/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

using System;
using System.IO;
using System.Collections.Generic;

using Hadoop.IO;
using Hadoop.Pipes;

namespace Hadoop
{
    class Program
    {
        private static readonly char[] splitChars = { ' ', '\r', '\n', '\t', '\x0085' };

        public static IEnumerable<KeyValuePair<string, long>> Map(long key, string value, Reporter reporter)
        {
            foreach (string word in value.Split(splitChars, StringSplitOptions.RemoveEmptyEntries))
                yield return new KeyValuePair<string, long>(word, 1);
        }

        public static IEnumerable<KeyValuePair<string, string>> Reduce(string key, IEnumerable<long> values, Reporter reporter)
        {
            long sum = 0;

            foreach (long value in values)
                sum += value;

            yield return new KeyValuePair<string, string>(key, sum.ToString());
        }

        public static void Main(string[] args)
        {
            JobDriver.Run<long, string, string, long, string, string>(Map, Reduce);
        }
    }
}