feat(news): add scraper adapters, article deduplication, blocklist service, and remove tracked publish artifacts

FinlyticNews/Database/NewsDbContext.cs

@@ -41,9 +41,9 @@ public class NewsDbContext : DbContext, ISettingsDbContext
     public DbSet<MatchedAssetEntity> MatchedAssets => Set<MatchedAssetEntity>();
 
     /// <summary>
-    /// Gets or sets the database set for microservice configuration settings.
+    /// Gets or sets the database set for blocked news URLs (unindexable or duplicate articles).
     /// </summary>
-    public DbSet<NewsSettingsEntity> Settings => Set<NewsSettingsEntity>();
+    public DbSet<BlockedNewsUrlEntity> BlockedNewsUrls => Set<BlockedNewsUrlEntity>();
 
     /// <summary>
     /// Configures the model mapping, database constraints, and unique indices.
@@ -64,16 +64,27 @@ public class NewsDbContext : DbContext, ISettingsDbContext
             .HasIndex(a => a.SourceUrl)
             .IsUnique();
 
-        // Performance indexes for news queries
+        // Performance & deduplication indexes for news queries
         modelBuilder.Entity<NewsArticleEntity>()
             .HasIndex(a => new { a.PublishedAt, a.ScrapedAt });
 
         modelBuilder.Entity<NewsArticleEntity>()
             .HasIndex(a => a.Status);
 
+        modelBuilder.Entity<NewsArticleEntity>()
+            .HasIndex(a => a.TitleHash);
+
+        modelBuilder.Entity<NewsArticleEntity>()
+            .HasIndex(a => a.SimHash);
+
         modelBuilder.Entity<MatchedAssetEntity>()
             .HasIndex(m => m.Isin);
 
+        // Blocked URLs index
+        modelBuilder.Entity<BlockedNewsUrlEntity>()
+            .HasIndex(b => b.Url)
+            .IsUnique();
+
         // Configure relationship between NewsArticle and MatchedAssets
         modelBuilder.Entity<MatchedAssetEntity>()
             .HasOne(m => m.NewsArticle)