Code bug fix & 1.0.1 release

CHANGELOG.md

@@ -1,5 +1,8 @@
-## Spark-submit
-##### Latest version: 0.1.0
+### Spark-submit
 
-#### 0.1.0 (2021-10-16)
+##### 1.0.1 (2021-10-22)
+- Fix wrong return code bug in `get_code()`
+- Change argument order in `submit()`
+
+##### 1.0.0 (2021-10-16)
 - First release

README.md

@@ -1,7 +1,7 @@
 ## Spark-submit
 
 [![PyPI version](https://badge.fury.io/py/spark-submit.svg)](https://badge.fury.io/py/spark-submit)
-[![Github All Releases](https://img.shields.io/github/downloads/PApostol/spark-submit/total.svg)]()
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/spark-submit)](https://pypi.org/project/spark-submit/)
 [![](https://img.shields.io/badge/python-3.5+-blue.svg)](https://www.python.org/downloads/)
 [![License](https://img.shields.io/badge/License-MIT-blue)](#license "Go to license section")
 [![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/PApostol/spark-submit/issues)
@@ -59,7 +59,7 @@ print(app.submit_cmd)
 print(app.env_vars)
 
 # monitor state in the background every x seconds with `await_result=x`
-app.submit(use_env_vars=True, await_result=10)
+app.submit(await_result=10, use_env_vars=True)
 
 print(app.get_state()) # 'SUBMITTED'
 
@@ -134,6 +134,15 @@ spark_args = {
 main_file = 's3a://mybucket/file.jar'
 app = SparkJob(main_file, **spark_args)
 ```
+
+#### Testing
+
+You can do some simple testing with local mode Spark after cloning the repo:
+
+`python tests/run_test.py`
+
+Note any additional requirements for running the tests: `pip install -r tests/requirements.txt`
+
 #### Additional methods
 
 `spark_submit.system_info()`: Collects Spark related system information, such as versions of spark-submit, Scala, Java, Python and OS
@@ -146,8 +155,8 @@ app = SparkJob(main_file, **spark_args)
 
 ### License
 
-Released under [MIT](/LICENSE) by [@PApostol](https://github.com/PApostol)
+Released under [MIT](/LICENSE) by [@PApostol](https://github.com/PApostol).
 
-- You can freely modify and reuse
-- The original license must be included with copies of this software
-- Please link back to this repo if you use a significant portion the source code
+- You can freely modify and reuse.
+- The original license must be included with copies of this software.
+- Please link back to this repo if you use a significant portion the source code.

setup.py

@@ -19,7 +19,7 @@
      license = about['__license__'],
      url = about['__url__'],
      description = about['__description__'],
-     long_description_content_type="text/markdown",
+     long_description_content_type = 'text/markdown',
      long_description = readme,
      packages = find_packages(),
      include_package_data = True,

spark_submit/__info__.py

@@ -11,7 +11,7 @@
 __author_email__ = 'foo@bar.com'
 __maintainer__ = 'PApostol'
 __license__ = 'MIT'
-__version__ = '1.0.0'
+__version__ = '1.0.1'
 __description__ = 'Python manager for spark-submit jobs'
 __url__ = 'https://github.com/PApostol/spark-submit'
 __bugtrack_url__ = f'{__url__}/issues'

spark_submit/sparkjob.py

@@ -116,16 +116,16 @@ def _check_submit(self) -> None:
                 self.submit_response['driver_state'] = driver_state[0]
 
 
-    def submit(self, use_env_vars: bool=False, await_result: int=0) -> None:
+    def submit(self, await_result: int=0, use_env_vars: bool=False) -> None:
         """Submits the current Spark job to Spark master
 
         Parameters
-            use_env_vars (bool): whether the environment variables obtained should be used (default: False)
             await_result (int): how often to poll for the Spark driver state in a background thread (default: 0, don't monitor in a background thread)
+            use_env_vars (bool): whether the environment variables obtained should be used (default: False)
 
         Returns:
             None
-       """
+        """
         env_vars = ''
         if use_env_vars:
             for env_var, val in self.env_vars.items():
@@ -146,7 +146,7 @@ def submit(self, use_env_vars: bool=False, await_result: int=0) -> None:
             self.submit_response['driver_state'] = 'ERROR'
             raise SparkSubmitError(f'{output}\nReturn code: {code}')
 
-        elif self.spark_args['deploy_mode']=='client':
+        elif self.spark_args['deploy_mode'] == 'client':
             self.submit_response['driver_state'] = 'FINISHED'
 
         else:
@@ -165,7 +165,7 @@ def get_state(self) -> str:
 
         Returns:
             str: Spark job driver state
-       """
+        """
         self._check_submit()
         return self.submit_response['driver_state']
 
@@ -175,7 +175,7 @@ def get_output(self) -> str:
 
         Returns:
             str: spark-submit stdout
-       """
+        """
         return self.submit_response['output']
 
 
@@ -184,16 +184,16 @@ def get_code(self) -> int:
 
         Returns:
             int: spark-submit return code (returns -1 if no code)
-       """
-        return self.submit_response['code'] if self.submit_response['code'] else -1
+        """
+        return self.submit_response['code'] if isinstance(self.submit_response['code'], int) else -1
 
 
     def kill(self) -> None:
         """Kills the running Spark job (cluster mode only)
 
         Returns:
             None
-       """
+        """
         if self.submit_response['driver_state'] in end_sates:
             logging.warning('Spark job "{0}" has concluded with state {1} and cannot be killed.'.format(self.spark_args['name'], self.submit_response['driver_state']))
         elif self.submit_response['submission_id']:

spark_submit/system.py

@@ -28,7 +28,7 @@ def system_info() -> str:
 
     Returns:
         str: system information
-   """
+    """
     spark_bin = os.environ.get('SPARK_HOME', os.path.expanduser('~/spark_home')) + '/bin/spark-submit'
     cmd = spark_bin + ' --version'