airflow-toolkit 2.2.0__tar.gz → 2.4.0__tar.gz

{airflow_toolkit-2.2.0/src/airflow_toolkit.egg-info → airflow_toolkit-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: airflow-toolkit
-Version: 2.2.0
+Version: 2.4.0
 Summary: A toolkit of operators, hooks and utilities for Apache Airflow 3
 Author-email: Biel Llobera <biel_llobera@dkl.digital>
 Requires-Python: <3.15,>=3.11
@@ -32,6 +32,10 @@ Provides-Extra: duckdb
 Requires-Dist: airflow-provider-duckdb>=0.1.2; extra == "duckdb"
 Provides-Extra: sqlite
 Requires-Dist: apache-airflow-providers-sqlite; extra == "sqlite"
+Provides-Extra: excel
+Requires-Dist: openpyxl>=3.1; extra == "excel"
+Provides-Extra: avro
+Requires-Dist: fastavro>=1.9; extra == "avro"
 Provides-Extra: airflow3-full
 Requires-Dist: apache-airflow<4,>=3; extra == "airflow3-full"
 Requires-Dist: apache-airflow-providers-fab>=3.0.0; extra == "airflow3-full"
@@ -49,6 +53,8 @@ Requires-Dist: requests>=2.31.0; extra == "airflow3-full"
 Requires-Dist: jmespath<2,>=1.0.1; extra == "airflow3-full"
 Requires-Dist: airflow-provider-duckdb>=0.1.2; extra == "airflow3-full"
 Requires-Dist: apache-airflow-providers-sqlite; extra == "airflow3-full"
+Requires-Dist: openpyxl>=3.1; extra == "airflow3-full"
+Requires-Dist: fastavro>=1.9; extra == "airflow3-full"
 Dynamic: license-file
 
 # Airflow Toolkit
@@ -136,10 +142,11 @@ pip install "airflow-toolkit[airflow3-full]"
 | `google` | `providers-google` | GCS filesystem backend |
 | `azure` | `providers-microsoft-azure` | Azure Blob / ADLS filesystem backend |
 | `sftp` | `providers-sftp` | SFTP filesystem backend |
-| `slack` | `providers-slack` | Slack failure notifications |
 | `http` | `providers-http`, `requests`, `jmespath`, `pandas` | `HttpToFilesystem`, `MultiHttpToFilesystem` |
 | `duckdb` | `airflow-provider-duckdb` | `DuckdbToDeltalake` operator |
 | `sqlite` | `providers-sqlite` | SQLite as source or destination |
+| `excel` | `openpyxl` | Excel (`.xlsx` / `.xls`) support in `FilesystemToDatabase` and `HttpToFilesystem` |
+| `avro` | `fastavro` | Avro support in `FilesystemToDatabase` and `HttpToFilesystem` |
 | `airflow3-full` | all of the above | Quick start / development |
 
 ---
@@ -184,7 +191,7 @@ Changing the connection's `conn_type` is all that is needed to switch backends
 
 ### HttpToFilesystem
 
-Calls an HTTP endpoint and writes the response to any filesystem. Supports pagination, JMESPath filtering, compression, and custom response transformations.
+Calls an HTTP endpoint and writes the response to any filesystem. Supports pagination, JMESPath filtering, compression, OAuth 2.0 authentication, rate limiting, and custom response transformations.
 
 ```python
 from airflow_toolkit.providers.filesystem.operators.http_to_filesystem import HttpToFilesystem
@@ -201,7 +208,7 @@ HttpToFilesystem(
 )
 ```
 
-With cursor-based pagination:
+**With cursor-based pagination:**
 
 ```python
 def next_page(response):
@@ -223,9 +230,70 @@ HttpToFilesystem(
 )
 ```
 
+**With OAuth 2.0 Client Credentials:**
+
+`OAuth2ClientCredentials.client_credentials()` returns a configured auth class that fetches the token lazily on the first request and refreshes it automatically 30 seconds before expiry — no manual token management required.
+
+```python
+from airflow_toolkit.providers.filesystem.operators.auth import OAuth2ClientCredentials
+
+HttpToFilesystem(
+    task_id='fetch_protected_data',
+    http_conn_id='my_api',
+    filesystem_conn_id='my_data_lake',
+    filesystem_path='raw/data/{{ ds }}/',
+    endpoint='/api/v1/data',
+    method='GET',
+    save_format='jsonl',
+    auth_type=OAuth2ClientCredentials.client_credentials(
+        token_url='https://auth.example.com/oauth2/token',
+        client_id='{{ var.value.oauth2_client_id }}',
+        client_secret='{{ var.value.oauth2_client_secret }}',
+        scope='read',           # optional
+    ),
+)
+```
+
+**With rate limiting:**
+
+Use `requests_per_second` to cap how fast paginated requests are sent. This is useful when the API enforces a rate limit.
+
+```python
+HttpToFilesystem(
+    task_id='fetch_with_rate_limit',
+    http_conn_id='my_api',
+    filesystem_conn_id='my_data_lake',
+    filesystem_path='raw/events/{{ ds }}/',
+    endpoint='/api/v1/events',
+    method='GET',
+    pagination_function=next_page,
+    save_format='jsonl',
+    requests_per_second=3.0,    # max 3 requests per second between pages
+)
+```
+
+**Supported response formats:**
+
+`save_format` controls how the response is written to the filesystem. For APIs that return binary formats natively (e.g. a reporting API that streams Excel files), set `source_format` to match the response content type:
+
+| `source_format` / `save_format` | File extension | Notes |
+|---|---|---|
+| `json` | `.json` | Single JSON object or array |
+| `jsonl` | `.jsonl` | Array response written as one record per line |
+| `csv` | `.csv` | Raw CSV text from the response |
+| `xml` | `.xml` | Raw XML text from the response |
+| `parquet` | `.parquet` | Binary passthrough — API must return Parquet bytes |
+| `excel` | `.xlsx` | Binary passthrough — API must return Excel bytes (requires `[excel]`) |
+| `avro` | `.avro` | Binary passthrough — API must return Avro bytes (requires `[avro]`) |
+| `fixed_width` | `.fwf` | Fixed-width text from the response |
+
+All text and JSON formats support gzip/zip compression via the `compression` parameter.
+
 ### MultiHttpToFilesystem
 
-Runs multiple HTTP requests in a single Airflow task, saving each response as a separate file. Useful for fetching multiple entities or date ranges without creating one task per request.
+Runs multiple HTTP requests in a single Airflow task, saving each response as a separate file. Requests can run **sequentially** (with optional rate limiting) or **in parallel** using a thread pool.
+
+**Sequential with rate limiting:**
 
 ```python
 from airflow_toolkit.providers.filesystem.operators.http_to_filesystem import MultiHttpToFilesystem
@@ -237,6 +305,7 @@ MultiHttpToFilesystem(
     filesystem_path='raw/reference/{{ ds }}/',
     method='GET',
     save_format='jsonl',
+    requests_per_second=2.0,    # max 2 requests per second between calls
     multi_requests=[
         {'endpoint': '/api/v1/categories'},
         {'endpoint': '/api/v1/statuses'},
@@ -245,6 +314,31 @@ MultiHttpToFilesystem(
 )
 ```
 
+**Parallel execution:**
+
+Set `max_workers` to run requests concurrently using a thread pool. Each request writes to its own file — there are no file collisions.
+
+```python
+MultiHttpToFilesystem(
+    task_id='fetch_users_parallel',
+    http_conn_id='my_api',
+    filesystem_conn_id='my_data_lake',
+    filesystem_path='raw/users/{{ ds }}/',
+    method='GET',
+    save_format='json',
+    max_workers=5,              # up to 5 concurrent threads
+    multi_requests=[
+        {'endpoint': '/api/v1/users/1'},
+        {'endpoint': '/api/v1/users/2'},
+        {'endpoint': '/api/v1/users/3'},
+        {'endpoint': '/api/v1/users/4'},
+        {'endpoint': '/api/v1/users/5'},
+    ],
+)
+```
+
+> Rate limiting (`requests_per_second`) applies only in sequential mode. In parallel mode the thread pool controls concurrency — use `max_workers` to avoid overwhelming the API.
+
 Each entry in `multi_requests` can override any base parameter (`endpoint`, `method`, `headers`, `data`, `jmespath_expression`, `save_format`, `compression`).
 
 ### SQLToFilesystem
@@ -313,7 +407,9 @@ FilesystemToFilesystem(
 
 ### FilesystemToDatabase
 
-Reads files (CSV, JSON, or Parquet) from any filesystem and loads them into any SQLAlchemy-compatible database. Handles schema drift automatically: columns present in the file but missing from the table are added; columns present in the table but missing from the file are filled with `NULL`.
+Reads files from any filesystem and loads them into any SQLAlchemy-compatible database. Handles schema drift automatically: columns present in the file but missing from the table are added; columns present in the table but missing from the file are filled with `NULL`.
+
+**Supported formats:** `csv`, `json`, `parquet`, `excel`, `avro`, `fixed_width`.
 
 ```python
 from airflow_toolkit.providers.deltalake.operators.filesystem_to_database import FilesystemToDatabaseOperator
@@ -325,7 +421,7 @@ FilesystemToDatabaseOperator(
     filesystem_path='raw/orders/{{ ds }}/',
     db_schema='public',
     db_table='orders',
-    source_format='csv',
+    source_format='csv',                   # 'csv' | 'json' | 'parquet' | 'excel' | 'avro' | 'fixed_width'
     table_aggregation_type='append',       # 'append' | 'replace' | 'fail'
     metadata={
         '_ds':          '{{ ds }}',
@@ -335,6 +431,52 @@ FilesystemToDatabaseOperator(
 )
 ```
 
+**Excel** (requires the `[excel]` extra):
+
+```python
+FilesystemToDatabaseOperator(
+    task_id='load_excel_report',
+    filesystem_conn_id='my_data_lake',
+    database_conn_id='my_postgres',
+    filesystem_path='raw/reports/{{ ds }}/',
+    db_table='monthly_report',
+    source_format='excel',
+    source_format_options={'sheet_name': 'Data'},
+)
+```
+
+**Avro** (requires the `[avro]` extra):
+
+```python
+FilesystemToDatabaseOperator(
+    task_id='load_avro_events',
+    filesystem_conn_id='my_data_lake',
+    database_conn_id='my_postgres',
+    filesystem_path='raw/events/{{ ds }}/',
+    db_table='events',
+    source_format='avro',
+)
+```
+
+**Fixed-width** (no extra required — pandas native):
+
+```python
+FilesystemToDatabaseOperator(
+    task_id='load_fixed_width',
+    filesystem_conn_id='my_data_lake',
+    database_conn_id='my_postgres',
+    filesystem_path='raw/exports/{{ ds }}/',
+    db_table='transactions',
+    source_format='fixed_width',
+    source_format_options={
+        'colspecs': [(0, 10), (10, 25), (25, 35)],
+        'names': ['date', 'description', 'amount'],
+    },
+)
+```
+
+Each format is matched by file extension: `.csv`/`.csv.gz`, `.json`/`.json.gz`, `.parquet`/`.parquet.gz`, `.xlsx`/`.xls`, `.avro`, `.fwf`/`.txt`/`.dat`. Files with other extensions in the same prefix are silently skipped.
+
 ### DuckdbToDeltalake
 
 Executes a DuckDB SQL query and writes the result directly to a Delta Lake table on Azure storage. Useful for in-process transformations that land results as an open table format.
@@ -530,6 +672,50 @@ Each environment maps to a distinct colour across all channels so alerts are rec
 
 ---
 
+## Testing Utilities
+
+### MockFilesystem
+
+`MockFilesystem` is an in-memory implementation of `FilesystemProtocol` for unit testing. It requires no Docker, no cloud credentials, and no network — all files are stored in a plain Python dict.
+
+```python
+from airflow_toolkit.testing import MockFilesystem
+
+# Pre-load files at construction time
+fs = MockFilesystem({
+    "raw/orders/2024-01-01/data.csv": b"id,amount\n1,100\n2,200",
+})
+
+# Or write files programmatically
+fs.write(b"id,amount\n3,300", "raw/orders/2024-01-02/data.csv")
+
+# Inspect the result in assertions
+assert fs.check_file("raw/orders/2024-01-01/data.csv")
+assert len(fs.list_files("raw/orders/")) == 2
+assert fs.files["raw/orders/2024-01-01/data.csv"] == b"id,amount\n1,100\n2,200"
+```
+
+Use it to patch `FilesystemFactory.get_data_lake_filesystem` in your operator tests:
+
+```python
+from unittest.mock import patch
+from airflow_toolkit.testing import MockFilesystem
+
+def test_my_pipeline(tmp_path):
+    fs = MockFilesystem({"data/file.csv": b"id,name\n1,Alice"})
+
+    with patch(
+        "airflow_toolkit.filesystems.filesystem_factory.FilesystemFactory.get_data_lake_filesystem",
+        return_value=fs,
+    ):
+        # run your operator or task here
+        ...
+```
+
+`MockFilesystem` implements the full `FilesystemProtocol`: `read`, `write`, `delete_file`, `create_prefix`, `delete_prefix`, `check_file`, `check_prefix`, `list_files`.
+
+---
+
 ## Running Tests
 
 ### Integration tests

{airflow_toolkit-2.2.0 → airflow_toolkit-2.4.0}/README.md

@@ -83,10 +83,11 @@ pip install "airflow-toolkit[airflow3-full]"
 | `google` | `providers-google` | GCS filesystem backend |
 | `azure` | `providers-microsoft-azure` | Azure Blob / ADLS filesystem backend |
 | `sftp` | `providers-sftp` | SFTP filesystem backend |
-| `slack` | `providers-slack` | Slack failure notifications |
 | `http` | `providers-http`, `requests`, `jmespath`, `pandas` | `HttpToFilesystem`, `MultiHttpToFilesystem` |
 | `duckdb` | `airflow-provider-duckdb` | `DuckdbToDeltalake` operator |
 | `sqlite` | `providers-sqlite` | SQLite as source or destination |
+| `excel` | `openpyxl` | Excel (`.xlsx` / `.xls`) support in `FilesystemToDatabase` and `HttpToFilesystem` |
+| `avro` | `fastavro` | Avro support in `FilesystemToDatabase` and `HttpToFilesystem` |
 | `airflow3-full` | all of the above | Quick start / development |
 
 ---
@@ -131,7 +132,7 @@ Changing the connection's `conn_type` is all that is needed to switch backends
 
 ### HttpToFilesystem
 
-Calls an HTTP endpoint and writes the response to any filesystem. Supports pagination, JMESPath filtering, compression, and custom response transformations.
+Calls an HTTP endpoint and writes the response to any filesystem. Supports pagination, JMESPath filtering, compression, OAuth 2.0 authentication, rate limiting, and custom response transformations.
 
 ```python
 from airflow_toolkit.providers.filesystem.operators.http_to_filesystem import HttpToFilesystem
@@ -148,7 +149,7 @@ HttpToFilesystem(
 )
 ```
 
-With cursor-based pagination:
+**With cursor-based pagination:**
 
 ```python
 def next_page(response):
@@ -170,9 +171,70 @@ HttpToFilesystem(
 )
 ```
 
+**With OAuth 2.0 Client Credentials:**
+
+`OAuth2ClientCredentials.client_credentials()` returns a configured auth class that fetches the token lazily on the first request and refreshes it automatically 30 seconds before expiry — no manual token management required.
+
+```python
+from airflow_toolkit.providers.filesystem.operators.auth import OAuth2ClientCredentials
+
+HttpToFilesystem(
+    task_id='fetch_protected_data',
+    http_conn_id='my_api',
+    filesystem_conn_id='my_data_lake',
+    filesystem_path='raw/data/{{ ds }}/',
+    endpoint='/api/v1/data',
+    method='GET',
+    save_format='jsonl',
+    auth_type=OAuth2ClientCredentials.client_credentials(
+        token_url='https://auth.example.com/oauth2/token',
+        client_id='{{ var.value.oauth2_client_id }}',
+        client_secret='{{ var.value.oauth2_client_secret }}',
+        scope='read',           # optional
+    ),
+)
+```
+
+**With rate limiting:**
+
+Use `requests_per_second` to cap how fast paginated requests are sent. This is useful when the API enforces a rate limit.
+
+```python
+HttpToFilesystem(
+    task_id='fetch_with_rate_limit',
+    http_conn_id='my_api',
+    filesystem_conn_id='my_data_lake',
+    filesystem_path='raw/events/{{ ds }}/',
+    endpoint='/api/v1/events',
+    method='GET',
+    pagination_function=next_page,
+    save_format='jsonl',
+    requests_per_second=3.0,    # max 3 requests per second between pages
+)
+```
+
+**Supported response formats:**
+
+`save_format` controls how the response is written to the filesystem. For APIs that return binary formats natively (e.g. a reporting API that streams Excel files), set `source_format` to match the response content type:
+
+| `source_format` / `save_format` | File extension | Notes |
+|---|---|---|
+| `json` | `.json` | Single JSON object or array |
+| `jsonl` | `.jsonl` | Array response written as one record per line |
+| `csv` | `.csv` | Raw CSV text from the response |
+| `xml` | `.xml` | Raw XML text from the response |
+| `parquet` | `.parquet` | Binary passthrough — API must return Parquet bytes |
+| `excel` | `.xlsx` | Binary passthrough — API must return Excel bytes (requires `[excel]`) |
+| `avro` | `.avro` | Binary passthrough — API must return Avro bytes (requires `[avro]`) |
+| `fixed_width` | `.fwf` | Fixed-width text from the response |
+
+All text and JSON formats support gzip/zip compression via the `compression` parameter.
+
 ### MultiHttpToFilesystem
 
-Runs multiple HTTP requests in a single Airflow task, saving each response as a separate file. Useful for fetching multiple entities or date ranges without creating one task per request.
+Runs multiple HTTP requests in a single Airflow task, saving each response as a separate file. Requests can run **sequentially** (with optional rate limiting) or **in parallel** using a thread pool.
+
+**Sequential with rate limiting:**
 
 ```python
 from airflow_toolkit.providers.filesystem.operators.http_to_filesystem import MultiHttpToFilesystem
@@ -184,6 +246,7 @@ MultiHttpToFilesystem(
     filesystem_path='raw/reference/{{ ds }}/',
     method='GET',
     save_format='jsonl',
+    requests_per_second=2.0,    # max 2 requests per second between calls
     multi_requests=[
         {'endpoint': '/api/v1/categories'},
         {'endpoint': '/api/v1/statuses'},
@@ -192,6 +255,31 @@ MultiHttpToFilesystem(
 )
 ```
 
+**Parallel execution:**
+
+Set `max_workers` to run requests concurrently using a thread pool. Each request writes to its own file — there are no file collisions.
+
+```python
+MultiHttpToFilesystem(
+    task_id='fetch_users_parallel',
+    http_conn_id='my_api',
+    filesystem_conn_id='my_data_lake',
+    filesystem_path='raw/users/{{ ds }}/',
+    method='GET',
+    save_format='json',
+    max_workers=5,              # up to 5 concurrent threads
+    multi_requests=[
+        {'endpoint': '/api/v1/users/1'},
+        {'endpoint': '/api/v1/users/2'},
+        {'endpoint': '/api/v1/users/3'},
+        {'endpoint': '/api/v1/users/4'},
+        {'endpoint': '/api/v1/users/5'},
+    ],
+)
+```
+
+> Rate limiting (`requests_per_second`) applies only in sequential mode. In parallel mode the thread pool controls concurrency — use `max_workers` to avoid overwhelming the API.
+
 Each entry in `multi_requests` can override any base parameter (`endpoint`, `method`, `headers`, `data`, `jmespath_expression`, `save_format`, `compression`).
 
 ### SQLToFilesystem
@@ -260,7 +348,9 @@ FilesystemToFilesystem(
 
 ### FilesystemToDatabase
 
-Reads files (CSV, JSON, or Parquet) from any filesystem and loads them into any SQLAlchemy-compatible database. Handles schema drift automatically: columns present in the file but missing from the table are added; columns present in the table but missing from the file are filled with `NULL`.
+Reads files from any filesystem and loads them into any SQLAlchemy-compatible database. Handles schema drift automatically: columns present in the file but missing from the table are added; columns present in the table but missing from the file are filled with `NULL`.
+
+**Supported formats:** `csv`, `json`, `parquet`, `excel`, `avro`, `fixed_width`.
 
 ```python
 from airflow_toolkit.providers.deltalake.operators.filesystem_to_database import FilesystemToDatabaseOperator
@@ -272,7 +362,7 @@ FilesystemToDatabaseOperator(
     filesystem_path='raw/orders/{{ ds }}/',
     db_schema='public',
     db_table='orders',
-    source_format='csv',
+    source_format='csv',                   # 'csv' | 'json' | 'parquet' | 'excel' | 'avro' | 'fixed_width'
     table_aggregation_type='append',       # 'append' | 'replace' | 'fail'
     metadata={
         '_ds':          '{{ ds }}',
@@ -282,6 +372,52 @@ FilesystemToDatabaseOperator(
 )
 ```
 
+**Excel** (requires the `[excel]` extra):
+
+```python
+FilesystemToDatabaseOperator(
+    task_id='load_excel_report',
+    filesystem_conn_id='my_data_lake',
+    database_conn_id='my_postgres',
+    filesystem_path='raw/reports/{{ ds }}/',
+    db_table='monthly_report',
+    source_format='excel',
+    source_format_options={'sheet_name': 'Data'},
+)
+```
+
+**Avro** (requires the `[avro]` extra):
+
+```python
+FilesystemToDatabaseOperator(
+    task_id='load_avro_events',
+    filesystem_conn_id='my_data_lake',
+    database_conn_id='my_postgres',
+    filesystem_path='raw/events/{{ ds }}/',
+    db_table='events',
+    source_format='avro',
+)
+```
+
+**Fixed-width** (no extra required — pandas native):
+
+```python
+FilesystemToDatabaseOperator(
+    task_id='load_fixed_width',
+    filesystem_conn_id='my_data_lake',
+    database_conn_id='my_postgres',
+    filesystem_path='raw/exports/{{ ds }}/',
+    db_table='transactions',
+    source_format='fixed_width',
+    source_format_options={
+        'colspecs': [(0, 10), (10, 25), (25, 35)],
+        'names': ['date', 'description', 'amount'],
+    },
+)
+```
+
+Each format is matched by file extension: `.csv`/`.csv.gz`, `.json`/`.json.gz`, `.parquet`/`.parquet.gz`, `.xlsx`/`.xls`, `.avro`, `.fwf`/`.txt`/`.dat`. Files with other extensions in the same prefix are silently skipped.
+
 ### DuckdbToDeltalake
 
 Executes a DuckDB SQL query and writes the result directly to a Delta Lake table on Azure storage. Useful for in-process transformations that land results as an open table format.
@@ -477,6 +613,50 @@ Each environment maps to a distinct colour across all channels so alerts are rec
 
 ---
 
+## Testing Utilities
+
+### MockFilesystem
+
+`MockFilesystem` is an in-memory implementation of `FilesystemProtocol` for unit testing. It requires no Docker, no cloud credentials, and no network — all files are stored in a plain Python dict.
+
+```python
+from airflow_toolkit.testing import MockFilesystem
+
+# Pre-load files at construction time
+fs = MockFilesystem({
+    "raw/orders/2024-01-01/data.csv": b"id,amount\n1,100\n2,200",
+})
+
+# Or write files programmatically
+fs.write(b"id,amount\n3,300", "raw/orders/2024-01-02/data.csv")
+
+# Inspect the result in assertions
+assert fs.check_file("raw/orders/2024-01-01/data.csv")
+assert len(fs.list_files("raw/orders/")) == 2
+assert fs.files["raw/orders/2024-01-01/data.csv"] == b"id,amount\n1,100\n2,200"
+```
+
+Use it to patch `FilesystemFactory.get_data_lake_filesystem` in your operator tests:
+
+```python
+from unittest.mock import patch
+from airflow_toolkit.testing import MockFilesystem
+
+def test_my_pipeline(tmp_path):
+    fs = MockFilesystem({"data/file.csv": b"id,name\n1,Alice"})
+
+    with patch(
+        "airflow_toolkit.filesystems.filesystem_factory.FilesystemFactory.get_data_lake_filesystem",
+        return_value=fs,
+    ):
+        # run your operator or task here
+        ...
+```
+
+`MockFilesystem` implements the full `FilesystemProtocol`: `read`, `write`, `delete_file`, `create_prefix`, `delete_prefix`, `check_file`, `check_prefix`, `list_files`.
+
+---
+
 ## Running Tests
 
 ### Integration tests

{airflow_toolkit-2.2.0 → airflow_toolkit-2.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "airflow-toolkit"
-version = "2.2.0"
+version = "2.4.0"
 description = "A toolkit of operators, hooks and utilities for Apache Airflow 3"
 authors = [{ name = "Biel Llobera", email = "biel_llobera@dkl.digital" }]
 requires-python = ">=3.11,<3.15"
@@ -49,6 +49,12 @@ duckdb = [
 sqlite = [
     "apache-airflow-providers-sqlite",
 ]
+excel = [
+    "openpyxl>=3.1",
+]
+avro = [
+    "fastavro>=1.9",
+]
 airflow3-full = [
     "apache-airflow>=3,<4",
     "apache-airflow-providers-fab>=3.0.0",
@@ -66,6 +72,8 @@ airflow3-full = [
     "jmespath>=1.0.1,<2",
     "airflow-provider-duckdb>=0.1.2",
     "apache-airflow-providers-sqlite",
+    "openpyxl>=3.1",
+    "fastavro>=1.9",
 ]
 
 [dependency-groups]

{airflow_toolkit-2.2.0 → airflow_toolkit-2.4.0}/src/airflow_toolkit/compression_utils.py

@@ -1,10 +1,10 @@
 import gzip
 import zipfile
 from io import BytesIO
-from typing import Literal, Union
+
+from airflow_toolkit.types import CompressionOptions
 
 DEFAULT_ZIP_FILENAME = "file.zip"
-CompressionOptions = Union[Literal["infer", "gzip", "bz2", "zip", "xz", "zstd"], None]
 
 
 def gzip_data(data: bytes) -> bytes: