dictionaryhelper.cs

http://wordnet.princeton.edu/ WordNet is a large lexical database of English, developed under the d

using System;
using System.Collections.Generic;
using System.Text;
using WordNetParser.Objects;
using System.IO;

namespace WordNetParser.Helpers
{
	internal class DictionaryHelper
	{
		private static long lastWordIndex = 0;
		private static List<string> completedFiles = new List<string>();

		#region GetDefinition
		internal static Dictionary<string, List<Definition>> GetDefinition( string word )
		{
			Dictionary<string, List<Definition>> retVal = new Dictionary<string, List<Definition>>();
			List<string> fileListIndex = DbFileHelper.GetIndexForType( DbPartOfSpechType.All );
			List<string> fileListData = DbFileHelper.GetDBaseForType( DbPartOfSpechType.All );

			for( int i = 0; i < fileListIndex.Count; i++ )
			{
				long offset = FileParser.FastSearch( word.ToLower(), fileListIndex[ i ] );
				if( offset > 0 )
				{
					Index idx = FileParser.ParseIndex( offset, fileListIndex[ i ], null );
					foreach( long synSetOffset in idx.SynSetsOffsets )
					{
						try
						{
							Definition def = FileParser.ParseDefinition( synSetOffset, fileListData[ i ], word );
							string wordKey = string.Join( ", ", def.Words.ToArray() );
							if( !retVal.ContainsKey( wordKey ) )
								retVal.Add( wordKey, new List<Definition>() );

							retVal[ wordKey ].Add( def );
						}
						catch( Exception ex )
						{
							string message = ex.Message;
						}
					}
				}
			}

			return retVal;
		}
		#endregion GetDefinition

		#region GetNextWord
		internal static string GetNextWord()
		{
			string retVal = string.Empty;
			List<string> indexFiles = DbFileHelper.GetIndexForType( DbPartOfSpechType.All );

			foreach( string indexFile in indexFiles )
			{
				if( completedFiles.Contains( indexFile ) )
					continue;

				using( FileStream fs = File.OpenRead( indexFile ) )
				{
					string line = string.Empty;

					do
					{
						fs.Seek( lastWordIndex, SeekOrigin.Begin );
						while( fs.ReadByte() != '\n' && fs.Position < fs.Length )
						{
							fs.Seek( 1, SeekOrigin.Current );
						}

						byte[] btData = new byte[ Constants.KEY_LEN ];
						int count = fs.Read( btData, 0, btData.Length );
						lastWordIndex = ( fs.Position - count ) + 1;

						string readData = Encoding.Default.GetString( btData );

						int actualLineLength = readData.IndexOf( '\n' );
						lastWordIndex = ( fs.Position - count ) + actualLineLength;

						retVal = readData.Split( Constants.Tokenizer )[ 0 ];
					}
					while( string.IsNullOrEmpty( retVal ) );

					if( fs.Position == fs.Length )
					{
						completedFiles.Add( indexFile );
						lastWordIndex = 0L;
					}
				}

				if( !string.IsNullOrEmpty( retVal ) )
					break;
			}
			return retVal;
		}
		#endregion GetNextWord
	}
}