Java String Split by Separator splitWorker(final String str, final char separatorChar, final boolean preserveAllTokens)

Description

Performs the logic for the split and splitPreserveAllTokens methods that do not return a maximum array length.

License

Apache License

Parameter

Parameter	Description
str	the String to parse, may be null
separatorChar	the separate character
preserveAllTokens	if true , adjacent separators are treated as empty token separators; if false , adjacent separators are treated as one separator.

Return

an array of parsed Strings, null if null String input

Declaration

private static String[] splitWorker(final String str, final char separatorChar,
        final boolean preserveAllTokens) 

Method Source Code

//package com.java2s;
//License from project: Apache License 

import java.util.*;

public class Main {
    /**/*  www  .j a  va2 s .co m*/
     * An empty immutable {@code String} array.
     */
    public static final String[] EMPTY_STRING_ARRAY = new String[0];

    /**
     * Performs the logic for the {@code split} and
     * {@code splitPreserveAllTokens} methods that do not return a maximum array
     * length.
     *
     * @param str               the String to parse, may be {@code null}
     * @param separatorChar     the separate character
     * @param preserveAllTokens if {@code true}, adjacent separators are treated as empty
     *                          token separators; if {@code false}, adjacent separators are
     *                          treated as one separator.
     * @return an array of parsed Strings, {@code null} if null String input
     */
    private static String[] splitWorker(final String str, final char separatorChar,
            final boolean preserveAllTokens) {
        // Performance tuned for 2.0 (JDK1.4)

        if (str == null) {
            return null;
        }
        final int len = str.length();
        if (len == 0) {
            return EMPTY_STRING_ARRAY;
        }
        final List<String> list = new ArrayList<String>();
        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 list.toArray(new String[list.size()]);
    }

    /**
     * Performs the logic for the {@code split} and
     * {@code splitPreserveAllTokens} methods that return a maximum array
     * length.
     *
     * @param str               the String to parse, may be {@code null}
     * @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}, adjacent separators are treated as empty
     *                          token separators; if {@code false}, adjacent separators are
     *                          treated as one separator.
     * @return an array of parsed Strings, {@code null} if null String input
     */
    private static String[] splitWorker(final String str, final String separatorChars, final int max,
            final 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;
        }
        final int len = str.length();
        if (len == 0) {
            return EMPTY_STRING_ARRAY;
        }
        final List<String> list = new ArrayList<String>();
        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
            final 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 list.toArray(new String[list.size()]);
    }

    public static String[] toArray(List<String> array) {
        return array.toArray(new String[] {});
    }
}

Related

1. splitToList(String s, String separator)
2. splitValues(String concatedValues, String separator)
3. splitValues(String values, String separator)
4. splitWithBreakingBrace(String str, char separator, char braceStart, char braceEnd)
5. splitWithoutEscaped(String str, char separatorChar)
6. stringSplit(String string, int separator, int escape)