-
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'move_preprocess_logic_to_toolkit' of https://github.com…
…/sillsdev/serval into move_preprocess_logic_to_toolkit
- Loading branch information
Showing
5 changed files
with
125 additions
and
39 deletions.
There are no files selected for viewing
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
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
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
49 changes: 25 additions & 24 deletions
49
src/ServiceToolkit/test/SIL.ServiceToolkit.Tests/SIL.ServiceToolkit.Tests.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 |
|---|---|---|
| @@ -1,32 +1,33 @@ | ||
| <Project Sdk="Microsoft.NET.Sdk"> | ||
|
|
||
| <PropertyGroup> | ||
| <TargetFramework>net8.0</TargetFramework> | ||
| <ImplicitUsings>enable</ImplicitUsings> | ||
| <Nullable>enable</Nullable> | ||
| </PropertyGroup> | ||
| <PropertyGroup> | ||
| <TargetFramework>net8.0</TargetFramework> | ||
| <ImplicitUsings>enable</ImplicitUsings> | ||
| <Nullable>enable</Nullable> | ||
| <RootNamespace>SIL.ServiceToolkit</RootNamespace> | ||
| </PropertyGroup> | ||
|
|
||
| <ItemGroup> | ||
| <PackageReference Include="coverlet.collector" Version="6.0.0"> | ||
| <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets> | ||
| <PrivateAssets>all</PrivateAssets> | ||
| </PackageReference> | ||
| <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.8.0" /> | ||
| <PackageReference Include="NSubstitute" Version="5.1.0" /> | ||
| <PackageReference Include="NSubstitute.Analyzers.CSharp" Version="1.0.16"> | ||
| <PrivateAssets>all</PrivateAssets> | ||
| <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets> | ||
| </PackageReference> | ||
| <PackageReference Include="NUnit" Version="4.0.1" /> | ||
| <PackageReference Include="NUnit3TestAdapter" Version="4.5.0" /> | ||
| <PackageReference Include="NUnit.Analyzers" Version="4.0.0"> | ||
| <PrivateAssets>all</PrivateAssets> | ||
| <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets> | ||
| </PackageReference> | ||
| <PackageReference Include="coverlet.collector" Version="6.0.0"> | ||
| <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets> | ||
| <PrivateAssets>all</PrivateAssets> | ||
| </PackageReference> | ||
| <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.8.0" /> | ||
| <PackageReference Include="NSubstitute" Version="5.1.0" /> | ||
| <PackageReference Include="NSubstitute.Analyzers.CSharp" Version="1.0.16"> | ||
| <PrivateAssets>all</PrivateAssets> | ||
| <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets> | ||
| </PackageReference> | ||
| <PackageReference Include="NUnit" Version="4.0.1" /> | ||
| <PackageReference Include="NUnit3TestAdapter" Version="4.5.0" /> | ||
| <PackageReference Include="NUnit.Analyzers" Version="4.0.0"> | ||
| <PrivateAssets>all</PrivateAssets> | ||
| <IncludeAssets>runtime; build; native; contentfiles; analyzers; buildtransitive</IncludeAssets> | ||
| </PackageReference> | ||
| </ItemGroup> | ||
|
|
||
| <ItemGroup> | ||
| <ProjectReference Include="../../src/SIL.ServiceToolkit/SIL.ServiceToolkit.csproj"/> | ||
| </ItemGroup> | ||
| <ItemGroup> | ||
| <ProjectReference Include="../../src/SIL.ServiceToolkit/SIL.ServiceToolkit.csproj" /> | ||
| </ItemGroup> | ||
|
|
||
| </Project> |
95 changes: 95 additions & 0 deletions
95
...viceToolkit/test/SIL.ServiceToolkit.Tests/Services/ParallelCorpusProcessorServiceTests.cs
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 +1,95 @@ | ||
| namespace SIL.ServiceToolkit.Services; | ||
|
|
||
| [TestFixture] | ||
| public class ParallelCorpusPreprocessorServiceTests | ||
| { | ||
| private static readonly string TestDataPath = Path.Combine( | ||
| AppContext.BaseDirectory, | ||
| "..", | ||
| "..", | ||
| "..", | ||
| "Services", | ||
| "data" | ||
| ); | ||
|
|
||
| [Test] | ||
| public void TestParallelCorpusPreprocessor() | ||
| { | ||
| ParallelCorpusPreprocessingService processor = new(new CorpusService()); | ||
| List<ParallelCorpus> corpora = | ||
| [ | ||
| new() | ||
| { | ||
| Id = "corpus1", | ||
| SourceCorpora = | ||
| [ | ||
| new() | ||
| { | ||
| Id = "source-corpus1", | ||
| Language = "en", | ||
| Files = | ||
| [ | ||
| new() | ||
| { | ||
| TextId = "textId1", | ||
| Format = FileFormat.Text, | ||
| Location = Path.Combine(TestDataPath, "source1.txt") | ||
| } | ||
| ] | ||
| }, | ||
| new() | ||
| { | ||
| Id = "source-corpus2", | ||
| Language = "en", | ||
| Files = | ||
| [ | ||
| new() | ||
| { | ||
| TextId = "textId1", | ||
| Format = FileFormat.Text, | ||
| Location = Path.Combine(TestDataPath, "source2.txt") | ||
| } | ||
| ] | ||
| } | ||
| ], | ||
| TargetCorpora = | ||
| [ | ||
| new() | ||
| { | ||
| Id = "target-corpus1", | ||
| Language = "en", | ||
| Files = | ||
| [ | ||
| new() | ||
| { | ||
| TextId = "textId1", | ||
| Format = FileFormat.Text, | ||
| Location = Path.Combine(TestDataPath, "target1.txt") | ||
| } | ||
| ] | ||
| } | ||
| ] | ||
| } | ||
| ]; | ||
| int trainCount = 0; | ||
| int pretranslateCount = 0; | ||
| processor.Preprocess( | ||
| corpora, | ||
| row => | ||
| { | ||
| if (row.SourceSegment.Length > 0 && row.TargetSegment.Length > 0) | ||
| trainCount++; | ||
| }, | ||
| (row, corpus) => | ||
| { | ||
| pretranslateCount++; | ||
| }, | ||
| false | ||
| ); | ||
| Assert.Multiple(() => | ||
| { | ||
| Assert.That(trainCount, Is.EqualTo(2)); | ||
| Assert.That(pretranslateCount, Is.EqualTo(3)); | ||
| }); | ||
| } | ||
| } |