From b77d028381819cb947342db4ff80590563822b4e Mon Sep 17 00:00:00 2001
From: BonfaceKilz
Date: Fri, 18 Mar 2022 15:41:12 +0300
Subject: Clean all csv fields before diffing

There was a subtle bug where "csvdiff" generated an error related to
"different column headings" caused something akin to diffing: "a, b \n, ..."
with "a, b\n, ...".

* gn3/csvcmp.py (csv_diff): Clean csv texts before any diffing.
* tests/unit/test_csvcmp.py (test_csv_diff_same_columns): Modify test case to
capture aforementioned bug.
---
 gn3/csvcmp.py             | 6 ++++--
 tests/unit/test_csvcmp.py | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/gn3/csvcmp.py b/gn3/csvcmp.py
index 10c5d3e..8db89ca 100644
--- a/gn3/csvcmp.py
+++ b/gn3/csvcmp.py
@@ -59,8 +59,10 @@ def clean_csv_text(csv_text: str) -> str:
 
 def csv_diff(base_csv, delta_csv, tmp_dir="/tmp") -> dict:
     """Diff 2 csv strings"""
-    base_csv_list = base_csv.strip().split("\n")
-    delta_csv_list = delta_csv.strip().split("\n")
+    base_csv = clean_csv_text(base_csv)
+    delta_csv = clean_csv_text(delta_csv)
+    base_csv_list = base_csv.split("\n")
+    delta_csv_list = delta_csv.split("\n")
 
     base_csv_header, delta_csv_header = "", ""
     for i, line in enumerate(base_csv_list):
diff --git a/tests/unit/test_csvcmp.py b/tests/unit/test_csvcmp.py
index ec4ca71..c2fda6b 100644
--- a/tests/unit/test_csvcmp.py
+++ b/tests/unit/test_csvcmp.py
@@ -55,7 +55,7 @@ def test_remove_insignificant_data():
 @pytest.mark.unit_test
 def test_csv_diff_same_columns():
     """Test csv diffing on data with the same number of columns"""
-    assert csv_diff(base_csv="a,b\n1,2\n", delta_csv="a,b\n1,3") == {
+    assert csv_diff(base_csv="a,b \n1,2\n", delta_csv="a,b\n1,3") == {
         "Additions": [],
         "Deletions": [],
         "Columns": "",
-- 
cgit v1.2.3