Skip to main content

This C# LINQ example shows how to merge files that contain lines of text and then sort the results. Specifically, it shows how to perform a simple concatenation, a union, and an intersection on the two sets of text lines.

// ----------------------------------------------------------------------------
// Combine and Compare String Collections
// <https://msdn.microsoft.com/en-us/library/mt693089.aspx>
//
// This example shows how to merge files that contain lines of text and then
// sort the results. Specifically, it shows how to perform a simple
// concatenation, a union, and an intersection on the two sets of text lines.
//
// To set up the project and the text files
//
// 1. Copy these names into a text file that is named names1.txt and save it in
//    your project folder:
//
//        Bankov, Peter
//        Holm, Michael
//        Garcia, Hugo
//        Potra, Cristina
//        Noriega, Fabricio
//        Aw, Kam Foo
//        Beebe, Ann
//        Toyoshima, Tim
//        Guy, Wey Yuan
//        Garcia, Debra
//
// 2. Copy these names into a text file that is named names2.txt and save it in
//    your project folder. Note that the two files have some names in common.
//
//        Liu, Jinghao
//        Bankov, Peter
//        Holm, Michael
//        Garcia, Hugo
//        Beebe, Ann
//        Gilchrist, Beth
//        Myrcha, Jacek
//        Giakoumakis, Leo
//        McLin, Nkenge
//        El Yassir, Mehdi
// ----------------------------------------------------------------------------

using System.Linq;
using System;

class MergeStrings
    {
        static void Main(string[] args)
        {
            //Put text files in your solution folder
            string[] fileA = System.IO.File.ReadAllLines(@"../../../names1.txt");
            string[] fileB = System.IO.File.ReadAllLines(@"../../../names2.txt");

            //Simple concatenation and sort. Duplicates are preserved.
            IEnumerable<string> concatQuery =
                fileA.Concat(fileB).OrderBy(s => s);

            // Pass the query variable to another function for execution.
            OutputQueryResults(concatQuery, "Simple concatenate and sort. Duplicates are preserved:");

            // Concatenate and remove duplicate names based on
            // default string comparer.
            IEnumerable<string> uniqueNamesQuery =
                fileA.Union(fileB).OrderBy(s => s);
            OutputQueryResults(uniqueNamesQuery, "Union removes duplicate names:");

            // Find the names that occur in both files (based on
            // default string comparer).
            IEnumerable<string> commonNamesQuery =
                fileA.Intersect(fileB);
            OutputQueryResults(commonNamesQuery, "Merge based on intersect:");

            // Find the matching fields in each list. Merge the two
            // results by using Concat, and then
            // sort using the default string comparer.
            string nameMatch = "Garcia";

            IEnumerable<String> tempQuery1 =
                from name in fileA
                let n = name.Split(',')
                where n[0] == nameMatch
                select name;

            IEnumerable<string> tempQuery2 =
                from name2 in fileB
                let n2 = name2.Split(',')
                where n2[0] == nameMatch
                select name2;

            IEnumerable<string> nameMatchQuery =
                tempQuery1.Concat(tempQuery2).OrderBy(s => s);
            OutputQueryResults(nameMatchQuery, String.Format("Concat based on partial name match \"{0}\":", nameMatch));

            // Keep the console window open in debug mode.
            Console.WriteLine("Press any key to exit");
            Console.ReadKey();
        }

        static void OutputQueryResults(IEnumerable<string> query, string message)
        {
            Console.WriteLine(System.Environment.NewLine + message);
            foreach (string item in query)
            {
                Console.WriteLine(item);
            }
            Console.WriteLine("{0} total names in list", query.Count());
        }
    }

/* Output:

    Simple concatenate and sort. Duplicates are preserved:
    Aw, Kam Foo
    Bankov, Peter
    Bankov, Peter
    Beebe, Ann
    Beebe, Ann
    El Yassir, Mehdi
    Garcia, Debra
    Garcia, Hugo
    Garcia, Hugo
    Giakoumakis, Leo
    Gilchrist, Beth
    Guy, Wey Yuan
    Holm, Michael
    Holm, Michael
    Liu, Jinghao
    McLin, Nkenge
    Myrcha, Jacek
    Noriega, Fabricio
    Potra, Cristina
    Toyoshima, Tim
    20 total names in list

    Union removes duplicate names:
    Aw, Kam Foo
    Bankov, Peter
    Beebe, Ann
    El Yassir, Mehdi
    Garcia, Debra
    Garcia, Hugo
    Giakoumakis, Leo
    Gilchrist, Beth
    Guy, Wey Yuan
    Holm, Michael
    Liu, Jinghao
    McLin, Nkenge
    Myrcha, Jacek
    Noriega, Fabricio
    Potra, Cristina
    Toyoshima, Tim
    16 total names in list

    Merge based on intersect:
    Bankov, Peter
    Holm, Michael
    Garcia, Hugo
    Beebe, Ann
    4 total names in list

    Concat based on partial name match "Garcia":
    Garcia, Debra
    Garcia, Hugo
    Garcia, Hugo
    3 total names in list
*/