Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Browse files
Browse the repository at this point in the history
added sample to list article to article links
- Loading branch information
Showing
4 changed files
with
154 additions
and
12 deletions.
There are no files selected for viewing
63 changes: 63 additions & 0 deletions
63
ListArticleToArticleLinks/ListArticleToArticleLinks.csproj
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,63 @@ | ||
<?xml version="1.0" encoding="utf-8"?> | ||
<Project ToolsVersion="4.0" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003"> | ||
<PropertyGroup> | ||
<Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration> | ||
<Platform Condition=" '$(Platform)' == '' ">x86</Platform> | ||
<ProductVersion>8.0.30703</ProductVersion> | ||
<SchemaVersion>2.0</SchemaVersion> | ||
<ProjectGuid>{A9CE01F9-D7DE-41DF-ADA2-B1057CD245AC}</ProjectGuid> | ||
<OutputType>Exe</OutputType> | ||
<AppDesignerFolder>Properties</AppDesignerFolder> | ||
<RootNamespace>ListArticleToArticleLinks</RootNamespace> | ||
<AssemblyName>ListArticleToArticleLinks</AssemblyName> | ||
<TargetFrameworkVersion>v4.0</TargetFrameworkVersion> | ||
<TargetFrameworkProfile>Client</TargetFrameworkProfile> | ||
<FileAlignment>512</FileAlignment> | ||
</PropertyGroup> | ||
<PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|x86' "> | ||
<PlatformTarget>x86</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|x86' "> | ||
<PlatformTarget>x86</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="Microsoft.CSharp" /> | ||
<Reference Include="System.Data" /> | ||
<Reference Include="System.Xml" /> | ||
</ItemGroup> | ||
<ItemGroup> | ||
<Compile Include="Program.cs" /> | ||
<Compile Include="Properties\AssemblyInfo.cs" /> | ||
</ItemGroup> | ||
<ItemGroup> | ||
<ProjectReference Include="..\Wikipedia SQL dump parser\Wikipedia SQL dump parser.csproj"> | ||
<Project>{F9AF62EB-FCC2-4739-8C6B-436A67D3A835}</Project> | ||
<Name>Wikipedia SQL dump parser</Name> | ||
</ProjectReference> | ||
</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> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,30 @@ | ||
using System; | ||
using System.Linq; | ||
using WpSqlDumpParser; | ||
using WpSqlDumpParser.EntityCollections; | ||
using WpSqlDumpParser.IO; | ||
|
||
namespace ListArticleToArticleLinks | ||
{ | ||
static class Program | ||
{ | ||
static void Main() | ||
{ | ||
// path, where the dumps will be downloaded | ||
CachingStream.CachePath = @"C:\Wikipedia dumps"; | ||
|
||
// we won't need other pages, so there's no need to load them into memory | ||
Pages.Instance.Limiter = pages => pages.Where(p => p.Namespace == Namespaces.Article); | ||
|
||
var pageLinks = PageLinks.Instance.Get("enwiki", DumpsManager.GetLastDumpDate("enwiki")); | ||
|
||
var articleToArticleLinks = | ||
pageLinks.Where( | ||
pl => pl.From != null // because of page limiter above, this will give only links from articles | ||
&& pl.ToNamespace == Namespaces.Article); // only links to articles | ||
|
||
foreach (var link in articleToArticleLinks) | ||
Console.WriteLine("{0}->{1}", link.From.Title, link.ToTitle); | ||
} | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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("ListArticleToArticleLinks")] | ||
[assembly: AssemblyDescription("")] | ||
[assembly: AssemblyConfiguration("")] | ||
[assembly: AssemblyCompany("")] | ||
[assembly: AssemblyProduct("ListArticleToArticleLinks")] | ||
[assembly: AssemblyCopyright("Copyright © 2012")] | ||
[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("a0cace9f-fc97-41c8-9f5a-79fac989e651")] | ||
|
||
// 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")] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters