fixed gzip decompression and index name for reports

czds/__init__.py

@@ -2,7 +2,9 @@
 # ICANN API for the Centralized Zones Data Service - developed by acidvegas (https://git.acid.vegas/czds)
 # czds/__init__.py
 
-__version__ = '1.3.4'
+from .client import CZDS
+
+__version__ = '1.3.8'
 __author__  = 'acidvegas'
 __email__   = 'acid.vegas@acid.vegas'
 __github__  = 'https://github.com/acidvegas/czds'

czds/client.py

@@ -6,6 +6,8 @@ import asyncio
 import json
 import logging
 import os
+import csv
+import io
 
 try:
     import aiohttp
@@ -138,15 +140,12 @@ class CZDS:
         Downloads the zone report stats from the API and scrubs the report for privacy
         
         :param filepath: Filepath to save the scrubbed report
-        :param scrub: Whether to scrub the username from the report
         :param format: Output format ('csv' or 'json')
         '''
-
         logging.info('Downloading zone stats report')
 
         # Send the request to the API
         async with self.session.get('https://czds-api.icann.org/czds/requests/report', headers=self.headers) as response:
-            # Check if the request was successful
             if response.status != 200:
                 raise Exception(f'Failed to download the zone stats report: {response.status} {await response.text()}')
 
@@ -157,9 +156,21 @@ class CZDS:
             content = content.replace(self.username, 'nobody@no.name')
             logging.debug('Scrubbed username from report')
 
-            # Convert the report to JSON format if requested (default is CSV)
+            # Convert the report to JSON format if requested
             if format.lower() == 'json':
-                content = json.dumps(content, indent=4)
+                # Parse CSV content
+                csv_reader = csv.DictReader(io.StringIO(content))
+                
+                # Convert to list of dicts with formatted keys
+                json_data = []
+                for row in csv_reader:
+                    formatted_row = {
+                        key.lower().replace(' ', '_'): value 
+                        for key, value in row.items()
+                    }
+                    json_data.append(formatted_row)
+                
+                content = json.dumps(json_data, indent=4)
                 logging.debug('Converted report to JSON format')
 
             # Save the report to a file if a filepath is provided

czds/utils.py

@@ -2,6 +2,7 @@
 # ICANN API for the Centralized Zones Data Service - developed by acidvegas (https://git.acid.vegas/czds)
 # czds/utils.py
 
+import asyncio
 import gzip
 import logging
 import os
@@ -24,41 +25,30 @@ async def gzip_decompress(filepath: str, cleanup: bool = True):
     :param filepath: Path to the gzip file
     :param cleanup: Whether to remove the original gzip file after decompressions
     '''
-
-    # Get the original size of the file
     original_size = os.path.getsize(filepath)
-
+    output_path = filepath[:-3]
+    
     logging.debug(f'Decompressing {filepath} ({humanize_bytes(original_size)})...')
 
-    # Remove the .gz extension
-    output_path = filepath[:-3]
+    # Use a large chunk size (256MB) for maximum throughput
+    chunk_size = 256 * 1024 * 1024
 
-    # Set the chunk size to 25MB
-    chunk_size = 25 * 1024 * 1024
-
-    # Create progress bar for decompression
+    # Run the actual decompression in a thread pool to prevent blocking
     with tqdm(total=original_size, unit='B', unit_scale=True, desc=f'Decompressing {os.path.basename(filepath)}', leave=False) as pbar:
-        # Decompress the file
-        with gzip.open(filepath, 'rb') as gz:
-            async with aiofiles.open(output_path, 'wb') as f_out:
+        async with aiofiles.open(output_path, 'wb') as f_out:
+            # Run gzip decompression in thread pool since it's CPU-bound
+            loop = asyncio.get_event_loop()
+            with gzip.open(filepath, 'rb') as gz:
                 while True:
-                    # Read the next chunk
-                    chunk = gz.read(chunk_size)
-
-                    # If the chunk is empty, break
+                    chunk = await loop.run_in_executor(None, gz.read, chunk_size)
                     if not chunk:
                         break
-
-                    # Write the chunk to the output file
                     await f_out.write(chunk)
                     pbar.update(len(chunk))
 
-    # Get the decompressed size of the file
     decompressed_size = os.path.getsize(output_path)
-
     logging.debug(f'Decompressed {filepath} ({humanize_bytes(decompressed_size)})')
 
-    # If the cleanup flag is set, remove the original gzip file
     if cleanup:
         os.remove(filepath)
         logging.debug(f'Removed original gzip file: {filepath}')

setup.py

@@ -11,7 +11,7 @@ with open('README.md', 'r', encoding='utf-8') as fh:
 
 setup(
 	name='czds-api',
-	version='1.3.4',
+	version='1.3.8',
 	author='acidvegas',
 	author_email='acid.vegas@acid.vegas',
 	description='ICANN API for the Centralized Zones Data Service',