Merge 23b8789 into ffbc152

.github/workflows/ci.yml

@@ -36,10 +36,11 @@ jobs:
       - run: flake8 .
       - run: isort . --check-only
       - run: pip install .[test] coveralls
-      - run: pytest --cov csvkit
-        env:
+      - env:
+          LANG: en_US.UTF-8
           PYTHONIOENCODING: utf-8
           PYTHONUTF8: 1
+        run: pytest --cov csvkit
       # CoverallsException: Not on TravisCI. You have to provide either repo_token in .coveralls.yml or set the COVERALLS_REPO_TOKEN env var.
       - if: matrix.python-version != '2.7'
         env:

AUTHORS.rst

@@ -105,3 +105,4 @@ The following individuals have contributed code to csvkit:
 * Bonifacio de Oliveira
 * Ryan Grout
 * badbunnyyy
+* Werner Robitza

CHANGELOG.rst

@@ -2,6 +2,7 @@ Unreleased
 ----------
 
 * feat: :doc:`/scripts/csvsql` accepts multiple :code:`--query` command-line arguments.
+* feat: :doc:`/scripts/csvstat` adds :code:`--no-grouping-separator` and :code:`--decimal-format` options.
 
 1.0.7 - March 6, 2022
 ---------------------

csvkit/utilities/csvstat.py

@@ -114,6 +114,13 @@ def add_arguments(self):
         self.argparser.add_argument(
             '--count', dest='count_only', action='store_true',
             help='Only output total row count.')
+        self.argparser.add_argument(
+            '--decimal-format', dest='decimal_format', type=str, default='%.3f',
+            help='%%-format specification for printing decimal numbers. '
+                 'Defaults to locale-specific formatting with "%%.3f".')
+        self.argparser.add_argument(
+            '-G', '--no-grouping-separator', dest='no_grouping_separator', action='store_true',
+            help='Do not use grouping separators in decimal numbers.')
         self.argparser.add_argument(
             '-y', '--snifflimit', dest='sniff_limit', type=int, default=1024,
             help='Limit CSV dialect sniffing to the specified number of bytes. '
@@ -215,7 +222,7 @@ def print_one(self, table, column_id, operation, label=True, **kwargs):
                     stat = table.aggregate(op(column_id))
 
                     if self.is_finite_decimal(stat):
-                        stat = format_decimal(stat)
+                        stat = format_decimal(stat, self.args.decimal_format, self.args.no_grouping_separator)
             except Exception:
                 stat = None
 
@@ -249,7 +256,7 @@ def calculate_stats(self, table, column_id, **kwargs):
                         v = table.aggregate(op(column_id))
 
                         if self.is_finite_decimal(v):
-                            v = format_decimal(v)
+                            v = format_decimal(v, self.args.decimal_format, self.args.no_grouping_separator)
 
                         stats[op_name] = v
                 except Exception:
@@ -293,7 +300,7 @@ def print_stats(self, table, column_ids, stats):
                             v = row['value']
 
                             if self.is_finite_decimal(v):
-                                v = format_decimal(v)
+                                v = format_decimal(v, self.args.decimal_format, self.args.no_grouping_separator)
                         else:
                             v = six.text_type(row['value'])
 
@@ -345,8 +352,8 @@ def print_csv(self, table, column_ids, stats):
             writer.writerow(output_row)
 
 
-def format_decimal(d):
-    return locale.format_string('%.3f', d, grouping=True).rstrip('0').rstrip('.')
+def format_decimal(d, f='%.3f', no_grouping_separator=False):
+    return locale.format_string(f, d, grouping=not no_grouping_separator).rstrip('0').rstrip('.')
 
 
 def get_type(table, column_id, **kwargs):

docs/scripts/csvstat.rst

@@ -12,7 +12,8 @@ Prints descriptive statistics for all columns in a CSV file. Will intelligently
                    [-K SKIP_LINES] [-v] [-l] [--zero] [-V] [--csv] [-n]
                    [-c COLUMNS] [--type] [--nulls] [--unique] [--min] [--max]
                    [--sum] [--mean] [--median] [--stdev] [--len] [--freq]
-                   [--freq-count FREQ_COUNT] [--count] [-y SNIFF_LIMIT]
+                   [--freq-count FREQ_COUNT] [--count]  [--decimal-format DECIMAL_FORMAT]
+                   [-G] [-y SNIFF_LIMIT]
                    [FILE]
 
     Print descriptive statistics for each column in a CSV file.
@@ -44,6 +45,11 @@ Prints descriptive statistics for all columns in a CSV file. Will intelligently
       --freq-count FREQ_COUNT
                             The maximum number of frequent values to display.
       --count               Only output total row count.
+      --decimal-format DECIMAL_FORMAT
+                            %-format specification for printing decimal numbers.
+                            Defaults to locale-specific formatting with "%.3f".
+      -G, --no-grouping-separator
+                            Do not use grouping separators in decimal numbers.
       -y SNIFF_LIMIT, --snifflimit SNIFF_LIMIT
                             Limit CSV dialect sniffing to the specified number of
                             bytes. Specify "0" to disable sniffing.

tests/test_utilities/test_csvstat.py

@@ -108,3 +108,20 @@ def test_csv_columns(self):
         self.assertEqual(row[2], 'Text')
         self.assertEqual(row[5], '')
         self.assertEqual(row[11], '16')
+
+    def test_decimal_format(self):
+        output = self.get_output(['-c', 'TOTAL', '--mean', 'examples/realdata/FY09_EDU_Recipients_by_State.csv'])
+
+        self.assertEqual(output, '9,748.346\n')
+
+        output = self.get_output([
+            '-c', 'TOTAL', '--mean', '--no-grouping-separator', 'examples/realdata/FY09_EDU_Recipients_by_State.csv'
+        ])
+
+        self.assertEqual(output, '9748.346\n')
+
+        output = self.get_output([
+            '-c', 'TOTAL', '--mean', '--decimal-format', '%.2f', 'examples/realdata/FY09_EDU_Recipients_by_State.csv'
+        ])
+
+        self.assertEqual(output, '9,748.35\n')