cloudcat 0.3.5__tar.gz → 0.3.7__tar.gz

{cloudcat-0.3.5 → cloudcat-0.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cloudcat
-Version: 0.3.5
+Version: 0.3.7
 Summary: Preview and analyze data files in Google Cloud Storage, AWS S3, and Azure Data Lake Storage Gen2 from your terminal
 Home-page: https://github.com/jonathansudhakar1/cloudcat
 Author: Jonathan Sudhakar
@@ -187,7 +187,7 @@ cloudcat -p gcs://my-bucket/data.csv
 cloudcat -p s3://my-bucket/analytics/events.parquet
 
 # Preview JSON data from Azure with pretty formatting
-cloudcat -p az://my-container/logs.json -o jsonp
+cloudcat -p abfss://my-container@account.dfs.core.windows.net/logs.json -o jsonp
 
 # Read Avro files from Kafka
 cloudcat -p s3://my-bucket/kafka-export.avro
@@ -196,7 +196,7 @@ cloudcat -p s3://my-bucket/kafka-export.avro
 cloudcat -p gcs://my-bucket/hive-table.orc
 
 # Read log files as plain text
-cloudcat -p az://logs/app.log -i text
+cloudcat -p abfss://logs@account.dfs.core.windows.net/app.log -i text
 
 # Read from a Spark output directory
 cloudcat -p s3://my-bucket/spark-output/ -i parquet
@@ -219,7 +219,6 @@ cloudcat -p gcs://bucket/data.csv --offset 100 -n 10
 |----------|------------|--------|
 | Google Cloud Storage | `gcs://` or `gs://` | ✅ Supported |
 | Amazon S3 | `s3://` | ✅ Supported |
-| Azure Blob Storage | `az://` or `azure://` | ✅ Supported |
 | Azure Data Lake Gen2 | `abfss://` | ✅ Supported |
 
 ### File Format Support
@@ -338,7 +337,7 @@ cloudcat -p s3://bucket/logs.csv --where "level=ERROR"
 # String matching filters
 cloudcat -p gcs://bucket/data.csv --where "name contains john"
 cloudcat -p s3://bucket/emails.json --where "email endswith @gmail.com"
-cloudcat -p az://logs/app.log --where "message startswith ERROR"
+cloudcat -p abfss://logs@account.dfs.core.windows.net/app.log --where "message startswith ERROR"
 
 # Skip first N rows (pagination)
 cloudcat -p gcs://bucket/data.csv --offset 100 -n 10
@@ -361,7 +360,7 @@ cloudcat -p gcs://bucket/events.parquet.zst
 cloudcat -p s3://bucket/data.csv.lz4
 
 # Bzip2 compressed (built-in)
-cloudcat -p az://container/archive.json.bz2
+cloudcat -p abfss://container@account.dfs.core.windows.net/archive.json.bz2
 ```
 
 ### Directory Operations
@@ -482,7 +481,7 @@ Usage: cloudcat [OPTIONS]
 Options:
   -p, --path TEXT              Cloud storage path (required)
                                Format: gcs://bucket/path, s3://bucket/path,
-                               or az://container/path
+                               or abfss://container@account.dfs.core.windows.net/path
 
   -o, --output-format TEXT     Output format: table, json, jsonp, csv
                                [default: table]
@@ -582,23 +581,24 @@ cloudcat -p s3://bucket/data.csv --profile production
 # Automatically detected
 ```
 
-### Azure Blob Storage
+### Azure Data Lake Storage Gen2
 
-CloudCat supports multiple authentication methods for Azure:
+CloudCat supports multiple authentication methods for Azure ADLS Gen2:
 
 ```bash
-# Option 1: Connection string (simplest)
-export AZURE_STORAGE_CONNECTION_STRING="DefaultEndpointsProtocol=https;AccountName=...;AccountKey=...;EndpointSuffix=core.windows.net"
+# Option 1: Access key (simplest)
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv --az-access-key "YOUR_KEY"
 
-# Option 2: Account URL with DefaultAzureCredential (for Azure AD auth)
-export AZURE_STORAGE_ACCOUNT_URL="https://youraccount.blob.core.windows.net"
-az login
+# Option 2: Access key via environment variable
+export AZURE_STORAGE_ACCESS_KEY="YOUR_KEY"
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv
 
-# Option 3: Specify storage account via CLI option
-cloudcat -p az://container/data.csv --account mystorageaccount
+# Option 3: Azure CLI with DefaultAzureCredential
+az login
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv
 ```
 
-**Path format:** `az://container-name/path/to/blob`
+**Path format:** `abfss://container@account.dfs.core.windows.net/path/to/file`
 
 ## Performance Tips
 

{cloudcat-0.3.5 → cloudcat-0.3.7}/README.md

@@ -109,7 +109,7 @@ cloudcat -p gcs://my-bucket/data.csv
 cloudcat -p s3://my-bucket/analytics/events.parquet
 
 # Preview JSON data from Azure with pretty formatting
-cloudcat -p az://my-container/logs.json -o jsonp
+cloudcat -p abfss://my-container@account.dfs.core.windows.net/logs.json -o jsonp
 
 # Read Avro files from Kafka
 cloudcat -p s3://my-bucket/kafka-export.avro
@@ -118,7 +118,7 @@ cloudcat -p s3://my-bucket/kafka-export.avro
 cloudcat -p gcs://my-bucket/hive-table.orc
 
 # Read log files as plain text
-cloudcat -p az://logs/app.log -i text
+cloudcat -p abfss://logs@account.dfs.core.windows.net/app.log -i text
 
 # Read from a Spark output directory
 cloudcat -p s3://my-bucket/spark-output/ -i parquet
@@ -141,7 +141,6 @@ cloudcat -p gcs://bucket/data.csv --offset 100 -n 10
 |----------|------------|--------|
 | Google Cloud Storage | `gcs://` or `gs://` | ✅ Supported |
 | Amazon S3 | `s3://` | ✅ Supported |
-| Azure Blob Storage | `az://` or `azure://` | ✅ Supported |
 | Azure Data Lake Gen2 | `abfss://` | ✅ Supported |
 
 ### File Format Support
@@ -260,7 +259,7 @@ cloudcat -p s3://bucket/logs.csv --where "level=ERROR"
 # String matching filters
 cloudcat -p gcs://bucket/data.csv --where "name contains john"
 cloudcat -p s3://bucket/emails.json --where "email endswith @gmail.com"
-cloudcat -p az://logs/app.log --where "message startswith ERROR"
+cloudcat -p abfss://logs@account.dfs.core.windows.net/app.log --where "message startswith ERROR"
 
 # Skip first N rows (pagination)
 cloudcat -p gcs://bucket/data.csv --offset 100 -n 10
@@ -283,7 +282,7 @@ cloudcat -p gcs://bucket/events.parquet.zst
 cloudcat -p s3://bucket/data.csv.lz4
 
 # Bzip2 compressed (built-in)
-cloudcat -p az://container/archive.json.bz2
+cloudcat -p abfss://container@account.dfs.core.windows.net/archive.json.bz2
 ```
 
 ### Directory Operations
@@ -404,7 +403,7 @@ Usage: cloudcat [OPTIONS]
 Options:
   -p, --path TEXT              Cloud storage path (required)
                                Format: gcs://bucket/path, s3://bucket/path,
-                               or az://container/path
+                               or abfss://container@account.dfs.core.windows.net/path
 
   -o, --output-format TEXT     Output format: table, json, jsonp, csv
                                [default: table]
@@ -504,23 +503,24 @@ cloudcat -p s3://bucket/data.csv --profile production
 # Automatically detected
 ```
 
-### Azure Blob Storage
+### Azure Data Lake Storage Gen2
 
-CloudCat supports multiple authentication methods for Azure:
+CloudCat supports multiple authentication methods for Azure ADLS Gen2:
 
 ```bash
-# Option 1: Connection string (simplest)
-export AZURE_STORAGE_CONNECTION_STRING="DefaultEndpointsProtocol=https;AccountName=...;AccountKey=...;EndpointSuffix=core.windows.net"
+# Option 1: Access key (simplest)
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv --az-access-key "YOUR_KEY"
 
-# Option 2: Account URL with DefaultAzureCredential (for Azure AD auth)
-export AZURE_STORAGE_ACCOUNT_URL="https://youraccount.blob.core.windows.net"
-az login
+# Option 2: Access key via environment variable
+export AZURE_STORAGE_ACCESS_KEY="YOUR_KEY"
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv
 
-# Option 3: Specify storage account via CLI option
-cloudcat -p az://container/data.csv --account mystorageaccount
+# Option 3: Azure CLI with DefaultAzureCredential
+az login
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv
 ```
 
-**Path format:** `az://container-name/path/to/blob`
+**Path format:** `abfss://container@account.dfs.core.windows.net/path/to/file`
 
 ## Performance Tips
 

{cloudcat-0.3.5 → cloudcat-0.3.7}/cloudcat/__init__.py

@@ -2,4 +2,4 @@
 #!/usr/bin/env python
 """cloudcat - A CLI utility to read and display files from cloud storage."""
 
-__version__ = "0.3.5"
+__version__ = "0.3.7"

{cloudcat-0.3.5 → cloudcat-0.3.7}/cloudcat/cli.py

@@ -163,8 +163,9 @@ def find_first_non_empty_file(
     service: str,
     bucket: str,
     prefix: str,
-    input_format: Optional[str] = None
-) -> str:
+    input_format: Optional[str] = None,
+    quiet: bool = False
+) -> Tuple[str, int]:
     """Find the first non-empty file in a directory that matches the input format.
 
     Args:
@@ -172,9 +173,10 @@ def find_first_non_empty_file(
         bucket: Bucket or container name.
         prefix: Directory prefix.
         input_format: Optional format filter.
+        quiet: If True, suppress output messages.
 
     Returns:
-        File path of the first suitable file.
+        Tuple of (file_path, file_size) for the first suitable file.
 
     Raises:
         ValueError: If no suitable files are found.
@@ -201,21 +203,24 @@ def find_first_non_empty_file(
             if matching_files:
                 # Use the first matching file
                 selected_file = matching_files[0]
-                click.echo(Fore.BLUE + f"Selected file: {selected_file[0]} ({selected_file[1]} bytes)" + Style.RESET_ALL)
-                return selected_file[0]
+                if not quiet:
+                    click.echo(Fore.BLUE + f"Selected file: {selected_file[0]} ({selected_file[1]} bytes)" + Style.RESET_ALL)
+                return selected_file[0], selected_file[1]
 
     # If no input_format specified or no matching files found, use the first non-empty file
     # Skip common metadata files
     for file_name, file_size in non_empty_files:
         # Skip if the file matches any of the patterns to ignore
         if not any(re.search(pattern, file_name) for pattern in SKIP_PATTERNS):
-            click.echo(Fore.BLUE + f"Selected file: {file_name} ({file_size} bytes)" + Style.RESET_ALL)
-            return file_name
+            if not quiet:
+                click.echo(Fore.BLUE + f"Selected file: {file_name} ({file_size} bytes)" + Style.RESET_ALL)
+            return file_name, file_size
 
     # If all files are skipped, use the first non-empty file anyway
     selected_file = non_empty_files[0]
-    click.echo(Fore.YELLOW + f"Only found metadata files, using: {selected_file[0]} ({selected_file[1]} bytes)" + Style.RESET_ALL)
-    return selected_file[0]
+    if not quiet:
+        click.echo(Fore.YELLOW + f"Only found metadata files, using: {selected_file[0]} ({selected_file[1]} bytes)" + Style.RESET_ALL)
+    return selected_file[0], selected_file[1]
 
 
 def detect_format_from_path(path: str) -> str:
@@ -838,8 +843,8 @@ def main(path, output_format, input_format, columns, num_rows, offset, where, sc
         # Parse the path
         service, bucket, object_path = parse_cloud_path(path)
 
-        # Check if path is a directory (ends with '/')
-        is_directory = object_path.endswith('/')
+        # Check if path is a directory (ends with '/' or is empty = bucket root)
+        is_directory = object_path.endswith('/') or object_path == ''
 
         # Initialize streaming stats
         streaming_stats = None
@@ -850,51 +855,83 @@ def main(path, output_format, input_format, columns, num_rows, offset, where, sc
             if multi_file_mode == 'first' or (multi_file_mode == 'auto' and max_size_mb <= 0):
                 # Use a single file
                 start_progress("Listing files...")
-                object_path = find_first_non_empty_file(service, bucket, object_path, input_format)
+
+                # Find first non-empty file (quiet during progress)
+                object_path, file_size = find_first_non_empty_file(service, bucket, object_path, input_format, quiet=True)
+                stop_progress()
+
+                # Show file selection info
+                click.echo(Fore.BLUE + f"Selected file: {object_path} ({file_size} bytes)" + Style.RESET_ALL)
 
                 # Determine input format if not specified
                 if not input_format:
                     input_format = detect_format_from_path(object_path)
+                click.echo(Fore.BLUE + f"Inferred input format: {input_format}" + Style.RESET_ALL)
 
                 # Get file name for display
                 file_name = object_path.split('/')[-1]
-                update_progress(f"Reading {file_name}...")
+                start_progress(f"Reading {file_name}...")
 
                 # Read the data from the single file with streaming
                 df, full_schema, streaming_stats = read_data_streaming(service, bucket, object_path, input_format, num_rows, columns, delimiter, offset)
                 total_record_count = None  # Will be computed later if needed
 
-                # Stop progress and show format info
+                # Stop progress
                 stop_progress()
-                click.echo(Fore.BLUE + f"Inferred input format: {input_format}" + Style.RESET_ALL)
             else:
                 # Read from multiple files
                 start_progress("Listing files...")
 
-                # Determine input format if not specified (use the first file to infer)
+                # Get files to read for preview (limited by max_size_mb)
+                # First, determine input format if not specified (use the first file to infer)
                 if not input_format:
-                    first_file = find_first_non_empty_file(service, bucket, object_path)
+                    stop_progress()
+                    first_file, _ = find_first_non_empty_file(service, bucket, object_path, quiet=True)
                     input_format = detect_format_from_path(first_file)
+                    start_progress(f"Selecting {input_format} files...")
+                else:
+                    update_progress(f"Selecting {input_format} files...")
 
-                update_progress(f"Selecting {input_format} files...")
-
-                # Get files to read for preview (limited by max_size_mb)
                 file_list = get_files_for_multiread(service, bucket, object_path, input_format, max_size_mb, quiet=True)
 
-                # Read data from multiple files with progress updates
-                update_progress(f"Reading {len(file_list)} files...")
-                df, full_schema, rows_in_files = read_data_from_multiple_files(
-                    service, bucket, file_list, input_format, num_rows, columns, delimiter, offset, quiet=True
-                )
+                # For a single file, use streaming read for efficiency
+                if len(file_list) == 1:
+                    single_file_path = file_list[0][0]
+                    file_name = single_file_path.split('/')[-1]
+                    update_progress(f"Reading {file_name}...")
 
-                # Calculate total size for stats
-                total_size = sum(f[1] for f in file_list)
-                streaming_stats = StreamingStats(file_size=total_size, bytes_read=total_size, format_type=input_format)
+                    # Use streaming read for all formats
+                    df, full_schema, streaming_stats = read_data_streaming(
+                        service, bucket, single_file_path, input_format, num_rows, columns, delimiter, offset
+                    )
+                    stop_progress()
+
+                    click.echo(Fore.BLUE + f"Inferred input format: {input_format}" + Style.RESET_ALL)
+                    multi_file_list = file_list
+                    total_record_count = None
+                elif len(file_list) > 1:
+                    # Read data from multiple files with progress updates
+                    update_progress(f"Reading {len(file_list)} files...")
+                    df, full_schema, rows_in_files = read_data_from_multiple_files(
+                        service, bucket, file_list, input_format, num_rows, columns, delimiter, offset, quiet=True
+                    )
+
+                    # Stop progress before any output
+                    stop_progress()
+
+                    # Calculate total size for stats
+                    total_size = sum(f[1] for f in file_list)
+                    streaming_stats = StreamingStats(file_size=total_size, bytes_read=total_size, format_type=input_format)
+
+                    click.echo(Fore.BLUE + f"Inferred input format: {input_format}" + Style.RESET_ALL)
+
+                    # total_record_count will be computed later if --count is specified
+                    total_record_count = None
+                    multi_file_list = file_list
 
                 # For --count, get ALL files (not limited by max_size_mb)
                 # so we can count records across the entire directory
                 if count:
-                    stop_progress()
                     all_files = get_files_for_multiread(service, bucket, object_path, input_format, max_size_mb=999999, quiet=True)
                     all_files_size = sum(f[1] for f in all_files)
                     all_files_size_mb = all_files_size / (1024 * 1024)
@@ -909,15 +946,6 @@ def main(path, output_format, input_format, columns, num_rows, offset, where, sc
                     multi_file_list = all_files
                     # Update stats to reflect all files
                     streaming_stats.file_size = all_files_size
-                else:
-                    stop_progress()
-                    multi_file_list = file_list
-
-                # Show format info
-                click.echo(Fore.BLUE + f"Inferred input format: {input_format}" + Style.RESET_ALL)
-
-                # total_record_count will be computed later if --count is specified
-                total_record_count = None
 
                 # Update object_path for display/logging purposes
                 num_files_display = len(multi_file_list) if count else len(file_list)
@@ -1008,6 +1036,7 @@ def main(path, output_format, input_format, columns, num_rows, offset, where, sc
             click.echo(Fore.BLUE + f"\n{streaming_stats.format_report()}" + Style.RESET_ALL)
 
     except Exception as e:
+        stop_progress()  # Make sure progress is stopped on error
         click.echo(Fore.RED + f"Error: {str(e)}" + Style.RESET_ALL, err=True)
         sys.exit(1)
 

{cloudcat-0.3.5 → cloudcat-0.3.7}/cloudcat/progress.py

@@ -46,9 +46,10 @@ class ProgressIndicator:
             self._thread.join(timeout=0.5)
             self._thread = None
 
-        # Clear the current line
-        sys.stderr.write('\r' + ' ' * 80 + '\r')
-        sys.stderr.flush()
+        # Clear the current line - use stdout since that's where output goes
+        # Use a wider clear to handle wide terminals
+        sys.stdout.write('\r' + ' ' * 120 + '\r')
+        sys.stdout.flush()
 
         # Show final message if provided
         if final_message:
@@ -66,11 +67,12 @@ class ProgressIndicator:
                 self._frame_index = (self._frame_index + 1) % len(self.SPINNER_FRAMES)
 
             # Write spinner and message, overwriting the line
+            # Use stdout to match the rest of the CLI output
             output = f'\r{Fore.CYAN}{frame}{Style.RESET_ALL} {message}'
             # Pad to clear any leftover characters from longer previous messages
-            output = output.ljust(80)
-            sys.stderr.write(output)
-            sys.stderr.flush()
+            output = output.ljust(120)
+            sys.stdout.write(output)
+            sys.stdout.flush()
 
             time.sleep(0.08)
 

{cloudcat-0.3.5 → cloudcat-0.3.7}/cloudcat/storage/azure.py

@@ -12,10 +12,21 @@ from ..config import cloud_config
 # Try to import Azure Data Lake client
 try:
     from azure.storage.filedatalake import DataLakeServiceClient
-    HAS_AZURE = True
+    HAS_AZURE_DATALAKE = True
 except ImportError:
     DataLakeServiceClient = None
-    HAS_AZURE = False
+    HAS_AZURE_DATALAKE = False
+
+# Try to import Azure Blob client (fallback for non-HNS accounts)
+try:
+    from azure.storage.blob import BlobServiceClient
+    HAS_AZURE_BLOB = True
+except ImportError:
+    BlobServiceClient = None
+    HAS_AZURE_BLOB = False
+
+# Combined availability check
+HAS_AZURE = HAS_AZURE_DATALAKE or HAS_AZURE_BLOB
 
 
 def get_azure_datalake_service_client():
@@ -32,7 +43,7 @@ def get_azure_datalake_service_client():
         SystemExit: If azure-storage-file-datalake is not installed.
         ValueError: If Azure credentials are not configured.
     """
-    if not HAS_AZURE:
+    if not HAS_AZURE_DATALAKE:
         sys.stderr.write(
             Fore.RED + "Error: azure-storage-file-datalake package is required for Azure access.\n" +
             "Install it with: pip install azure-storage-file-datalake\n" + Style.RESET_ALL
@@ -62,6 +73,39 @@ def get_azure_datalake_service_client():
         return DataLakeServiceClient(account_url=account_url, credential=credential)
 
 
+def _get_blob_service_client():
+    """Get an Azure BlobServiceClient for fallback operations.
+
+    Used when DataLake API is not available or fails (e.g., non-HNS accounts).
+
+    Returns:
+        azure.storage.blob.BlobServiceClient instance.
+    """
+    if not HAS_AZURE_BLOB:
+        sys.stderr.write(
+            Fore.RED + "Error: azure-storage-blob package is required for Azure access.\n" +
+            "Install it with: pip install azure-storage-blob\n" + Style.RESET_ALL
+        )
+        sys.exit(1)
+
+    account_name = cloud_config.azure_account
+    if not account_name:
+        raise ValueError(
+            "Azure storage account not found. Use abfss:// URL format: "
+            "abfss://container@account.dfs.core.windows.net/path"
+        )
+
+    account_url = f"https://{account_name}.blob.core.windows.net"
+    access_key = cloud_config.azure_access_key or os.environ.get('AZURE_STORAGE_ACCESS_KEY')
+
+    if access_key:
+        return BlobServiceClient(account_url=account_url, credential=access_key)
+    else:
+        from azure.identity import DefaultAzureCredential
+        credential = DefaultAzureCredential()
+        return BlobServiceClient(account_url=account_url, credential=credential)
+
+
 # Keep old function name as alias for backwards compatibility
 get_azure_blob_service_client = get_azure_datalake_service_client
 
@@ -106,16 +150,8 @@ def get_azure_file_size(container_name: str, file_path: str) -> int:
     return properties.size
 
 
-def list_azure_directory(container_name: str, prefix: str) -> List[Tuple[str, int]]:
-    """List files in an Azure Data Lake Storage directory.
-
-    Args:
-        container_name: Azure filesystem (container) name.
-        prefix: Directory prefix.
-
-    Returns:
-        List of (filename, size) tuples.
-    """
+def _list_azure_directory_datalake(container_name: str, prefix: str) -> List[Tuple[str, int]]:
+    """List files using Azure Data Lake Storage API (requires HNS enabled)."""
     datalake_service_client = get_azure_datalake_service_client()
     file_system_client = datalake_service_client.get_file_system_client(file_system=container_name)
 
@@ -125,9 +161,68 @@ def list_azure_directory(container_name: str, prefix: str) -> List[Tuple[str, in
 
     # List paths with the prefix
     file_list = []
-    paths = file_system_client.get_paths(path=prefix.rstrip('/'))
+    paths = file_system_client.get_paths(path=prefix.rstrip('/') if prefix else None)
     for path in paths:
         if not path.is_directory:
             file_list.append((path.name, path.content_length))
 
     return file_list
+
+
+def _list_azure_directory_blob(container_name: str, prefix: str) -> List[Tuple[str, int]]:
+    """List files using Azure Blob Storage API (works with any storage account)."""
+    blob_service_client = _get_blob_service_client()
+    container_client = blob_service_client.get_container_client(container_name)
+
+    # Ensure prefix ends with / to indicate a directory (if not empty)
+    if prefix and not prefix.endswith('/'):
+        prefix = prefix + '/'
+
+    # List blobs with the prefix
+    file_list = []
+    blobs = container_client.list_blobs(name_starts_with=prefix if prefix else None)
+    for blob in blobs:
+        # Skip "directory" blobs (size 0, name ends with /)
+        if blob.size > 0 and not blob.name.endswith('/'):
+            file_list.append((blob.name, blob.size))
+
+    return file_list
+
+
+def list_azure_directory(container_name: str, prefix: str) -> List[Tuple[str, int]]:
+    """List files in an Azure storage directory.
+
+    Tries Data Lake API first (for HNS-enabled accounts), then falls back
+    to Blob Storage API (works with any storage account).
+
+    Args:
+        container_name: Azure filesystem (container) name.
+        prefix: Directory prefix.
+
+    Returns:
+        List of (filename, size) tuples.
+    """
+    # Try Data Lake API first (better performance for HNS accounts)
+    if HAS_AZURE_DATALAKE:
+        try:
+            return _list_azure_directory_datalake(container_name, prefix)
+        except Exception as e:
+            # Check if it's an endpoint/feature incompatibility error
+            error_str = str(e)
+            if 'EndpointUnsupportedAccountFeatures' in error_str or 'BlobStorageEvents' in error_str:
+                # Fall back to Blob API
+                if HAS_AZURE_BLOB:
+                    return _list_azure_directory_blob(container_name, prefix)
+            # Re-raise other errors
+            raise
+
+    # Fall back to Blob API if Data Lake not available
+    if HAS_AZURE_BLOB:
+        return _list_azure_directory_blob(container_name, prefix)
+
+    # Neither API available
+    sys.stderr.write(
+        Fore.RED + "Error: azure-storage-file-datalake or azure-storage-blob package is required.\n" +
+        "Install with: pip install azure-storage-file-datalake\n" + Style.RESET_ALL
+    )
+    sys.exit(1)

{cloudcat-0.3.5 → cloudcat-0.3.7}/cloudcat/storage/base.py

@@ -48,7 +48,7 @@ def parse_cloud_path(path: str) -> Tuple[str, str, str]:
             bucket = netloc
         object_path = parsed.path.lstrip('/')
     else:
-        raise ValueError(f"Unsupported scheme: {parsed.scheme}. Use gcs://, s3://, az://, or abfss://")
+        raise ValueError(f"Unsupported scheme: {parsed.scheme}. Use gcs://, s3://, or abfss://")
 
     return service, bucket, object_path
 

{cloudcat-0.3.5 → cloudcat-0.3.7}/cloudcat.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cloudcat
-Version: 0.3.5
+Version: 0.3.7
 Summary: Preview and analyze data files in Google Cloud Storage, AWS S3, and Azure Data Lake Storage Gen2 from your terminal
 Home-page: https://github.com/jonathansudhakar1/cloudcat
 Author: Jonathan Sudhakar
@@ -187,7 +187,7 @@ cloudcat -p gcs://my-bucket/data.csv
 cloudcat -p s3://my-bucket/analytics/events.parquet
 
 # Preview JSON data from Azure with pretty formatting
-cloudcat -p az://my-container/logs.json -o jsonp
+cloudcat -p abfss://my-container@account.dfs.core.windows.net/logs.json -o jsonp
 
 # Read Avro files from Kafka
 cloudcat -p s3://my-bucket/kafka-export.avro
@@ -196,7 +196,7 @@ cloudcat -p s3://my-bucket/kafka-export.avro
 cloudcat -p gcs://my-bucket/hive-table.orc
 
 # Read log files as plain text
-cloudcat -p az://logs/app.log -i text
+cloudcat -p abfss://logs@account.dfs.core.windows.net/app.log -i text
 
 # Read from a Spark output directory
 cloudcat -p s3://my-bucket/spark-output/ -i parquet
@@ -219,7 +219,6 @@ cloudcat -p gcs://bucket/data.csv --offset 100 -n 10
 |----------|------------|--------|
 | Google Cloud Storage | `gcs://` or `gs://` | ✅ Supported |
 | Amazon S3 | `s3://` | ✅ Supported |
-| Azure Blob Storage | `az://` or `azure://` | ✅ Supported |
 | Azure Data Lake Gen2 | `abfss://` | ✅ Supported |
 
 ### File Format Support
@@ -338,7 +337,7 @@ cloudcat -p s3://bucket/logs.csv --where "level=ERROR"
 # String matching filters
 cloudcat -p gcs://bucket/data.csv --where "name contains john"
 cloudcat -p s3://bucket/emails.json --where "email endswith @gmail.com"
-cloudcat -p az://logs/app.log --where "message startswith ERROR"
+cloudcat -p abfss://logs@account.dfs.core.windows.net/app.log --where "message startswith ERROR"
 
 # Skip first N rows (pagination)
 cloudcat -p gcs://bucket/data.csv --offset 100 -n 10
@@ -361,7 +360,7 @@ cloudcat -p gcs://bucket/events.parquet.zst
 cloudcat -p s3://bucket/data.csv.lz4
 
 # Bzip2 compressed (built-in)
-cloudcat -p az://container/archive.json.bz2
+cloudcat -p abfss://container@account.dfs.core.windows.net/archive.json.bz2
 ```
 
 ### Directory Operations
@@ -482,7 +481,7 @@ Usage: cloudcat [OPTIONS]
 Options:
   -p, --path TEXT              Cloud storage path (required)
                                Format: gcs://bucket/path, s3://bucket/path,
-                               or az://container/path
+                               or abfss://container@account.dfs.core.windows.net/path
 
   -o, --output-format TEXT     Output format: table, json, jsonp, csv
                                [default: table]
@@ -582,23 +581,24 @@ cloudcat -p s3://bucket/data.csv --profile production
 # Automatically detected
 ```
 
-### Azure Blob Storage
+### Azure Data Lake Storage Gen2
 
-CloudCat supports multiple authentication methods for Azure:
+CloudCat supports multiple authentication methods for Azure ADLS Gen2:
 
 ```bash
-# Option 1: Connection string (simplest)
-export AZURE_STORAGE_CONNECTION_STRING="DefaultEndpointsProtocol=https;AccountName=...;AccountKey=...;EndpointSuffix=core.windows.net"
+# Option 1: Access key (simplest)
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv --az-access-key "YOUR_KEY"
 
-# Option 2: Account URL with DefaultAzureCredential (for Azure AD auth)
-export AZURE_STORAGE_ACCOUNT_URL="https://youraccount.blob.core.windows.net"
-az login
+# Option 2: Access key via environment variable
+export AZURE_STORAGE_ACCESS_KEY="YOUR_KEY"
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv
 
-# Option 3: Specify storage account via CLI option
-cloudcat -p az://container/data.csv --account mystorageaccount
+# Option 3: Azure CLI with DefaultAzureCredential
+az login
+cloudcat -p abfss://container@account.dfs.core.windows.net/data.csv
 ```
 
-**Path format:** `az://container-name/path/to/blob`
+**Path format:** `abfss://container@account.dfs.core.windows.net/path/to/file`
 
 ## Performance Tips
 

{cloudcat-0.3.5 → cloudcat-0.3.7}/tests/test_cli.py

@@ -164,7 +164,7 @@ class TestCLI:
     @patch('cloudcat.cli.parse_cloud_path')
     def test_directory_path_first_mode(self, mock_parse, mock_read, mock_find):
         mock_parse.return_value = ("gcs", "bucket", "folder/")
-        mock_find.return_value = "folder/data.csv"
+        mock_find.return_value = ("folder/data.csv", 1024)  # Now returns tuple (path, size)
         mock_df = pd.DataFrame({"name": ["John"], "age": [25]})
         mock_read.return_value = (mock_df, mock_df.dtypes, StreamingStats())
 
@@ -182,7 +182,7 @@ class TestCLI:
     @patch('cloudcat.cli.find_first_non_empty_file')
     def test_directory_path_all_mode(self, mock_find, mock_parse, mock_read_multi, mock_get_files):
         mock_parse.return_value = ("s3", "bucket", "folder/")
-        mock_find.return_value = "folder/data.csv"
+        mock_find.return_value = ("folder/data.csv", 1024)  # Now returns tuple (path, size)
         mock_get_files.return_value = [("file1.csv", 1024), ("file2.csv", 2048)]
         mock_df = pd.DataFrame({"name": ["John"], "age": [25]})
         mock_read_multi.return_value = (mock_df, mock_df.dtypes, 100)

{cloudcat-0.3.5 → cloudcat-0.3.7}/tests/test_file_filtering.py

@@ -96,9 +96,10 @@ class TestFileFiltering:
             ("data2.csv", 2048)
         ]
 
-        first_file = find_first_non_empty_file("gcs", "bucket", "prefix")
+        file_path, file_size = find_first_non_empty_file("gcs", "bucket", "prefix", quiet=True)
 
-        assert first_file == "data1.csv"
+        assert file_path == "data1.csv"
+        assert file_size == 1024
 
     @patch('cloudcat.cli.list_directory')
     def test_find_first_non_empty_file_with_format_filter(self, mock_list_dir):
@@ -108,9 +109,10 @@ class TestFileFiltering:
             ("data3.parquet", 4096)
         ]
 
-        first_file = find_first_non_empty_file("gcs", "bucket", "prefix", input_format="json")
+        file_path, file_size = find_first_non_empty_file("gcs", "bucket", "prefix", input_format="json", quiet=True)
 
-        assert first_file == "data2.json"
+        assert file_path == "data2.json"
+        assert file_size == 2048
 
     @patch('cloudcat.cli.list_directory')
     def test_find_first_non_empty_file_azure(self, mock_list_dir):
@@ -119,9 +121,10 @@ class TestFileFiltering:
             ("data.csv", 1024)
         ]
 
-        first_file = find_first_non_empty_file("azure", "container", "prefix")
+        file_path, file_size = find_first_non_empty_file("azure", "container", "prefix", quiet=True)
 
-        assert first_file == "data.csv"
+        assert file_path == "data.csv"
+        assert file_size == 1024
 
     @patch('cloudcat.cli.list_directory')
     def test_get_files_for_multiread_no_files_raises_error(self, mock_list_dir):