refactor: update cli to take logging arguments and add description (#14)

* Updated Description to be in Cli

* Updated Logging Level to be set via Cli

* updated readme with new cli option

* udpated env vars to be consistent

* updated readme

Author: kiran94

README.md

@@ -41,6 +41,8 @@ usage: dgraphpandas [-h] -f FILE -c CONFIG -ck CONFIG_FILE_KEY [-o OUTPUT_DIR]
                     [--drop_na_edge_objects DROP_NA_EDGE_OBJECTS]
                     [--illegal_characters ILLEGAL_CHARACTERS]
                     [--illegal_characters_intrinsic_object ILLEGAL_CHARACTERS_INTRINSIC_OBJECT]
+                    [--version]
+                    [-v {DEBUG,INFO,WARNING,ERROR,NOTSET}]
 ```
 
 This is a real example which you can find in the [samples folder](https://github.com/kiran94/dgraphpandas/tree/main/samples) and run from the root of this repository:

dgraphpandas/__init__.py

@@ -1,2 +1,3 @@
 __name__ = 'dgraphpandas'
-__version__ = '0.0.9'
+__version__ = '0.0.10'
+__description__ = 'Transform Pandas DataFrames into Exports to be sent to DGraph'

dgraphpandas/__main__.py

@@ -8,32 +8,24 @@
 
 import pandas as pd
 
-from dgraphpandas import __version__
+from dgraphpandas import __version__, __description__
 from dgraphpandas.strategies.horizontal import horizontal_transform
 from dgraphpandas.strategies.vertical import vertical_transform
 from dgraphpandas.writers.upserts import generate_upserts
 
-logger = logging.getLogger(__name__)
-
-try:
-    import coloredlogs
-    coloredlogs.install(level='DEBUG')
-except ImportError as e:
-    logger.warning(e)
-
 pd.set_option('mode.chained_assignment', None)
 
 
 def main():
-    parser = argparse.ArgumentParser()
+    parser = argparse.ArgumentParser(description=__description__)
     parser.add_argument('-f', '--file', required=True, help='The Data File (CSV) to convert into RDF.')
     parser.add_argument('-c', '--config', required=True, help='The DgraphPandas Configuration. See Documentation for options/examples.')
     parser.add_argument('-ck', '--config_file_key', required=True, help='The Entry in the Configuration to use for this passed file.')
     parser.add_argument('-o', '--output_dir', default='.', help='The output directory to write files.')
     parser.add_argument('--console', action='store_true', default=False, help='Write the Preprocessed DataFrames to console (for debugging)')
     parser.add_argument('--pre_csv', action='store_true', default=False, help='Write the Preprocessed DataFrame to CSV (for debugging)')
     parser.add_argument('--skip_upsert_generation', action='store_true', default=False, help="Don't generate RDF files")
-    parser.add_argument('--encoding', default=os.environ.get('DGRAPH_PANDAS_ENCODING', 'utf-8'), help='The Encoding to write files.')
+    parser.add_argument('--encoding', default=os.environ.get('DGRAPHPANDAS_ENCODING', 'utf-8'), help='The Encoding to write files.')
     parser.add_argument('--chunk_size', default=10_000_000, type=int, help='Process and output in chunks rather all at once')
     parser.add_argument('--gz_compression_level', default=9, type=int, help='Compression level to set output gzip files to')
     parser.add_argument('--key_separator')
@@ -43,9 +35,21 @@ def main():
     parser.add_argument('--illegal_characters', default=['%', '\\.', '\\s', '\"', '\\n', '\\r\\n'])
     parser.add_argument('--illegal_characters_intrinsic_object', default=['\"', '\\n', '\\r\\n'])
     parser.add_argument('--version', action='version', version=__version__)
+    parser.add_argument('-v', '--verbosity',
+                        choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'NOTSET'],
+                        default=os.environ.get('DGRAPHPANDAS_LOG', 'INFO'))
 
     args = parser.parse_args()
 
+    logging.basicConfig(level=args.verbosity)
+    logger = logging.getLogger(__name__)
+
+    try:
+        import coloredlogs
+        coloredlogs.install(level=args.verbosity)
+    except ImportError as e:
+        logger.debug(e)
+
     with open(args.config, 'r') as f:
         global_config: Dict[str, Any] = json.load(f)
         logger.debug('Global Config \n %s', pformat(global_config))

dgraphpandas/strategies/vertical_helpers.py

@@ -25,7 +25,7 @@ def _expand_csv_edges(frame: pd.DataFrame, csv_edges: List[str], seperator=',')
         raise ValueError('frame')
 
     if csv_edges:
-        logger.info(f'Detected csv_edges {csv_edges}. Breaking up those columns')
+        logger.debug(f'Detected csv_edges {csv_edges}. Breaking up those columns')
         csv_edge_frame = frame[frame['predicate'].isin(csv_edges)]
         csv_edge_frame['object'] = csv_edge_frame['object'].str.split(seperator)
         csv_edge_frame = csv_edge_frame.explode(column='object')

setup.py

@@ -1,5 +1,5 @@
 from setuptools import setup, find_packages
-from dgraphpandas import __name__, __version__
+from dgraphpandas import __name__, __version__, __description__
 
 with open("README.md", "r") as desc:
     long_description = desc.read()
@@ -15,7 +15,7 @@
             install_requires=requirements,
             long_description=long_description,
             long_description_content_type="text/markdown",
-            description="Transform Pandas DataFrames into Exports to be sent to DGraph",
+            description=__description__,
             url="https://github.com/kiran94/dgraphpandas",
             entry_points={
                 'console_scripts': [