#1-4 ルビ検出の正規表現を厳格に修正

OUCC · Apr 5, 2024 · ca0a6cf · ca0a6cf
1 parent acdfb43
commit ca0a6cf
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/Epub/KoeBook.Epub/Services/AnalyzerService.cs b/Epub/KoeBook.Epub/Services/AnalyzerService.cs
@@ -12,8 +12,7 @@ public partial class AnalyzerService(IScraperSelectorService scrapingService, IE
 {
     private readonly IScraperSelectorService _scrapingService = scrapingService;
     private readonly IEpubDocumentStoreService _epubDocumentStoreService = epubDocumentStoreService;
-    private readonly ILlmAnalyzerService _llmAnalyzerService = llmAnalyzerService;
-    private Dictionary<string, string> _rubyReplacements = new Dictionary<string, string>();
+    private readonly ILlmAnalyzerService _llmAnalyzerService = llmAnalyzerService; 
 
     public async ValueTask<BookScripts> AnalyzeAsync(BookProperties bookProperties, string tempDirectory, CancellationToken cancellationToken)
     {
@@ -76,6 +75,6 @@ private static string ReplaceBaseTextWithRuby(string text)
         return RubyRegex().Replace(text, m => m.Groups[2].Value);
     }
 
-    [GeneratedRegex("<ruby><rb>(.*?)</rb><rp>（</rp><rt>(.*?)</rt><rp>）</rp></ruby>")]
+    [GeneratedRegex(@"<ruby>\s*<rb>(.*?)</rb>\s*<rp>\s*[（《\(]\s*</rp>\s*<rt>(.*?)</rt>\s*<rp>\s*[）》\)]\s*</rp>\s*</ruby>", RegexOptions.Multiline)]
     private static partial Regex RubyRegex();
 }
diff --git a/KoeBook.Test/Epub/AnalyzerServiceTest.cs b/KoeBook.Test/Epub/AnalyzerServiceTest.cs
@@ -14,9 +14,10 @@ public class AnalyzerServiceTest
         ああ<ruby><rb>漢字</rb><rp>（</rp><rt>かんじ</rt><rp>）</rp></ruby>あああ
         ああ<ruby><rb>漢字1</rb><rp>（</rp><rt>かんじ1</rt><rp>）</rp></ruby>あああ
         """, "ああかんじあああ\nああかんじあああ\nああかんじ1あああ")]
-    [InlineData("<ruby><rb>佐久平</rb><rp>《</rp><rt>さくだいら</rt><rp>》</rp></ruby>　<ruby><rb>啓介</rb><rp>《</rp><rt>けいすけ</rt><rp>》</rp></ruby>",
-        "<ruby><rb>佐久平</rb><rp>《</rp><rt>さくだいら</rt><rp>》</rp></ruby>　<ruby><rb>啓介</rb><rp>《</rp><rt>けいすけ</rt><rp>》</rp></ruby>")]
-    [InlineData("<ruby><rb>漢字</rb>\n<rp>（</rp><rt>かんじ</rt><rp>）</rp></ruby>", "<ruby><rb>漢字</rb>\n<rp>（</rp><rt>かんじ</rt><rp>）</rp></ruby>")]
+    [InlineData("<ruby> <rb>佐久平</rb> <rp>\n《 </rp> <rt>さくだいら</rt> <rp>》</rp>  </ruby>　<ruby><rb>啓介</rb><rp>《</rp><rt>けいすけ</rt><rp>》</rp></ruby>",
+        "さくだいら　けいすけ")]
+    [InlineData("<ruby><rb>漢字</rb>\n<rp>（</rp><rt>かんじ</rt><rp>）</rp></ruby>", "かんじ")]
+    [InlineData("ああ<ruby><rb>漢字</rb><rp>（</rp><rt>かんじ</rt><rp>）</rp></ruby>あああ<ruby><rb>漢字</rb><rp>（</rp><rt>カンジ</rt><rp>）</rp></ruby>", "ああかんじあああカンジ")]
     public void ReplaceBaseTextWithRuby(string input, string expected)
     {
         var result = AnalyzerServiceProxy.ReplaceBaseTextWithRuby(null, input);