From a93b5b31c5fc960af9ed603c587e4ebbd7f65811 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Sun, 28 Jul 2019 20:31:57 +0300
Subject: [PATCH] Add support for command line arguments

Currently only supports specifying input and output files with -i
and -o. Eventually I'll add more options like dry run, debug, and
maybe things like forcing unsafe fixes.
---
 csv_metadata_quality/__main__.py |  3 ++-
 csv_metadata_quality/app.py      | 19 ++++++++++++++++---
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/csv_metadata_quality/__main__.py b/csv_metadata_quality/__main__.py
index 2c273f7..82e0811 100644
--- a/csv_metadata_quality/__main__.py
+++ b/csv_metadata_quality/__main__.py
@@ -1,4 +1,5 @@
 from csv_metadata_quality import app
+from sys import argv
 
 if __name__ == '__main__':
-        app.main()
+    app.main(argv)
diff --git a/csv_metadata_quality/app.py b/csv_metadata_quality/app.py
index 902011e..3fcc45d 100644
--- a/csv_metadata_quality/app.py
+++ b/csv_metadata_quality/app.py
@@ -1,11 +1,24 @@
+import argparse
 import csv_metadata_quality.check as check
 import csv_metadata_quality.fix as fix
 import pandas as pd
 import re
 
-def main():
+
+def parse_args(argv):
+    parser = argparse.ArgumentParser(description='Metadata quality checker and fixer.')
+    parser.add_argument('--input-file', '-i', help='Path to input file. Can be UTF-8 CSV or Excel XLSX.', required=True, type=argparse.FileType('r', encoding='UTF-8'))
+    parser.add_argument('--output-file', '-o', help='Path to output file (always CSV).', required=True, type=argparse.FileType('w', encoding='UTF-8'))
+    args = parser.parse_args()
+
+    return args
+
+
+def main(argv):
+    args = parse_args(argv)
+
     # Read all fields as strings so dates don't get converted from 1998 to 1998.0
-    df = pd.read_csv('data/test.csv', dtype=str)
+    df = pd.read_csv(args.input_file, dtype=str)
 
     # Fix whitespace in all columns
     for column in df.columns.values.tolist():
@@ -31,4 +44,4 @@ def main():
             df[column] = df[column].apply(check.date)
 
     # Write
-    df.to_csv('/tmp/test.fixed.csv', index=False)
+    df.to_csv(args.output_file, index=False)