feat(csvclean): Add --label option

CHANGELOG.rst

@@ -25,6 +25,8 @@ Other changes:
    -  :code:`--length-mismatch`, to error on data rows that are shorter or longer than the header row
    -  :code:`--empty-columns`, to error on empty columns
    -  :code:`--enable-all-checks`, to enable all error reporting.
+   -  :code:`--omit-error-rows`, to omit data rows that contain errors, from standard output.
+   -  :code:`--label`, to add a "label" column to standard error.
    -  :code:`--header-normalize-space`, to strip leading and trailing whitespace and replace sequences of whitespace characters by a single space in the header
    -  :code:`--separator`, to change the string with which to join short rows
    -  :code:`--fill-short-rows`, to fill short rows with the missing cells

csvkit/utilities/csvclean.py

@@ -25,6 +25,10 @@ def add_arguments(self):
         self.argparser.add_argument(
             '--omit-error-rows', dest='omit_error_rows', action='store_true',
             help='Omit data rows that contain errors, from standard output.')
+        self.argparser.add_argument(
+            '--label', dest='label',
+            help='Add a "label" column to standard error. Useful in automated workflows. '
+                 'Use "-" to default to the input filename.')
         self.argparser.add_argument(
             '--header-normalize-space', dest='header_normalize_space', action='store_true',
             help='Strip leading and trailing whitespace and replace sequences of whitespace characters by a single '
@@ -81,16 +85,31 @@ def main(self):
             omit_error_rows=self.args.omit_error_rows,
         )
 
+        label = self.args.label
+        if label == '-':
+            if self.input_file == sys.stdin:
+                label = 'stdin'
+            else:
+                label = self.input_file.name
+
         output_writer = agate.csv.writer(self.output_file, **self.writer_kwargs)
         output_writer.writerow(checker.column_names)
         for row in checker.checked_rows():
             output_writer.writerow(row)
 
         if checker.errors:
             error_writer = agate.csv.writer(self.error_file, **self.writer_kwargs)
-            error_writer.writerow(['line_number', 'msg'] + checker.column_names)
+
+            fieldnames = ['line_number', 'msg'] + checker.column_names
+            if self.args.label:
+                fieldnames.insert(0, 'label')
+            error_writer.writerow(fieldnames)
+
             for error in checker.errors:
-                error_writer.writerow([error.line_number, error.msg] + error.row)
+                row = [error.line_number, error.msg] + error.row
+                if self.args.label:
+                    row.insert(0, label)
+                error_writer.writerow(row)
 
             sys.exit(1)
 

docs/scripts/csvclean.rst

@@ -125,6 +125,8 @@ Usage
                            Enable all error reporting.
      --omit-error-rows     Omit data rows that contain errors, from standard
                            output.
+     --label LABEL         Add a "label" column to standard error. Useful in
+                           automated workflows.
      --header-normalize-space
                            Strip leading and trailing whitespace and replace
                            sequences of whitespace characters by a single space

tests/test_utilities/test_csvclean.py

@@ -5,7 +5,7 @@
 import agate
 
 from csvkit.utilities.csvclean import CSVClean, launch_new_instance
-from tests.utils import CSVKitTestCase, EmptyFileTests
+from tests.utils import CSVKitTestCase, EmptyFileTests, stdin_as_string
 
 
 class TestCSVClean(CSVKitTestCase, EmptyFileTests):
@@ -180,6 +180,43 @@ def test_enable_all_checks(self):
             ['1', "Empty columns named 'b', '', ''! Try: csvcut -C 2,4,5", '', '', '', '', ''],
         ])
 
+    def test_label(self):
+        self.assertCleaned(['-a', '--label', 'xyz', 'examples/test_empty_columns.csv'], [
+            ['a', 'b', 'c', '', ''],
+            ['a', '', '', '', ''],
+            ['', '', 'c', ''],
+            ['', '', '', '', ''],
+        ], [
+            ['label', 'line_number', 'msg', 'a', 'b', 'c', '', ''],
+            ['xyz', '2', 'Expected 5 columns, found 4 columns', '', '', 'c', ''],
+            ['xyz', '1', "Empty columns named 'b', '', ''! Try: csvcut -C 2,4,5", '', '', '', '', ''],
+        ])
+
+    def test_label_default(self):
+        self.assertCleaned(['-a', '--label', '-', 'examples/test_empty_columns.csv'], [
+            ['a', 'b', 'c', '', ''],
+            ['a', '', '', '', ''],
+            ['', '', 'c', ''],
+            ['', '', '', '', ''],
+        ], [
+            ['label', 'line_number', 'msg', 'a', 'b', 'c', '', ''],
+            ['examples/test_empty_columns.csv', '2', 'Expected 5 columns, found 4 columns', '', '', 'c', ''],
+            ['examples/test_empty_columns.csv', '1', "Empty columns named 'b', '', ''! Try: csvcut -C 2,4,5", '', '', '', '', ''],  # noqa: E501
+        ])
+
+    def test_label_default_stdin(self):
+        input_file = io.BytesIO(b'a,b,c\n,\n')
+
+        with stdin_as_string(input_file):
+            self.assertCleaned(['-a', '--label', '-'], [
+                ['a', 'b', 'c'],
+                ['', ''],
+            ], [
+                ['label', 'line_number', 'msg', 'a', 'b', 'c'],
+                ['stdin', '1', 'Expected 3 columns, found 2 columns', '', ''],
+                ['stdin', '1', "Empty columns named 'a', 'b', 'c'! Try: csvcut -C 1,2,3", '', '', ''],
+            ])
+
     def test_removes_optional_quote_characters(self):
         self.assertCleaned(['--length-mismatch', 'examples/optional_quote_characters.csv'], [
             ['a', 'b', 'c'],