RemoveUnicodeCharacters: support Subtitle Edit Batch convert

.github/workflows/remove-unicode-characters.yml

@@ -5,11 +5,13 @@ on:
     branches: [main]
     paths:
       - 'se5/RemoveUnicodeCharacters/**'
+      - 'se5/RemoveUnicodeCharacters.Tests/**'
       - 'se5/Plugin-Shared/**'
       - '.github/workflows/remove-unicode-characters.yml'
   pull_request:
     paths:
       - 'se5/RemoveUnicodeCharacters/**'
+      - 'se5/RemoveUnicodeCharacters.Tests/**'
       - 'se5/Plugin-Shared/**'
       - '.github/workflows/remove-unicode-characters.yml'
   workflow_dispatch:
@@ -90,8 +92,22 @@ jobs:
           echo "ref=$ref"          >> "$GITHUB_OUTPUT"
           echo "release=$release_flag" >> "$GITHUB_OUTPUT"
 
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup .NET 8
+        uses: actions/setup-dotnet@v4
+        with:
+          dotnet-version: '8.0.x'
+
+      - name: Test
+        run: dotnet test se5/RemoveUnicodeCharacters.Tests/RemoveUnicodeCharacters.Tests.csproj -c Release
+
   build:
-    needs: prepare
+    needs: [prepare, test]
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false

se5/RemoveUnicodeCharacters.Tests/BatchModeTests.cs

@@ -0,0 +1,121 @@
+using SubtitleEdit.Plugins.RemoveUnicodeCharacters;
+using SubtitleEdit.Plugins.Shared;
+using System.Text.Json;
+
+namespace RemoveUnicodeCharacters.Tests;
+
+/// <summary>Subtitle Edit Batch convert: "batch" applies the batch list headless; Configure edits that list.</summary>
+public class BatchModeTests
+{
+    private static JsonElement Json(string json) => JsonDocument.Parse(json).RootElement.Clone();
+
+    private static PluginRequest Request(string? settingsJson, params string[] texts) => new()
+    {
+        RequestType = PluginRequestType.Batch,
+        Subtitle = new PluginSubtitle
+        {
+            Format = "Advanced Sub Station Alpha",
+            Paragraphs = texts.Select((t, i) => new PluginParagraph { StartMs = i * 1000, EndMs = i * 1000 + 900, Text = t, Style = "Top" }).ToList(),
+        },
+        Settings = settingsJson == null ? null : Json(settingsJson),
+    };
+
+    [Fact]
+    public void Batch_NoSettings_ReplacesOnlyBuiltInDefaults()
+    {
+        var response = BatchMode.BuildBatchResponse(Request(null, "♪ Привет ♫", "don’t", "Plain"));
+
+        Assert.Equal(PluginStatus.Ok, response.Status);
+        Assert.Equal(new[] { "# Привет #", "don’t", "Plain" }, response.Subtitle!.Paragraphs!.Select(p => p.Text));
+        Assert.Equal("Advanced Sub Station Alpha", response.Subtitle.Format);
+        Assert.All(response.Subtitle.Paragraphs!, p => Assert.Equal("Top", p.Style));
+        Assert.Null(response.Settings);
+        Assert.Null(response.SettingsVersion);
+    }
+
+    [Fact]
+    public void Batch_NothingToChange_ReturnsOkWithoutSubtitle()
+    {
+        var response = BatchMode.BuildBatchResponse(Request(null, "Привет", "café"));
+
+        Assert.Equal(PluginStatus.Ok, response.Status);
+        Assert.Null(response.Subtitle);
+    }
+
+    [Fact]
+    public void Batch_NotConfigured_UsesNonBlankWindowReplacementsOnly()
+    {
+        // Blank window entries are also saved for unchecked rows - they must not remove anything in batch.
+        var settings = "{\"replacements\":{\"2019\":\"'\",\"0410\":\"\",\"266A\":\"\"}}";
+
+        var response = BatchMode.BuildBatchResponse(Request(settings, "don’t А ♪ ♫"));
+
+        Assert.Equal("don't А ♪ #", response.Subtitle!.Paragraphs![0].Text);
+    }
+
+    [Fact]
+    public void Batch_ConfiguredList_ReplacesListedAndKeepsOthers()
+    {
+        var settings = "{\"replacements\":{\"2019\":\"'\"},\"batchReplacements\":{\"200B\":\"\",\"2014\":\"-\"},\"batchRemoveOthers\":false}";
+
+        var response = BatchMode.BuildBatchResponse(Request(settings, "a​b — don’t ♪"));
+
+        Assert.Equal("ab - don’t ♪", response.Subtitle!.Paragraphs![0].Text);
+        Assert.Contains("2 ", response.Message);
+    }
+
+    [Fact]
+    public void Batch_RemoveOthers_RemovesUnlistedNonAnsi()
+    {
+        var settings = "{\"batchReplacements\":{\"266A\":\"#\"},\"batchRemoveOthers\":true}";
+
+        var response = BatchMode.BuildBatchResponse(Request(settings, "♪ Привет café ♪"));
+
+        Assert.Equal("#  café #", response.Subtitle!.Paragraphs![0].Text);
+    }
+
+    [Fact]
+    public void Batch_LegacyRequestWithoutParagraphs_ReturnsSubRip()
+    {
+        var request = new PluginRequest
+        {
+            RequestType = PluginRequestType.Batch,
+            Subtitle = new PluginSubtitle { Format = "SubRip", SubRip = "1\n00:00:01,000 --> 00:00:02,000\n♪ Hi\n\n" },
+        };
+
+        var response = BatchMode.BuildBatchResponse(request);
+
+        Assert.Equal("SubRip", response.Subtitle!.Format);
+        Assert.Contains("# Hi", response.Subtitle.Native);
+    }
+
+    [Fact]
+    public void ConfigureSettings_KeepWindowReplacements()
+    {
+        var list = new SortedDictionary<char, string> { ['​'] = "" };
+        var settings = BatchMode.BuildSettings(new Dictionary<string, string> { ["2019"] = "'" }, null, list, removeOthers: true);
+
+        Assert.Equal("'", settings.GetProperty("replacements").GetProperty("2019").GetString());
+        Assert.Equal("", settings.GetProperty("batchReplacements").GetProperty("200B").GetString());
+        Assert.True(settings.GetProperty("batchRemoveOthers").GetBoolean());
+        Assert.Equal(new[] { '​' }, BatchMode.LoadBatchList(settings).Keys);
+    }
+
+    [Fact]
+    public void RunSettings_KeepBatchConfiguration()
+    {
+        var previous = Json("{\"replacements\":{},\"batchReplacements\":{\"2014\":\"-\"},\"batchRemoveOthers\":true}");
+
+        var settings = BatchMode.BuildSettings(new Dictionary<string, string> { ["266A"] = "*" }, previous);
+
+        Assert.Equal("*", settings.GetProperty("replacements").GetProperty("266A").GetString());
+        Assert.Equal("-", settings.GetProperty("batchReplacements").GetProperty("2014").GetString());
+        Assert.True(BatchMode.LoadRemoveOthers(settings));
+    }
+
+    [Fact]
+    public void ParseCharacters_AcceptsGlyphsAndCodes()
+    {
+        Assert.Equal(new[] { '—', '​', '♪' }, BatchMode.ParseCharacters("—abc U+200B u+266a ♪ U+0041"));
+    }
+}

se5/RemoveUnicodeCharacters.Tests/RemoveUnicodeCharacters.Tests.csproj

@@ -0,0 +1,27 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <TargetFramework>net8.0</TargetFramework>
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+    <IsPackable>false</IsPackable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <Using Include="Xunit" />
+  </ItemGroup>
+
+  <PropertyGroup>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.11.1" />
+    <PackageReference Include="xunit" Version="2.9.2" />
+    <PackageReference Include="xunit.runner.visualstudio" Version="2.8.2" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\RemoveUnicodeCharacters\RemoveUnicodeCharacters.csproj" />
+  </ItemGroup>
+
+</Project>