FilterReader: Add new project

DDMonorepo.sln

@@ -146,6 +146,8 @@ Project("{F184B08F-C81C-45F6-A57F-5ABD9991F28F}") = "Base", "Modules.Base\Base\B
 EndProject
 Project("{F184B08F-C81C-45F6-A57F-5ABD9991F28F}") = "MessageBoxEx", "MessageBoxEx\MessageBoxEx.vbproj", "{EF29F400-BE45-4283-9D18-CA7ACD9ACCC9}"
 EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "FilterReader", "FilterReader\FilterReader.csproj", "{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU
@@ -392,6 +394,10 @@ Global
 		{EF29F400-BE45-4283-9D18-CA7ACD9ACCC9}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{EF29F400-BE45-4283-9D18-CA7ACD9ACCC9}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{EF29F400-BE45-4283-9D18-CA7ACD9ACCC9}.Release|Any CPU.Build.0 = Release|Any CPU
+		{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC}.Release|Any CPU.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -457,6 +463,7 @@ Global
 		{E3DA65CA-964D-4896-991A-B5426884E215} = {7AF3F9C2-C939-4A08-95C1-0453207E298A}
 		{6EA0C51F-C2B1-4462-8198-3DE0B32B74F8} = {3E2008C8-27B1-41DD-9B1A-0C4029F6AECC}
 		{EF29F400-BE45-4283-9D18-CA7ACD9ACCC9} = {F98C0329-C004-417F-B2AB-7466E88D8220}
+		{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC} = {3E2008C8-27B1-41DD-9B1A-0C4029F6AECC}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {C1BE4090-A0FD-48AF-86CB-39099D14B286}

FilterReader/ComHelper.cs

@@ -0,0 +1,110 @@
+using System;
+using System.Collections.Generic;
+using System.Text;
+using System.Runtime.InteropServices;
+
+namespace DigitalData.Modules.FilterReader
+{
+    [ComVisible(false)]
+    [ComImport, InterfaceType(ComInterfaceType.InterfaceIsIUnknown), Guid("00000001-0000-0000-C000-000000000046")]
+    internal interface IClassFactory
+    {
+        void CreateInstance([MarshalAs(UnmanagedType.Interface)] object pUnkOuter, ref Guid refiid, [MarshalAs(UnmanagedType.Interface)] out object ppunk);
+        void LockServer(bool fLock);
+    }
+
+    /// <summary>
+    /// Utility class to get a Class Factory for a certain Class ID 
+    /// by loading the dll that implements that class
+    /// </summary>
+    internal static class ComHelper
+    {
+        //DllGetClassObject fuction pointer signature
+        private delegate int DllGetClassObject(ref Guid ClassId, ref Guid InterfaceId, [Out, MarshalAs(UnmanagedType.Interface)] out object ppunk);
+
+        //Some win32 methods to load\unload dlls and get a function pointer
+        private class Win32NativeMethods
+        {
+            [DllImport("kernel32.dll", CharSet = CharSet.Ansi)]
+            public static extern IntPtr GetProcAddress(IntPtr hModule, string lpProcName);
+
+            [DllImport("kernel32.dll")]
+            public static extern bool FreeLibrary(IntPtr hModule);
+
+            [DllImport("kernel32.dll")]
+            public static extern IntPtr LoadLibrary(string lpFileName);
+        }
+
+        /// <summary>
+        /// Holds a list of dll handles and unloads the dlls 
+        /// in the destructor
+        /// </summary>
+        private class DllList
+        {
+            private List<IntPtr> _dllList = new List<IntPtr>();
+            public void AddDllHandle(IntPtr dllHandle)
+            {
+                lock (_dllList)
+                {
+                    _dllList.Add(dllHandle);
+                }
+            }
+
+            ~DllList()
+            {
+                foreach (IntPtr dllHandle in _dllList)
+                {
+                    try
+                    {
+                        Win32NativeMethods.FreeLibrary(dllHandle);
+                    }
+                    catch { };
+                }
+            }
+        }
+
+        static DllList _dllList = new DllList();
+
+        /// <summary>
+        /// Gets a class factory for a specific COM Class ID. 
+        /// </summary>
+        /// <param name="dllName">The dll where the COM class is implemented</param>
+        /// <param name="filterPersistClass">The requested Class ID</param>
+        /// <returns>IClassFactory instance used to create instances of that class</returns>
+        internal static IClassFactory GetClassFactory(string dllName, string filterPersistClass)
+        {
+            //Load the class factory from the dll
+            IClassFactory classFactory = GetClassFactoryFromDll(dllName, filterPersistClass);
+            return classFactory;
+        }
+
+        private static IClassFactory GetClassFactoryFromDll(string dllName, string filterPersistClass)
+        {
+            //Load the dll
+            IntPtr dllHandle = Win32NativeMethods.LoadLibrary(dllName);
+            if (dllHandle == IntPtr.Zero)
+                return null;
+
+            //Keep a reference to the dll until the process\AppDomain dies
+            _dllList.AddDllHandle(dllHandle);
+
+            //Get a pointer to the DllGetClassObject function
+            IntPtr dllGetClassObjectPtr = Win32NativeMethods.GetProcAddress(dllHandle, "DllGetClassObject");
+            if (dllGetClassObjectPtr == IntPtr.Zero)
+                return null;
+
+            //Convert the function pointer to a .net delegate
+            DllGetClassObject dllGetClassObject = (DllGetClassObject)Marshal.GetDelegateForFunctionPointer(dllGetClassObjectPtr, typeof(DllGetClassObject));
+
+            //Call the DllGetClassObject to retreive a class factory for out Filter class
+            Guid filterPersistGUID = new Guid(filterPersistClass);
+            Guid IClassFactoryGUID = new Guid("00000001-0000-0000-C000-000000000046"); //IClassFactory class id
+            Object unk;
+            if (dllGetClassObject(ref filterPersistGUID, ref IClassFactoryGUID, out unk) != 0)
+                return null;
+
+            //Yippie! cast the returned object to IClassFactory
+            return (unk as IClassFactory);
+        }
+    }
+}

FilterReader/FilterLoader.cs

@@ -0,0 +1,225 @@
+using System;
+using System.Collections.Generic;
+using System.Text;
+using Microsoft.Win32;
+using System.IO;
+using System.Runtime.InteropServices.ComTypes;
+using System.Runtime.InteropServices;
+
+namespace DigitalData.Modules.FilterReader
+{
+    /// <summary>
+    /// FilterLoader finds the dll and ClassID of the COM object responsible  
+    /// for filtering a specific file extension. 
+    /// It then loads that dll, creates the appropriate COM object and returns 
+    /// a pointer to an IFilter instance
+    /// </summary>
+    static class FilterLoader
+    {
+        #region CacheEntry
+        private class CacheEntry
+        {
+            public string DllName;
+            public string ClassName;
+
+            public CacheEntry(string dllName, string className)
+            {
+                DllName = dllName;
+                ClassName = className;
+            }
+        }
+        #endregion
+
+        static Dictionary<string, CacheEntry> _cache = new Dictionary<string, CacheEntry>();
+
+        #region Registry Read String helper
+        static string ReadStrFromHKLM(string key)
+        {
+            return ReadStrFromHKLM(key, null);
+        }
+        static string ReadStrFromHKLM(string key, string value)
+        {
+            RegistryKey rk = Registry.LocalMachine.OpenSubKey(key);
+            if (rk == null)
+                return null;
+
+            using (rk)
+            {
+                return (string)rk.GetValue(value);
+            }
+        }
+        #endregion
+
+        /// <summary>
+        /// finds an IFilter implementation for a file type
+        /// </summary>
+        /// <param name="ext">The extension of the file</param>
+        /// <returns>an IFilter instance used to retreive text from that file type</returns>
+        private static IFilter LoadIFilter(string ext)
+        {
+            //Find the dll and ClassID
+            if (GetFilterDllAndClass(ext, out string dllName, out string filterPersistClass))
+            {
+                //load the dll and return an IFilter instance.
+                return LoadFilterFromDll(dllName, filterPersistClass);
+            }
+            return null;
+        }
+
+        internal static IFilter LoadAndInitIFilter(string fileName)
+        {
+            return LoadAndInitIFilter(fileName, Path.GetExtension(fileName));
+        }
+
+        internal static IFilter LoadAndInitIFilter(string fileName, string extension)
+        {
+            IFilter filter = LoadIFilter(extension);
+            if (filter == null)
+                return null;
+
+            IPersistFile persistFile = (filter as IPersistFile);
+            if (persistFile != null)
+            {
+                persistFile.Load(fileName, 0);
+                IFILTER_FLAGS flags;
+                IFILTER_INIT iflags =
+                            IFILTER_INIT.CANON_HYPHENS |
+                            IFILTER_INIT.CANON_PARAGRAPHS |
+                            IFILTER_INIT.CANON_SPACES |
+                            IFILTER_INIT.APPLY_INDEX_ATTRIBUTES |
+                            IFILTER_INIT.HARD_LINE_BREAKS |
+                            IFILTER_INIT.FILTER_OWNED_VALUE_OK;
+
+                if (filter.Init(iflags, 0, IntPtr.Zero, out flags) == IFilterReturnCode.S_OK)
+                    return filter;
+            }
+            //If we failed to retreive an IPersistFile interface or to initialize 
+            //the filter, we release it and return null.
+            Marshal.ReleaseComObject(filter);
+            return null;
+        }
+
+        private static IFilter LoadFilterFromDll(string dllName, string filterPersistClass)
+        {
+            //Get a classFactory for our classID
+            IClassFactory classFactory = ComHelper.GetClassFactory(dllName, filterPersistClass);
+            if (classFactory == null)
+                return null;
+
+            //And create an IFilter instance using that class factory
+            Guid IFilterGUID = new Guid("89BCB740-6119-101A-BCB7-00DD010655AF");
+            Object obj;
+            classFactory.CreateInstance(null, ref IFilterGUID, out obj);
+            return (obj as IFilter);
+        }
+
+        private static bool GetFilterDllAndClass(string ext, out string dllName, out string filterPersistClass)
+        {
+            if (!GetFilterDllAndClassFromCache(ext, out dllName, out filterPersistClass))
+            {
+                string persistentHandlerClass;
+
+                persistentHandlerClass = GetPersistentHandlerClass(ext, true);
+                if (persistentHandlerClass != null)
+                {
+                    GetFilterDllAndClassFromPersistentHandler(persistentHandlerClass,
+                      out dllName, out filterPersistClass);
+                }
+                AddExtensionToCache(ext, dllName, filterPersistClass);
+            }
+            return (dllName != null && filterPersistClass != null);
+        }
+
+        private static void AddExtensionToCache(string ext, string dllName, string filterPersistClass)
+        {
+            lock (_cache)
+            {
+                _cache.Add(ext.ToLower(), new CacheEntry(dllName, filterPersistClass));
+            }
+        }
+
+        private static bool GetFilterDllAndClassFromPersistentHandler(string persistentHandlerClass, out string dllName, out string filterPersistClass)
+        {
+            dllName = null;
+            filterPersistClass = null;
+
+            //Read the CLASS ID of the IFilter persistent handler
+            filterPersistClass = ReadStrFromHKLM(@"Software\Classes\CLSID\" + persistentHandlerClass +
+              @"\PersistentAddinsRegistered\{89BCB740-6119-101A-BCB7-00DD010655AF}");
+            if (String.IsNullOrEmpty(filterPersistClass))
+                return false;
+
+            //Read the dll name 
+            dllName = ReadStrFromHKLM(@"Software\Classes\CLSID\" + filterPersistClass +
+              @"\InprocServer32");
+            return (!String.IsNullOrEmpty(dllName));
+        }
+
+        private static string GetPersistentHandlerClass(string ext, bool searchContentType)
+        {
+            //Try getting the info from the file extension
+            string persistentHandlerClass = GetPersistentHandlerClassFromExtension(ext);
+            if (string.IsNullOrEmpty(persistentHandlerClass))
+                //try getting the info from the document type 
+                persistentHandlerClass = GetPersistentHandlerClassFromDocumentType(ext);
+            if (searchContentType && string.IsNullOrEmpty(persistentHandlerClass))
+                //Try getting the info from the Content Type
+                persistentHandlerClass = GetPersistentHandlerClassFromContentType(ext);
+            return persistentHandlerClass;
+        }
+
+        private static string GetPersistentHandlerClassFromContentType(string ext)
+        {
+            string contentType = ReadStrFromHKLM(@"Software\Classes\" + ext, "Content Type");
+            if (string.IsNullOrEmpty(contentType))
+                return null;
+
+            string contentTypeExtension = ReadStrFromHKLM(@"Software\Classes\MIME\Database\Content Type\" + contentType,
+                "Extension");
+            if (ext.Equals(contentTypeExtension, StringComparison.CurrentCultureIgnoreCase))
+                return null; //No need to look further. This extension does not have any persistent handler
+
+            //We know the extension that is assciated with that content type. Simply try again with the new extension
+            return GetPersistentHandlerClass(contentTypeExtension, false); //Don't search content type this time.
+        }
+
+        private static string GetPersistentHandlerClassFromDocumentType(string ext)
+        {
+            //Get the DocumentType of this file extension
+            string docType = ReadStrFromHKLM(@"Software\Classes\" + ext);
+            if (String.IsNullOrEmpty(docType))
+                return null;
+
+            //Get the Class ID for this document type
+            string docClass = ReadStrFromHKLM(@"Software\Classes\" + docType + @"\CLSID");
+            if (String.IsNullOrEmpty(docType))
+                return null;
+
+            //Now get the PersistentHandler for that Class ID
+            return ReadStrFromHKLM(@"Software\Classes\CLSID\" + docClass + @"\PersistentHandler");
+        }
+
+        private static string GetPersistentHandlerClassFromExtension(string ext)
+        {
+            return ReadStrFromHKLM(@"Software\Classes\" + ext + @"\PersistentHandler");
+        }
+
+        private static bool GetFilterDllAndClassFromCache(string ext, out string dllName, out string filterPersistClass)
+        {
+            string lowerExt = ext.ToLower();
+            lock (_cache)
+            {
+                CacheEntry cacheEntry;
+                if (_cache.TryGetValue(lowerExt, out cacheEntry))
+                {
+                    dllName = cacheEntry.DllName;
+                    filterPersistClass = cacheEntry.ClassName;
+                    return true;
+                }
+            }
+            dllName = null;
+            filterPersistClass = null;
+            return false;
+        }
+    }
+}

FilterReader/FilterReader.cs

@@ -0,0 +1,169 @@
+using System;
+using System.Collections.Generic;
+using System.Text;
+using System.IO;
+using System.Runtime.InteropServices;
+
+namespace DigitalData.Modules.FilterReader
+{
+    /// <summary>
+    /// Implements a TextReader that reads from an IFilter. 
+    /// </summary>
+    public class FilterReader : TextReader
+    {
+        IFilter _filter;
+        private bool _done;
+        private STAT_CHUNK _currentChunk;
+        private bool _currentChunkValid;
+        private char[] _charsLeftFromLastRead;
+
+        public override void Close()
+        {
+            Dispose(true);
+            GC.SuppressFinalize(this);
+        }
+
+        ~FilterReader()
+        {
+            Dispose(false);
+        }
+
+        protected override void Dispose(bool disposing)
+        {
+            if (_filter != null)
+                Marshal.ReleaseComObject(_filter);
+        }
+
+        public override int Read(char[] array, int offset, int count)
+        {
+            int endOfChunksCount = 0;
+            int charsRead = 0;
+
+            while (!_done && charsRead < count)
+            {
+                if (_charsLeftFromLastRead != null)
+                {
+                    int charsToCopy = (_charsLeftFromLastRead.Length < count - charsRead) ? _charsLeftFromLastRead.Length : count - charsRead;
+                    Array.Copy(_charsLeftFromLastRead, 0, array, offset + charsRead, charsToCopy);
+                    charsRead += charsToCopy;
+                    if (charsToCopy < _charsLeftFromLastRead.Length)
+                    {
+                        char[] tmp = new char[_charsLeftFromLastRead.Length - charsToCopy];
+                        Array.Copy(_charsLeftFromLastRead, charsToCopy, tmp, 0, tmp.Length);
+                        _charsLeftFromLastRead = tmp;
+                    }
+                    else
+                        _charsLeftFromLastRead = null;
+                    continue;
+                };
+
+                if (!_currentChunkValid)
+                {
+                    IFilterReturnCode res = _filter.GetChunk(out _currentChunk);
+                    _currentChunkValid = (res == IFilterReturnCode.S_OK) && ((_currentChunk.flags & CHUNKSTATE.CHUNK_TEXT) != 0);
+
+                    if (res == IFilterReturnCode.FILTER_E_END_OF_CHUNKS)
+                        endOfChunksCount++;
+
+                    if (endOfChunksCount > 1)
+                        _done = true; //That's it. no more chuncks available
+                }
+
+                if (_currentChunkValid)
+                {
+                    uint bufLength = (uint)(count - charsRead);
+                    if (bufLength < 8192)
+                        bufLength = 8192; //Read ahead
+
+                    char[] buffer = new char[bufLength];
+                    IFilterReturnCode res = _filter.GetText(ref bufLength, buffer);
+                    if (res == IFilterReturnCode.S_OK || res == IFilterReturnCode.FILTER_S_LAST_TEXT)
+                    {
+                        int cRead = (int)bufLength;
+                        if (cRead + charsRead > count)
+                        {
+                            int charsLeft = (cRead + charsRead - count);
+                            _charsLeftFromLastRead = new char[charsLeft];
+                            Array.Copy(buffer, cRead - charsLeft, _charsLeftFromLastRead, 0, charsLeft);
+                            cRead -= charsLeft;
+                        }
+                        else
+                            _charsLeftFromLastRead = null;
+
+                        Array.Copy(buffer, 0, array, offset + charsRead, cRead);
+                        charsRead += cRead;
+                    }
+
+                    if (res == IFilterReturnCode.FILTER_S_LAST_TEXT || res == IFilterReturnCode.FILTER_E_NO_MORE_TEXT)
+                        _currentChunkValid = false;
+                }
+            }
+            return charsRead;
+        }
+
+        public override string ReadToEnd()
+        {
+            IList<string> chunks = new List<string>();
+
+            // read all the chunks
+            IFilterReturnCode chunckResult = _filter.GetChunk(out _currentChunk);
+            while (chunckResult != IFilterReturnCode.FILTER_E_END_OF_CHUNKS)
+            {
+
+                // process only text type chunks
+                bool textChunk = (chunckResult == IFilterReturnCode.S_OK) && ((_currentChunk.flags & CHUNKSTATE.CHUNK_TEXT) != 0);
+                if (textChunk)
+                {
+
+                    string chunkText = "";
+                    uint bufLength = 8 * 1024;
+                    char[] buffer = new char[bufLength];
+
+                    // build chunk list of strings
+                    IFilterReturnCode textResult = _filter.GetText(ref bufLength, buffer);
+                    while (textResult == IFilterReturnCode.S_OK || textResult == IFilterReturnCode.FILTER_S_LAST_TEXT)
+                    {
+                        chunkText += new string(buffer).Replace("\0", "").Replace("\t", " ") + " ";
+
+                        if (textResult == IFilterReturnCode.S_OK)
+                        {
+
+                            // read more text
+                            buffer = new char[bufLength]; // get fresh buffer
+                            bufLength = 8 * 1024;
+                            textResult = _filter.GetText(ref bufLength, buffer);
+
+                            if (textResult != IFilterReturnCode.S_OK)
+                            {
+                                chunkText = chunkText.Trim();
+                                if (!string.IsNullOrEmpty(chunkText))
+                                    chunks.Add(chunkText);
+                            }
+                        }
+                        else
+                        {
+
+                            // stop reading text
+                            textResult = IFilterReturnCode.FILTER_E_NO_MORE_TEXT;
+                            chunkText = chunkText.Trim();
+                            if (!string.IsNullOrEmpty(chunkText))
+                                chunks.Add(chunkText);
+                        }
+                    }
+                }
+
+                // get next chunk
+                chunckResult = _filter.GetChunk(out _currentChunk);
+            }
+
+            return string.Join("\r\n", chunks);
+        }
+
+        public FilterReader(string fileName)
+        {
+            _filter = FilterLoader.LoadAndInitIFilter(fileName);
+            if (_filter == null)
+                throw new ArgumentException("no filter defined for " + fileName);
+        }
+    }
+}

FilterReader/FilterReader.csproj

@@ -0,0 +1,51 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" />
+  <PropertyGroup>
+    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
+    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
+    <ProjectGuid>{10C922FB-DD8D-4E0B-A50C-30EE658FBDDC}</ProjectGuid>
+    <OutputType>Library</OutputType>
+    <AppDesignerFolder>Properties</AppDesignerFolder>
+    <RootNamespace>DigitalData.Modules.FilterReader</RootNamespace>
+    <AssemblyName>DigitalData.Modules.FilterReader</AssemblyName>
+    <TargetFrameworkVersion>v4.6.2</TargetFrameworkVersion>
+    <FileAlignment>512</FileAlignment>
+    <Deterministic>true</Deterministic>
+  </PropertyGroup>
+  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
+    <DebugSymbols>true</DebugSymbols>
+    <DebugType>full</DebugType>
+    <Optimize>false</Optimize>
+    <OutputPath>bin\Debug\</OutputPath>
+    <DefineConstants>DEBUG;TRACE</DefineConstants>
+    <ErrorReport>prompt</ErrorReport>
+    <WarningLevel>4</WarningLevel>
+  </PropertyGroup>
+  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
+    <DebugType>pdbonly</DebugType>
+    <Optimize>true</Optimize>
+    <OutputPath>bin\Release\</OutputPath>
+    <DefineConstants>TRACE</DefineConstants>
+    <ErrorReport>prompt</ErrorReport>
+    <WarningLevel>4</WarningLevel>
+  </PropertyGroup>
+  <ItemGroup>
+    <Reference Include="System" />
+    <Reference Include="System.Core" />
+    <Reference Include="System.Xml.Linq" />
+    <Reference Include="System.Data.DataSetExtensions" />
+    <Reference Include="Microsoft.CSharp" />
+    <Reference Include="System.Data" />
+    <Reference Include="System.Net.Http" />
+    <Reference Include="System.Xml" />
+  </ItemGroup>
+  <ItemGroup>
+    <Compile Include="ComHelper.cs" />
+    <Compile Include="FilterLoader.cs" />
+    <Compile Include="FilterReader.cs" />
+    <Compile Include="IFilter.cs" />
+    <Compile Include="Properties\AssemblyInfo.cs" />
+  </ItemGroup>
+  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
+</Project>

FilterReader/IFilter.cs

@@ -0,0 +1,435 @@
+using System;
+using System.Text;
+using System.Runtime.InteropServices;
+
+//Contains IFilter interface translation
+//Most translations are from PInvoke.net
+
+namespace DigitalData.Modules.FilterReader
+{
+    [StructLayout(LayoutKind.Sequential)]
+    public struct FULLPROPSPEC
+    {
+        public Guid guidPropSet;
+        public PROPSPEC psProperty;
+    }
+
+    [StructLayout(LayoutKind.Sequential)]
+    internal struct FILTERREGION
+    {
+        public int idChunk;
+        public int cwcStart;
+        public int cwcExtent;
+    }
+
+    [StructLayout(LayoutKind.Explicit)]
+    public struct PROPSPEC
+    {
+        [FieldOffset(0)] public int ulKind;     // 0 - string used; 1 - PROPID
+        [FieldOffset(4)] public int propid;
+        [FieldOffset(4)] public IntPtr lpwstr;
+    }
+
+    [Flags]
+    internal enum IFILTER_FLAGS
+    {
+        /// <summary>
+        /// The caller should use the IPropertySetStorage and IPropertyStorage
+        /// interfaces to locate additional properties. 
+        /// When this flag is set, properties available through COM
+        /// enumerators should not be returned from IFilter. 
+        /// </summary>
+        IFILTER_FLAGS_OLE_PROPERTIES = 1
+    }
+
+    /// <summary>
+    /// Flags controlling the operation of the FileFilter
+    /// instance.
+    /// </summary>
+    [Flags]
+    internal enum IFILTER_INIT
+    {
+        NONE = 0,
+        /// <summary>
+        /// Paragraph breaks should be marked with the Unicode PARAGRAPH
+        /// SEPARATOR (0x2029)
+        /// </summary>
+        CANON_PARAGRAPHS = 1,
+
+        /// <summary>
+        /// Soft returns, such as the newline character in Microsoft Word, should
+        /// be replaced by hard returnsLINE SEPARATOR (0x2028). Existing hard
+        /// returns can be doubled. A carriage return (0x000D), line feed (0x000A),
+        /// or the carriage return and line feed in combination should be considered
+        /// a hard return. The intent is to enable pattern-expression matches that
+        /// match against observed line breaks. 
+        /// </summary>
+        HARD_LINE_BREAKS = 2,
+
+        /// <summary>
+        /// Various word-processing programs have forms of hyphens that are not
+        /// represented in the host character set, such as optional hyphens
+        /// (appearing only at the end of a line) and nonbreaking hyphens. This flag
+        /// indicates that optional hyphens are to be converted to nulls, and
+        /// non-breaking hyphens are to be converted to normal hyphens (0x2010), or
+        /// HYPHEN-MINUSES (0x002D). 
+        /// </summary>
+        CANON_HYPHENS = 4,
+
+        /// <summary>
+        /// Just as the CANON_HYPHENS flag standardizes hyphens,
+        /// this one standardizes spaces. All special space characters, such as
+        /// nonbreaking spaces, are converted to the standard space character
+        /// (0x0020). 
+        /// </summary>
+        CANON_SPACES = 8,
+
+        /// <summary>
+        /// Indicates that the client wants text split into chunks representing
+        /// public value-type properties. 
+        /// </summary>
+        APPLY_INDEX_ATTRIBUTES = 16,
+
+        /// <summary>
+        /// Indicates that the client wants text split into chunks representing
+        /// properties determined during the indexing process. 
+        /// </summary>
+        APPLY_CRAWL_ATTRIBUTES = 256,
+
+        /// <summary>
+        /// Any properties not covered by the APPLY_INDEX_ATTRIBUTES
+        /// and APPLY_CRAWL_ATTRIBUTES flags should be emitted. 
+        /// </summary>
+        APPLY_OTHER_ATTRIBUTES = 32,
+
+        /// <summary>
+        /// Optimizes IFilter for indexing because the client calls the
+        /// IFilter::Init method only once and does not call IFilter::BindRegion.
+        /// This eliminates the possibility of accessing a chunk both before and
+        /// after accessing another chunk. 
+        /// </summary>
+        INDEXING_ONLY = 64,
+
+        /// <summary>
+        /// The text extraction process must recursively search all linked
+        /// objects within the document. If a link is unavailable, the
+        /// IFilter::GetChunk call that would have obtained the first chunk of the
+        /// link should return FILTER_E_LINK_UNAVAILABLE. 
+        /// </summary>
+        SEARCH_LINKS = 128,
+
+        /// <summary>
+        /// The content indexing process can return property values set by the  filter. 
+        /// </summary>
+        FILTER_OWNED_VALUE_OK = 512
+    }
+
+    public struct STAT_CHUNK
+    {
+        /// <summary>
+        /// The chunk identifier. Chunk identifiers must be unique for the
+        /// current instance of the IFilter interface. 
+        /// Chunk identifiers must be in ascending order. The order in which
+        /// chunks are numbered should correspond to the order in which they appear
+        /// in the source document. Some search engines can take advantage of the
+        /// proximity of chunks of various properties. If so, the order in which
+        /// chunks with different properties are emitted will be important to the
+        /// search engine. 
+        /// </summary>
+        public int idChunk;
+
+        /// <summary>
+        /// The type of break that separates the previous chunk from the current
+        ///  chunk. Values are from the CHUNK_BREAKTYPE enumeration. 
+        /// </summary>
+        [MarshalAs(UnmanagedType.U4)]
+        public CHUNK_BREAKTYPE breakType;
+
+        /// <summary>
+        /// Flags indicate whether this chunk contains a text-type or a
+        /// value-type property. 
+        /// Flag values are taken from the CHUNKSTATE enumeration. If the CHUNK_TEXT flag is set, 
+        /// IFilter::GetText should be used to retrieve the contents of the chunk
+        /// as a series of words. 
+        /// If the CHUNK_VALUE flag is set, IFilter::GetValue should be used to retrieve 
+        /// the value and treat it as a single property value. If the filter dictates that the same 
+        /// content be treated as both text and as a value, the chunk should be emitted twice in two       
+        /// different chunks, each with one flag set. 
+        /// </summary>
+        [MarshalAs(UnmanagedType.U4)]
+        public CHUNKSTATE flags;
+
+        /// <summary>
+        /// The language and sublanguage associated with a chunk of text. Chunk locale is used 
+        /// by document indexers to perform proper word breaking of text. If the chunk is 
+        /// neither text-type nor a value-type with data type VT_LPWSTR, VT_LPSTR or VT_BSTR, 
+        /// this field is ignored. 
+        /// </summary>
+        public int locale;
+
+        /// <summary>
+        /// The property to be applied to the chunk. If a filter requires that       the same text 
+        /// have more than one property, it needs to emit the text once for each       property 
+        /// in separate chunks. 
+        /// </summary>
+        public FULLPROPSPEC attribute;
+
+        /// <summary>
+        /// The ID of the source of a chunk. The value of the idChunkSource     member depends on the nature of the chunk: 
+        /// If the chunk is a text-type property, the value of the idChunkSource       member must be the same as the value of the idChunk member. 
+        /// If the chunk is an public value-type property derived from textual       content, the value of the idChunkSource member is the chunk ID for the
+        /// text-type chunk from which it is derived. 
+        /// If the filter attributes specify to return only public value-type
+        /// properties, there is no content chunk from which to derive the current
+        /// public value-type property. In this case, the value of the
+        /// idChunkSource member must be set to zero, which is an invalid chunk. 
+        /// </summary>
+        public int idChunkSource;
+
+        /// <summary>
+        /// The offset from which the source text for a derived chunk starts in
+        /// the source chunk. 
+        /// </summary>
+        public int cwcStartSource;
+
+        /// <summary>
+        /// The length in characters of the source text from which the current
+        /// chunk was derived. 
+        /// A zero value signifies character-by-character correspondence between
+        /// the source text and 
+        /// the derived text. A nonzero value means that no such direct
+        /// correspondence exists
+        /// </summary>
+        public int cwcLenSource;
+    }
+
+    /// <summary>
+    /// Enumerates the different breaking types that occur between 
+    /// chunks of text read out by the FileFilter.
+    /// </summary>
+    public enum CHUNK_BREAKTYPE
+    {
+        /// <summary>
+        /// No break is placed between the current chunk and the previous chunk.
+        /// The chunks are glued together. 
+        /// </summary>
+        CHUNK_NO_BREAK = 0,
+        /// <summary>
+        /// A word break is placed between this chunk and the previous chunk that
+        /// had the same attribute. 
+        /// Use of CHUNK_EOW should be minimized because the choice of word
+        /// breaks is language-dependent, 
+        /// so determining word breaks is best left to the search engine. 
+        /// </summary>
+        CHUNK_EOW = 1,
+        /// <summary>
+        /// A sentence break is placed between this chunk and the previous chunk
+        /// that had the same attribute. 
+        /// </summary>
+        CHUNK_EOS = 2,
+        /// <summary>
+        /// A paragraph break is placed between this chunk and the previous chunk
+        /// that had the same attribute.
+        /// </summary>     
+        CHUNK_EOP = 3,
+        /// <summary>
+        /// A chapter break is placed between this chunk and the previous chunk
+        /// that had the same attribute. 
+        /// </summary>
+        CHUNK_EOC = 4
+    }
+
+
+    public enum CHUNKSTATE
+    {
+        /// <summary>
+        /// The current chunk is a text-type property.
+        /// </summary>
+        CHUNK_TEXT = 0x1,
+        /// <summary>
+        /// The current chunk is a value-type property. 
+        /// </summary>
+        CHUNK_VALUE = 0x2,
+        /// <summary>
+        /// Reserved
+        /// </summary>
+        CHUNK_FILTER_OWNED_VALUE = 0x4
+    }
+
+    internal enum IFilterReturnCode : UInt32
+    {
+        /// <summary>
+        /// Success
+        /// </summary>
+        S_OK = 0,
+        /// <summary>
+        /// The function was denied access to the filter file. 
+        /// </summary>
+        E_ACCESSDENIED = 0x80070005,
+        /// <summary>
+        /// The function encountered an invalid handle,
+        /// probably due to a low-memory situation. 
+        /// </summary>
+        E_HANDLE = 0x80070006,
+        /// <summary>
+        /// The function received an invalid parameter.
+        /// </summary>
+        E_INVALIDARG = 0x80070057,
+        /// <summary>
+        /// Out of memory
+        /// </summary>
+        E_OUTOFMEMORY = 0x8007000E,
+        /// <summary>
+        /// Not implemented
+        /// </summary>
+        E_NOTIMPL = 0x80004001,
+        /// <summary>
+        /// Unknown error
+        /// </summary>
+        E_FAIL = 0x80000008,
+        /// <summary>
+        /// File not filtered due to password protection
+        /// </summary>
+        FILTER_E_PASSWORD = 0x8004170B,
+        /// <summary>
+        /// The document format is not recognised by the filter
+        /// </summary>
+        FILTER_E_UNKNOWNFORMAT = 0x8004170C,
+        /// <summary>
+        /// No text in current chunk
+        /// </summary>
+        FILTER_E_NO_TEXT = 0x80041705,
+        /// <summary>
+        /// No more chunks of text available in object
+        /// </summary>
+        FILTER_E_END_OF_CHUNKS = 0x80041700,
+        /// <summary>
+        /// No more text available in chunk
+        /// </summary>
+        FILTER_E_NO_MORE_TEXT = 0x80041701,
+        /// <summary>
+        /// No more property values available in chunk
+        /// </summary>
+        FILTER_E_NO_MORE_VALUES = 0x80041702,
+        /// <summary>
+        /// Unable to access object
+        /// </summary>
+        FILTER_E_ACCESS = 0x80041703,
+        /// <summary>
+        /// Moniker doesn't cover entire region
+        /// </summary>
+        FILTER_W_MONIKER_CLIPPED = 0x00041704,
+        /// <summary>
+        /// Unable to bind IFilter for embedded object
+        /// </summary>
+        FILTER_E_EMBEDDING_UNAVAILABLE = 0x80041707,
+        /// <summary>
+        /// Unable to bind IFilter for linked object
+        /// </summary>
+        FILTER_E_LINK_UNAVAILABLE = 0x80041708,
+        /// <summary>
+        ///  This is the last text in the current chunk
+        /// </summary>
+        FILTER_S_LAST_TEXT = 0x00041709,
+        /// <summary>
+        /// This is the last value in the current chunk
+        /// </summary>
+        FILTER_S_LAST_VALUES = 0x0004170A
+    }
+
+    [ComImport, Guid("89BCB740-6119-101A-BCB7-00DD010655AF")]
+    [InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
+    internal interface IFilter
+    {
+        /// <summary>
+        /// The IFilter::Init method initializes a filtering session.
+        /// </summary>
+        [PreserveSig]
+        IFilterReturnCode Init(
+          //[in] Flag settings from the IFILTER_INIT enumeration for
+          // controlling text standardization, property output, embedding
+          // scope, and IFilter access patterns. 
+          IFILTER_INIT grfFlags,
+
+          // [in] The size of the attributes array. When nonzero, cAttributes
+          //  takes 
+          // precedence over attributes specified in grfFlags. If no
+          // attribute flags 
+          // are specified and cAttributes is zero, the default is given by
+          // the 
+          // PSGUID_STORAGE storage property set, which contains the date and
+          //  time 
+          // of the last write to the file, size, and so on; and by the
+          //  PID_STG_CONTENTS 
+          // 'contents' property, which maps to the main contents of the
+          // file. 
+          // For more information about properties and property sets, see
+          // Property Sets. 
+          int cAttributes,
+
+          //[in] Array of pointers to FULLPROPSPEC structures for the
+          // requested properties. 
+          // When cAttributes is nonzero, only the properties in aAttributes
+          // are returned. 
+          IntPtr aAttributes,
+
+          // [out] Information about additional properties available to the
+          //  caller; from the IFILTER_FLAGS enumeration. 
+          out IFILTER_FLAGS pdwFlags);
+
+        /// <summary>
+        /// The IFilter::GetChunk method positions the filter at the beginning
+        /// of the next chunk, 
+        /// or at the first chunk if this is the first call to the GetChunk
+        /// method, and returns a description of the current chunk. 
+        /// </summary>
+        [PreserveSig]
+        IFilterReturnCode GetChunk(out STAT_CHUNK pStat);
+
+        /// <summary>
+        /// The IFilter::GetText method retrieves text (text-type properties)
+        /// from the current chunk, 
+        /// which must have a CHUNKSTATE enumeration value of CHUNK_TEXT.
+        /// </summary>
+        [PreserveSig]
+        IFilterReturnCode GetText(
+          // [in/out] On entry, the size of awcBuffer array in wide/Unicode
+          // characters. On exit, the number of Unicode characters written to
+          // awcBuffer. 
+          // Note that this value is not the number of bytes in the buffer. 
+          ref uint pcwcBuffer,
+
+          // Text retrieved from the current chunk. Do not terminate the
+          // buffer with a character.  
+          [Out(), MarshalAs(UnmanagedType.LPArray)]
+      char[] awcBuffer);
+
+        /// <summary>
+        /// The IFilter::GetValue method retrieves a value (public
+        /// value-type property) from a chunk, 
+        /// which must have a CHUNKSTATE enumeration value of CHUNK_VALUE.
+        /// </summary>
+        [PreserveSig]
+        int GetValue(
+          // Allocate the PROPVARIANT structure with CoTaskMemAlloc. Some
+          // PROPVARIANT 
+          // structures contain pointers, which can be freed by calling the
+          // PropVariantClear function. 
+          // It is up to the caller of the GetValue method to call the
+          //   PropVariantClear method.            
+          // ref IntPtr ppPropValue
+          // [MarshalAs(UnmanagedType.Struct)]
+          ref IntPtr PropVal);
+
+        /// <summary>
+        /// The IFilter::BindRegion method retrieves an interface representing
+        /// the specified portion of the object. 
+        /// Currently reserved for future use.
+        /// </summary>
+        [PreserveSig]
+        int BindRegion(ref FILTERREGION origPos,
+          ref Guid riid, ref object ppunk);
+    }
+
+
+}

FilterReader/Properties/AssemblyInfo.cs

@@ -0,0 +1,36 @@
+using System.Reflection;
+using System.Runtime.CompilerServices;
+using System.Runtime.InteropServices;
+
+// Allgemeine Informationen über eine Assembly werden über die folgenden
+// Attribute gesteuert. Ändern Sie diese Attributwerte, um die Informationen zu ändern,
+// die einer Assembly zugeordnet sind.
+[assembly: AssemblyTitle("FilterReader")]
+[assembly: AssemblyDescription("")]
+[assembly: AssemblyConfiguration("")]
+[assembly: AssemblyCompany("")]
+[assembly: AssemblyProduct("FilterReader")]
+[assembly: AssemblyCopyright("Copyright ©  2022")]
+[assembly: AssemblyTrademark("")]
+[assembly: AssemblyCulture("")]
+
+// Durch Festlegen von ComVisible auf FALSE werden die Typen in dieser Assembly
+// für COM-Komponenten unsichtbar.  Wenn Sie auf einen Typ in dieser Assembly von
+// COM aus zugreifen müssen, sollten Sie das ComVisible-Attribut für diesen Typ auf "True" festlegen.
+[assembly: ComVisible(false)]
+
+// Die folgende GUID bestimmt die ID der Typbibliothek, wenn dieses Projekt für COM verfügbar gemacht wird
+[assembly: Guid("10c922fb-dd8d-4e0b-a50c-30ee658fbddc")]
+
+// Versionsinformationen für eine Assembly bestehen aus den folgenden vier Werten:
+//
+//      Hauptversion
+//      Nebenversion
+//      Buildnummer
+//      Revision
+//
+// Sie können alle Werte angeben oder Standardwerte für die Build- und Revisionsnummern verwenden,
+// indem Sie "*" wie unten gezeigt eingeben:
+// [assembly: AssemblyVersion("1.0.*")]
+[assembly: AssemblyVersion("1.0.0.0")]
+[assembly: AssemblyFileVersion("1.0.0.0")]

GUIs.Test.TestGUI/TestGUI.vbproj

@@ -180,6 +180,12 @@
     <Compile Include="frmFolderWatcher.vb">
       <SubType>Form</SubType>
     </Compile>
+    <Compile Include="frmFulltext.Designer.vb">
+      <DependentUpon>frmFulltext.vb</DependentUpon>
+    </Compile>
+    <Compile Include="frmFulltext.vb">
+      <SubType>Form</SubType>
+    </Compile>
     <Compile Include="frmLookup.Designer.vb">
       <DependentUpon>frmLookup.vb</DependentUpon>
     </Compile>
@@ -256,6 +262,9 @@
     <EmbeddedResource Include="frmFolderWatcher.resx">
       <DependentUpon>frmFolderWatcher.vb</DependentUpon>
     </EmbeddedResource>
+    <EmbeddedResource Include="frmFulltext.resx">
+      <DependentUpon>frmFulltext.vb</DependentUpon>
+    </EmbeddedResource>
     <EmbeddedResource Include="frmLookup.resx">
       <DependentUpon>frmLookup.vb</DependentUpon>
     </EmbeddedResource>
@@ -312,6 +321,10 @@
       <Project>{3e7bc8a9-91ef-49b8-8110-2c01f664c24a}</Project>
       <Name>SQLEditor</Name>
     </ProjectReference>
+    <ProjectReference Include="..\FilterReader\FilterReader.csproj">
+      <Project>{10c922fb-dd8d-4e0b-a50c-30ee658fbddc}</Project>
+      <Name>FilterReader</Name>
+    </ProjectReference>
     <ProjectReference Include="..\GUIs.Common\Common.vbproj">
       <Project>{D20A6BF2-C7C6-4A7A-B34D-FA27D775A049}</Project>
       <Name>Common</Name>

GUIs.Test.TestGUI/frmFulltext.Designer.vb

@@ -0,0 +1,71 @@
+<Global.Microsoft.VisualBasic.CompilerServices.DesignerGenerated()> _
+Partial Class frmFulltext
+    Inherits System.Windows.Forms.Form
+
+    'Das Formular überschreibt den Löschvorgang, um die Komponentenliste zu bereinigen.
+    <System.Diagnostics.DebuggerNonUserCode()> _
+    Protected Overrides Sub Dispose(ByVal disposing As Boolean)
+        Try
+            If disposing AndAlso components IsNot Nothing Then
+                components.Dispose()
+            End If
+        Finally
+            MyBase.Dispose(disposing)
+        End Try
+    End Sub
+
+    'Wird vom Windows Form-Designer benötigt.
+    Private components As System.ComponentModel.IContainer
+
+    'Hinweis: Die folgende Prozedur ist für den Windows Form-Designer erforderlich.
+    'Das Bearbeiten ist mit dem Windows Form-Designer möglich.  
+    'Das Bearbeiten mit dem Code-Editor ist nicht möglich.
+    <System.Diagnostics.DebuggerStepThrough()> _
+    Private Sub InitializeComponent()
+        Me.TextBox1 = New System.Windows.Forms.TextBox()
+        Me.OpenFileDialog1 = New System.Windows.Forms.OpenFileDialog()
+        Me.Button1 = New System.Windows.Forms.Button()
+        Me.SuspendLayout()
+        '
+        'TextBox1
+        '
+        Me.TextBox1.Anchor = CType((((System.Windows.Forms.AnchorStyles.Top Or System.Windows.Forms.AnchorStyles.Bottom) _
+            Or System.Windows.Forms.AnchorStyles.Left) _
+            Or System.Windows.Forms.AnchorStyles.Right), System.Windows.Forms.AnchorStyles)
+        Me.TextBox1.Location = New System.Drawing.Point(12, 45)
+        Me.TextBox1.Multiline = True
+        Me.TextBox1.Name = "TextBox1"
+        Me.TextBox1.Size = New System.Drawing.Size(776, 393)
+        Me.TextBox1.TabIndex = 0
+        '
+        'OpenFileDialog1
+        '
+        Me.OpenFileDialog1.FileName = "OpenFileDialog1"
+        '
+        'Button1
+        '
+        Me.Button1.Location = New System.Drawing.Point(12, 16)
+        Me.Button1.Name = "Button1"
+        Me.Button1.Size = New System.Drawing.Size(75, 23)
+        Me.Button1.TabIndex = 1
+        Me.Button1.Text = "Open"
+        Me.Button1.UseVisualStyleBackColor = True
+        '
+        'frmFulltext
+        '
+        Me.AutoScaleDimensions = New System.Drawing.SizeF(6.0!, 13.0!)
+        Me.AutoScaleMode = System.Windows.Forms.AutoScaleMode.Font
+        Me.ClientSize = New System.Drawing.Size(800, 450)
+        Me.Controls.Add(Me.Button1)
+        Me.Controls.Add(Me.TextBox1)
+        Me.Name = "frmFulltext"
+        Me.Text = "frmFulltext"
+        Me.ResumeLayout(False)
+        Me.PerformLayout()
+
+    End Sub
+
+    Friend WithEvents TextBox1 As TextBox
+    Friend WithEvents OpenFileDialog1 As OpenFileDialog
+    Friend WithEvents Button1 As Button
+End Class

GUIs.Test.TestGUI/frmFulltext.resx

@@ -0,0 +1,123 @@
+<?xml version="1.0" encoding="utf-8"?>
+<root>
+  <!-- 
+    Microsoft ResX Schema 
+    
+    Version 2.0
+    
+    The primary goals of this format is to allow a simple XML format 
+    that is mostly human readable. The generation and parsing of the 
+    various data types are done through the TypeConverter classes 
+    associated with the data types.
+    
+    Example:
+    
+    ... ado.net/XML headers & schema ...
+    <resheader name="resmimetype">text/microsoft-resx</resheader>
+    <resheader name="version">2.0</resheader>
+    <resheader name="reader">System.Resources.ResXResourceReader, System.Windows.Forms, ...</resheader>
+    <resheader name="writer">System.Resources.ResXResourceWriter, System.Windows.Forms, ...</resheader>
+    <data name="Name1"><value>this is my long string</value><comment>this is a comment</comment></data>
+    <data name="Color1" type="System.Drawing.Color, System.Drawing">Blue</data>
+    <data name="Bitmap1" mimetype="application/x-microsoft.net.object.binary.base64">
+        <value>[base64 mime encoded serialized .NET Framework object]</value>
+    </data>
+    <data name="Icon1" type="System.Drawing.Icon, System.Drawing" mimetype="application/x-microsoft.net.object.bytearray.base64">
+        <value>[base64 mime encoded string representing a byte array form of the .NET Framework object]</value>
+        <comment>This is a comment</comment>
+    </data>
+                
+    There are any number of "resheader" rows that contain simple 
+    name/value pairs.
+    
+    Each data row contains a name, and value. The row also contains a 
+    type or mimetype. Type corresponds to a .NET class that support 
+    text/value conversion through the TypeConverter architecture. 
+    Classes that don't support this are serialized and stored with the 
+    mimetype set.
+    
+    The mimetype is used for serialized objects, and tells the 
+    ResXResourceReader how to depersist the object. This is currently not 
+    extensible. For a given mimetype the value must be set accordingly:
+    
+    Note - application/x-microsoft.net.object.binary.base64 is the format 
+    that the ResXResourceWriter will generate, however the reader can 
+    read any of the formats listed below.
+    
+    mimetype: application/x-microsoft.net.object.binary.base64
+    value   : The object must be serialized with 
+            : System.Runtime.Serialization.Formatters.Binary.BinaryFormatter
+            : and then encoded with base64 encoding.
+    
+    mimetype: application/x-microsoft.net.object.soap.base64
+    value   : The object must be serialized with 
+            : System.Runtime.Serialization.Formatters.Soap.SoapFormatter
+            : and then encoded with base64 encoding.
+
+    mimetype: application/x-microsoft.net.object.bytearray.base64
+    value   : The object must be serialized into a byte array 
+            : using a System.ComponentModel.TypeConverter
+            : and then encoded with base64 encoding.
+    -->
+  <xsd:schema id="root" xmlns="" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:msdata="urn:schemas-microsoft-com:xml-msdata">
+    <xsd:import namespace="http://www.w3.org/XML/1998/namespace" />
+    <xsd:element name="root" msdata:IsDataSet="true">
+      <xsd:complexType>
+        <xsd:choice maxOccurs="unbounded">
+          <xsd:element name="metadata">
+            <xsd:complexType>
+              <xsd:sequence>
+                <xsd:element name="value" type="xsd:string" minOccurs="0" />
+              </xsd:sequence>
+              <xsd:attribute name="name" use="required" type="xsd:string" />
+              <xsd:attribute name="type" type="xsd:string" />
+              <xsd:attribute name="mimetype" type="xsd:string" />
+              <xsd:attribute ref="xml:space" />
+            </xsd:complexType>
+          </xsd:element>
+          <xsd:element name="assembly">
+            <xsd:complexType>
+              <xsd:attribute name="alias" type="xsd:string" />
+              <xsd:attribute name="name" type="xsd:string" />
+            </xsd:complexType>
+          </xsd:element>
+          <xsd:element name="data">
+            <xsd:complexType>
+              <xsd:sequence>
+                <xsd:element name="value" type="xsd:string" minOccurs="0" msdata:Ordinal="1" />
+                <xsd:element name="comment" type="xsd:string" minOccurs="0" msdata:Ordinal="2" />
+              </xsd:sequence>
+              <xsd:attribute name="name" type="xsd:string" use="required" msdata:Ordinal="1" />
+              <xsd:attribute name="type" type="xsd:string" msdata:Ordinal="3" />
+              <xsd:attribute name="mimetype" type="xsd:string" msdata:Ordinal="4" />
+              <xsd:attribute ref="xml:space" />
+            </xsd:complexType>
+          </xsd:element>
+          <xsd:element name="resheader">
+            <xsd:complexType>
+              <xsd:sequence>
+                <xsd:element name="value" type="xsd:string" minOccurs="0" msdata:Ordinal="1" />
+              </xsd:sequence>
+              <xsd:attribute name="name" type="xsd:string" use="required" />
+            </xsd:complexType>
+          </xsd:element>
+        </xsd:choice>
+      </xsd:complexType>
+    </xsd:element>
+  </xsd:schema>
+  <resheader name="resmimetype">
+    <value>text/microsoft-resx</value>
+  </resheader>
+  <resheader name="version">
+    <value>2.0</value>
+  </resheader>
+  <resheader name="reader">
+    <value>System.Resources.ResXResourceReader, System.Windows.Forms, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089</value>
+  </resheader>
+  <resheader name="writer">
+    <value>System.Resources.ResXResourceWriter, System.Windows.Forms, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089</value>
+  </resheader>
+  <metadata name="OpenFileDialog1.TrayLocation" type="System.Drawing.Point, System.Drawing, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a">
+    <value>17, 17</value>
+  </metadata>
+</root>

GUIs.Test.TestGUI/frmFulltext.vb

@@ -0,0 +1,25 @@
+Imports DigitalData.Modules.FilterReader
+
+Public Class frmFulltext
+    Private Sub frmFulltext_Load(sender As Object, e As EventArgs) Handles MyBase.Load
+
+    End Sub
+
+    Private Sub Button1_Click(sender As Object, e As EventArgs) Handles Button1.Click
+        Dim oResult = OpenFileDialog1.ShowDialog()
+
+        If oResult = DialogResult.OK Then
+            Dim oFileName = OpenFileDialog1.FileName
+
+
+            Try
+                Using oReader As New FilterReader(oFileName)
+                    Dim oContents = oReader.ReadToEnd()
+                    TextBox1.Text = oContents
+                End Using
+            Catch ex As Exception
+                TextBox1.Text = $"Fulltext could not be extracted!{vbNewLine}{ex.Message}"
+            End Try
+        End If
+    End Sub
+End Class

GUIs.Test.TestGUI/frmStart.Designer.vb

@@ -32,6 +32,7 @@ Partial Class frmStart
         Me.Button8 = New System.Windows.Forms.Button()
         Me.Button9 = New System.Windows.Forms.Button()
         Me.Button10 = New System.Windows.Forms.Button()
+        Me.Button11 = New System.Windows.Forms.Button()
         Me.SuspendLayout()
         '
         'Button1
@@ -124,6 +125,15 @@ Partial Class frmStart
         Me.Button10.Text = "MsgBox"
         Me.Button10.UseVisualStyleBackColor = True
         '
+        'Button11
+        '
+        Me.Button11.Location = New System.Drawing.Point(254, 260)
+        Me.Button11.Name = "Button11"
+        Me.Button11.Size = New System.Drawing.Size(236, 60)
+        Me.Button11.TabIndex = 2
+        Me.Button11.Text = "Fulltext"
+        Me.Button11.UseVisualStyleBackColor = True
+        '
         'frmStart
         '
         Me.AutoScaleDimensions = New System.Drawing.SizeF(6.0!, 13.0!)
@@ -132,6 +142,7 @@ Partial Class frmStart
         Me.Controls.Add(Me.Button10)
         Me.Controls.Add(Me.Button9)
         Me.Controls.Add(Me.Button6)
+        Me.Controls.Add(Me.Button11)
         Me.Controls.Add(Me.Button5)
         Me.Controls.Add(Me.Button4)
         Me.Controls.Add(Me.Button3)
@@ -155,4 +166,5 @@ Partial Class frmStart
     Friend WithEvents Button8 As Button
     Friend WithEvents Button9 As Button
     Friend WithEvents Button10 As Button
+    Friend WithEvents Button11 As Button
 End Class

GUIs.Test.TestGUI/frmStart.vb

@@ -55,4 +55,9 @@ Public Class frmStart
         Dim oForm As New frmMsgBox(LogConfig, Database)
         oForm.Show()
     End Sub
+
+    Private Sub Button11_Click(sender As Object, e As EventArgs) Handles Button11.Click
+        Dim oform As New frmFulltext()
+        oform.Show()
+    End Sub
 End Class