initial commit from concordia-server repository

LemmaGenSockets.sln

@@ -0,0 +1,22 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 14
+VisualStudioVersion = 14.0.25420.1
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "LemmaGenSockets", "LemmaGenSockets\LemmaGenSockets.csproj", "{3098BC55-2CC9-4612-9F79-8C812B3BE539}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{3098BC55-2CC9-4612-9F79-8C812B3BE539}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{3098BC55-2CC9-4612-9F79-8C812B3BE539}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{3098BC55-2CC9-4612-9F79-8C812B3BE539}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{3098BC55-2CC9-4612-9F79-8C812B3BE539}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+EndGlobal

LemmaGenSockets/App.config

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<configuration>
+    <startup> 
+        <supportedRuntime version="v4.0" sku=".NETFramework,Version=v4.5.2" />
+    </startup>
+</configuration>

LemmaGenSockets/LemmaGenSockets.csproj

@@ -0,0 +1,73 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="14.0" DefaultTargets="Build" 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>{3098BC55-2CC9-4612-9F79-8C812B3BE539}</ProjectGuid>
+    <OutputType>Exe</OutputType>
+    <AppDesignerFolder>Properties</AppDesignerFolder>
+    <RootNamespace>LemmaGenSockets</RootNamespace>
+    <AssemblyName>LemmaGenSockets</AssemblyName>
+    <TargetFrameworkVersion>v4.5.2</TargetFrameworkVersion>
+    <FileAlignment>512</FileAlignment>
+    <AutoGenerateBindingRedirects>true</AutoGenerateBindingRedirects>
+  </PropertyGroup>
+  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
+    <PlatformTarget>AnyCPU</PlatformTarget>
+    <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' ">
+    <PlatformTarget>AnyCPU</PlatformTarget>
+    <DebugType>pdbonly</DebugType>
+    <Optimize>true</Optimize>
+    <OutputPath>bin\Release\</OutputPath>
+    <DefineConstants>TRACE</DefineConstants>
+    <ErrorReport>prompt</ErrorReport>
+    <WarningLevel>4</WarningLevel>
+  </PropertyGroup>
+  <ItemGroup>
+    <Reference Include="LemmaSharp">
+      <HintPath>..\LemmaGen\LemmaSharp.dll</HintPath>
+    </Reference>
+    <Reference Include="LemmaSharpPrebuilt">
+      <HintPath>..\LemmaGen\LemmaSharpPrebuilt.dll</HintPath>
+    </Reference>
+    <Reference Include="LemmaSharpPrebuiltCompact">
+      <HintPath>..\LemmaGen\LemmaSharpPrebuiltCompact.dll</HintPath>
+    </Reference>
+    <Reference Include="Lzma#">
+      <HintPath>..\LemmaGen\Lzma#.dll</HintPath>
+    </Reference>
+    <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="LemmatizerListener.cs" />
+    <Compile Include="Program.cs" />
+    <Compile Include="Properties\AssemblyInfo.cs" />
+  </ItemGroup>
+  <ItemGroup>
+    <None Include="App.config" />
+  </ItemGroup>
+  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
+  <!-- To modify your build process, add your task inside one of the targets below and uncomment it. 
+       Other similar extension points exist, see Microsoft.Common.targets.
+  <Target Name="BeforeBuild">
+  </Target>
+  <Target Name="AfterBuild">
+  </Target>
+  -->
+</Project>

LemmaGenSockets/LemmatizerListener.cs

@@ -0,0 +1,180 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Text;
+using System.Net;
+using System.Net.Sockets;
+using System.Threading.Tasks;
+using LemmaSharp;
+
+namespace LemmaGenSockets
+{
+    class LemmatizerListener
+    {
+        private Dictionary<String, ILemmatizer> lemmatizersDict = new Dictionary<string, ILemmatizer>();
+
+        private char[] wordInnerSeparator = { '-' };
+        
+
+        private void initializeLemmatizers()
+        {
+            lemmatizersDict.Add("pl", new LemmatizerPrebuiltCompact(LemmaSharp.LanguagePrebuilt.Polish));
+            lemmatizersDict.Add("en", new LemmatizerPrebuiltCompact(LemmaSharp.LanguagePrebuilt.English));
+            lemmatizersDict.Add("hr", new LemmatizerPrebuiltCompact(LemmaSharp.LanguagePrebuilt.Serbian));
+            lemmatizersDict.Add("fr", new LemmatizerPrebuiltCompact(LemmaSharp.LanguagePrebuilt.French));
+        }
+
+        public LemmatizerListener()
+        {
+            initializeLemmatizers();
+        }
+
+        private string lemmatizeSentence(string languageCode, string sentence)
+        {
+            if (lemmatizersDict.ContainsKey(languageCode))
+            {
+                string[] tokens = sentence.Split(null);
+
+                string result = "";
+                foreach (string token in tokens)
+                {
+                    result += lemmatizeWord(languageCode, token) + " ";
+                }
+
+                return result.Trim();
+            }
+            else
+            {
+                //if we can not lemmatize, let's not do it at all
+                //primum non nocere
+                return sentence;
+            }
+        }
+
+        private string lemmatizeWord(string languageCode, string word)
+        {
+            // exceptions
+            if (word.StartsWith("ne_"))
+            {
+                return word;
+            }
+
+
+            Dictionary<String, HashSet<String>> exceptions = new Dictionary<string, HashSet<string>>();
+
+            HashSet<String> plExceptions = new HashSet<string>();
+            plExceptions.Add("i");
+            plExceptions.Add("o");
+            plExceptions.Add("do");
+            exceptions.Add("pl", plExceptions);
+
+            HashSet<String> enExceptions = new HashSet<string>();
+            enExceptions.Add("d");
+            exceptions.Add("en", enExceptions);
+
+            HashSet<String> languageExceptions;
+            if (exceptions.TryGetValue(languageCode, out languageExceptions))
+            {
+                if(languageExceptions.Contains(word))
+                {
+                    return word;
+                }
+            }
+
+
+            string result = "";
+            string[] parts = word.Split(wordInnerSeparator);
+            if (parts.Length == 2)
+            {
+                string firstPart = parts[0];
+                if (!parts[0].EndsWith("o"))
+                {
+                    firstPart = lemmatizersDict[languageCode].Lemmatize(firstPart);
+                }
+                string secondPart = lemmatizersDict[languageCode].Lemmatize(parts[1]);
+                result = firstPart + "-" + secondPart;
+            }
+            else
+            {
+                result = lemmatizersDict[languageCode].Lemmatize(word);
+            }
+
+            if (result == "")
+            {
+                return word;
+            }
+            else
+            {
+                return result;
+            }
+        }
+
+        public void DoListening()
+        {
+            // Data buffer for incoming data.  
+            byte[] bytes = new Byte[1024];
+
+            string data;
+
+            // Establish the local endpoint for the socket.  
+            IPAddress ipAddress = IPAddress.Parse("127.0.0.1");
+            IPEndPoint localEndPoint = new IPEndPoint(ipAddress, 11000);
+
+            // Create a TCP/IP socket.  
+            Socket listener = new Socket(AddressFamily.InterNetwork,
+                SocketType.Stream, ProtocolType.Tcp);
+
+            // Bind the socket to the local endpoint and   
+            // listen for incoming connections.  
+            try
+            {
+                listener.Bind(localEndPoint);
+                listener.Listen(10);
+
+                // Start listening for connections.  
+                while (true)
+                {
+                    // Program is suspended while waiting for an incoming connection.  
+                    Socket handler = listener.Accept();
+                    data = null;
+
+                    // An incoming connection needs to be processed.  
+                    while (true)
+                    {
+                        bytes = new byte[1024];
+                        int bytesRec = handler.Receive(bytes);
+                        data += Encoding.UTF8.GetString(bytes, 0, bytesRec);
+                        if (data.IndexOf("@#@") > -1)
+                        {
+                            break;
+                        }
+                    }
+
+                    data = data.Substring(0, data.IndexOf("@#@"));
+
+                    string languageCode = data.Substring(0, 2);
+                    string sentence = data.Substring(2);
+
+
+                    // Show the data on the console.  
+                    // Console.WriteLine("Sentence received : "+ sentence + ", language code : "+languageCode);
+
+                    // Send lemmatized data back to client.  
+                    byte[] msg = Encoding.UTF8.GetBytes(lemmatizeSentence(languageCode, sentence) + "@#@");
+
+                    handler.Send(msg);
+                    handler.Shutdown(SocketShutdown.Both);
+                    handler.Close();
+                }
+
+            }
+            catch (Exception e)
+            {
+                Console.WriteLine(e.ToString());
+            }
+
+        }
+
+
+    }
+}

LemmaGenSockets/Program.cs

@@ -0,0 +1,26 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Text;
+using System.Net;
+using System.Net.Sockets;
+using System.Threading.Tasks;
+using LemmaSharp;
+
+namespace LemmaGenSockets
+{
+    class Program
+    {
+
+        // Incoming data from the client.  
+        public static string data = null;
+
+
+
+        static void Main(string[] args)
+        {
+            LemmatizerListener listener = new LemmatizerListener();
+            listener.DoListening();
+        }
+    }
+}

LemmaGenSockets/Properties/AssemblyInfo.cs

@@ -0,0 +1,36 @@
+using System.Reflection;
+using System.Runtime.CompilerServices;
+using System.Runtime.InteropServices;
+
+// General Information about an assembly is controlled through the following 
+// set of attributes. Change these attribute values to modify the information
+// associated with an assembly.
+[assembly: AssemblyTitle("LemmaGenSockets")]
+[assembly: AssemblyDescription("")]
+[assembly: AssemblyConfiguration("")]
+[assembly: AssemblyCompany("")]
+[assembly: AssemblyProduct("LemmaGenSockets")]
+[assembly: AssemblyCopyright("Copyright ©  2017")]
+[assembly: AssemblyTrademark("")]
+[assembly: AssemblyCulture("")]
+
+// Setting ComVisible to false makes the types in this assembly not visible 
+// to COM components.  If you need to access a type in this assembly from 
+// COM, set the ComVisible attribute to true on that type.
+[assembly: ComVisible(false)]
+
+// The following GUID is for the ID of the typelib if this project is exposed to COM
+[assembly: Guid("3098bc55-2cc9-4612-9f79-8c812b3be539")]
+
+// Version information for an assembly consists of the following four values:
+//
+//      Major Version
+//      Minor Version 
+//      Build Number
+//      Revision
+//
+// You can specify all the values or you can default the Build and Revision Numbers 
+// by using the '*' as shown below:
+// [assembly: AssemblyVersion("1.0.*")]
+[assembly: AssemblyVersion("1.0.0.0")]
+[assembly: AssemblyFileVersion("1.0.0.0")]

LemmaGenSockets/bin/Debug/LemmaGenSockets.exe.config

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<configuration>
+    <startup> 
+        <supportedRuntime version="v4.0" sku=".NETFramework,Version=v4.5.2" />
+    </startup>
+</configuration>

LemmaGenSockets/bin/Debug/LemmaGenSockets.vshost.exe.config

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="utf-8" ?>
+<configuration>
+    <startup> 
+        <supportedRuntime version="v4.0" sku=".NETFramework,Version=v4.5.2" />
+    </startup>
+</configuration>

LemmaGenSockets/bin/Debug/LemmaGenSockets.vshost.exe.manifest

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<assembly xmlns="urn:schemas-microsoft-com:asm.v1" manifestVersion="1.0">
+  <assemblyIdentity version="1.0.0.0" name="MyApplication.app"/>
+  <trustInfo xmlns="urn:schemas-microsoft-com:asm.v2">
+    <security>
+      <requestedPrivileges xmlns="urn:schemas-microsoft-com:asm.v3">
+        <requestedExecutionLevel level="asInvoker" uiAccess="false"/>
+      </requestedPrivileges>
+    </security>
+  </trustInfo>
+</assembly>

LemmaGenSockets/obj/Debug/LemmaGenSockets.csproj.FileListAbsolute.txt

@@ -0,0 +1,21 @@
+j:\documents\visual studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaGenSockets.exe.config
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaGenSockets.exe
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaGenSockets.pdb
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaSharp.dll
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaSharpPrebuilt.dll
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaSharpPrebuiltCompact.dll
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\bin\Debug\Lzma#.dll
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.csprojResolveAssemblyReference.cache
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.exe
+j:\Documents\Visual Studio 2015\Projects\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.pdb
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaGenSockets.exe.config
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaGenSockets.exe
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaGenSockets.pdb
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaSharp.dll
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaSharpPrebuilt.dll
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\LemmaSharpPrebuiltCompact.dll
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\bin\Debug\Lzma#.dll
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.csprojResolveAssemblyReference.cache
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.csproj.CoreCompileInputs.cache
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.exe
+J:\projects\concordia-server\LemmaGenSockets\LemmaGenSockets\obj\Debug\LemmaGenSockets.pdb