From 7ac86dafa981efd7a8c08634b3fe20e716e8ecd8 Mon Sep 17 00:00:00 2001
From: John O'Keefe <jrokeefe@protonmail.com>
Date: Sun, 12 Apr 2026 20:43:42 -0400
Subject: [PATCH] feat(schema): Add processing_issues table for tracking media
 validation problems

- Add processing_issues table to track media items that cannot be properly processed in their assigned library
- Include fields for issue type, description, severity, and resolution status
- Add indexes for efficient querying by library and severity
- Support tracking format mismatches and other processing problems
- Unique constraint on media_item_id and issue_type to prevent duplicates
---
 database/schema/schema.sql | 57 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/database/schema/schema.sql b/database/schema/schema.sql
index 1e96b3d..b7defda 100644
--- a/database/schema/schema.sql
+++ b/database/schema/schema.sql
@@ -16,8 +16,8 @@ CREATE TABLE IF NOT EXISTS library_types (
 -- Insert default library types
 INSERT INTO library_types (name, description, allowed_extensions) VALUES
 ('ebooks', 'Ebook files including EPUB, PDF, MOBI, etc.', ARRAY['.epub', '.pdf', '.mobi', '.azw', '.azw3', '.txt', '.rtf', '.doc', '.docx', '.lit', '.fb2', '.pdb']),
-('comics', 'Comic book archives and image formats', ARRAY['.cbz', '.cbr', '.cb7', '.cbt', '.pdf']),
-('manga', 'Manga files including archives and image folders', ARRAY['.cbz', '.cbr', '.png', '.jpg', '.jpeg', '.gif', '.bmp', '.webp'])
+('comics', 'Comic book archives and image formats', ARRAY['.cbz', '.cbr', '.cb7', '.cbt', '.epub', '.pdf']),
+('manga', 'Manga files including archives and image folders', ARRAY['.cbz', '.cbr', '.epub', '.png', '.jpg', '.jpeg', '.gif', '.bmp', '.webp'])
 ON CONFLICT (name) DO NOTHING;
 
 -- Create users table
@@ -387,6 +387,30 @@ CREATE INDEX IF NOT EXISTS idx_kobo_shelves_device_id ON kobo_shelves(device_id)
 CREATE INDEX IF NOT EXISTS idx_kobo_shelves_media_item_id ON kobo_shelves(media_item_id);
 CREATE INDEX IF NOT EXISTS idx_kobo_shelves_shelf_name ON kobo_shelves(shelf_name);
 
+-- Table to track items that can't be processed in their library
+CREATE TABLE IF NOT EXISTS processing_issues (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    media_item_id UUID NOT NULL REFERENCES media_items(id) ON DELETE CASCADE,
+    library_id UUID NOT NULL REFERENCES libraries(id) ON DELETE CASCADE,
+    issue_type VARCHAR(50) NOT NULL,
+    issue_description TEXT NOT NULL,
+    severity VARCHAR(20) NOT NULL DEFAULT 'warning',
+    resolved BOOLEAN DEFAULT FALSE,
+    resolved_at TIMESTAMP WITH TIME ZONE,
+    created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
+    UNIQUE(media_item_id, issue_type)
+);
+
+-- Indexes for querying problem items
+CREATE INDEX IF NOT EXISTS idx_processing_issues_library 
+  ON processing_issues(library_id, resolved);
+CREATE INDEX IF NOT EXISTS idx_processing_issues_severity 
+  ON processing_issues(severity, resolved);
+
+-- Add comment for documentation
+COMMENT ON TABLE processing_issues IS 'Tracks media items that cannot be properly processed in their assigned library due to format mismatches or other issues';
+
+
 -- ============================================
 -- KOBO ENTITLEMENTS TRACKING
 -- ============================================
@@ -711,6 +735,35 @@ BEGIN
 END;
 $$ LANGUAGE plpgsql;
 
+-- Function to detect fixed-layout EPUBs from OPF content
+CREATE OR REPLACE FUNCTION detect_fixed_layout_epub(opf_content TEXT)
+RETURNS BOOLEAN AS $$
+BEGIN
+  -- Check for pre-paginated metadata
+  IF opf_content LIKE '%rendition:layout">pre-paginated<%' THEN
+    RETURN TRUE;
+  END IF;
+  
+  IF opf_content LIKE '%rendition:layout="pre-paginated"%' THEN
+    RETURN TRUE;
+  END IF;
+  
+  -- Check for RTL page progression (manga indicator)
+  IF opf_content LIKE '%page-progression-direction="rtl"%' THEN
+    RETURN TRUE;
+  END IF;
+  
+  -- Check for image-heavy content (count <img> tags)
+  -- Threshold of 50 images suggests manga/comic vs novel
+  IF array_length(string_to_array(opf_content, '<img')), 1) - 1 > 50 THEN
+    RETURN TRUE;
+  END IF;
+  
+  RETURN FALSE;
+END;
+$$ LANGUAGE plpgsql;
+
+
 -- Convert progress between format groups
 CREATE OR REPLACE FUNCTION convert_progress(
   source_format VARCHAR,