Hackerrank - Detect HTML Tags

Problem Statement
A description of the problem can be found on Hackerrank.

Solution
Parse all tags by regex pattern <\s*[a-z0-9]+. Then sort them and print unique tags.

I created solution in:

Java
JavaScript
Scala
Ruby

All solutions are also available on my GitHub.

Java

import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collector;
import java.util.stream.Collectors;

public class DetectHtmlTags {

    private static final String TAG_PATTERN = "<\\s*[a-z0-9]+";

    public static void main(String[] args) {
        Scanner stdin = new Scanner(System.in);
        int lines = Integer.parseInt(stdin.nextLine());
        Set<String> tags = new TreeSet<>();
        for(int i = 0; i < lines; i++) {
            String line = stdin.nextLine();
            Pattern pattern = Pattern.compile(TAG_PATTERN);
            Matcher matcher = pattern.matcher(line);
            while (matcher.find()) {
                tags.add(matcher.group().replaceAll("<", ""));
            }
        }
        Collector col = Collectors.joining(";");
        System.out.println(tags.stream().collect(col));
        stdin.close();
    }
}

import java.util.*;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

import java.util.stream.Collector;

import java.util.stream.Collectors;

public class DetectHtmlTags {

private static final String TAG_PATTERN = "<\\s*[a-z0-9]+";

public static void main(String[] args) {

Scanner stdin = new Scanner(System.in);

int lines = Integer.parseInt(stdin.nextLine());

Set<String> tags = new TreeSet<>();

for(int i = 0; i < lines; i++) {

String line = stdin.nextLine();

Pattern pattern = Pattern.compile(TAG_PATTERN);

Matcher matcher = pattern.matcher(line);

while (matcher.find()) {

tags.add(matcher.group().replaceAll("<", ""));

}

Collector col = Collectors.joining(";");

System.out.println(tags.stream().collect(col));

stdin.close();

}

JavaScript

function processData(input) {
    const tagPattern = /<\s*[a-z0-9]+/g
    var lines = input.split("\n");
    var tagSet = {};
    for(var i = 1; i < lines.length; i++) {
        var tags = lines[i].match(tagPattern);
        if(tags) {
        tags = tags.map(function(item) {return item.replace(/</, '')});
            for(var j = 0; j < tags.length; j++) {
                tagSet[tags[j]] = true;
            }
        }
    }
    var tags = [];
    for(prop in tagSet) {
        if(tagSet.hasOwnProperty(prop)) {
            tags.push(prop);
        }
    }
    console.log(tags.sort(function (s1, s2) {return s1.localeCompare(s2)}).join(";"));
}

process.stdin.resume();
process.stdin.setEncoding("ascii");
_input = "";
process.stdin.on("data", function (input) {
    _input += input;
});

process.stdin.on("end", function () {
    processData(_input);
});

function processData(input) {

const tagPattern = /<\s*[a-z0-9]+/g

var lines = input.split("\n");

var tagSet = {};

for(var i = 1; i < lines.length; i++) {

var tags = lines[i].match(tagPattern);

if(tags) {

tags = tags.map(function(item) {return item.replace(/</, '')});

for(var j = 0; j < tags.length; j++) {

tagSet[tags[j]] = true;

}

var tags = [];

for(prop in tagSet) {

if(tagSet.hasOwnProperty(prop)) {

tags.push(prop);

}

console.log(tags.sort(function (s1, s2) {return s1.localeCompare(s2)}).join(";"));

}

process.stdin.resume();

process.stdin.setEncoding("ascii");

_input = "";

process.stdin.on("data", function (input) {

_input += input;

});

process.stdin.on("end", function () {

processData(_input);

});

Scala

import scala.io.Source

object DetectHtmlTags extends App {
  private[this] val TAG_PATTERN = "<\\s*[a-z0-9]+"

  val lines = Source.stdin.getLines().drop(1)

  val tags = lines.map(parseTags).flatten.toList
  val tagsSet = tags.distinct.sorted
  println(tagsSet.mkString(";"))

  def parseTags(s: String): Iterator[String] = {
    TAG_PATTERN.r.findAllMatchIn(s).map(_.toString).map(_.replaceAll("<", ""))
  }
}

import scala.io.Source

object DetectHtmlTags extends App {

private[this] val TAG_PATTERN = "<\\s*[a-z0-9]+"

val lines = Source.stdin.getLines().drop(1)

val tags = lines.map(parseTags).flatten.toList

val tagsSet = tags.distinct.sorted

println(tagsSet.mkString(";"))

def parseTags(s: String): Iterator[String] = {

TAG_PATTERN.r.findAllMatchIn(s).map(_.toString).map(_.replaceAll("<", ""))

}

Ruby

require "set"

lines = gets.chomp.to_i
tags = SortedSet.new
lines.times do
  line = gets.chomp.downcase
  line.scan(/<\s*[a-z0-9]+/) do |tag|
     tags << tag.gsub(/</, "")
   end
end

tags_arr = tags.to_a
for i in 0...tags_arr.length - 1 do
  print "#{tags_arr[i]};"
end
print "#{tags_arr[tags_arr.length - 1]}"

require "set"

lines = gets.chomp.to_i

tags = SortedSet.new

lines.times do

line = gets.chomp.downcase

line.scan(/<\s*[a-z0-9]+/) do |tag|

tags << tag.gsub(/</, "")

end

tags_arr = tags.to_a

for i in 0...tags_arr.length - 1 do

print "#{tags_arr[i]};"

end

print "#{tags_arr[tags_arr.length - 1]}"

Pavol Pidanič

I can count to 1023 with 10 fingers

Hackerrank – Detect HTML Tags