csvgrep: add --ignore-case option for case-insensitive matching

AUTHORS.rst

@@ -116,3 +116,4 @@ The following individuals have contributed code to csvkit:
 * lamdevhs
 * Sai Asish Y
 * Peng-Yu Chen
+* Chris

CHANGELOG.rst

@@ -1,6 +1,7 @@
 Unreleased
 ----------
 
+-  feat: :doc:`/scripts/csvgrep` adds an :code:`--ignore-case` option to match case-insensitively, for the :code:`-m`, :code:`-r` and :code:`-f` options.
 -  feat: :doc:`/scripts/csvcut` adds an :code:`--ignore-unknown-columns` option to skip identifiers in :code:`-c/--columns` that do not match a column in the input.
 -  feat: :doc:`/scripts/csvclean` adds a :code:`--remove-empty-columns` option to remove empty columns from standard output.
 -  feat: :doc:`/scripts/in2csv` guesses the ``ndjson`` format for files with :code:`.ndjson`, :code:`.jsonl` and :code:`.jl` extensions.

csvkit/utilities/csvgrep.py

@@ -37,6 +37,9 @@ def add_arguments(self):
         self.argparser.add_argument(
             '-a', '--any-match', dest='any_match', action='store_true',
             help='Select rows in which any column matches, instead of all columns.')
+        self.argparser.add_argument(
+            '--ignore-case', dest='ignore_case', action='store_true',
+            help='Ignore case when matching, for the -m, -r and -f options.')
 
     def main(self):
         if self.args.names_only:
@@ -61,13 +64,24 @@ def main(self):
         rows, column_names, column_ids = self.get_rows_and_column_names_and_column_ids(**reader_kwargs)
 
         if self.args.regex:
-            pattern = re.compile(self.args.regex)
+            pattern = re.compile(self.args.regex, re.IGNORECASE if self.args.ignore_case else 0)
         elif self.args.matchfile:
             lines = {line.rstrip() for line in self.args.matchfile}
             self.args.matchfile.close()
 
+            if self.args.ignore_case:
+                lines = {line.lower() for line in lines}
+
+                def pattern(x):
+                    return x.lower() in lines
+            else:
+                def pattern(x):
+                    return x in lines
+        elif self.args.ignore_case:
+            needle = self.args.pattern.lower()
+
             def pattern(x):
-                return x in lines
+                return needle in x.lower()
         else:
             pattern = self.args.pattern
 

docs/scripts/csvgrep.rst

@@ -13,7 +13,7 @@ Filter tabular data to only those rows where certain columns contain a given val
                   [-p ESCAPECHAR] [-z FIELD_SIZE_LIMIT] [-e ENCODING] [-S] [-H]
                   [-K SKIP_LINES] [-v] [-l] [--zero] [-V] [-n] [-c COLUMNS]
                   [-m PATTERN] [-r REGEX] [-f MATCHFILE] [-i] [-a]
-                  [FILE]
+                  [--ignore-case] [FILE]
 
    Search CSV files. Like the Unix "grep" command, but for tabular data.
 
@@ -39,6 +39,8 @@ Filter tabular data to only those rows where certain columns contain a given val
      -i, --invert-match    Select non-matching rows, instead of matching rows.
      -a, --any-match       Select rows in which any column matches, instead of
                            all columns.
+     --ignore-case         Ignore case when matching, for the -m, -r and -f
+                           options.
 
 See also: :doc:`../common_arguments`.
 
@@ -67,6 +69,12 @@ Search for rows that do not contain an empty state cell:
 
 Perform a case-insensitive search:
 
+.. code-block:: bash
+
+   csvgrep -c 1 --ignore-case -m illinois examples/realdata/FY09_EDU_Recipients_by_State.csv
+
+The ``--ignore-case`` option applies to the ``-m``, ``-r`` and ``-f`` options. Alternatively, an inline flag can be used in a regular expression:
+
 .. code-block:: bash
 
    csvgrep -c 1 -r "(?i)illinois" examples/realdata/FY09_EDU_Recipients_by_State.csv

examples/test_ignore_case_matchfile.txt

@@ -0,0 +1 @@
+illinois

tests/test_utilities/test_csvgrep.py

@@ -85,6 +85,45 @@ def test_string_match(self):
             ['ILLINOIS', 'IL', '17', '15,659', '2,491', '2,025', '1,770', '19', '21,964', ''],
         ])
 
+    def test_match_ignore_case(self):
+        self.assertRows(['-c', '1', '-m', 'illinois', '--ignore-case',
+                         'examples/realdata/FY09_EDU_Recipients_by_State.csv'], [
+            ['State Name', 'State Abbreviate', 'Code', 'Montgomery GI Bill-Active Duty',
+                'Montgomery GI Bill- Selective Reserve', 'Dependents\' Educational Assistance',
+                'Reserve Educational Assistance Program', 'Post-Vietnam Era Veteran\'s Educational Assistance Program',
+                'TOTAL', ''],
+            ['ILLINOIS', 'IL', '17', '15,659', '2,491', '2,025', '1,770', '19', '21,964', ''],
+        ])
+
+    def test_match_case_sensitive_by_default(self):
+        self.assertRows(['-c', '1', '-m', 'illinois',
+                         'examples/realdata/FY09_EDU_Recipients_by_State.csv'], [
+            ['State Name', 'State Abbreviate', 'Code', 'Montgomery GI Bill-Active Duty',
+                'Montgomery GI Bill- Selective Reserve', 'Dependents\' Educational Assistance',
+                'Reserve Educational Assistance Program', 'Post-Vietnam Era Veteran\'s Educational Assistance Program',
+                'TOTAL', ''],
+        ])
+
+    def test_re_match_ignore_case(self):
+        self.assertRows(['-c', '1', '-r', '^illinois$', '--ignore-case',
+                         'examples/realdata/FY09_EDU_Recipients_by_State.csv'], [
+            ['State Name', 'State Abbreviate', 'Code', 'Montgomery GI Bill-Active Duty',
+                'Montgomery GI Bill- Selective Reserve', 'Dependents\' Educational Assistance',
+                'Reserve Educational Assistance Program', 'Post-Vietnam Era Veteran\'s Educational Assistance Program',
+                'TOTAL', ''],
+            ['ILLINOIS', 'IL', '17', '15,659', '2,491', '2,025', '1,770', '19', '21,964', ''],
+        ])
+
+    def test_file_match_ignore_case(self):
+        self.assertRows(['-c', '1', '-f', 'examples/test_ignore_case_matchfile.txt', '--ignore-case',
+                         'examples/realdata/FY09_EDU_Recipients_by_State.csv'], [
+            ['State Name', 'State Abbreviate', 'Code', 'Montgomery GI Bill-Active Duty',
+                'Montgomery GI Bill- Selective Reserve', 'Dependents\' Educational Assistance',
+                'Reserve Educational Assistance Program', 'Post-Vietnam Era Veteran\'s Educational Assistance Program',
+                'TOTAL', ''],
+            ['ILLINOIS', 'IL', '17', '15,659', '2,491', '2,025', '1,770', '19', '21,964', ''],
+        ])
+
     def test_match_with_line_numbers(self):
         self.assertRows(['-c', '1', '-m', 'ILLINOIS', '--linenumbers',
                          'examples/realdata/FY09_EDU_Recipients_by_State.csv'], [