import java.util.ArrayList;

import java.util.List;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class LogTokenizer {

public static List<String> tokenize(String logEntry) {

List<String> tokens = new ArrayList<>();

// Define regular expression patterns for different token types

Pattern pattern1 = Pattern.compile("\\w+"); // Matches words (alphanumeric characters)

Pattern pattern2 = Pattern.compile("\\d+"); // Matches numbers

Pattern pattern3 = Pattern.compile("\\[\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2}\\.\\d{3}\\+\\d{4}\\]"); // Matches timestamp format

Pattern pattern4 = Pattern.compile("\\w+=\\w+"); // Matches key-value pairs

// Split the log entry into tokens using the defined patterns

Matcher matcher1 = pattern1.matcher(logEntry);

while (matcher1.find()) {

tokens.add(matcher1.group());

}

Matcher matcher2 = pattern2.matcher(logEntry);

while (matcher2.find()) {

tokens.add(matcher2.group());

}

Matcher matcher3 = pattern3.matcher(logEntry);

while (matcher3.find()) {

tokens.add(matcher3.group());

}

Matcher matcher4 = pattern4.matcher(logEntry);

while (matcher4.find()) {

tokens.add(matcher4.group());

}

return tokens;

}

public static void main(String[] args) {

String logEntry = "2023-10-27 10:00:00.123+0000 [INFO] User logged in. user=john.doe, role=admin";

List<String> tokens = tokenize(logEntry);

System.out.println(tokens);

}

}