feat(csvsort): Add --ignore-case option, closes #1175

CHANGELOG.rst

@@ -3,6 +3,7 @@ Unreleased
 
 * feat: Add support for Zstandard files with the ``.zst`` extension, if the ``zstandard`` package is installed.
 * feat: :doc:`/scripts/csvformat` adds a :code:`--out-asv` (:code:`--A`) option to use the ASCII unit separator and record separator.
+* feat: :doc:`/scripts/csvsort` adds a :code:`--ignore-case` (:code:`--i`) option to perform case-independent sorting.
 
 1.4.0 - February 13, 2024
 -------------------------

csvkit/utilities/csvsort.py

@@ -5,6 +5,17 @@
 from csvkit.cli import CSVKitUtility, parse_column_identifiers
 
 
+def ignore_case_sort(key):
+
+    def inner(row):
+        return tuple(
+            agate.NullOrder() if row[n] is None else (row[n].upper() if isinstance(row[n], str) else row[n])
+            for n in key
+        )
+
+    return inner
+
+
 class CSVSort(CSVKitUtility):
     description = 'Sort CSV files. Like the Unix "sort" command, but for tabular data.'
 
@@ -19,6 +30,9 @@ def add_arguments(self):
         self.argparser.add_argument(
             '-r', '--reverse', dest='reverse', action='store_true',
             help='Sort in descending order.')
+        self.argparser.add_argument(
+            '-i', '--ignore-case', dest='ignore_case', action='store_true',
+            help='Perform case-independent sorting.')
         self.argparser.add_argument(
             '-y', '--snifflimit', dest='sniff_limit', type=int, default=1024,
             help='Limit CSV dialect sniffing to the specified number of bytes. '
@@ -44,13 +58,16 @@ def main(self):
             **self.reader_kwargs,
         )
 
-        column_ids = parse_column_identifiers(
+        key = parse_column_identifiers(
             self.args.columns,
             table.column_names,
             self.get_column_offset(),
         )
 
-        table = table.order_by(column_ids, reverse=self.args.reverse)
+        if self.args.ignore_case:
+            key = ignore_case_sort(key)
+
+        table = table.order_by(key, reverse=self.args.reverse)
         table.to_csv(self.output_file, **self.writer_kwargs)
 
 

docs/scripts/csvsort.rst

@@ -14,7 +14,7 @@ Sort CSV files. Like the Unix "sort" command, but for tabular data:
                   [-S] [--blanks] [--null-value NULL_VALUES [NULL_VALUES ...]]
                   [--date-format DATE_FORMAT] [--datetime-format DATETIME_FORMAT]
                   [-H] [-K SKIP_LINES] [-v] [-l] [--zero] [-V] [-n] [-c COLUMNS]
-                  [-r] [-y SNIFF_LIMIT] [-I]
+                  [-r] [-i] [-y SNIFF_LIMIT] [-I]
                   [FILE]
 
    Sort CSV files. Like the Unix "sort" command, but for tabular data.
@@ -32,6 +32,7 @@ Sort CSV files. Like the Unix "sort" command, but for tabular data:
                            ranges to sort by, e.g. "1,id,3-5". Defaults to all
                            columns.
      -r, --reverse         Sort in descending order.
+     -i, --ignore-case     Perform case-independent sorting.
      -y SNIFF_LIMIT, --snifflimit SNIFF_LIMIT
                            Limit CSV dialect sniffing to the specified number of
                            bytes. Specify "0" to disable sniffing.

examples/test_ignore_case.csv

@@ -0,0 +1,6 @@
+a,b,c
+100,2003-01-01,a
+100,2003-01-01,A
+20,2002-01-01,b
+20,2001-01-01,c
+3,2009-01-01,d

tests/test_utilities/test_csvsort.py

@@ -41,6 +41,16 @@ def test_sort_date(self):
         new_order = [str(r[0]) for r in reader]
         self.assertEqual(test_order, new_order)
 
+    def test_ignore_case(self):
+        self.assertRows(['-i', 'examples/test_ignore_case.csv'], [
+            ['a', 'b', 'c'],
+            ['3', '2009-01-01', 'd'],
+            ['20', '2001-01-01', 'c'],
+            ['20', '2002-01-01', 'b'],
+            ['100', '2003-01-01', 'a'],
+            ['100', '2003-01-01', 'A'],
+        ])
+
     def test_no_blanks(self):
         reader = self.get_output_as_reader(['examples/blanks.csv'])
         test_order = [