import java.util.regex.*;

        

String regex = // Puts a doublequoted field into group(1), an unquoted field into group(2)
   "\\G(?:^|,)                                  \n"+
   "(?:                                         \n"+
   "   # Either a double-quoted field . . .        \n"+
   "   \"  # field's opening quote              \n"+
   "    (   (?: [^\"]++ | \"\" )*+   )          \n"+
   "   \"  # field's closing quote              \n"+
   " |#  . . . or . . .                               \n"+
   "       # some non-quote/non-comma text . . .  \n"+
   "   ( [^\",]* )                              \n"+
   " )                       \n";
// Create a matcher, using the regex above, with dummy text for the time being.
Matcher mMain = Pattern.compile(regex, Pattern.COMMENTS).matcher("");

// Create a matcher for  「"" , with dummy text for the time being
Matcher mQuote = Pattern.compile("\"\"").matcher("");

        

// Above is the preparation; the code below is executed on a per-line basis
mMain.reset(line); // Use this line of <ACRONYM>CSV</ACRONYM> text in the processing below

while (mMain.find())
{
    String field;
    if (mMain.start(2) >= 0)
        field = mMain.group(2); // The field is unquoted, so we can use it as is
    else
        // The field is quoted, so we must replace paired doublequotes with one double quote
        field = mQuote.reset(mMain.group(1)).replaceAll("\"");

    // We can now work with field . . . 
    System.out.println("Field [" + field + "]");
}




-----------------------------------------------------------------------------
Copyright 1997-2024 Jeffrey Friedl