feat(csvpy): Add --no-number-ellipsis, --sniff-limit, --no-inference.…

… fix(csvpy): Support --locale, --blanks, --null-value, --date-format, --datetime-format, --skip-lines. Remove --linenumbers, --zero. (closes #1231)

CHANGELOG.rst

@@ -1,8 +1,24 @@
 Unreleased
 ----------
 
+* feat: :doc:`/scripts/csvpy` adds the options:
+
+   * :code:`--no-number-ellipsis`, to disable the ellipsis (``…``) if max precision is exceeded, for example, when using ``table.print_table()``
+   * :code:`--sniff-limit``
+   * :code:`--no-inference``
+
+* feat: :doc:`/scripts/csvpy` removes the ``--linenumbers`` and ``--zero`` output options, which had no effect.
 * feat: :doc:`/scripts/in2csv` adds a :code:`--reset-dimensions` option to `recalculate <https://openpyxl.readthedocs.io/en/stable/optimized.html#worksheet-dimensions>`_ the dimensions of an XLSX file, instead of trusting the file's metadata. csvkit's dependency `agate-excel <https://agate-excel.readthedocs.io/en/latest/>`_ 0.4.0 automatically recalculates the dimensions if the file's metadata expresses dimensions of "A1:A1" (a single cell).
 * fix: :doc:`/scripts/csvlook` only reads up to :code:`--max-rows` rows instead of the entire file.
+* fix: :doc:`/scripts/csvpy` supports the existing input options:
+
+   * :code:`--locale`
+   * :code:`--blanks`
+   * :code:`--null-value`
+   * :code:`--date-format`
+   * :code:`--datetime-format`
+   * :code:`--skip-lines`
+
 * fix: :doc:`/scripts/in2csv`: :code:`--write-sheets` no longer errors when standard input is an XLS or XLSX file.
 * Update minimum agate version to 1.6.3.
 

csvkit/utilities/csvpy.py

@@ -3,40 +3,69 @@
 import sys
 
 import agate
+from agate import config
 
 from csvkit.cli import CSVKitUtility
 
 
 class CSVPy(CSVKitUtility):
     description = 'Load a CSV file into a CSV reader and then drop into a Python shell.'
+    override_flags = ['l', 'zero']
 
     def add_arguments(self):
-        self.argparser.add_argument('--dict', dest='as_dict', action='store_true',
-                                    help='Load the CSV file into a DictReader.')
-        self.argparser.add_argument('--agate', dest='as_agate', action='store_true',
-                                    help='Load the CSV file into an agate table.')
+        self.argparser.add_argument(
+            '--dict', dest='as_dict', action='store_true',
+            help='Load the CSV file into a DictReader.')
+        self.argparser.add_argument(
+            '--agate', dest='as_agate', action='store_true',
+            help='Load the CSV file into an agate table.')
+        self.argparser.add_argument(
+            '--no-number-ellipsis', dest='no_number_ellipsis', action='store_true',
+            help='Disable the ellipsis if the max precision is exceeded.')
+        self.argparser.add_argument(
+            '-y', '--snifflimit', dest='sniff_limit', type=int, default=1024,
+            help='Limit CSV dialect sniffing to the specified number of bytes. '
+                 'Specify "0" to disable sniffing entirely, or "-1" to sniff the entire file.')
+        self.argparser.add_argument(
+            '-I', '--no-inference', dest='no_inference', action='store_true',
+            help='Disable type inference when parsing the input. This disables the reformatting of values.')
 
     def main(self):
         if self.input_file == sys.stdin:
             self.argparser.error('csvpy cannot accept input as piped data via STDIN.')
 
+        if self.args.no_number_ellipsis:
+            config.set_option('number_truncation_chars', '')
+
         # Attempt reading filename, will cause lazy loader to access file and raise error if it does not exist
         filename = self.input_file.name
 
         if self.args.as_dict:
             klass = agate.csv.DictReader
             class_name = 'agate.csv.DictReader'
             variable_name = 'reader'
+            input_file = self.skip_lines()
+            kwargs = {}
         elif self.args.as_agate:
             klass = agate.Table.from_csv
             class_name = 'agate.Table'
             variable_name = 'table'
+            input_file = self.input_file
+
+            sniff_limit = self.args.sniff_limit if self.args.sniff_limit != -1 else None
+            kwargs = dict(
+                skip_lines=self.args.skip_lines,
+                sniff_limit=sniff_limit,
+                column_types=self.get_column_types(),
+            )
         else:
             klass = agate.csv.reader
             class_name = 'agate.csv.reader'
             variable_name = 'reader'
+            input_file = self.skip_lines()
+            kwargs = {}
 
-        variable = klass(self.input_file, **self.reader_kwargs)
+        variable = klass(input_file, **kwargs, **self.reader_kwargs)
 
         welcome_message = 'Welcome! "{}" has been loaded in an {} object named "{}".'.format(
             filename, class_name, variable_name)

docs/scripts/csvpy.rst

@@ -14,6 +14,7 @@ Loads a CSV file into a :class:`agate.csv.Reader` object and then drops into a P
                 [-S] [--blanks] [--null-value NULL_VALUES [NULL_VALUES ...]]
                 [--date-format DATE_FORMAT] [--datetime-format DATETIME_FORMAT]
                 [-H] [-K SKIP_LINES] [-v] [-l] [--zero] [-V] [--dict] [--agate]
+                [--no-number-ellipsis] [-y SNIFF_LIMIT] [-I]
                 [FILE]
 
    Load a CSV file into a CSV reader and then drop into a Python shell.
@@ -26,6 +27,13 @@ Loads a CSV file into a :class:`agate.csv.Reader` object and then drops into a P
      -h, --help            show this help message and exit
      --dict                Load the CSV file into a DictReader.
      --agate               Load the CSV file into an agate table.
+     --no-number-ellipsis  Disable the ellipsis if the max precision is exceeded.
+     -y SNIFF_LIMIT, --snifflimit SNIFF_LIMIT
+                           Limit CSV dialect sniffing to the specified number of
+                           bytes. Specify "0" to disable sniffing entirely, or
+                           "-1" to sniff the entire file.
+     -I, --no-inference    Disable type inference when parsing the input. This
+                           disables the reformatting of values.
 
 This tool will automatically use the IPython shell if it is installed, otherwise it will use the running Python shell.