Lucene API comparison tool, #1022

.gitignore

@@ -42,6 +42,7 @@ test-files/analysis/data/
 out.dot
 release/
 _artifacts/
+download/
 
 # NuGet v3's project.json files produces more ignoreable files
 *.nuget.props
@@ -67,4 +68,8 @@ svn-*/
 
 # Visual Studio Code/Rider files
 .vscode/
-.idea/
+**/.idea/
+
+# macOS
+.DS_Store
+

Lucene.Net.sln

@@ -46,6 +46,8 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Solution Items", "Solution
 		NOTICE.txt = NOTICE.txt
 		NuGet.config = NuGet.config
 		README.md = README.md
+		apicheck.ps1 = apicheck.ps1
+		apicheck-config.jsonc = apicheck-config.jsonc
 	EndProjectSection
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Lucene.Net", "src\Lucene.Net\Lucene.Net.csproj", "{3A0AA37E-2B7B-4416-B528-DA4E0E6A6706}"
@@ -208,6 +210,9 @@ EndProject
 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Lucene.Net.TestFramework.TestData.NUnit", "src\dotnet\Lucene.Net.TestFramework.TestData.NUnit\Lucene.Net.TestFramework.TestData.NUnit.csproj", "{6E131ACF-D27A-45AF-923B-A1932EB11E2D}"
 EndProject
 Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Lucene.Net.Tests.TestFramework.NUnitExtensions", "src\Lucene.Net.Tests.TestFramework.NUnitExtensions\Lucene.Net.Tests.TestFramework.NUnitExtensions.csproj", "{724CFF92-5ED6-4F7D-9D2C-53ABA0589F37}"
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Lucene.Net.ApiCheck", "src\dotnet\Lucene.Net.ApiCheck\Lucene.Net.ApiCheck.csproj", "{8CF1AE3D-31C3-436E-B08B-1DD026D3F375}"
+EndProject
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Lucene.Net.Tests.ApiCheck", "src\dotnet\Lucene.Net.Tests.ApiCheck\Lucene.Net.Tests.ApiCheck.csproj", "{87E78608-D8B8-43FE-9235-B594C5EFBEC7}"
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
@@ -503,6 +508,14 @@ Global
 		{724CFF92-5ED6-4F7D-9D2C-53ABA0589F37}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{724CFF92-5ED6-4F7D-9D2C-53ABA0589F37}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{724CFF92-5ED6-4F7D-9D2C-53ABA0589F37}.Release|Any CPU.Build.0 = Release|Any CPU
+		{8CF1AE3D-31C3-436E-B08B-1DD026D3F375}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{8CF1AE3D-31C3-436E-B08B-1DD026D3F375}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{8CF1AE3D-31C3-436E-B08B-1DD026D3F375}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{8CF1AE3D-31C3-436E-B08B-1DD026D3F375}.Release|Any CPU.Build.0 = Release|Any CPU
+		{87E78608-D8B8-43FE-9235-B594C5EFBEC7}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{87E78608-D8B8-43FE-9235-B594C5EFBEC7}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{87E78608-D8B8-43FE-9235-B594C5EFBEC7}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{87E78608-D8B8-43FE-9235-B594C5EFBEC7}.Release|Any CPU.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -522,6 +535,8 @@ Global
 		{FED4A824-1F32-4948-8D37-2B7610804DB5} = {42599646-275F-4970-BC60-A3349F6498CC}
 		{C0448DD3-68D2-485F-B31A-D2806E589FA7} = {42599646-275F-4970-BC60-A3349F6498CC}
 		{6E131ACF-D27A-45AF-923B-A1932EB11E2D} = {8CA61D33-3590-4024-A304-7B1F75B50653}
+		{8CF1AE3D-31C3-436E-B08B-1DD026D3F375} = {8CA61D33-3590-4024-A304-7B1F75B50653}
+		{87E78608-D8B8-43FE-9235-B594C5EFBEC7} = {8CA61D33-3590-4024-A304-7B1F75B50653}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {9F2179CC-CFD2-4419-AB74-D72856931F36}

Lucene.Net.sln.DotSettings

@@ -1,10 +1,24 @@
 <wpf:ResourceDictionary xml:space="preserve" xmlns:x="http://schemas.microsoft.com/winfx/2006/xaml" xmlns:s="clr-namespace:System;assembly=mscorlib" xmlns:ss="urn:shemas-jetbrains-com:settings-storage-xaml" xmlns:wpf="http://schemas.microsoft.com/winfx/2006/xaml/presentation">
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=carrotsearch/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=charfilter/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=Coord/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=csharpsquid/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=docvalues/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=egothor/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=intblock/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=kuromoji/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=LUCENENET/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=stopword/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=stopwords/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=streamutils/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=subdir/@EntryIndexedValue">True</s:Boolean>
 	<s:Boolean x:Key="/Default/UserDictionary/Words/=synch/@EntryIndexedValue">True</s:Boolean>
-	<s:Boolean x:Key="/Default/UserDictionary/Words/=testsettings/@EntryIndexedValue">True</s:Boolean></wpf:ResourceDictionary>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=queryparser/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=randomizedtesting/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=smartcn/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=stempel/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=testsettings/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=tokenattributes/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=trec/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=valuesource/@EntryIndexedValue">True</s:Boolean>
+	<s:Boolean x:Key="/Default/UserDictionary/Words/=writercache/@EntryIndexedValue">True</s:Boolean></wpf:ResourceDictionary>

apicheck-config.jsonc

@@ -0,0 +1,111 @@
+{
+    "libraries": [
+        {
+            "luceneNetName": "Lucene.Net",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.Common",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.Kuromoji",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.Morfologik",
+            "mavenDependencies": [
+                "org.carrot2:morfologik-stemming:1.7.1",
+                "org.carrot2:morfologik-fsa:1.7.1",
+                "org.carrot2:morfologik-polish:1.7.1"
+            ]
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.OpenNLP",
+            "mavenDependencies": [
+                "org.apache.opennlp:opennlp-tools:1.9.1",
+            ]
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.Phonetic",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.SmartCn",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Analysis.Stempel",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Benchmark",
+            "mavenDependencies": [
+                "com.ibm.icu:icu4j:53.1",
+                "org.apache.commons:commons-compress:1.7"
+            ]
+        },
+        {
+            "luceneNetName": "Lucene.Net.Classification",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Codecs",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Demo",
+            "mavenDependencies": [
+                "javax.servlet:servlet-api:2.4",
+                "org.antlr:antlr-runtime:3.5",
+                "org.ow2.asm:asm:4.1",
+                "org.ow2.asm:asm-commons:4.1",
+            ]
+        },
+        {
+            "luceneNetName": "Lucene.Net.Expressions",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Facet",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Grouping",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Highlighter",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Join",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Memory",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Misc",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Queries",
+        },
+        {
+            "luceneNetName": "Lucene.Net.QueryParser",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Replicator",
+        },
+        {
+            "luceneNetName": "Lucene.Net.Sandbox",
+            "mavenDependencies": [
+                "jakarta-regexp:jakarta-regexp:1.4"
+            ]
+        },
+        {
+            "luceneNetName": "Lucene.Net.Spatial",
+            "mavenDependencies": [
+                "com.spatial4j:spatial4j:0.4.1"
+            ]
+        },
+        {
+            "luceneNetName": "Lucene.Net.Suggest",
+        },
+        {
+            "luceneNetName": "Lucene.Net.TestFramework",
+            "mavenDependencies": [
+                "junit:junit:4.10",
+                "com.carrotsearch.randomizedtesting:randomizedtesting-runner:2.1.3",
+                "com.carrotsearch.randomizedtesting:junit4-ant:2.1.3",
+            ]
+        }
+    ]
+}

apicheck.ps1

@@ -0,0 +1,80 @@
+param (
+    [switch] $clean = $false
+)
+
+$ErrorActionPreference = "Stop"
+
+# The Java API extractor lives in its own Apache-licensed repository:
+#   https://github.com/paulirwin/java-api-extractor
+# We download the pre-built shaded ("fat") jar from a pinned GitHub Release and run it with `java -jar`.
+#
+# Requirements:
+#   - The GitHub CLI (`gh`) must be installed and authenticated (`gh auth login`).
+#     It is used to download the release asset.
+#   - A Java 21+ runtime on PATH (the extractor targets Java 21).
+
+$extractorRepo = "paulirwin/java-api-extractor"
+$extractorVersion = "v0.1.0"
+# The release attaches the shaded fat jar named "<artifact>-<version>-all.jar".
+$jarAssetPattern = "*-all.jar"
+
+$dotnetProjectPath = "src/dotnet/Lucene.Net.ApiCheck/Lucene.Net.ApiCheck.csproj"
+$configFilePath = "apicheck-config.jsonc"
+$jarCachePath = "_artifacts/java-api-extractor/$extractorVersion"
+$downloadPath = "_artifacts/lucene-api-extractor/download"
+$outputPath = "_artifacts/lucene-api-extractor/output"
+
+if ($clean)
+{
+    # delete existing output and cached jar
+    Remove-Item -Recurse -Force $outputPath -ErrorAction SilentlyContinue
+    Remove-Item -Recurse -Force $jarCachePath -ErrorAction SilentlyContinue
+}
+
+# create download, output, and jar cache paths recursively
+New-Item -ItemType Directory -Force -Path $downloadPath -InformationAction SilentlyContinue -ErrorAction SilentlyContinue | Out-Null
+New-Item -ItemType Directory -Force -Path $outputPath -InformationAction SilentlyContinue -ErrorAction SilentlyContinue | Out-Null
+New-Item -ItemType Directory -Force -Path $jarCachePath -InformationAction SilentlyContinue -ErrorAction SilentlyContinue | Out-Null
+
+# Reuse a previously downloaded jar if present (use -clean to force a fresh download).
+$jarFile = Get-ChildItem -Path $jarCachePath -Filter $jarAssetPattern -ErrorAction SilentlyContinue | Select-Object -First 1
+
+if (-not $jarFile)
+{
+    # The download requires the GitHub CLI.
+    if (-not (Get-Command gh -ErrorAction SilentlyContinue))
+    {
+        Write-Host "The GitHub CLI ('gh') is required to download the java-api-extractor jar but was not found on PATH."
+        Write-Host "Install it from https://cli.github.com/ and run 'gh auth login', then re-run this script."
+        exit 1
+    }
+
+    Write-Host "Downloading java-api-extractor $extractorVersion fat jar from $extractorRepo..."
+    gh release download $extractorVersion --repo $extractorRepo --pattern $jarAssetPattern --dir $jarCachePath --clobber
+
+    if ($LASTEXITCODE -ne 0)
+    {
+        Write-Host "Failed to download the java-api-extractor release asset. Exiting."
+        exit $LASTEXITCODE
+    }
+
+    $jarFile = Get-ChildItem -Path $jarCachePath -Filter $jarAssetPattern -ErrorAction SilentlyContinue | Select-Object -First 1
+
+    if (-not $jarFile)
+    {
+        Write-Host "Download succeeded but no jar matching '$jarAssetPattern' was found in $jarCachePath. Exiting."
+        exit 1
+    }
+}
+
+Write-Host "Jar file: $($jarFile.FullName)"
+
+if ($clean) {
+    # Clean the API Check project
+    Write-Host "Cleaning API Check project..."
+    dotnet clean $dotnetProjectPath
+}
+
+# Run the API check
+Write-Host "Running API check..."
+dotnet run --project $dotnetProjectPath -- report -j $jarFile.FullName -c $configFilePath -o $outputPath -d $downloadPath

src/Lucene.Net.Analysis.Common/Properties/AssemblyInfo.cs

@@ -19,6 +19,7 @@
  *
  */
 
+using Lucene.Net.Reflection;
 using System;
 using System.Reflection;
 using System.Runtime.InteropServices;
@@ -38,3 +39,7 @@
 
 // The following GUID is for the ID of the typelib if this project is exposed to COM
 [assembly: Guid("f57314a7-e71f-4b3c-860f-564046ca398b")]
+
+[assembly: LuceneMavenMapping("org.apache.lucene", "lucene-analyzers-common", "4.8.1")]
+[assembly: LucenePackageMapping("Lucene.Net.Analysis.CharFilters", "org.apache.lucene.analysis.charfilter")]
+[assembly: LucenePackageMapping("Lucene.Net.Tartarus.Snowball", "org.tartarus.snowball")]

src/Lucene.Net.Analysis.Kuromoji/Properties/AssemblyInfo.cs

@@ -15,6 +15,7 @@
 * limitations under the License.
 */
 
+using Lucene.Net.Reflection;
 using System;
 using System.Reflection;
 using System.Runtime.InteropServices;
@@ -34,3 +35,5 @@
 
 // The following GUID is for the ID of the typelib if this project is exposed to COM
 [assembly: Guid("8408625a-2508-46d5-8519-045183c43724")]
+
+[assembly: LuceneMavenMapping("org.apache.lucene", "lucene-analyzers-kuromoji", "4.8.1")]

src/Lucene.Net.Analysis.Morfologik/Lucene.Net.Analysis.Morfologik.csproj

@@ -39,20 +39,10 @@
     <NoWarn>$(NoWarn);1591;1573</NoWarn>
   </PropertyGroup>
 
-
-
-  <ItemGroup>
-    <Compile Remove="Properties\AssemblyInfo.cs" />
-  </ItemGroup>
-
   <ItemGroup>
     <EmbeddedResource Include="Uk/**/*" Exclude="*.cs" />
   </ItemGroup>
 
-  <ItemGroup>
-    <None Include="Properties\AssemblyInfo.cs" />
-  </ItemGroup>
-
   <ItemGroup>
     <PackageReference Include="Morfologik.Fsa" Version="$(MorfologikFsaPackageVersion)" />
     <PackageReference Include="Morfologik.Polish" Version="$(MorfologikPolishPackageVersion)" />

src/Lucene.Net.Analysis.Morfologik/Morfologik/TokenAttributes/MorphosyntacticTagsAttribute.cs

@@ -1,4 +1,6 @@
 // Lucene version compatibility level 8.2.0
+
+using Lucene.Net.Reflection;
 using Lucene.Net.Util;
 using System.Collections.Generic;
 using System.Text;
@@ -27,6 +29,7 @@ namespace Lucene.Net.Analysis.Morfologik.TokenAttributes
     /// surface forms. For the exact format and description of these,
     /// see the project's documentation.
     /// </summary>
+    [LuceneType("org.apache.lucene.analysis.morfologik", "MorphosyntacticTagsAttribute", Justification = "Namespace/package mismatch, not able to be inferred by convention")]
     public interface IMorphosyntacticTagsAttribute : IAttribute
     {
         /// <summary>

src/Lucene.Net.Analysis.Morfologik/Morfologik/TokenAttributes/MorphosyntacticTagsAttributeImpl.cs

@@ -1,4 +1,6 @@
 // Lucene version compatibility level 8.2.0
+
+using Lucene.Net.Reflection;
 using Lucene.Net.Util;
 using System;
 using System.Collections.Generic;
@@ -29,6 +31,7 @@ namespace Lucene.Net.Analysis.Morfologik.TokenAttributes
     /// Morphosyntactic annotations for surface forms.
     /// </summary>
     /// <seealso cref="IMorphosyntacticTagsAttribute"/>
+    [LuceneType("org.apache.lucene.analysis.morfologik", "MorphosyntacticTagsAttributeImpl", Justification = "Namespace/package mismatch, not able to be inferred by convention")]
     public class MorphosyntacticTagsAttribute : Attribute, IMorphosyntacticTagsAttribute // LUCENENET specific: Not implementing ICloneable per Microsoft's recommendation
     {
         /// <summary>Initializes this attribute with no tags</summary>

src/Lucene.Net.Analysis.Morfologik/Properties/AssemblyInfo.cs

@@ -15,6 +15,7 @@
 * limitations under the License.
 */
 
+using Lucene.Net.Reflection;
 using System;
 using System.Reflection;
 using System.Runtime.CompilerServices;
@@ -35,3 +36,5 @@
 
 // The following GUID is for the ID of the typelib if this project is exposed to COM
 [assembly: Guid("2e4a99a0-c52e-4e66-9246-69ef75124b61")]
+
+[assembly: LuceneMavenMapping("org.apache.lucene", "lucene-analyzers-morfologik", "4.8.1")]

src/Lucene.Net.Analysis.OpenNLP/Properties/AssemblyInfo.cs

@@ -15,9 +15,9 @@
 * limitations under the License.
 */
 
+using Lucene.Net.Reflection;
 using System;
 using System.Reflection;
-using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
 
 // General Information about an assembly is controlled through the following
@@ -35,3 +35,5 @@
 
 // The following GUID is for the ID of the typelib if this project is exposed to COM
 [assembly: Guid("7695c395-37dd-42d1-af27-6e0bf82bdb15")]
+
+[assembly: LuceneMavenMapping("org.apache.lucene", "lucene-analyzers-opennlp", "8.2.0")]