Initial commit

ashish01 · Oct 16, 2013 · b1893b4 · b1893b4
1 parent 1b07835
commit b1893b4
Show file tree

Hide file tree

Showing 8 changed files with 1,029 additions and 1 deletion.
diff --git a/CollinsTagger/CollinsTagger.csproj b/CollinsTagger/CollinsTagger.csproj
@@ -0,0 +1,61 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" 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>{A80F8E1D-1A71-4C58-9436-8F332555CC20}</ProjectGuid>
+    <OutputType>Exe</OutputType>
+    <AppDesignerFolder>Properties</AppDesignerFolder>
+    <RootNamespace>CollinsTagger</RootNamespace>
+    <AssemblyName>CollinsTagger</AssemblyName>
+    <TargetFrameworkVersion>v3.5</TargetFrameworkVersion>
+    <FileAlignment>512</FileAlignment>
+    <TargetFrameworkProfile />
+  </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="System" />
+    <Reference Include="System.Core" />
+    <Reference Include="System.Xml.Linq" />
+    <Reference Include="System.Data.DataSetExtensions" />
+    <Reference Include="System.Data" />
+    <Reference Include="System.Xml" />
+  </ItemGroup>
+  <ItemGroup>
+    <Compile Include="MurMur3.cs" />
+    <Compile Include="Program.cs" />
+    <Compile Include="Tagger.cs" />
+    <Compile Include="Trainer.cs" />
+    <Compile Include="Viterbi.cs" />
+  </ItemGroup>
+  <ItemGroup>
+    <Folder Include="Properties\" />
+  </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>
diff --git a/CollinsTagger/CollinsTagger.sln b/CollinsTagger/CollinsTagger.sln
@@ -0,0 +1,20 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio 2012
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "CollinsTagger", "CollinsTagger.csproj", "{A80F8E1D-1A71-4C58-9436-8F332555CC20}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{A80F8E1D-1A71-4C58-9436-8F332555CC20}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{A80F8E1D-1A71-4C58-9436-8F332555CC20}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{A80F8E1D-1A71-4C58-9436-8F332555CC20}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{A80F8E1D-1A71-4C58-9436-8F332555CC20}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+EndGlobal
diff --git a/CollinsTagger/MurMur3.cs b/CollinsTagger/MurMur3.cs
@@ -0,0 +1,111 @@
+/*
+This code is public domain.
+ 
+The MurmurHash3 algorithm was created by Austin Appleby and put into the public domain. See http://code.google.com/p/smhasher/
+ 
+This C# variant was authored by
+Elliott B. Edwards and was placed into the public domain as a gist
+Status...Working on verification (Test Suite)
+Set up to run as a LinqPad (linqpad.net) script (thus the ".Dump()" call)
+*/
+
+using System.IO;
+namespace CollinsTagger
+{
+    public static class MurMurHash3
+    {
+        //Change to suit your needs
+        const uint seed = 144;
+
+        public static int Hash(byte[] data)
+        {
+            const uint c1 = 0xcc9e2d51;
+            const uint c2 = 0x1b873593;
+
+            uint h1 = seed;
+            uint k1 = 0;
+            uint streamLength = 0;
+
+            using (BinaryReader reader = new BinaryReader(new MemoryStream(data)))
+            {
+                byte[] chunk = reader.ReadBytes(4);
+                while (chunk.Length > 0)
+                {
+                    streamLength += (uint)chunk.Length;
+                    switch (chunk.Length)
+                    {
+                        case 4:
+                            /* Get four bytes from the input into an uint */
+                            k1 = (uint)
+                            (chunk[0]
+                            | chunk[1] << 8
+                            | chunk[2] << 16
+                            | chunk[3] << 24);
+
+                            /* bitmagic hash */
+                            k1 *= c1;
+                            k1 = rotl32(k1, 15);
+                            k1 *= c2;
+
+                            h1 ^= k1;
+                            h1 = rotl32(h1, 13);
+                            h1 = h1 * 5 + 0xe6546b64;
+                            break;
+                        case 3:
+                            k1 = (uint)
+                            (chunk[0]
+                            | chunk[1] << 8
+                            | chunk[2] << 16);
+                            k1 *= c1;
+                            k1 = rotl32(k1, 15);
+                            k1 *= c2;
+                            h1 ^= k1;
+                            break;
+                        case 2:
+                            k1 = (uint)
+                            (chunk[0]
+                            | chunk[1] << 8);
+                            k1 *= c1;
+                            k1 = rotl32(k1, 15);
+                            k1 *= c2;
+                            h1 ^= k1;
+                            break;
+                        case 1:
+                            k1 = (uint)(chunk[0]);
+                            k1 *= c1;
+                            k1 = rotl32(k1, 15);
+                            k1 *= c2;
+                            h1 ^= k1;
+                            break;
+                    }
+                    chunk = reader.ReadBytes(4);
+                }
+            }
+            // finalization, magic chants to wrap it all up
+            h1 ^= streamLength;
+            h1 = fmix(h1);
+
+            unchecked //ignore overflow
+            {
+                return (int)h1;
+            }
+        }
+
+        private static uint rotl32(uint x, byte r)
+        {
+            return (x << r) | (x >> (32 - r));
+        }
+
+        private static uint fmix(uint h)
+        {
+            h ^= h >> 16;
+            h *= 0x85ebca6b;
+            h ^= h >> 13;
+            h *= 0xc2b2ae35;
+            h ^= h >> 16;
+            return h;
+        }
+    }
+}
+
+