Click here to Skip to main content
15,880,469 members
Articles / Programming Languages / C#

hOOt - full text search engine

Rate me:
Please Sign up or sign in to vote.
4.92/5 (156 votes)
24 Feb 2019CPOL17 min read 1.1M   22.5K   388  
Smallest full text search engine (lucene replacement) built from scratch using inverted MGRB bitmap index, highly compact storage, operating in database and document modes
using System;
using System.Collections.Generic;
using System.Text;

namespace hOOt
{
    #region [ internal classes ]
    internal class KeyPointer
    {
        public KeyPointer(bytearr key, int recno, int duppage)
        {
            RecordNum = recno;
            Key = key;
            DuplicatesPage = duppage;
        }

        public KeyPointer(bytearr key, int recno)
        {
            RecordNum = recno;
            Key = key;
            DuplicatesPage = -1;
        }

        public bytearr Key;
        public int RecordNum;
        public int DuplicatesPage = -1;

        //public override string ToString()
        //{
        //    return "" + Key;
        //}

        public KeyPointer Copy()
        {
            return new KeyPointer(Key, RecordNum);
        }
    }

    public struct bytearr
    {
        public bytearr(byte[] key)
        {
            val = key;
        }
        public byte[] val;

        //public override string ToString()
        //{
        //    return "" + val[0];
        //}
        public override int GetHashCode()
        {
            int result = 17;
            foreach (byte b in val)
            {
                result = result * 31 + b;
            }
            return result;
        }
    }
    #endregion


    internal class Bucket
    {
        internal int BucketNumber = -1;
        internal List<KeyPointer> Pointers = new List<KeyPointer>();
        internal List<int> Duplicates = new List<int>();
        internal int DiskPageNumber = -1;
        internal int NextPageNumber = -1;
        internal bool isDirty = false;
        internal bool isBucket = true;
        internal bool isOverflow = false;

        public Bucket(byte type, int bucketnumber, List<KeyPointer> pointers, List<int> duplicates, int diskpage, int nextpage)
        {
            DiskPageNumber = diskpage;
            BucketNumber = bucketnumber;
            NextPageNumber = nextpage;
            if ((type & 8) == 8)
                isBucket = true;
            if ((type & 16) == 16)
                isOverflow = true;
            Pointers = pointers;
            Duplicates = duplicates;
        }

        public Bucket(int page)
        {
            DiskPageNumber = page;
        }

        public short Count
        {
            get { return (short)Pointers.Count; }
        }

        //public override string ToString()
        //{
        //    return "count = " + Pointers.Count;
        //}
    }
}

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 Code Project Open License (CPOL)


Written By
Architect -
United Kingdom United Kingdom
Mehdi first started programming when he was 8 on BBC+128k machine in 6512 processor language, after various hardware and software changes he eventually came across .net and c# which he has been using since v1.0.
He is formally educated as a system analyst Industrial engineer, but his programming passion continues.

* Mehdi is the 5th person to get 6 out of 7 Platinum's on Code-Project (13th Jan'12)
* Mehdi is the 3rd person to get 7 out of 7 Platinum's on Code-Project (26th Aug'16)

Comments and Discussions