <a href="http://www.w3.org/TR/2000/REC-xml-20001006#NT-Char">the
 * standard</a>. This method will return an empty String if the input is
 * null or empty.
 *
 * @param in The String whose non-valid characters we want to remove.
 * @return The in String, stripped of non-valid characters.
 */
public static String cleanInvalidXmlChars(String text) {

    if (null == text || text.isEmpty()) {
        return text;
    }

    final int len = text.length();
    char current = 0;
    int codePoint = 0;
    StringBuilder sb = new StringBuilder();
    for (int i = 0; i < len; i++) {
        current = text.charAt(i);
        boolean surrogate = false;
        if (Character.isHighSurrogate(current) && i + 1 < len && Character.isLowSurrogate(text.charAt(i + 1))) {
            surrogate = true;
            codePoint = text.codePointAt(i++);
        } else {
            codePoint = current;
        }
        if ((codePoint == 0x9) || (codePoint == 0xA) || (codePoint == 0xD)
                || ((codePoint >= 0x20) && (codePoint <= 0xD7FF))
                || ((codePoint >= 0xE000) && (codePoint <= 0xFFFD))
                || ((codePoint >= 0x10000) && (codePoint <= 0x10FFFF))) {
            sb.append(current);

            if (surrogate) {
                sb.append(text.charAt(i));
            }
        } else {

            // 
            // Invalid Char at index transformed into hex 
            //System.err.println("Index=["+ i +"] Char=["+ String.format("%04x", (int)text.charAt(i)) +"] CodePoint=[" + codePoint + "]");
            //sb.append("hex"+String.format("%04x", (int)text.charAt(i)));
        }
    }

    return sb.toString();
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• »