Splits the provided text into an array, separator string specified. - Java java.lang

Description

Splits the provided text into an array, separator string specified.

Demo Code

/*/*from   ww w  .jav a  2  s .c o  m*/
 * Copyright 2013 Guidewire Software, Inc.
 */
/**
 * This class is based, in part, on org.apache.commons.lang.StringUtils and is intended
 * to break the dependency on that project.
 *
 * @author <a href="http://jakarta.apache.org/turbine/">Apache Jakarta Turbine</a>
 * @author <a href="mailto:jon@latchkey.com">Jon S. Stevens</a>
 * @author Daniel L. Rall
 * @author <a href="mailto:gcoladonato@yahoo.com">Greg Coladonato</a>
 * @author <a href="mailto:ed@apache.org">Ed Korthof</a>
 * @author <a href="mailto:rand_mcneely@yahoo.com">Rand McNeely</a>
 * @author Stephen Colebourne
 * @author <a href="mailto:fredrik@westermarck.com">Fredrik Westermarck</a>
 * @author Holger Krauth
 * @author <a href="mailto:alex@purpletech.com">Alexander Day Chaffee</a>
 * @author <a href="mailto:hps@intermeta.de">Henning P. Schmiedehausen</a>
 * @author Arun Mammen Thomas
 * @author Gary Gregory
 * @author Phil Steitz
 * @author Al Chou
 * @author Michael Davey
 * @author Reuben Sivan
 * @author Chris Hyzer
 *  Johnson

 */
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.util.Arrays;
import java.util.Collection;
import java.util.ArrayList;
import java.util.Formatter;
import java.util.List;
import java.util.Iterator;
import java.util.Locale;
import java.util.regex.Pattern;
import java.util.regex.Matcher;

public class Main{
    public static void main(String[] argv){
        String str = "java2s.com";
        String separator = "java2s.com";
        System.out.println(java.util.Arrays.toString(splitByWholeSeparatorPreserveAllTokens(str,separator)));
    }
    private static final String[] EMPTY_STRING_ARRAY = new String[0];
    /**
     * The empty String <code>""</code>.
     * @since 2.0
     */
    public static final String EMPTY = "";
    /**
     * <p>Splits the provided text into an array, separator string specified. </p>
     *
     * <p>The separator is not included in the returned String array.
     * Adjacent separators are treated as separators for empty tokens.
     * For more control over the split use the StrTokenizer class.</p>
     *
     * <p>A <code>null</code> input String returns <code>null</code>.
     * A <code>null</code> separator splits on whitespace.</p>
     *
     * <pre>
     * splitByWholeSeparatorPreserveAllTokens(null, *)               = null
     * splitByWholeSeparatorPreserveAllTokens("", *)                 = []
     * splitByWholeSeparatorPreserveAllTokens("ab de fg", null)      = ["ab", "de", "fg"]
     * splitByWholeSeparatorPreserveAllTokens("ab   de fg", null)    = ["ab", "", "", "de", "fg"]
     * splitByWholeSeparatorPreserveAllTokens("ab:cd:ef", ":")       = ["ab", "cd", "ef"]
     * splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-") = ["ab", "cd", "ef"]
     * </pre>
     *
     * @param str  the String to parse, may be null
     * @param separator  String containing the String to be used as a delimiter,
     *  <code>null</code> splits on whitespace
     * @return an array of parsed Strings, <code>null</code> if null String was input
     * @since 2.4
     */
    public static String[] splitByWholeSeparatorPreserveAllTokens(
            String str, String separator) {
        return splitByWholeSeparatorWorker(str, separator, -1, true);
    }
    /**
     * <p>Splits the provided text into an array, separator string specified.
     * Returns a maximum of <code>max</code> substrings.</p>
     *
     * <p>The separator is not included in the returned String array.
     * Adjacent separators are treated as separators for empty tokens.
     * For more control over the split use the StrTokenizer class.</p>
     *
     * <p>A <code>null</code> input String returns <code>null</code>.
     * A <code>null</code> separator splits on whitespace.</p>
     *
     * <pre>
     * splitByWholeSeparatorPreserveAllTokens(null, *, *)               = null
     * splitByWholeSeparatorPreserveAllTokens("", *, *)                 = []
     * splitByWholeSeparatorPreserveAllTokens("ab de fg", null, 0)      = ["ab", "de", "fg"]
     * splitByWholeSeparatorPreserveAllTokens("ab   de fg", null, 0)    = ["ab", "", "", "de", "fg"]
     * splitByWholeSeparatorPreserveAllTokens("ab:cd:ef", ":", 2)       = ["ab", "cd:ef"]
     * splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-", 5) = ["ab", "cd", "ef"]
     * splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-", 2) = ["ab", "cd-!-ef"]
     * </pre>
     *
     * @param str  the String to parse, may be null
     * @param separator  String containing the String to be used as a delimiter,
     *  <code>null</code> splits on whitespace
     * @param max  the maximum number of elements to include in the returned
     *  array. A zero or negative value implies no limit.
     * @return an array of parsed Strings, <code>null</code> if null String was input
     * @since 2.4
     */
    public static String[] splitByWholeSeparatorPreserveAllTokens(
            String str, String separator, int max) {
        return splitByWholeSeparatorWorker(str, separator, max, true);
    }
    /**
     * Performs the logic for the <code>splitByWholeSeparatorPreserveAllTokens</code> methods.
     *
     * @param str  the String to parse, may be <code>null</code>
     * @param separator  String containing the String to be used as a delimiter,
     *  <code>null</code> splits on whitespace
     * @param max  the maximum number of elements to include in the returned
     *  array. A zero or negative value implies no limit.
     * @param preserveAllTokens if <code>true</code>, adjacent separators are
     * treated as empty token separators; if <code>false</code>, adjacent
     * separators are treated as one separator.
     * @return an array of parsed Strings, <code>null</code> if null String input
     * @since 2.4
     */
    private static String[] splitByWholeSeparatorWorker(String str,
            String separator, int max, boolean preserveAllTokens) {
        if (str == null) {
            return null;
        }

        int len = str.length();

        if (len == 0) {
            return EMPTY_STRING_ARRAY;
        }

        if ((separator == null) || (EMPTY.equals(separator))) {
            // Split on whitespace.
            return splitWorker(str, null, max, preserveAllTokens);
        }

        int separatorLength = separator.length();

        ArrayList substrings = new ArrayList();
        int numberOfSubstrings = 0;
        int beg = 0;
        int end = 0;
        while (end < len) {
            end = str.indexOf(separator, beg);

            if (end > -1) {
                if (end > beg) {
                    numberOfSubstrings += 1;

                    if (numberOfSubstrings == max) {
                        end = len;
                        substrings.add(str.substring(beg));
                    } else {
                        // The following is OK, because String.substring( beg, end ) excludes
                        // the character at the position 'end'.
                        substrings.add(str.substring(beg, end));

                        // Set the starting point for the next search.
                        // The following is equivalent to beg = end + (separatorLength - 1) + 1,
                        // which is the right calculation:
                        beg = end + separatorLength;
                    }
                } else {
                    // We found a consecutive occurrence of the separator, so skip it.
                    if (preserveAllTokens) {
                        numberOfSubstrings += 1;
                        if (numberOfSubstrings == max) {
                            end = len;
                            substrings.add(str.substring(beg));
                        } else {
                            substrings.add(EMPTY);
                        }
                    }
                    beg = end + separatorLength;
                }
            } else {
                // String.substring( beg ) goes from 'beg' to the end of the String.
                substrings.add(str.substring(beg));
                end = len;
            }
        }

        return (String[]) substrings.toArray(new String[substrings.size()]);
    }
    /**
     * Gets a String's length or <code>0</code> if the String is <code>null</code>.
     *
     * @param str
     *            a String or <code>null</code>
     * @return String length or <code>0</code> if the String is <code>null</code>.
     * @since 2.4
     */
    public static int length(String str) {
        return str == null ? 0 : str.length();
    }
    /**
     * <p>Compares two Strings, returning <code>true</code> if they are equal.</p>
     *
     * <p><code>null</code>s are handled without exceptions. Two <code>null</code>
     * references are considered to be equal. The comparison is case sensitive.</p>
     *
     * <pre>
     * equals(null, null)   = true
     * equals(null, "abc")  = false
     * equals("abc", null)  = false
     * equals("abc", "abc") = true
     * equals("abc", "ABC") = false
     * </pre>
     *
     * @see java.lang.String#equals(Object)
     * @param str1  the first String, may be null
     * @param str2  the second String, may be null
     * @return <code>true</code> if the Strings are equal, case sensitive, or
     *  both <code>null</code>
     */
    public static boolean equals(String str1, String str2) {
        return str1 == null ? str2 == null : str1.equals(str2);
    }
    /**
     * Performs the logic for the <code>split</code> and
     * <code>splitPreserveAllTokens</code> methods that do not return a
     * maximum array length.
     *
     * @param str  the String to parse, may be <code>null</code>
     * @param separatorChar the separate character
     * @param preserveAllTokens if <code>true</code>, adjacent separators are
     * treated as empty token separators; if <code>false</code>, adjacent
     * separators are treated as one separator.
     * @return an array of parsed Strings, <code>null</code> if null String input
     */
    private static String[] splitWorker(String str, char separatorChar,
            boolean preserveAllTokens) {
        // Performance tuned for 2.0 (JDK1.4)

        if (str == null) {
            return null;
        }
        int len = str.length();
        if (len == 0) {
            return EMPTY_STRING_ARRAY;
        }
        List list = new ArrayList();
        int i = 0, start = 0;
        boolean match = false;
        boolean lastMatch = false;
        while (i < len) {
            if (str.charAt(i) == separatorChar) {
                if (match || preserveAllTokens) {
                    list.add(str.substring(start, i));
                    match = false;
                    lastMatch = true;
                }
                start = ++i;
                continue;
            }
            lastMatch = false;
            match = true;
            i++;
        }
        if (match || (preserveAllTokens && lastMatch)) {
            list.add(str.substring(start, i));
        }
        return (String[]) list.toArray(new String[list.size()]);
    }
    /**
     * Performs the logic for the <code>split</code> and
     * <code>splitPreserveAllTokens</code> methods that return a maximum array
     * length.
     *
     * @param str  the String to parse, may be <code>null</code>
     * @param separatorChars the separate character
     * @param max  the maximum number of elements to include in the
     *  array. A zero or negative value implies no limit.
     * @param preserveAllTokens if <code>true</code>, adjacent separators are
     * treated as empty token separators; if <code>false</code>, adjacent
     * separators are treated as one separator.
     * @return an array of parsed Strings, <code>null</code> if null String input
     */
    private static String[] splitWorker(String str, String separatorChars,
            int max, boolean preserveAllTokens) {
        // Performance tuned for 2.0 (JDK1.4)
        // Direct code is quicker than StringTokenizer.
        // Also, StringTokenizer uses isSpace() not isWhitespace()

        if (str == null) {
            return null;
        }
        int len = str.length();
        if (len == 0) {
            return EMPTY_STRING_ARRAY;
        }
        List list = new ArrayList();
        int sizePlus1 = 1;
        int i = 0, start = 0;
        boolean match = false;
        boolean lastMatch = false;
        if (separatorChars == null) {
            // Null separator means use whitespace
            while (i < len) {
                if (Character.isWhitespace(str.charAt(i))) {
                    if (match || preserveAllTokens) {
                        lastMatch = true;
                        if (sizePlus1++ == max) {
                            i = len;
                            lastMatch = false;
                        }
                        list.add(str.substring(start, i));
                        match = false;
                    }
                    start = ++i;
                    continue;
                }
                lastMatch = false;
                match = true;
                i++;
            }
        } else if (separatorChars.length() == 1) {
            // Optimise 1 character case
            char sep = separatorChars.charAt(0);
            while (i < len) {
                if (str.charAt(i) == sep) {
                    if (match || preserveAllTokens) {
                        lastMatch = true;
                        if (sizePlus1++ == max) {
                            i = len;
                            lastMatch = false;
                        }
                        list.add(str.substring(start, i));
                        match = false;
                    }
                    start = ++i;
                    continue;
                }
                lastMatch = false;
                match = true;
                i++;
            }
        } else {
            // standard case
            while (i < len) {
                if (separatorChars.indexOf(str.charAt(i)) >= 0) {
                    if (match || preserveAllTokens) {
                        lastMatch = true;
                        if (sizePlus1++ == max) {
                            i = len;
                            lastMatch = false;
                        }
                        list.add(str.substring(start, i));
                        match = false;
                    }
                    start = ++i;
                    continue;
                }
                lastMatch = false;
                match = true;
                i++;
            }
        }
        if (match || (preserveAllTokens && lastMatch)) {
            list.add(str.substring(start, i));
        }
        return (String[]) list.toArray(new String[list.size()]);
    }
    /**
     * <p>Finds the first index within a String, handling <code>null</code>.
     * This method uses {@link String#indexOf(int)}.</p>
     *
     * <p>A <code>null</code> or empty ("") String will return <code>-1</code>.</p>
     *
     * <pre>
     * indexOf(null, *)         = -1
     * indexOf("", *)           = -1
     * indexOf("aabaabaa", 'a') = 0
     * indexOf("aabaabaa", 'b') = 2
     * </pre>
     *
     * @param str  the String to check, may be null
     * @param searchChar  the character to find
     * @return the first index of the search character,
     *  -1 if no match or <code>null</code> string input
     * @since 2.0
     */
    public static int indexOf(String str, char searchChar) {
      if (str==null || str.isEmpty()) {
            return -1;
        }
        return str.indexOf(searchChar);
    }
    /**
     * <p>Finds the first index within a String from a start position,
     * handling <code>null</code>.
     * This method uses {@link String#indexOf(int, int)}.</p>
     *
     * <p>A <code>null</code> or empty ("") String will return <code>-1</code>.
     * A negative start position is treated as zero.
     * A start position greater than the string length returns <code>-1</code>.</p>
     *
     * <pre>
     * indexOf(null, *, *)          = -1
     * indexOf("", *, *)            = -1
     * indexOf("aabaabaa", 'b', 0)  = 2
     * indexOf("aabaabaa", 'b', 3)  = 5
     * indexOf("aabaabaa", 'b', 9)  = -1
     * indexOf("aabaabaa", 'b', -1) = 2
     * </pre>
     *
     * @param str  the String to check, may be null
     * @param searchChar  the character to find
     * @param startPos  the start position, negative treated as zero
     * @return the first index of the search character,
     *  -1 if no match or <code>null</code> string input
     * @since 2.0
     */
    public static int indexOf(String str, char searchChar, int startPos) {
        if (str==null || str.isEmpty()) {
            return -1;
        }
        return str.indexOf(searchChar, startPos);
    }
    /**
     * <p>Finds the first index within a String, handling <code>null</code>.
     * This method uses {@link String#indexOf(String)}.</p>
     *
     * <p>A <code>null</code> String will return <code>-1</code>.</p>
     *
     * <pre>
     * indexOf(null, *)          = -1
     * indexOf(*, null)          = -1
     * indexOf("", "")           = 0
     * indexOf("aabaabaa", "a")  = 0
     * indexOf("aabaabaa", "b")  = 2
     * indexOf("aabaabaa", "ab") = 1
     * indexOf("aabaabaa", "")   = 0
     * </pre>
     *
     * @param str  the String to check, may be null
     * @param searchStr  the String to find, may be null
     * @return the first index of the search String,
     *  -1 if no match or <code>null</code> string input
     * @since 2.0
     */
    public static int indexOf(String str, String searchStr) {
        if (str == null || searchStr == null) {
            return -1;
        }
        return str.indexOf(searchStr);
    }
    /**
     * <p>Finds the first index within a String, handling <code>null</code>.
     * This method uses {@link String#indexOf(String, int)}.</p>
     *
     * <p>A <code>null</code> String will return <code>-1</code>.
     * A negative start position is treated as zero.
     * An empty ("") search String always matches.
     * A start position greater than the string length only matches
     * an empty search String.</p>
     *
     * <pre>
     * indexOf(null, *, *)          = -1
     * indexOf(*, null, *)          = -1
     * indexOf("", "", 0)           = 0
     * indexOf("aabaabaa", "a", 0)  = 0
     * indexOf("aabaabaa", "b", 0)  = 2
     * indexOf("aabaabaa", "ab", 0) = 1
     * indexOf("aabaabaa", "b", 3)  = 5
     * indexOf("aabaabaa", "b", 9)  = -1
     * indexOf("aabaabaa", "b", -1) = 2
     * indexOf("aabaabaa", "", 2)   = 2
     * indexOf("abc", "", 9)        = 3
     * </pre>
     *
     * @param str  the String to check, may be null
     * @param searchStr  the String to find, may be null
     * @param startPos  the start position, negative treated as zero
     * @return the first index of the search String,
     *  -1 if no match or <code>null</code> string input
     * @since 2.0
     */
    public static int indexOf(String str, String searchStr, int startPos) {
        if (str == null || searchStr == null) {
            return -1;
        }
        // JDK1.2/JDK1.3 have a bug, when startPos > str.length for "", hence
        if (searchStr.length() == 0 && startPos >= str.length()) {
            return str.length();
        }
        return str.indexOf(searchStr, startPos);
    }
    /**
     * <p>Gets a substring from the specified String avoiding exceptions.</p>
     *
     * <p>A negative start position can be used to start <code>n</code>
     * characters from the end of the String.</p>
     *
     * <p>A <code>null</code> String will return <code>null</code>.
     * An empty ("") String will return "".</p>
     *
     * <pre>
     * substring(null, *)   = null
     * substring("", *)     = ""
     * substring("abc", 0)  = "abc"
     * substring("abc", 2)  = "c"
     * substring("abc", 4)  = ""
     * substring("abc", -2) = "bc"
     * substring("abc", -4) = "abc"
     * </pre>
     *
     * @param str  the String to get the substring from, may be null
     * @param start  the position to start from, negative means
     *  count back from the end of the String by this many characters
     * @return substring from start position, <code>null</code> if null String input
     */
    public static String substring(String str, int start) {
        if (str == null) {
            return null;
        }

        // handle negatives, which means last n characters
        if (start < 0) {
            start = str.length() + start; // remember start is negative
        }

        if (start < 0) {
            start = 0;
        }
        if (start > str.length()) {
            return EMPTY;
        }

        return str.substring(start);
    }
    /**
     * <p>Gets a substring from the specified String avoiding exceptions.</p>
     *
     * <p>A negative start position can be used to start/end <code>n</code>
     * characters from the end of the String.</p>
     *
     * <p>The returned substring starts with the character in the <code>start</code>
     * position and ends before the <code>end</code> position. All position counting is
     * zero-based -- i.e., to start at the beginning of the string use
     * <code>start = 0</code>. Negative start and end positions can be used to
     * specify offsets relative to the end of the String.</p>
     *
     * <p>If <code>start</code> is not strictly to the left of <code>end</code>, ""
     * is returned.</p>
     *
     * <pre>
     * substring(null, *, *)    = null
     * substring("", * ,  *)    = "";
     * substring("abc", 0, 2)   = "ab"
     * substring("abc", 2, 0)   = ""
     * substring("abc", 2, 4)   = "c"
     * substring("abc", 4, 6)   = ""
     * substring("abc", 2, 2)   = ""
     * substring("abc", -2, -1) = "b"
     * substring("abc", -4, 2)  = "ab"
     * </pre>
     *
     * @param str  the String to get the substring from, may be null
     * @param start  the position to start from, negative means
     *  count back from the end of the String by this many characters
     * @param end  the position to end at (exclusive), negative means
     *  count back from the end of the String by this many characters
     * @return substring from start position to end positon,
     *  <code>null</code> if null String input
     */
    public static String substring(String str, int start, int end) {
        if (str == null) {
            return null;
        }

        // handle negatives
        if (end < 0) {
            end = str.length() + end; // remember end is negative
        }
        if (start < 0) {
            start = str.length() + start; // remember start is negative
        }

        // check length next
        if (end > str.length()) {
            end = str.length();
        }

        // if start is greater than end, return ""
        if (start > end) {
            return EMPTY;
        }

        if (start < 0) {
            start = 0;
        }
        if (end < 0) {
            end = 0;
        }

        return str.substring(start, end);
    }
}

• Previous
• Next

Related Tutorials

• split function that supplement the default String.split method that does not allow returning an empty split.
• Splits a String by Character type as returned by java.lang.Character.getType(char).
• Splits the provided text into an array, separator string specified. The separator(s) will not be included in the returned String array.
• Splits the provided text into an array, using whitespace as the separator.
• Splits the provided text into an array, using whitespace as the separator, preserving all tokens, including empty tokens created by adjacent separators.