Splits a line of sentinel-separated values into tokens

SplitXSV.java

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

public class SplitXSV {

  public static void main (String[] args) {

    // split lines of (RFC 4180) standard CSV
    splitAndPrint("a,b, c ,d,e, f", ','); // basic CSV
    splitAndPrint("a,\" b \",\" \"\"c\"\" \",", ',');

    // split IP addresses, phone numbers, sentences, etc.
    splitAndPrint("144.123.222.0", '.');   // XSV with sentinel '.'
    splitAndPrint("1-800-944-2345", '-');  // XSV with sentinel '-'
    splitAndPrint("hi how are you", ' ');  // XSV with sentinel ' '
    splitAndPrint("\nline2\nline3", '\n'); // XSV with sentinel '\n'
    splitAndPrint("col1\tcol2", '\t');     // XSV with sentinel '\t'

  }

  public static String doubleLine = "=========================";
  public static String singleLine = "----------";

  public static void splitAndPrint(String line, char sentinel) {
    System.out.printf("%2$s%n%ngiven sentinel: '%3$s'%n%ngiven string:%n%1$s" +
      "%n{%4$s}%n%1$s%n%nresult:%n%1$s%n%5$s%n%1$s%n%n", singleLine, doubleLine,
      sentinel, line, splitXSV(line, sentinel).stream().map(e ->
        String.format("{%s}", e)).collect(Collectors.joining("\n")));
  }

  public static List<String> splitXSV (String line, char sentinel) {

    // if line is null or empty, return an empty array
    if (line == null || "".equals(line)) return new ArrayList<String>(0);

    // if character is not [a-zA-Z0-9], prepend "\" to escape
    //   this means that even tokens like \t and \n can be used as sentinels
    String sanitized = (Character.isLetterOrDigit(sentinel)) ?
      String.valueOf(sentinel) : ("\\" + sentinel);

    // regex string for parsing lines of CSV
    String regex = String.format(
      "(?:%1$s|\\n|^)((?:\"(?:(?:\"\")*[^\"]*)*\")|(?:[^\"%1$s\\n]*)|(?:\\n|$))",
        sanitized);

    // (?:,|\\n|^)    -- token MUST begin with , OR newline OR start of text
    // (              -- capture everything from here on
    //   (?:\"        -- (1) first option is a quoted string
    //     (?:            -- which can contain any number of
    //       (?:\"\")*    -- escaped quotes ("")
    //       [^\"]*       -- or any other non-quote character
    //     )*             -- zero or more times (empty "" is allowed)
    //   \")              -- must begin and end on a "
    //   |            -- (2) second option is a "plain" token, which contains
    //   (?:[^\",\\n]*)   -- any number of non-{" , \n} characters, 0+ times
    //   |            -- (3) third option is an empty token at the end of a line
    //   (?:\\n|$)        -- which will just be a \n or the end of the file, $
    // )              -- ...that's it!

    // compile regex pattern and apply it to the given line
    Matcher matcher = Pattern.compile(regex).matcher(line);

    // save all of the matches to this ArrayList
    List<String> list = new ArrayList<>(30); // initial capacity: 30
    while (matcher.find()) list.add(matcher.group(1));

    // If the first character of a line is the sentinel, the regex above will
    // miss the fact that the first entry is null. So we add an empty String to
    // the beginning of the ArrayList.

    if (line.charAt(0) == sentinel)  list.add(0, "");
    return list;

  } // end splitXSV()

} // end SplitXSV class


/******************************* PROGRAM OUTPUT ********************************

=========================

given sentinel: ','

given string:
----------
{a,b, c ,d,e, f}
----------

result:
----------
{a}
{b}
{ c }
{d}
{e}
{ f}
----------

=========================

given sentinel: ','

given string:
----------
{a," b "," ""c"" ",}
----------

result:
----------
{a}
{" b "}
{" ""c"" "}
{}
----------

=========================

given sentinel: '.'

given string:
----------
{144.123.222.0}
----------

result:
----------
{144}
{123}
{222}
{0}
----------

=========================

given sentinel: '-'

given string:
----------
{1-800-944-2345}
----------

result:
----------
{1}
{800}
{944}
{2345}
----------

=========================

given sentinel: ' '

given string:
----------
{hi how are you}
----------

result:
----------
{hi}
{how}
{are}
{you}
----------

=========================

given sentinel: '
'

given string:
----------
{
line2
line3}
----------

result:
----------
{}
{line2}
{line3}
----------

=========================

given sentinel: '	'

given string:
----------
{col1	col2}
----------

result:
----------
{col1}
{col2}
----------

*******************************************************************************/