From 787fa9e8d955f6581443b78d4b288184dc1fddf3 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Fri, 8 Oct 2021 14:36:23 +0300
Subject: [PATCH] Add field name to fix.newlines output

---
 csv_metadata_quality/app.py | 2 +-
 csv_metadata_quality/fix.py | 4 ++--
 tests/test_fix.py           | 3 ++-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/csv_metadata_quality/app.py b/csv_metadata_quality/app.py
index 715921c..7c1c7cf 100644
--- a/csv_metadata_quality/app.py
+++ b/csv_metadata_quality/app.py
@@ -89,7 +89,7 @@ def run(argv):
 
         # Fix: newlines
         if args.unsafe_fixes:
-            df[column] = df[column].apply(fix.newlines)
+            df[column] = df[column].apply(fix.newlines, field_name=column)
 
         # Fix: missing space after comma. Only run on author and citation
         # fields for now, as this problem is mostly an issue in names.
diff --git a/csv_metadata_quality/fix.py b/csv_metadata_quality/fix.py
index deb7da0..0a0adb3 100755
--- a/csv_metadata_quality/fix.py
+++ b/csv_metadata_quality/fix.py
@@ -180,7 +180,7 @@ def duplicates(field, field_name):
     return new_field
 
 
-def newlines(field):
+def newlines(field, field_name):
     """Fix newlines.
 
     Single metadata values should not span multiple lines because this is not
@@ -205,7 +205,7 @@ def newlines(field):
     match = re.findall(r"\n", field)
 
     if match:
-        print(f"{Fore.GREEN}Removing newline: {Fore.RESET}{field}")
+        print(f"{Fore.GREEN}Removing newline ({field_name}): {Fore.RESET}{field}")
         field = field.replace("\n", "")
 
     return field
diff --git a/tests/test_fix.py b/tests/test_fix.py
index 9ecba75..ad7ec42 100644
--- a/tests/test_fix.py
+++ b/tests/test_fix.py
@@ -76,8 +76,9 @@ def test_fix_newlines():
 
     value = """Ken
 ya"""
+    field_name = "dcterms.subject"
 
-    assert fix.newlines(value) == "Kenya"
+    assert fix.newlines(value, field_name) == "Kenya"
 
 
 def test_fix_comma_space():