Run "autopep8 -r --in-place --ignore E501 ."

csvkit/cleanup.py

@@ -2,6 +2,7 @@
 
 from csvkit.exceptions import CSVTestException, LengthMismatchError
 
+
 def join_rows(rows, joiner=' '):
     """
     Given a series of rows, return them as a single row where the inner edge cells are merged. By default joins with a single space character, but you can specify new-line, empty string, or anything else with the 'joiner' kwarg.
@@ -12,12 +13,13 @@ def join_rows(rows, joiner=' '):
     for row in rows[1:]:
         if len(row) == 0:
             row = ['']
-        
+
         fixed_row[-1] += "%s%s" % (joiner, row[0])
         fixed_row.extend(row[1:])
 
     return fixed_row
-
+
+
 def fix_length_errors(errs, target_line_length, joiner=' '):
     """
     If possible, transform the rows backed up in the list of errors into rows of the correct length.
@@ -28,20 +30,21 @@ def fix_length_errors(errs, target_line_length, joiner=' '):
 
     fixed_rows = []
     backlog = []
-    
+
     for err in errs:
         if type(err) is not LengthMismatchError:
-            return [] # give up if any are not length errors
+            return []  # give up if any are not length errors
 
         backlog.append(err)
         fixed_row = join_rows([err.row for err in backlog])
 
         if len(fixed_row) == target_line_length:
             fixed_rows.append(fixed_row)
-            backlog = [] # reset
-        
+            backlog = []  # reset
+
     return fixed_rows
 
+
 def extract_joinable_row_errors(errs):
     joinable = []
 
@@ -54,14 +57,16 @@ def extract_joinable_row_errors(errs):
 
         joinable.append(err)
 
-    joinable.reverse() 
+    joinable.reverse()
 
     return joinable
 
+
 class RowChecker(object):
     """
     Iterate over rows of a CSV producing cleaned rows and storing error rows.
     """
+
     def __init__(self, reader):
         self.reader = reader
         self.column_names = next(reader)
@@ -75,7 +80,7 @@ def checked_rows(self):
         A generator which yields rows which are ready to write to output.
         """
         line_number = self.reader.line_num
-        
+
         for row in self.reader:
             try:
                 if len(row) != len(self.column_names):
@@ -86,7 +91,7 @@ def checked_rows(self):
                 self.errors.append(e)
 
                 joinable_row_errors = extract_joinable_row_errors(self.errors)
-                
+
                 while joinable_row_errors:
                     fixed_row = join_rows([err.row for err in joinable_row_errors], joiner=' ')
 
@@ -98,16 +103,15 @@ def checked_rows(self):
                         self.joins += 1
 
                         yield fixed_row
-                        
+
                         for fixed in joinable_row_errors:
                             self.errors.remove(fixed)
-                        
+
                         break
 
-                    joinable_row_errors = joinable_row_errors[1:] # keep trying in case we're too long because of a straggler
+                    joinable_row_errors = joinable_row_errors[1:]  # keep trying in case we're too long because of a straggler
 
             except CSVTestException as e:
                 self.errors.append(e)
-        
+
             line_number = self.reader.line_num
-

csvkit/cli.py

@@ -12,12 +12,14 @@
 
 from csvkit.exceptions import ColumnIdentifierError, RequiredHeaderError
 
+
 def lazy_opener(fn):
     def wrapped(self, *args, **kwargs):
         self._lazy_open()
         fn(*args, **kwargs)
     return wrapped
 
+
 class LazyFile(six.Iterator):
     """
     A proxy for a File object that delays opening it until
@@ -26,6 +28,7 @@ class LazyFile(six.Iterator):
     Currently this implements only the minimum methods to be useful,
     but it could easily be expanded.
     """
+
     def __init__(self, init, *args, **kwargs):
         self.init = init
         self.f = None
@@ -56,6 +59,7 @@ def __next__(self):
 
         return next(self.f)
 
+
 class CSVKitUtility(object):
     description = ''
     epilog = ''
@@ -94,7 +98,7 @@ def __init__(self, args=None, output_file=None):
             import signal
             signal.signal(signal.SIGPIPE, signal.SIG_DFL)
         except (ImportError, AttributeError):
-            #Do nothing on platforms that don't have signals or don't have SIGPIPE
+            # Do nothing on platforms that don't have signals or don't have SIGPIPE
             pass
 
     def add_arguments(self):
@@ -125,50 +129,50 @@ def _init_common_parser(self):
         # Input
         if 'f' not in self.override_flags:
             self.argparser.add_argument(metavar="FILE", nargs='?', dest='input_path',
-                help='The CSV file to operate on. If omitted, will accept input on STDIN.')
+                                        help='The CSV file to operate on. If omitted, will accept input on STDIN.')
         if 'd' not in self.override_flags:
             self.argparser.add_argument('-d', '--delimiter', dest='delimiter',
-                help='Delimiting character of the input CSV file.')
+                                        help='Delimiting character of the input CSV file.')
         if 't' not in self.override_flags:
             self.argparser.add_argument('-t', '--tabs', dest='tabs', action='store_true',
-                help='Specifies that the input CSV file is delimited with tabs. Overrides "-d".')
+                                        help='Specifies that the input CSV file is delimited with tabs. Overrides "-d".')
         if 'q' not in self.override_flags:
             self.argparser.add_argument('-q', '--quotechar', dest='quotechar',
-                help='Character used to quote strings in the input CSV file.')
+                                        help='Character used to quote strings in the input CSV file.')
         if 'u' not in self.override_flags:
-            self.argparser.add_argument('-u', '--quoting', dest='quoting', type=int, choices=[0,1,2,3],
-                help='Quoting style used in the input CSV file. 0 = Quote Minimal, 1 = Quote All, 2 = Quote Non-numeric, 3 = Quote None.')
+            self.argparser.add_argument('-u', '--quoting', dest='quoting', type=int, choices=[0, 1, 2, 3],
+                                        help='Quoting style used in the input CSV file. 0 = Quote Minimal, 1 = Quote All, 2 = Quote Non-numeric, 3 = Quote None.')
         if 'b' not in self.override_flags:
             self.argparser.add_argument('-b', '--doublequote', dest='doublequote', action='store_true',
-                help='Whether or not double quotes are doubled in the input CSV file.')
+                                        help='Whether or not double quotes are doubled in the input CSV file.')
         if 'p' not in self.override_flags:
             self.argparser.add_argument('-p', '--escapechar', dest='escapechar',
-                help='Character used to escape the delimiter if --quoting 3 ("Quote None") is specified and to escape the QUOTECHAR if --doublequote is not specified.')
+                                        help='Character used to escape the delimiter if --quoting 3 ("Quote None") is specified and to escape the QUOTECHAR if --doublequote is not specified.')
         if 'z' not in self.override_flags:
             self.argparser.add_argument('-z', '--maxfieldsize', dest='maxfieldsize', type=int,
-                help='Maximum length of a single field in the input CSV file.')
+                                        help='Maximum length of a single field in the input CSV file.')
         if 'e' not in self.override_flags:
             self.argparser.add_argument('-e', '--encoding', dest='encoding', default='utf-8',
-                help='Specify the encoding the input CSV file.')
+                                        help='Specify the encoding the input CSV file.')
         if 'S' not in self.override_flags:
             self.argparser.add_argument('-S', '--skipinitialspace', dest='skipinitialspace', default=False, action='store_true',
-                help='Ignore whitespace immediately following the delimiter.')
+                                        help='Ignore whitespace immediately following the delimiter.')
         if 'H' not in self.override_flags:
             self.argparser.add_argument('-H', '--no-header-row', dest='no_header_row', action='store_true',
-                help='Specifies that the input CSV file has no header row. Will create default headers (A,B,C,...).')
+                                        help='Specifies that the input CSV file has no header row. Will create default headers (A,B,C,...).')
         if 'v' not in self.override_flags:
             self.argparser.add_argument('-v', '--verbose', dest='verbose', action='store_true',
-                help='Print detailed tracebacks when errors occur.')
+                                        help='Print detailed tracebacks when errors occur.')
 
         # Output
         if 'l' not in self.override_flags:
             self.argparser.add_argument('-l', '--linenumbers', dest='line_numbers', action='store_true',
-                                help='Insert a column of line numbers at the front of the output. Useful when piping to grep or as a simple primary key.')
+                                        help='Insert a column of line numbers at the front of the output. Useful when piping to grep or as a simple primary key.')
 
         # Input/Output
         if 'zero' not in self.override_flags:
             self.argparser.add_argument('--zero', dest='zero_based', action='store_true',
-                            help='When interpreting or displaying column numbers, use zero-based numbering instead of the default 1-based numbering.')
+                                        help='When interpreting or displaying column numbers, use zero-based numbering instead of the default 1-based numbering.')
 
     def _open_input_file(self, path):
         """
@@ -179,7 +183,7 @@ def _open_input_file(self, path):
             kwargs = {}
         else:
             mode = 'rt'
-            kwargs = { 'encoding': self.args.encoding }
+            kwargs = {'encoding': self.args.encoding}
 
         if not path or path == '-':
             f = sys.stdin
@@ -274,9 +278,9 @@ def print_column_names(self):
         output = self.output_file
 
         try:
-            zero_based=self.args.zero_based
+            zero_based = self.args.zero_based
         except:
-            zero_based=False
+            zero_based = False
 
         rows = agate.reader(f, **self.reader_kwargs)
         column_names = next(rows)
@@ -314,6 +318,7 @@ def match_column_identifier(column_names, c, zero_based=False):
 
     return c
 
+
 def parse_column_identifiers(ids, column_names, zero_based=False, excluded_columns=None):
     """
     Parse a comma-separated list of column indices AND/OR names into a list of integer indices.
@@ -338,9 +343,9 @@ def parse_column_identifiers(ids, column_names, zero_based=False, excluded_colum
                 columns.append(match_column_identifier(column_names, c, zero_based))
             except ColumnIdentifierError:
                 if ':' in c:
-                    a,b = c.split(':',1)
+                    a, b = c.split(':', 1)
                 elif '-' in c:
-                    a,b = c.split('-',1)
+                    a, b = c.split('-', 1)
                 else:
                     raise
 
@@ -357,7 +362,7 @@ def parse_column_identifiers(ids, column_names, zero_based=False, excluded_colum
                 except ValueError:
                     raise ColumnIdentifierError("Invalid range %s. Ranges must be two integers separated by a - or : character.")
 
-                for x in range(a,b):
+                for x in range(a, b):
                     columns.append(match_column_identifier(column_names, x, zero_based))
 
     excludes = []
@@ -370,9 +375,9 @@ def parse_column_identifiers(ids, column_names, zero_based=False, excluded_colum
                 excludes.append(match_column_identifier(column_names, c, zero_based))
             except ColumnIdentifierError:
                 if ':' in c:
-                    a,b = c.split(':',1)
+                    a, b = c.split(':', 1)
                 elif '-' in c:
-                    a,b = c.split('-',1)
+                    a, b = c.split('-', 1)
                 else:
                     raise
 
@@ -389,7 +394,7 @@ def parse_column_identifiers(ids, column_names, zero_based=False, excluded_colum
                 except ValueError:
                     raise ColumnIdentifierError("Invalid range %s. Ranges must be two integers separated by a - or : character.")
 
-                for x in range(a,b):
+                for x in range(a, b):
                     excludes.append(match_column_identifier(column_names, x, zero_based))
 
     return [c for c in columns if c not in excludes]

csvkit/convert/__init__.py

@@ -18,6 +18,7 @@
 
     SUPPORTED_FORMATS.append('dbf')
 
+
 def convert(f, format, schema=None, key=None, **kwargs):
     """
     Convert a file of a specified format to CSV.
@@ -52,6 +53,7 @@ def convert(f, format, schema=None, key=None, **kwargs):
     else:
         raise ValueError('format "%s" is not supported' % format)
 
+
 def guess_format(filename):
     """
     Try to guess a file's format based on its extension (or lack thereof).

csvkit/convert/csvitself.py

@@ -4,6 +4,7 @@
 
 import agate
 
+
 def csv2csv(f, **kwargs):
     """
     "Convert" a CSV into a new CSV by normalizing types and correcting for other anomalies.

csvkit/convert/dbase.py

@@ -8,6 +8,7 @@
 import dbf
 import six
 
+
 def dbf2csv(f, **kwargs):
     """
     Convert a dBASE .dbf file to csv.

csvkit/convert/fixed.py

@@ -6,6 +6,7 @@
 import agate
 import six
 
+
 def fixed2csv(f, schema, output=None, **kwargs):
     """
     Convert a fixed-width file to csv using a CSV-formatted schema description.
@@ -45,6 +46,7 @@ def fixed2csv(f, schema, output=None, **kwargs):
     # Return empty string when streaming
     return ''
 
+
 class FixedWidthReader(six.Iterator):
     """
     Given a fixed-width file and a schema file, produce an analog to a csv
@@ -58,6 +60,7 @@ class FixedWidthReader(six.Iterator):
     in the 'start' column are assumed to be "zero-based" unless the first value
     is "1" in which case all values are assumed to be "one-based."
     """
+
     def __init__(self, f, schema, encoding=None):
         if encoding is not None:
             f = iterdecode(f, encoding)
@@ -78,24 +81,26 @@ def __next__(self):
 
 FixedWidthField = namedtuple('FixedWidthField', ['name', 'start', 'length'])
 
+
 class FixedWidthRowParser(object):
     """
     Instantiated with a schema, able to return a sequence of trimmed strings
     representing fields given a fixed-length line. Flexible about where the
     columns are, as long as they are headed with the literal names 'column',
     'start', and 'length'.
     """
+
     def __init__(self, schema):
-        self.fields = [] # A list of FixedWidthFields
+        self.fields = []  # A list of FixedWidthFields
 
         schema_reader = agate.reader(schema)
         schema_decoder = SchemaDecoder(next(schema_reader))
 
-        for i,row in enumerate(schema_reader):
+        for i, row in enumerate(schema_reader):
             try:
                 self.fields.append(schema_decoder(row))
             except Exception as e:
-                raise ValueError("Error reading schema at line %i: %s" % (i + 2,e))
+                raise ValueError("Error reading schema at line %i: %s" % (i + 2, e))
 
     def parse(self, line):
         values = []
@@ -105,18 +110,18 @@ def parse(self, line):
 
         return values
 
-
     def parse_dict(self, line):
         """
         Convenience method returns a dict. Equivalent to
         ``dict(zip(self.headers,self.parse(line)))``.
         """
-        return dict(zip(self.headers,self.parse(line)))
+        return dict(zip(self.headers, self.parse(line)))
 
     @property
     def headers(self):
         return [field.name for field in self.fields]
 
+
 class SchemaDecoder(object):
     """
     Extracts column, start, and length columns from schema rows. Once

csvkit/convert/geojs.py

@@ -10,6 +10,7 @@
 import agate
 import six
 
+
 def geojson2csv(f, key=None, **kwargs):
     """
     Convert a GeoJSON document into CSV format.