import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Example {
public static void main(String[] args) {
final String regex = "(^\\S+\\s\\S+\\s\\s|^\\S+\\s\\s)((?![-])|(?![_]))";
final String string = "Washington, DC November 27, 2019\n"
+ "USDA Truck Rate Report\n\n"
+ "WA_FV190 \n\n"
+ "FIRST PRICE RANGE FOR WEEK OF NOVEMBER 20-26 2019 \n"
+ "SECOND PRICE MOSTLY FOR TUESDAY NOVEMBER 26 2019 \n\n"
+ "PERCENTAGE OF CHANGE FROM TUESDAY NOVEMBER 19 2019 SHOWN IN (). \n\n"
+ "In areas where rates are based on package rates, per-load rates were \n"
+ "derived by multiplying the package rate by the number of packages in \n"
+ "the most usual load in a 48-53 foot trailer.\n\n"
+ "CENTRAL AND WESTERN ARIZONA \n"
+ "-- LETTUCE, BROCCOLI, CAULIFLOWER, ROMAINE AND LEAF LETTUCE SLIGHT SHORTAGE \n"
+ "-- \n\n"
+ "ATLANTA 5100 5500 \n"
+ "BALTIMORE 6300 6600 \n"
+ "BOSTON 7000 7300 \n"
+ "CHICAGO 4500 4900 \n"
+ "DALLAS 3400 3800 \n"
+ "MIAMI 6400 6700 \n"
+ "NEW YORK 6600 6900 \n"
+ "PHILADELPHIA 6400 6700 \n\n"
+ " 2019 2018 \n\n"
+ " NOV 17-23 NOV 18-24 \n\n"
+ "U.S. 25,701 22,956 \n"
+ "IMPORTS 13,653 15,699 \n"
+ " ------------ -------------- \n"
+ "sum 39,354 38,655 \n";
final Pattern pattern = Pattern.compile(regex, Pattern.MULTILINE);
final Matcher matcher = pattern.matcher(string);
while (matcher.find()) {
System.out.println("Full match: " + matcher.group(0));
for (int i = 1; i <= matcher.groupCount(); i++) {
System.out.println("Group " + i + ": " + matcher.group(i));
}
}
}
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Java, please visit: https://docs.oracle.com/javase/7/docs/api/java/util/regex/Pattern.html