Fixed #456 - Handled trailing spaces in field name when doing

`transform`

Author: chinyeungli

docs/CHANGELOG.rst

@@ -6,6 +6,7 @@
     * Fixed #442 no special characters allowed for `license_key`, `license_name` and `license_expression`
     * Fixed #446 Better error handling
     * Add support to collect redistributable sources #22
+    * Handle trailing spaces in field names during `transform` #456
 
 2020-08-11
     Release 5.0.0

src/attributecode/cmd.py

@@ -578,7 +578,7 @@ def transform(location, output, configuration, quiet, verbose):  # NOQA
     errors = unique(errors)
     errors_count = report_errors(errors, quiet, verbose, log_file_loc=output + '-error.log')
     if not quiet and not errors:
-        msg = 'Transformed file written to {output}.'.format(**locals())
+        msg = 'Transformed file is written to {output}.'.format(**locals())
         click.echo(msg)
     sys.exit(errors_count)
 

src/attributecode/transform.py

@@ -51,8 +51,8 @@ def transform_csv_to_csv(location, output, transformer):
 
     errors = []
     data = iter(rows)
-    field_names = next(rows)
-
+    names = next(rows)
+    field_names = strip_trailing_fields_csv(names)
     dupes = check_duplicate_fields(field_names)
 
     if dupes:
@@ -82,7 +82,8 @@ def transform_json_to_json(location, output, transformer):
     if not transformer:
         raise ValueError('Cannot transform without Transformer')
 
-    data = read_json(location)
+    items = read_json(location)
+    data = strip_trailing_fields_json(items)
     new_data = normalize_dict_data(data)
 
     field_names, updated_data, errors = transform_data(new_data, transformer)
@@ -93,6 +94,28 @@ def transform_json_to_json(location, output, transformer):
         write_json(output, updated_data)
         return []
 
+def strip_trailing_fields_csv(names):
+    """
+    Strip trailing spaces for field names #456
+    """
+    field_names = []
+    for name in names:
+        field_names.append(name.strip())
+    return field_names
+
+
+def strip_trailing_fields_json(items):
+    """
+    Strip trailing spaces for field name #456
+    """
+    data = []
+    od = OrderedDict()
+    for item in items:
+        for field in item:
+            stripped_field_name = field.strip()
+            od[stripped_field_name] = item[field]
+        data.append(od)
+    return data
 
 def normalize_dict_data(data):
     """

tests/test_transform.py

@@ -34,6 +34,8 @@
 from attributecode.transform import read_json
 from attributecode.transform import transform_data
 from attributecode.transform import normalize_dict_data
+from attributecode.transform import strip_trailing_fields_csv
+from attributecode.transform import strip_trailing_fields_json
 from attributecode.transform import Transformer
 
 from attributecode.util import python2
@@ -160,3 +162,14 @@ def test_check_duplicate_fields(self):
         dups = check_duplicate_fields(field_name)
         assert dups == expected
 
+    def test_strip_trailing_fields_csv(self):
+        test = [u'about_resource', u'name ', u' version ']
+        expected = [u'about_resource', u'name', u'version']
+        result = strip_trailing_fields_csv(test)
+        assert result == expected
+
+    def test_strip_trailing_fields_json(self):
+        test = [OrderedDict([(u'about_resource', u'/this.c'), (u'name ', u'this.c'), (u' version ', u'0.11.0')])]
+        expected = [OrderedDict([(u'about_resource', u'/this.c'), (u'name', u'this.c'), (u'version', u'0.11.0')])]
+        result = strip_trailing_fields_json(test)
+        assert result == expected