fix ingestion tests errors

hadith-ingestion/.env

@@ -1,5 +1,6 @@
 # Database
-DATABASE_HOST=postgres.db.svc.cluster.local
+# DATABASE_HOST=postgres.db.svc.cluster.local
+DATABASE_HOST = pg.betelgeusebytes.io
 DATABASE_PORT=5432
 DATABASE_NAME=hadith_db
 DATABASE_USER=hadith_ingest

hadith-ingestion/config/settings.py

@@ -10,7 +10,8 @@ class Settings(BaseSettings):
     """Application settings loaded from environment variables"""
     
     # Database
-    DATABASE_HOST: str = "postgres.db.svc.cluster.local"
+    # DATABASE_HOST: str = "postgres.db.svc.cluster.local"
+    DATABASE_HOST: str = "pg.betelgeusebytes.io"
     DATABASE_PORT: int = 5432
     DATABASE_NAME: str = "hadith_db"
     DATABASE_USER: str = "hadith_ingest"
@@ -37,9 +38,6 @@ class Settings(BaseSettings):
     MINIO_BUCKET_RAW: str = "hadith-raw-data"
     MINIO_BUCKET_PROCESSED: str = "hadith-processed"
     MINIO_SECURE: bool = False
-    
-    # APIs
-    SUNNAH_API_KEY: Optional[str] = None
     SUNNAH_BASE_URL: str = "https://api.sunnah.com/v1"
     HADITH_ONE_API_KEY: Optional[str] = "$2y$10$nTJnyX3WUDoGmjKrKqSmbecANVsQWKyffmtp9fxmsQwR15DEv4mK"
     # HadithAPI.com

hadith-ingestion/src/database/repository.py

@@ -2,6 +2,7 @@
 Database repository for hadith data operations
 """
 from typing import List, Dict, Any, Optional
+import json
 from uuid import UUID
 import structlog
 from sqlalchemy import create_engine, text, select, insert, update
@@ -20,6 +21,12 @@ class HadithRepository:
         self.engine = create_engine(self.database_url, pool_pre_ping=True)
         self.SessionLocal = sessionmaker(bind=self.engine)
 
+    @staticmethod
+    def _coerce_uuid(value: Any) -> UUID:
+        if isinstance(value, UUID):
+            return value
+        return UUID(str(value))
+
     def get_session(self) -> Session:
         """Get database session"""
         return self.SessionLocal()
@@ -68,6 +75,7 @@ class HadithRepository:
         metadata: Optional[Dict] = None
     ) -> UUID:
         """Insert or update a book"""
+        metadata_json = json.dumps(metadata or {})
         with self.get_session() as session:
             query = text("""
                 INSERT INTO books (collection_id, book_number, name_english, name_arabic, metadata)
@@ -85,11 +93,11 @@ class HadithRepository:
                 "book_number": book_number,
                 "name_english": name_english,
                 "name_arabic": name_arabic,
-                "metadata": metadata or {}
+                "metadata": metadata_json
             })
             session.commit()
 
-            return UUID(result.fetchone()[0])
+            return self._coerce_uuid(result.fetchone()[0])
 
     def get_book(self, collection_id: UUID, book_number: int) -> Optional[Dict[str, Any]]:
         """Get book by collection and book number"""
@@ -125,6 +133,7 @@ class HadithRepository:
         source_metadata: Optional[Dict] = None
     ) -> UUID:
         """Insert or update a hadith"""
+        
         with self.get_session() as session:
             query = text("""
                 INSERT INTO hadiths (
@@ -152,6 +161,7 @@ class HadithRepository:
                     updated_at = NOW()
                 RETURNING id
             """)
+            metadata_json = json.dumps(source_metadata or {})
 
             result = session.execute(query, {
                 "collection_id": str(collection_id),
@@ -165,11 +175,11 @@ class HadithRepository:
                 "chapter_name": chapter_name,
                 "source_id": source_id,
                 "source_url": source_url,
-                "source_metadata": source_metadata or {}
+                "source_metadata": metadata_json
             })
             session.commit()
 
-            return UUID(result.fetchone()[0])
+            return self._coerce_uuid(result.fetchone()[0])
 
     def get_hadiths_without_embeddings(
         self,
@@ -204,6 +214,7 @@ class HadithRepository:
     def mark_embedding_generated(self, hadith_id: UUID, version: str = "v1"):
         """Mark hadith as having embedding generated"""
         with self.get_session() as session:
+            # Prepare the update query
             query = text("""
                 UPDATE hadiths
                 SET embedding_generated = TRUE,
@@ -211,6 +222,9 @@ class HadithRepository:
                     updated_at = NOW()
                 WHERE id = :id
             """)
+            # Pre-serialize parameters (keeping consistent with other methods that
+            # serialize payloads/configs before execution)
+            params = {"id": str(hadith_id), "version": version}
             session.execute(query, {"id": str(hadith_id), "version": version})
             session.commit()
 
@@ -230,15 +244,16 @@ class HadithRepository:
                 VALUES (:job_name, :job_type, :source_name, :config, 'running', NOW())
                 RETURNING id
             """)
+            # serialize config as JSON for storage
             result = session.execute(query, {
                 "job_name": job_name,
                 "job_type": job_type,
                 "source_name": source_name,
-                "config": config or {}
+                "config": json.dumps(config or {})
             })
             session.commit()
-            
-            return UUID(result.fetchone()[0])
+            job_id = result.fetchone()[0]
+            return job_id if isinstance(job_id, UUID) else UUID(str(job_id))
     
     def update_job_progress(
         self,
@@ -311,11 +326,12 @@ class HadithRepository:
                 INSERT INTO processing_logs (job_id, log_level, message, details)
                 VALUES (:job_id, :level, :message, :details)
             """)
+            details_json = json.dumps(details or {})
             session.execute(query, {
                 "job_id": str(job_id),
                 "level": level,
                 "message": message,
-                "details": details or {}
+                "details": details_json
             })
             session.commit()
 

hadith-ingestion/src/main_hadithapi.py

@@ -7,9 +7,9 @@ from typing import Optional, Dict, Any
 from uuid import UUID
 import structlog
 from config.settings import settings
-from api_clients.hadithapi_client import HadithAPIClient
-from database.repository import HadithRepository
-from processors.text_cleaner import ArabicTextProcessor, TextCleaner
+from src.api_clients.hadithapi_client import HadithAPIClient
+from src.database.repository import HadithRepository
+from src.processors.text_cleaner import ArabicTextProcessor, TextCleaner
 
 # Configure structured logging
 structlog.configure(
@@ -35,14 +35,15 @@ logger = structlog.get_logger()
 BOOK_SLUG_MAPPING = {
     'sahih-bukhari': 'bukhari',
     'sahih-muslim': 'muslim',
-    'sunan-abu-dawood': 'abudawud',
-    'jami-at-tirmidhi': 'tirmidhi',
-    'sunan-an-nasai': 'nasai',
-    'sunan-ibn-e-majah': 'ibnmajah',
+    'abu-dawood': 'abudawud',
+    'al-tirmidhi': 'tirmidhi',
+    'sunan-nasai': 'nasai',
+    'ibn-e-majah': 'ibnmajah',
     'muwatta-imam-malik': 'malik',
     'musnad-ahmad': 'ahmad',
     'sunan-ad-darimi': 'darimi',
-    'mishkat-al-masabih': 'mishkat'
+    'mishkat': 'mishkat',
+    'al-silsila-sahiha': 'al-silsila-sahiha'
 }
 
 
@@ -68,10 +69,10 @@ class HadithAPIIngestionService:
         api_books = self.api_client.get_books()
 
         book_mapping = {}
-        
+        # print(BOOK_SLUG_MAPPING)
         for api_book in api_books:
             book_slug = api_book.get('bookSlug')
-            
+            # print(book_slug)
             # Map to our collection abbreviation
             collection_abbr = BOOK_SLUG_MAPPING.get(book_slug)
             
@@ -82,7 +83,6 @@ class HadithAPIIngestionService:
                     book_name=api_book.get('bookName')
                 )
                 continue
-            
             # Get or verify collection exists in database
             collection = self.repo.get_collection_by_abbreviation(collection_abbr)
             
@@ -94,7 +94,9 @@ class HadithAPIIngestionService:
                 )
                 continue
 
-            collection_id = UUID(collection['id'])
+            collection_id = collection['id']
+            if not isinstance(collection_id, UUID):
+                collection_id = UUID(str(collection_id))
             book_mapping[book_slug] = {
                 'collection_id': collection_id,
                 'book_id': api_book.get('id'),
@@ -305,7 +307,7 @@ class HadithAPIIngestionService:
         
         if not arabic_text:
             raise ValueError("Missing Arabic text")
-        
+        # passed logger.warning("Arabic text extracted and validated", hadith_number=hadith_number)
         # Clean texts
         arabic_text = self.text_cleaner.clean_text(arabic_text)
         if english_text:
@@ -319,14 +321,15 @@ class HadithAPIIngestionService:
         # Get or create chapter (book in our schema)
         book_id = None
         chapter_name = None
-        
+        # logger.warning("Processing chapter data####", chapter_data.get('positional_args', {}).get('id'))
+        # logger.info("Processing chapter data####2####", chapter_data.get('id'))
         if chapter_data:
             chapter_id = chapter_data.get('id')
             chapter_number = chapter_data.get('chapterNumber')
             chapter_name_en = chapter_data.get('chapterEnglish')
             chapter_name_ar = chapter_data.get('chapterArabic')
             chapter_name = chapter_name_en
-            
+            # print(chapter_number, chapter_name)
             if chapter_number:
                 try:
                     chapter_number = int(chapter_number)
@@ -335,7 +338,8 @@ class HadithAPIIngestionService:
                 
                 # Get or create book (chapter in HadithAPI = book in our schema)
                 existing_book = self.repo.get_book(collection_id, chapter_number)
-                
+                # logger.warning("EXISTING BOOK : ", existing_book)
+                # logger.warning("Fetched or created book", collection_id=collection_id, chapter_number=chapter_number, chapter_name=chapter_name)
                 if not existing_book:
                     book_id = self.repo.upsert_book(
                         collection_id=collection_id,
@@ -345,7 +349,11 @@ class HadithAPIIngestionService:
                         metadata=chapter_data
                     )
                 else:
-                    book_id = UUID(existing_book['id'])
+                    # print(existing_book['id'])
+                    existing_id = existing_book['id']
+                    if isinstance(existing_id, str):
+                        existing_id = UUID(existing_id)
+                    book_id = existing_id
 
         # Build source metadata
         source_metadata = {
@@ -356,7 +364,7 @@ class HadithAPIIngestionService:
             'chapterId': hadith_data.get('chapterId'),
             'chapter': chapter_data
         }
-        
+        # logger.warning("Hadith metadata built", source_metadata)
         # Store hadith
         hadith_id = self.repo.upsert_hadith(
             collection_id=collection_id,

hadith-ingestion/test_mainhadithapi.py

@@ -0,0 +1,109 @@
+#!/usr/bin/env python3
+"""
+Test script for main_hadithapi.py
+"""
+import sys
+import os
+sys.path.insert(0, '.')
+
+from src.main_hadithapi import HadithAPIIngestionService
+
+def test_main_hadithapi():
+    """Test the main HadithAPI ingestion service"""
+    print("=== Testing HadithAPI Ingestion Service ===\n")
+    
+    try:
+        # Initialize the service
+        print("1. Initializing HadithAPIIngestionService...")
+        service = HadithAPIIngestionService()
+        print("✓ Service initialized successfully\n")
+        
+        # Test 1: List available books
+        print("2. Testing book synchronization...")
+        book_mapping = service.sync_books_from_api()
+        print(f"✓ Found {len(book_mapping)} mapped books")
+        for book_slug, info in list(book_mapping.items())[:3]:  # Show first 3
+            print(f"  - {book_slug}: {info['book_name']} ({info['hadiths_count']} hadiths)")
+        print()
+        
+        # Test 2: Test ingestion with limit
+        print("3. Testing limited ingestion (10 hadiths from Sahih Bukhari)...")
+        stats = service.ingest_collection(
+            book_slug='sahih-bukhari',
+            limit=10
+        )
+        print(f"✓ Ingestion completed with stats:")
+        print(f"  Processed: {stats['processed']}")
+        print(f"  Failed: {stats['failed']}")
+        print(f"  Skipped: {stats['skipped']}\n")
+        
+        # Test 3: List books functionality
+        print("4. Testing book listing...")
+        print("\n=== Available Books ===\n")
+        for book_slug, info in book_mapping.items():
+            print(f"Book Slug: {book_slug}")
+            print(f"  Name: {info['book_name']}")
+            print(f"  Hadiths: {info['hadiths_count']}")
+            print(f"  Chapters: {info['chapters_count']}")
+            print()
+        
+        # Clean up
+        service.close()
+        print("=== All Tests Passed! ===")
+        return True
+        
+    except Exception as e:
+        print(f"✗ Test failed with error: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+
+def test_command_line_args():
+    """Test command line argument parsing"""
+    print("=== Testing Command Line Arguments ===\n")
+    
+    # We'll simulate command line arguments
+    import argparse
+    from src.main_hadithapi import main
+    
+    # Test --list-books argument
+    print("1. Testing --list-books argument...")
+    original_argv = sys.argv.copy()
+    
+    try:
+        sys.argv = ['main_hadithapi.py', '--list-books']
+        # We won't actually run main() as it would exit, but we can check the parsing
+        parser = argparse.ArgumentParser(description="Ingest hadiths from HadithAPI.com")
+        parser.add_argument("--book-slug", help="Book slug (e.g., sahih-bukhari)")
+        parser.add_argument("--limit", type=int, help="Limit number of hadiths to ingest")
+        parser.add_argument("--list-books", action="store_true", help="List available books and exit")
+        
+        args = parser.parse_args(['--list-books'])
+        print(f"✓ Argument parsing successful: list_books={args.list_books}")
+        
+        # Test book-slug argument
+        args = parser.parse_args(['--book-slug', 'sahih-bukhari', '--limit', '5'])
+        print(f"✓ Argument parsing successful: book_slug={args.book_slug}, limit={args.limit}")
+        
+        print("✓ Command line argument parsing works correctly\n")
+        return True
+        
+    except Exception as e:
+        print(f"✗ Argument parsing failed: {e}")
+        return False
+    finally:
+        sys.argv = original_argv
+
+if __name__ == "__main__":
+    print("Starting tests for main_hadithapi.py...\n")
+    
+    # Test command line arguments
+    if not test_command_line_args():
+        sys.exit(1)
+    
+    # Test main functionality
+    if not test_main_hadithapi():
+        sys.exit(1)
+    
+    print("\n🎉 All tests passed successfully!")
+    sys.exit(0)