From 6a80fbda7e2d0972df915348bdaf42c3a57cefcc Mon Sep 17 00:00:00 2001
From: Vraj Mohan <r.vrajmohan@gmail.com>
Date: Thu, 21 Jul 2016 06:58:53 -0400
Subject: [PATCH 1/3] Remove library that is not needed

As the product is database agnostic, there is no need to install
psycopg2.
---
 requirements.txt | 1 -
 1 file changed, 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 306999b..ac8147a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,7 +4,6 @@ invoke==0.10.1
 pandas
 # intentionally leaving pandas version blank, b/c `pip install` generally
 # fails on Linux - must use the package manager version
-psycopg2==2.6.1
 requests==2.7.0
 gunicorn==19.3.0
 cryptography>=1.0

From d95be730f50b664540ae5baccfd41bdeb427b4e7 Mon Sep 17 00:00:00 2001
From: Vraj Mohan <r.vrajmohan@gmail.com>
Date: Thu, 21 Jul 2016 07:00:59 -0400
Subject: [PATCH 2/3] Remove unnecessary imports

---
 utils.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/utils.py b/utils.py
index dd7f063..9945b6b 100644
--- a/utils.py
+++ b/utils.py
@@ -1,8 +1,6 @@
 import logging
-import multiprocessing
 import os
 import tempfile
-import threading
 
 import pandas as pd
 import sqlalchemy as sa

From 9a7349d278ad5b66f5fdb51e728b959f5ff3bb0b Mon Sep 17 00:00:00 2001
From: Vraj Mohan <r.vrajmohan@gmail.com>
Date: Thu, 21 Jul 2016 07:05:05 -0400
Subject: [PATCH 3/3] Skip spaces after delimiter

This removes leading spaces in field names and field values.
E.g,
name, age
Tom, 12

will be parsed as:
"name", "age"
"Tom", 12
---
 utils.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/utils.py b/utils.py
index 9945b6b..11af670 100644
--- a/utils.py
+++ b/utils.py
@@ -85,11 +85,13 @@ def load_table(filename,
     engine = engine or sa.create_engine(config.SQLA_URI)
     file = ensure_csv(filename)
     # Pass data types to iterator to ensure consistent types across chunks
-    dtypes = pd.read_csv(file.name, nrows=infer_size).dtypes
+    dtypes = pd.read_csv(file.name, nrows=infer_size,
+                         skipinitialspace=True).dtypes
     chunks = pd.read_csv(file.name,
                          chunksize=chunk_size,
                          iterator=True,
-                         dtype=dtypes)
+                         dtype=dtypes,
+                         skipinitialspace=True)
     for idx, chunk in enumerate(chunks):
         chunk.index += chunk_size * idx
         sql_engine = pandasSQL_builder(engine)