utils_devops 0.1.138__tar.gz → 0.1.140__tar.gz

{utils_devops-0.1.138 → utils_devops-0.1.140}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: utils_devops
-Version: 0.1.138
+Version: 0.1.140
 Summary: Lightweight DevOps utilities for automation scripts: config editing (YAML/JSON/INI/.env), templating, diffing, and CLI tools
 License: MIT
 Keywords: devops,automation,nginx,cli,jinja2,yaml,config,diff,templating,logging,docker,compose,file-ops

{utils_devops-0.1.138 → utils_devops-0.1.140}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "utils_devops"
-version = "0.1.138"  # Bumped for new string features + diffing
+version = "0.1.140"  # Bumped for new string features + diffing
 description = "Lightweight DevOps utilities for automation scripts: config editing (YAML/JSON/INI/.env), templating, diffing, and CLI tools"
 authors = ["Hamed Sheikhan <sh.sheikhan.m@gmail.com>"]
 license = "MIT"

{utils_devops-0.1.138 → utils_devops-0.1.140}/src/utils_devops/extras/docker_ops.py

@@ -767,75 +767,67 @@ def check_service_health(compose_file: str, service: str,
         logger.error(f"Error checking health for {service}: {e}")
         return {"healthy": False, "error": str(e)}
 
-def wait_for_healthy(compose_file: str, services: Optional[List[str]] = None,
-                    timeout: int = 300, interval: int = 5, logger: Optional[Logger] = None,env_file: Optional[str] = None) -> bool:
-    """Wait for services to become healthy - ENHANCED LOGGING VERSION"""
-    # Use parent function's logger if provided, otherwise get default
-    logger = logger or DEFAULT_LOGGER
-    
+import time
+from collections import defaultdict
+
+def wait_for_healthy(
+    compose_file: str,
+    services: List[str],
+    timeout: int,
+    interval: int,
+    logger: logger,
+    env_file: Optional[str] = None
+) -> bool:
+    """Wait for services to become healthy with detailed status logging."""
     start_time = time.time()
-    services_to_check = services or get_services_from_compose(compose_file , env_file)
+    attempt = 1
     
-    logger.info(f"🩺 Starting health checks for {len(services_to_check)} services: {services_to_check}")
-    logger.info(f"⏰ Timeout: {timeout}s, Check interval: {interval}s")
-    
-    attempt = 0
     while time.time() - start_time < timeout:
-        attempt += 1
         elapsed = time.time() - start_time
-        time_remaining = timeout - elapsed
-        
-        all_healthy = True
-        unhealthy_services = []
-        healthy_services = []
-        
-        # Check each service
-        for service in services_to_check:
-            health_result = check_service_health(compose_file, service)
-            is_healthy = health_result.get('healthy', False)
-            
-            if is_healthy:
-                healthy_services.append(service)
+        remaining = timeout - elapsed
+        logger.info(f"🔍 Health check attempt {attempt} ({elapsed:.1f}s elapsed, {remaining:.1f}s remaining):")
+        
+        # Get detailed health status
+        detailed_health = _get_detailed_health_status(compose_file, services, logger)
+        
+        # Group services by overall_status
+        status_groups = defaultdict(list)
+        for service, status in detailed_health.items():
+            overall = status['overall_status']
+            if overall == 'healthy':
+                status_groups[overall].append(service)
             else:
-                all_healthy = False
-                unhealthy_services.append({
-                    'service': service,
-                    'status': health_result.get('status', 'unknown'),
-                    'error': health_result.get('error', 'No error details')
-                })
-        
-        # Log detailed status for each attempt
-        logger.info(f"🔍 Health check attempt {attempt} ({elapsed:.1f}s elapsed, {time_remaining:.1f}s remaining):")
-        logger.info(f"   ✅ Healthy ({len(healthy_services)}): {healthy_services}")
-        
-        if unhealthy_services:
-            logger.info(f"   ❌ Unhealthy ({len(unhealthy_services)}):")
-            for us in unhealthy_services:
-                logger.info(f"      - {us['service']}: {us['status']} | Error: {us['error']}")
+                detail = f"{service}: {status['status']} (health: {status['health']}) | Error: {status['error']}"
+                status_groups[overall].append(detail)
+        
+        # Define order and emojis
+        statuses = ['healthy', 'starting', 'restarting', 'unhealthy', 'not found']
+        emojis = {'healthy': '✅', 'starting': '🚀', 'restarting': '🔄', 'unhealthy': '❌', 'not found': '❓'}
+        
+        # Log groups if they have items
+        for status in statuses:
+            group = status_groups[status]
+            if group:
+                emoji = emojis[status]
+                logger.info(f"   {emoji} {status.capitalize()} ({len(group)}):")
+                if status == 'healthy':
+                    logger.info(f"      {sorted(group)}")
+                else:
+                    for detail in sorted(group):
+                        logger.info(f"      - {detail}")
         
-        if all_healthy:
-            total_time = time.time() - start_time
-            logger.info(f"🎉 ALL SERVICES HEALTHY! Completed in {total_time:.1f}s after {attempt} attempts")
+        # Check if all healthy
+        if len(status_groups['healthy']) == len(services):
+            logger.info(f"🎉 ALL SERVICES HEALTHY! Completed in {elapsed:.1f}s after {attempt} attempts")
             return True
         
-        # Wait before next check
-        if time_remaining > interval:
-            logger.info(f"⏳ Waiting {interval}s before next health check...")
-            dt_ops.time.sleep(interval)
-        else:
-            # Don't sleep if we're about to timeout
-            break
-    
-    # Timeout reached
-    elapsed = time.time() - start_time
-    logger.error(f"⏰ HEALTH CHECK TIMEOUT after {elapsed:.1f}s and {attempt} attempts!")
-    logger.error(f"💔 Final status - Healthy: {len(healthy_services)}, Unhealthy: {len(unhealthy_services)}")
-    
-    if unhealthy_services:
-        logger.error("📋 Unhealthy services details:")
-        for us in unhealthy_services:
-            logger.error(f"   - {us['service']}: {us['status']} | {us['error']}")
+        # Wait for next attempt
+        logger.info(f"⏳ Waiting {interval}s before next health check...")
+        time.sleep(interval)
+        attempt += 1
     
+    # Timeout
+    logger.error(f"❌ Health check timeout after {time.time() - start_time:.1f}s")
     return False
 
 def health_check_docker_compose(compose_file: str) -> bool:
@@ -1281,6 +1273,8 @@ def _check_missing_images(
     
     return missing_services
 
+from collections import defaultdict  # Add this import at the top of your file
+
 def _perform_health_checks(
     compose_file: str,
     services: List[str],
@@ -1312,7 +1306,32 @@ def _perform_health_checks(
     # Get detailed health status for all services
     detailed_health = _get_detailed_health_status(compose_file, services, logger)
    
-    healthy_count = sum(1 for status in detailed_health.values() if status.get('overall_status') == 'healthy')
+    # Group services by overall_status for detailed logging
+    status_groups = defaultdict(list)
+    for service, status in detailed_health.items():
+        overall = status['overall_status']
+        if overall == 'healthy':
+            status_groups[overall].append(service)
+        else:
+            detail = f"{service}: {status['status']} (health: {status['health']}) | Error: {status['error']}"
+            status_groups[overall].append(detail)
+   
+    # Log grouped statuses
+    statuses = ['healthy', 'starting', 'restarting', 'unhealthy', 'not found']
+    emojis = {'healthy': '✅', 'starting': '🚀', 'restarting': '🔄', 'unhealthy': '❌', 'not found': '❓'}
+   
+    for status in statuses:
+        group = status_groups[status]
+        if group:
+            emoji = emojis[status]
+            logger.info(f"{emoji} {status.capitalize()} ({len(group)}):")
+            if status == 'healthy':
+                logger.info(f"   {sorted(group)}")
+            else:
+                for detail in sorted(group):
+                    logger.info(f"   - {detail}")
+   
+    healthy_count = len(status_groups['healthy'])
     unhealthy_count = len(services) - healthy_count
    
     logger.info(f"   Healthy: {healthy_count}/{len(services)}, Unhealthy: {unhealthy_count}")
@@ -1347,7 +1366,7 @@ def _get_detailed_health_status(
                 'error': service_status.get('error', 'No error details'),
                 'overall_status': overall_status
             }
-            logger.info(f"   {service}: {overall_status}")
+            # Removed: logger.info(f"   {service}: {overall_status}")  # Now handled grouped in _perform_health_checks
            
     except Exception as e:
         logger.error(f"Failed to get detailed health status: {e}")