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

FinlyticNews/Entities/BlockedNewsUrlEntity.cs

@@ -0,0 +1,25 @@
+using System;
+using System.ComponentModel.DataAnnotations;
+using System.ComponentModel.DataAnnotations.Schema;
+
+namespace FinlyticNews.Entities;
+
+/// <summary>
+/// Entity representing a blocked news URL (e.g. duplicates, missing content, or no matched assets).
+/// Prevents redundant re-discovery and re-scraping of known bad or duplicate URLs.
+/// </summary>
+[Table("BlockedNewsUrls")]
+public class BlockedNewsUrlEntity
+{
+    [Key]
+    public Guid Id { get; set; } = Guid.NewGuid();
+
+    [Required]
+    [MaxLength(2048)]
+    public string Url { get; set; } = string.Empty;
+
+    [MaxLength(256)]
+    public string Reason { get; set; } = string.Empty;
+
+    public DateTime BlockedAtUtc { get; set; } = DateTime.UtcNow;
+}

FinlyticNews/Entities/NewsArticleEntity.cs

@@ -57,11 +57,22 @@ public class NewsArticleEntity
     public DateTime PublishedAt { get; set; }
 
     /// <summary>
-    /// Gets or sets the processing lifecycle state (e.g., "Pending", "Processing", "Completed", "Analyzed", "Failed").
+    /// Gets or sets the processing lifecycle state (e.g., "Pending", "Processing", "Completed", "Analyzed", "Failed", "Duplicate").
     /// </summary>
     [Required]
     public string Status { get; set; } = "Pending";
 
+    /// <summary>
+    /// Gets or sets the normalized SHA-256 hash of the cleaned title for duplicate detection.
+    /// </summary>
+    [MaxLength(64)]
+    public string? TitleHash { get; set; }
+
+    /// <summary>
+    /// Gets or sets the 64-bit SimHash content fingerprint for fuzzy duplicate text detection.
+    /// </summary>
+    public long? SimHash { get; set; }
+
     /// <summary>
     /// Gets or sets the list of financial assets matched and associated with this news article.
     /// </summary>

FinlyticNews/Entities/NewsSettingsEntity.cs

@@ -1,47 +0,0 @@
-using System;
-using System.ComponentModel.DataAnnotations;
-
-namespace FinlyticNews.Entities;
-
-/// <summary>
-/// Entity representing global runtime settings for the FinlyticNews microservice.
-/// Persisted in PostgreSQL and updated dynamically via Admin Panel MQTT events.
-/// </summary>
-public class NewsSettingsEntity
-{
-    /// <summary>
-    /// Gets or sets the primary key for the settings row.
-    /// </summary>
-    [Key]
-    public Guid Id { get; set; }
-
-    /// <summary>
-    /// Frequency in minutes for polling RSS feed sources.
-    /// </summary>
-    public int PollingFrequencyMinutes { get; set; } = 15;
-
-    /// <summary>
-    /// Article retention period in days before archival or cleanup.
-    /// </summary>
-    public int ArticleRetentionDays { get; set; } = 90;
-
-    /// <summary>
-    /// Default page size for historical news API pagination queries.
-    /// </summary>
-    public int DefaultPageSize { get; set; } = 20;
-
-    /// <summary>
-    /// Background scraper interval in minutes.
-    /// </summary>
-    public int ScrapingIntervalMinutes { get; set; } = 15;
-
-    /// <summary>
-    /// Webhook URL for n8n AI article analysis.
-    /// </summary>
-    public string N8nWebhookUrl { get; set; } = "http://localhost:5678/webhook/finlytic-news";
-
-    /// <summary>
-    /// Timestamp of last modification.
-    /// </summary>
-    public DateTime UpdatedAt { get; set; } = DateTime.UtcNow;
-}