Click here to Skip to main content
15,886,038 members
Articles / Programming Languages / C#

Solving complex parsing tasks with RegexTreeer

Rate me:
Please Sign up or sign in to vote.
3.75/5 (8 votes)
23 Oct 2008LGPL39 min read 33.2K   440   23  
Solving complex parsing tasks by utilizing Regular Expression trees built with RegexTreeer.
//********************************************************************************************
//Author: Sergey Stoyan, CliverSoft.com
//        http://cliversoft.com
//        stoyan@cliversoft.com
//        sergey.stoyan@gmail.com
//        22 March 2008
//Copyright: (C) 2008, Sergey Stoyan
//********************************************************************************************
using System;
using System.IO;
using Cliver;

namespace Test
{
    class Test2
    {
        internal void Run()
        {
            //text to be parsed
            string page = File.ReadAllText("../../_pages/Companies.txt");

            process_company_list(page);
        }

        //create CliverSoft.Parser from the regex tree stored in the file
        Cliver.Parser company_parser = new Parser("../../_config_files/Companies.rgx");

        /// <summary>
        /// Process the page by Cliver.Parser
        /// </summary>
        /// <param name="page">text to be parsed</param>
        void process_company_list(string page)
        {
            Cliver.GroupCapture gc = company_parser.Parse(page);

            foreach (Cliver.GroupCapture company in gc["Company"])
            {
                Console.WriteLine("\n\n>>>>>>>Company:>>>>>>>");

                //generally number of group captures can be more than 1 
                //that's why we always have to ask to retrieve the first capture 
                //in spite of that we know that company name is only one for each company
                Console.WriteLine("Name: " + company.FirstValueOf("CompanyName"));
                Console.WriteLine("Address: " + company.FirstValueOf("CompanyAddress"));
                Console.WriteLine("Site: " + company.FirstValueOf("CompanySite"));

                foreach (Cliver.GroupCapture employee in company["Employee"])
                {
                    Console.WriteLine("\n-------Employee:-------");
                    Console.WriteLine("Name: " + employee.FirstValueOf("EmployeeName"));

                    //employee can have more than one phone in our sample, that's why we enum them in a cycle
                    foreach (string phone in employee.ValuesOf("EmployeePhone"))
                    {
                        Console.WriteLine("Pnone: " + phone);
                    }

                    Console.WriteLine("Mobile: " + employee.FirstValueOf("EmployeeMobile"));

                    Console.WriteLine("Email: " + employee.FirstValueOf("EmployeeEmail"));
                }
            }
        }
    }
}

By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.

If a file you wish to view isn't highlighted, and is a text file (not binary), please let us know and we'll add colourisation support for it.

License

This article, along with any associated source code and files, is licensed under The GNU Lesser General Public License (LGPLv3)


Written By
Architect CliverSoft (www.cliversoft.com)
Ukraine Ukraine
Sergey is graduated as applied mathematician. He is specialized in custom development including parsing tools, client/server applications.
github: https://github.com/sergeystoyan
site: http://cliversoft.com

Comments and Discussions