CHANGELOG.md: Add note about fix.newlines

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 well as dcterms.bibliographicCitation) in `experimental.correct_language()`
 - Regular expression to match dc.title and dcterms.title, but
 ignore dc.title.alternative `check.duplicate_items()`
+- Missing field name in `fix.newlines()` output
 
 ## [0.4.7] - 2021-03-17
 ### Changed

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.

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

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():