patchy mcpatchy

patch here patch there patch everywhere

README.md

@@ -1,7 +1,8 @@
-# IggyAPI
+# IggyAPI - IGGY: Your IG Spirit Animal
+Knows every guide inside out, and helps you fetch, explore, and use them.
 ![IggyAPI Logo](IggyAPI.png)
 
-IggyAPI is a FastAPI-based application designed to search, retrieve, and manage FHIR Implementation Guides (IGs) and their associated StructureDefinitions (profiles). It offers a powerful interface for querying FHIR packages, listing profiles within an IG, and fetching specific StructureDefinitions with the option to strip narrative content. Tailored to support healthcare interoperability in an Australian context, IggyAPI focuses on AU Core profiles but is capable of handling IGs from various FHIR registries worldwide.
+IggyAPI is a FastAPI-based application designed to search, retrieve, and manage FHIR Implementation Guides (IGs) and their associated StructureDefinitions (profiles). It offers a powerful interface for querying FHIR packages, listing profiles within an IG, and fetching specific StructureDefinitions with the option to strip narrative content. Tailored to support healthcare interoperability in an Australian context, IggyAPI is capable of handling IGs from various FHIR registries worldwide.
 
 ## Table of Contents
 
@@ -476,4 +477,4 @@ Please ensure your code follows PEP 8 style guidelines and includes appropriate
 
 ## License
 
-IggyAPI is licensed under the MIT License. See the `LICENSE` file for details.
+IggyAPI is licensed under the MIT License. See the `LICENSE` file for details.

main.py

@@ -10,6 +10,7 @@ import tarfile
 import json
 from datetime import datetime, timedelta
 import asyncio
+import os
 
 # Import from core
 from core import (
@@ -381,7 +382,106 @@ async def search_igs(query: str = '', search_type: str = 'semantic'):
     finally:
         db.close()
         logger.info("Closed database session after search")
+#-----------------------------------------------------------------------------OLD
+# @app.get("/igs/{ig_id}/profiles", response_model=List[ProfileMetadata])
+# async def list_profiles(ig_id: str, version: Optional[str] = None):
+#     """List StructureDefinition profiles in the specified IG, optionally for a specific version."""
+#     logger.info(f"Listing profiles for IG: {ig_id}, version: {version}")
 
+#     # Parse ig_id for version if it includes a '#'
+#     ig_name = ig_id
+#     if '#' in ig_id:
+#         parts = ig_id.split('#', 1)
+#         ig_name = parts[0]
+#         if version and parts[1] != version:
+#             logger.warning(f"Version specified in ig_id ({parts[1]}) conflicts with version parameter ({version}). Using version parameter.")
+#         else:
+#             version = parts[1]
+#         logger.info(f"Parsed ig_id: name={ig_name}, version={version}")
+
+#     # Validate ig_name
+#     if not ig_name or not re.match(r'^[a-zA-Z0-9\.\-_]+$', ig_name):
+#         logger.error(f"Invalid IG name: {ig_name}")
+#         raise HTTPException(status_code=400, detail="Invalid IG name. Use format like 'hl7.fhir.au.core'.")
+
+#     # Validate version if provided
+#     if version and not re.match(r'^[a-zA-Z0-9\.\-_]+$', version):
+#         logger.error(f"Invalid version: {version}")
+#         raise HTTPException(status_code=400, detail="Invalid version format. Use format like '1.1.0-preview'.")
+
+#     # Check if profiles are cached
+#     cache_key = f"{ig_name}#{version if version else 'latest'}"
+#     if cache_key in app_config["PROFILE_CACHE"]:
+#         logger.info(f"Returning cached profiles for IG {ig_name} (version: {version if version else 'latest'})")
+#         return app_config["PROFILE_CACHE"][cache_key]
+
+#     # Fetch package metadata from cache
+#     packages = app_config["MANUAL_PACKAGE_CACHE"]
+#     if not packages:
+#         logger.error("Package cache is empty. Please refresh the cache using /refresh-cache.")
+#         raise HTTPException(status_code=500, detail="Package cache is empty. Please refresh the cache.")
+
+#     # Find the package
+#     package = None
+#     for pkg in packages:
+#         if pkg['package_name'].lower() == ig_name.lower():
+#             package = pkg
+#             break
+
+#     if not package:
+#         logger.error(f"IG {ig_name} not found in cached packages.")
+#         raise HTTPException(status_code=404, detail=f"IG '{ig_name}' not found.")
+
+#     # Determine the version to fetch
+#     if version:
+#         target_version = None
+#         for ver_entry in package['all_versions']:
+#             if ver_entry['version'] == version:
+#                 target_version = ver_entry['version']
+#                 break
+#         if not target_version:
+#             logger.error(f"Version {version} not found for IG {ig_name}.")
+#             raise HTTPException(status_code=404, detail=f"Version '{version}' not found for IG '{ig_name}'.")
+#     else:
+#         target_version = package['latest_version']
+#         version = target_version
+#         logger.info(f"No version specified, using latest version: {target_version}")
+
+#     # Download the package
+#     tgz_path, error = download_package(ig_name, version, package)
+#     if not tgz_path:
+#         logger.error(f"Failed to download package for IG {ig_name} (version: {version}): {error}")
+#         if "404" in error:
+#             raise HTTPException(status_code=404, detail=f"Package for IG '{ig_name}' (version: {version}) not found.")
+#         raise HTTPException(status_code=500, detail=f"Failed to fetch package: {error}")
+
+#     # Extract profiles from the .tgz file
+#     profiles = []
+#     try:
+#         with tarfile.open(tgz_path, mode="r:gz") as tar:
+#             for member in tar.getmembers():
+#                 if member.name.endswith('.json') and 'StructureDefinition' in member.name:
+#                     f = tar.extractfile(member)
+#                     if f:
+#                         resource = json.load(f)
+#                         if resource.get("resourceType") == "StructureDefinition":
+#                             profiles.append(ProfileMetadata(
+#                                 name=resource.get("name", ""),
+#                                 description=resource.get("description"),
+#                                 version=resource.get("version"),
+#                                 url=resource.get("url", "")
+#                             ))
+#     except Exception as e:
+#         logger.error(f"Failed to extract profiles from package for IG {ig_name} (version: {version}): {str(e)}")
+#         raise HTTPException(status_code=500, detail=f"Failed to extract profiles: {str(e)}")
+
+#     # Cache the profiles
+#     app_config["PROFILE_CACHE"][cache_key] = profiles
+#     logger.info(f"Cached {len(profiles)} profiles for IG {ig_name} (version: {version})")
+
+#     logger.info(f"Found {len(profiles)} profiles in IG {ig_name} (version: {version})")
+#     return profiles
+#----------------------------------------------------------------------------end
 @app.get("/igs/{ig_id}/profiles", response_model=List[ProfileMetadata])
 async def list_profiles(ig_id: str, version: Optional[str] = None):
     """List StructureDefinition profiles in the specified IG, optionally for a specific version."""
@@ -459,17 +559,27 @@ async def list_profiles(ig_id: str, version: Optional[str] = None):
     try:
         with tarfile.open(tgz_path, mode="r:gz") as tar:
             for member in tar.getmembers():
-                if member.name.endswith('.json') and 'StructureDefinition' in member.name:
+                if member.name.endswith('.json'):  # Check all JSON files
+                    logger.debug(f"Processing file: {member.name}")
                     f = tar.extractfile(member)
                     if f:
-                        resource = json.load(f)
-                        if resource.get("resourceType") == "StructureDefinition":
-                            profiles.append(ProfileMetadata(
-                                name=resource.get("name", ""),
-                                description=resource.get("description"),
-                                version=resource.get("version"),
-                                url=resource.get("url", "")
-                            ))
+                        try:
+                            resource = json.load(f)
+                            # Check if the resource is a StructureDefinition
+                            if resource.get("resourceType") == "StructureDefinition":
+                                logger.debug(f"Found StructureDefinition in file: {member.name}")
+                                profiles.append(ProfileMetadata(
+                                    name=resource.get("name", ""),
+                                    description=resource.get("description"),
+                                    version=resource.get("version"),
+                                    url=resource.get("url", "")
+                                ))
+                            else:
+                                logger.debug(f"File {member.name} is not a StructureDefinition, resourceType: {resource.get('resourceType', 'unknown')}")
+                        except json.JSONDecodeError as e:
+                            logger.warning(f"Failed to parse JSON in file {member.name}: {str(e)}")
+                        except Exception as e:
+                            logger.warning(f"Error processing file {member.name}: {str(e)}")
     except Exception as e:
         logger.error(f"Failed to extract profiles from package for IG {ig_name} (version: {version}): {str(e)}")
         raise HTTPException(status_code=500, detail=f"Failed to extract profiles: {str(e)}")
@@ -480,6 +590,153 @@ async def list_profiles(ig_id: str, version: Optional[str] = None):
 
     logger.info(f"Found {len(profiles)} profiles in IG {ig_name} (version: {version})")
     return profiles
+#------------------------------------------------------------------OLD
+# @app.get("/igs/{ig_id}/profiles/{profile_id}", response_model=StructureDefinition)
+# async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None, include_narrative: bool = True):
+#     """
+#     Retrieve a specific StructureDefinition from an Implementation Guide (IG).
+
+#     This endpoint fetches a specific FHIR StructureDefinition (profile) from the given IG.
+#     It supports optional version specification and an option to strip the narrative content.
+
+#     Args:
+#         ig_id (str): The ID of the Implementation Guide (e.g., 'hl7.fhir.au.core' or 'hl7.fhir.au.core#1.1.0-preview').
+#                      If the version is included in the ig_id (after '#'), it takes precedence unless overridden by the version parameter.
+#         profile_id (str): The ID or name of the profile to retrieve (e.g., 'AUCorePatient').
+#         version (str, optional): The version of the IG (e.g., '1.1.0-preview'). If not provided and ig_id contains a version,
+#                                  the version from ig_id is used; otherwise, the latest version is used.
+#         include_narrative (bool, optional): Whether to include the narrative (`text` element) in the StructureDefinition.
+#                                             Defaults to True. Set to False to strip the narrative, removing human-readable content.
+
+#     Returns:
+#         StructureDefinition: A dictionary containing the requested StructureDefinition resource.
+#                              The response includes the `resource` field with the StructureDefinition JSON.
+#                              If `include_narrative=False`, the `text` element will be set to null.
+
+#     Raises:
+#         HTTPException: 
+#             - 400: If the IG name, version, or profile ID is invalid.
+#             - 404: If the IG, version, or profile is not found.
+#             - 500: If an error occurs during package retrieval or profile extraction.
+
+#     Example:
+#         - GET /igs/hl7.fhir.au.core/profiles/AUCorePatient?version=1.1.0-preview
+#           Returns the AUCorePatient profile with narrative included.
+#         - GET /igs/hl7.fhir.au.core/profiles/AUCorePatient?version=1.1.0-preview&include_narrative=false
+#           Returns the AUCorePatient profile with the narrative (`text` element) stripped.
+#     """
+#     logger.info(f"Retrieving profile {profile_id} for IG: {ig_id}, version: {version}, include_narrative: {include_narrative}")
+
+#     # Parse ig_id for version if it includes a '#'
+#     ig_name = ig_id
+#     if '#' in ig_id:
+#         parts = ig_id.split('#', 1)
+#         ig_name = parts[0]
+#         if version and parts[1] != version:
+#             logger.warning(f"Version specified in ig_id ({parts[1]}) conflicts with version parameter ({version}). Using version parameter.")
+#         else:
+#             version = parts[1]
+#         logger.info(f"Parsed ig_id: name={ig_name}, version={version}")
+
+#     # Validate ig_name
+#     if not ig_name or not re.match(r'^[a-zA-Z0-9\.\-_]+$', ig_name):
+#         logger.error(f"Invalid IG name: {ig_name}")
+#         raise HTTPException(status_code=400, detail="Invalid IG name. Use format like 'hl7.fhir.au.core'.")
+
+#     # Validate version if provided
+#     if version and not re.match(r'^[a-zA-Z0-9\.\-_]+$', version):
+#         logger.error(f"Invalid version: {version}")
+#         raise HTTPException(status_code=400, detail="Invalid version format. Use format like '1.1.0-preview'.")
+
+#     # Validate profile_id
+#     if not profile_id or not re.match(r'^[a-zA-Z0-9\.\-_]+$', profile_id):
+#         logger.error(f"Invalid profile ID: {profile_id}")
+#         raise HTTPException(status_code=400, detail="Invalid profile ID format.")
+
+#     # Check if profiles are cached
+#     cache_key = f"{ig_name}#{version if version else 'latest'}"
+#     if cache_key in app_config["PROFILE_CACHE"]:
+#         logger.info(f"Using cached profiles for IG {ig_name} (version: {version if version else 'latest'})")
+#         profiles = app_config["PROFILE_CACHE"][cache_key]
+#         for profile in profiles:
+#             if profile.name == profile_id or profile.url.endswith(profile_id):
+#                 break
+#         else:
+#             logger.error(f"Profile {profile_id} not found in cached profiles for IG {ig_name} (version: {version if version else 'latest'})")
+#             raise HTTPException(status_code=404, detail=f"Profile '{profile_id}' not found in IG '{ig_name}' (version: {version if version else 'latest'}).")
+#     else:
+#         profiles = await list_profiles(ig_id, version)
+
+#     # Fetch package metadata
+#     packages = app_config["MANUAL_PACKAGE_CACHE"]
+#     if not packages:
+#         logger.error("Package cache is empty. Please refresh the cache using /refresh-cache.")
+#         raise HTTPException(status_code=500, detail="Package cache is empty. Please refresh the cache.")
+
+#     package = None
+#     for pkg in packages:
+#         if pkg['package_name'].lower() == ig_name.lower():
+#             package = pkg
+#             break
+
+#     if not package:
+#         logger.error(f"IG {ig_name} not found in cached packages.")
+#         raise HTTPException(status_code=404, detail=f"IG '{ig_name}' not found.")
+
+#     # Determine the version to fetch
+#     if version:
+#         target_version = None
+#         for ver_entry in package['all_versions']:
+#             if ver_entry['version'] == version:
+#                 target_version = ver_entry['version']
+#                 break
+#         if not target_version:
+#             logger.error(f"Version {version} not found for IG {ig_name}.")
+#             raise HTTPException(status_code=404, detail=f"Version '{version}' not found for IG '{ig_name}'.")
+#     else:
+#         target_version = package['latest_version']
+#         version = target_version
+#         logger.info(f"No version specified, using latest version: {target_version}")
+
+#     # Download the package
+#     tgz_path, error = download_package(ig_name, version, package)
+#     if not tgz_path:
+#         logger.error(f"Failed to download package for IG {ig_name} (version: {version}): {error}")
+#         if "404" in error:
+#             raise HTTPException(status_code=404, detail=f"Package for IG '{ig_name}' (version: {version}) not found.")
+#         raise HTTPException(status_code=500, detail=f"Failed to fetch package: {error}")
+
+#     # Extract the specific profile from the .tgz file
+#     profile_resource = None
+#     try:
+#         with tarfile.open(tgz_path, mode="r:gz") as tar:
+#             for member in tar.getmembers():
+#                 if member.name.endswith('.json') and 'StructureDefinition' in member.name:
+#                     f = tar.extractfile(member)
+#                     if f:
+#                         resource = json.load(f)
+#                         if resource.get("resourceType") == "StructureDefinition":
+#                             resource_name = resource.get("name", "")
+#                             resource_url = resource.get("url", "")
+#                             if resource_name == profile_id or resource_url.endswith(profile_id):
+#                                 profile_resource = resource
+#                                 break
+#         if not profile_resource:
+#             logger.error(f"Profile {profile_id} not found in package for IG {ig_name} (version: {version})")
+#             raise HTTPException(status_code=404, detail=f"Profile '{profile_id}' not found in IG '{ig_name}' (version: {version}).")
+#     except Exception as e:
+#         logger.error(f"Failed to extract profile {profile_id} from package for IG {ig_name} (version: {version}): {str(e)}")
+#         raise HTTPException(status_code=500, detail=f"Failed to extract profile: {str(e)}")
+
+#     # Strip narrative if requested
+#     if not include_narrative:
+#         logger.info(f"Stripping narrative from profile {profile_id}")
+#         if "text" in profile_resource:
+#             profile_resource["text"] = None
+
+#     logger.info(f"Successfully retrieved profile {profile_id} for IG {ig_name} (version: {version})")
+#     return StructureDefinition(resource=profile_resource)
+#------------------------------------------------------------------------------end
 
 @app.get("/igs/{ig_id}/profiles/{profile_id}", response_model=StructureDefinition)
 async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None, include_narrative: bool = True):
@@ -492,7 +749,7 @@ async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None
     Args:
         ig_id (str): The ID of the Implementation Guide (e.g., 'hl7.fhir.au.core' or 'hl7.fhir.au.core#1.1.0-preview').
                      If the version is included in the ig_id (after '#'), it takes precedence unless overridden by the version parameter.
-        profile_id (str): The ID or name of the profile to retrieve (e.g., 'AUCorePatient').
+        profile_id (str): The ID or name of the profile to retrieve (e.g., 'AUCorePatient' or 'DAV_PR_ERP_Abrechnungszeilen').
         version (str, optional): The version of the IG (e.g., '1.1.0-preview'). If not provided and ig_id contains a version,
                                  the version from ig_id is used; otherwise, the latest version is used.
         include_narrative (bool, optional): Whether to include the narrative (`text` element) in the StructureDefinition.
@@ -546,15 +803,24 @@ async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None
     # Check if profiles are cached
     cache_key = f"{ig_name}#{version if version else 'latest'}"
     if cache_key in app_config["PROFILE_CACHE"]:
-        logger.info(f"Using cached profiles for IG {ig_name} (version: {version if version else 'latest'})")
+        logger.info(f"Cache hit for IG {ig_name} (version: {version if version else 'latest'})")
         profiles = app_config["PROFILE_CACHE"][cache_key]
+        logger.debug(f"Cached profiles: {[profile.name for profile in profiles]}")
+        profile_found = False
+        # Normalize profile_id for matching (remove hyphens, underscores, and convert to lowercase)
+        normalized_profile_id = profile_id.lower().replace('-', '').replace('_', '')
         for profile in profiles:
-            if profile.name == profile_id or profile.url.endswith(profile_id):
+            normalized_name = profile.name.lower().replace('-', '').replace('_', '') if profile.name else ''
+            normalized_url_end = profile.url.lower().split('/')[-1].replace('-', '').replace('_', '') if profile.url else ''
+            if normalized_name == normalized_profile_id or normalized_url_end == normalized_profile_id:
+                logger.info(f"Found profile {profile_id} in cached profiles: name={profile.name}, url={profile.url}")
+                profile_found = True
                 break
-        else:
+        if not profile_found:
             logger.error(f"Profile {profile_id} not found in cached profiles for IG {ig_name} (version: {version if version else 'latest'})")
             raise HTTPException(status_code=404, detail=f"Profile '{profile_id}' not found in IG '{ig_name}' (version: {version if version else 'latest'}).")
     else:
+        logger.info(f"Cache miss for IG {ig_name} (version: {version if version else 'latest'}), calling list_profiles")
         profiles = await list_profiles(ig_id, version)
 
     # Fetch package metadata
@@ -588,7 +854,15 @@ async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None
         version = target_version
         logger.info(f"No version specified, using latest version: {target_version}")
 
+    # Check directory state before calling download_package
+    instance_dir = "instance"
+    if os.path.exists(instance_dir):
+        logger.info(f"Directory {instance_dir} exists before calling download_package in get_profile")
+    else:
+        logger.warning(f"Directory {instance_dir} does NOT exist before calling download_package in get_profile")
+
     # Download the package
+    logger.info(f"Calling download_package for IG {ig_name} (version: {version}) in get_profile")
     tgz_path, error = download_package(ig_name, version, package)
     if not tgz_path:
         logger.error(f"Failed to download package for IG {ig_name} (version: {version}): {error}")
@@ -600,17 +874,34 @@ async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None
     profile_resource = None
     try:
         with tarfile.open(tgz_path, mode="r:gz") as tar:
+            # Normalize profile_id for matching (remove hyphens, underscores, and convert to lowercase)
+            normalized_profile_id = profile_id.lower().replace('-', '').replace('_', '')
             for member in tar.getmembers():
-                if member.name.endswith('.json') and 'StructureDefinition' in member.name:
+                if member.name.endswith('.json'):  # Check all JSON files
+                    logger.debug(f"Processing file: {member.name}")
                     f = tar.extractfile(member)
                     if f:
-                        resource = json.load(f)
-                        if resource.get("resourceType") == "StructureDefinition":
-                            resource_name = resource.get("name", "")
-                            resource_url = resource.get("url", "")
-                            if resource_name == profile_id or resource_url.endswith(profile_id):
-                                profile_resource = resource
-                                break
+                        try:
+                            resource = json.load(f)
+                            # Check if the resource is a StructureDefinition
+                            if resource.get("resourceType") == "StructureDefinition":
+                                resource_name = resource.get("name", "")
+                                resource_url = resource.get("url", "")
+                                # Normalize name and URL for matching
+                                normalized_name = resource_name.lower().replace('-', '').replace('_', '') if resource_name else ''
+                                normalized_url_end = resource_url.lower().split('/')[-1].replace('-', '').replace('_', '') if resource_url else ''
+                                logger.debug(f"Found StructureDefinition in file: {member.name}, name={resource_name}, url={resource_url}, normalized_name={normalized_name}, normalized_url_end={normalized_url_end}")
+                                # Match profile_id against name or the last segment of the URL
+                                if normalized_name == normalized_profile_id or normalized_url_end == normalized_profile_id:
+                                    logger.info(f"Matched profile {profile_id} in file {member.name}: name={resource_name}, url={resource_url}")
+                                    profile_resource = resource
+                                    break
+                            else:
+                                logger.debug(f"File {member.name} is not a StructureDefinition, resourceType: {resource.get('resourceType', 'unknown')}")
+                        except json.JSONDecodeError as e:
+                            logger.warning(f"Failed to parse JSON in file {member.name}: {str(e)}")
+                        except Exception as e:
+                            logger.warning(f"Error processing file {member.name}: {str(e)}")
         if not profile_resource:
             logger.error(f"Profile {profile_id} not found in package for IG {ig_name} (version: {version})")
             raise HTTPException(status_code=404, detail=f"Profile '{profile_id}' not found in IG '{ig_name}' (version: {version}).")
@@ -626,7 +917,6 @@ async def get_profile(ig_id: str, profile_id: str, version: Optional[str] = None
 
     logger.info(f"Successfully retrieved profile {profile_id} for IG {ig_name} (version: {version})")
     return StructureDefinition(resource=profile_resource)
-
 @app.get("/status", response_model=RefreshStatus)
 async def get_refresh_status():
     """Get the status of the last cache refresh."""