Merge pull request #27 from lnyemba/v2.2.0

bug fix: registry and emails

LICENSE

@@ -1,9 +0,0 @@
-MIT License
-
-Copyright (c) <year> <copyright holders>
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -4,11 +4,12 @@ This project implements an abstraction of objects that can have access to a vari
 
 # Why Use Data-Transport ?
 
-Data transport is a simple framework that:
+Mostly data scientists that don't really care about the underlying database and would like a simple and consistent way to read/write and move data are well served. Additionally we implemented lightweight Extract Transform Loading API and command line (CLI) tool. Finally it is possible to add pre/post processing pipeline functions to read/write
-- easy to install & modify (open-source)
+
-- enables access to multiple database technologies (pandas, SQLAlchemy)
+1. Familiarity with **pandas data-frames**
-- enables notebook sharing without exposing database credential.
+2. Connectivity **drivers** are included
-- supports pre/post processing specifications (pipeline)
+3. Reading/Writing data from various sources
+4. Useful for data migrations or **ETL**
 
 
 ## Installation
@@ -17,16 +18,19 @@ Within the virtual environment perform the following :
 
     pip install git+https://github.com/lnyemba/data-transport.git
 
-Options to install components in square brackets
+## Features
 
-    pip install data-transport[nosql,cloud,warehouse,all]@git+https://github.com/lnyemba/data-transport.git
+    - read/write from over a dozen databases
+    - run ETL jobs seamlessly
+    - scales and integrates into shared environments like apache zeppelin; jupyterhub; SageMaker; ...
 
+## What's new
 
-## Additional features
+Unlike older versions 2.0 and under, we focus on collaborative environments like jupyter-x servers; apache zeppelin:
 
-    - In addition to read/write, there is support for functions for pre/post processing
+    1. Simpler syntax to create reader or writer
-    - CLI interface to add to registry, run ETL
+    2. auth-file registry that can be referenced using a label
-    - scales and integrates into shared environments like apache zeppelin; jupyterhub; SageMaker; ...
+    3. duckdb support
 
 
 ## Learn More

bin/transport

@@ -53,9 +53,9 @@ def wait(jobs):
     while jobs :
         jobs = [thread for thread in jobs if thread.is_alive()]
         time.sleep(1)
-# def wait (jobs):
+def wait (jobs):
-#     while jobs :
+    while jobs :
-#             jobs = [pthread for pthread in jobs if pthread.is_alive()]
+            jobs = [pthread for pthread in jobs if pthread.is_alive()]
 
 @app_e.command(name="run")
 def apply (path:Annotated[str,typer.Argument(help="path of the configuration file")],

pyproject.toml

@@ -18,17 +18,25 @@ classifiers = [
 ]
 dependencies = [
     "termcolor","sqlalchemy", "aiosqlite","duckdb-engine",
-    "mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite",
+    "typer","pandas","numpy","sqlalchemy","pyarrow",
-    "typer","pandas","numpy","sqlalchemy","pyarrow","smart-open",
     "plugin-ix@git+https://github.com/lnyemba/plugins-ix"
 ]
 [project.optional-dependencies]
-#sql         = ["mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite"]
+sql         = ["mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite"]
 nosql       = ["pymongo","cloudant"]
-cloud       = ["boto","boto3","botocore","pyncclient","pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore"]
+cloud       = ["pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore"]
 warehouse   = ["pydrill","pyspark","sqlalchemy_drill"]
-other       = ["pika","flask-session"]
+rabbitmq    = ["pika"]
-all         = ["pymongo","cloudant","pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore","pydrill","pyspark","sqlalchemy_drill", "pika","aiosqlite","boto3","boto","botocore", "pyncclient"]
+sqlite      = ["aiosqlite"]
+aws3        = ["boto3","boto","botocore"]
+nextcloud   =  ["pyncclient"]
+mongodb     = ["pymongo"]
+netezza     = ["nzpy"]
+mysql       = ["mysql-connector-python"]
+postgresql  = ["psycopg2-binary"]
+sqlserver   = ["pymssql"]
+http       = ["flask-session"]
+all         = ["mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite","pymongo","cloudant","pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore","pydrill","pyspark","sqlalchemy_drill", "pika","aiosqlite","boto3","boto","botocore", "pyncclient"]
 
 [project.urls]
 Homepage = "https://healthcareio.the-phi.com/git/code/transport.git"

transport/__init__.py

@@ -18,27 +18,7 @@ Source Code is available under MIT License:
 """
 import numpy as np
 
-#from transport import sql, nosql, cloud, other, warehouse
+from transport import sql, nosql, cloud, other, warehouse
-from transport import sql
-try:
-    from transport import  nosql
-except Exception as e:
-    nosql = {}
-try:
-    from transport import  cloud
-except Exception as e:
-    cloud = {}
-try:
-    from transport import  warehouse
-except Exception as e:
-    warehouse = {}
-try:
-    from transport import  other
-except Exception as e:
-    other = {}
-
-
-
 import pandas as pd
 import json
 import os
@@ -55,7 +35,7 @@ def init():
     global PROVIDERS
     for _module in [cloud,sql,nosql,other,warehouse] :
         for _provider_name in dir(_module) :
-            if _provider_name.startswith('__') or _provider_name == 'common' or type(_module) in [None,str,dict]:
+            if _provider_name.startswith('__') or _provider_name == 'common':
                 continue
             PROVIDERS[_provider_name] = {'module':getattr(_module,_provider_name),'type':_module.__name__}
     #

transport/registry.py

@@ -49,8 +49,7 @@ def init (email,path=REGISTRY_PATH,override=False,_file=REGISTRY_FILE):
     Initializing the registry and will raise an exception in the advent of an issue
     """
     p = '@' in email
-    #q = False if '.' not in email else email.split('.')[-1] in ['edu','com','io','ai','org']
+    q = False if '.' not in email else email.split('.')[-1] in ['edu','com','io','ai','org']
-    q = len(email.split('.')[-1]) in [2,3]
     if p and q :
         _config = {"email":email,'version':__version__}
         if not os.path.exists(path):