Python pretty print dictionary of lists, abbreviate long lists

You could use IPython.lib.pretty.

from IPython.lib.pretty import pprint

> pprint(obj, max_seq_length=5)
{'key_1': ['EG8XYD9FVN',
  'S2WARDCVAO',
  'J00YCU55DP',
  'R07BUIF2F7',
  'VGPS1JD0UM',
  ...],
 'key_2': ['162LO154PM',
  '3ROAV881V2',
  'I4T79LP18J',
  'WBD36EM6QL',
  'DEIODVQU46',
  ...]}

> pprint(dict(map(lambda i: (i, range(i + 5)), range(100))), max_seq_length=10)
{0: [0, 1, 2, 3, 4],
 1: [0, 1, 2, 3, 4, 5],
 2: [0, 1, 2, 3, 4, 5, 6],
 3: [0, 1, 2, 3, 4, 5, 6, 7],
 4: [0, 1, 2, 3, 4, 5, 6, 7, 8],
 5: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
 6: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, ...],
 7: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, ...],
 8: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, ...],
 9: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, ...],
 ...}

For older versions of IPython, you might exploit RepresentationPrinter:

from IPython.lib.pretty import RepresentationPrinter
import sys

def compact_pprint(obj, max_seq_length=10):
    printer = RepresentationPrinter(sys.stdout)
    printer.max_seq_length = max_seq_length
    printer.pretty(obj)
    printer.flush()

If it weren't for the pretty printing, the reprlib module would be the way to go: Safe, elegant and customizable handling of deeply nested and recursive / self-referencing data structures is what it has been made for.

However, it turns out combining the reprlib and pprint modules isn't trivial, at least I couldn't come up with a clean way without breaking (some) of the pretty printing aspects.

So instead, here's a solution that just subclasses PrettyPrinter to crop / abbreviate lists as necessary:

from pprint import PrettyPrinter


obj = {
    'key_1': [
        'EG8XYD9FVN', 'S2WARDCVAO', 'J00YCU55DP', 'R07BUIF2F7', 'VGPS1JD0UM',
        'WL3TWSDP8E', 'LD8QY7DMJ3', 'J36U3Z9KOQ', 'KU2FUGYB2U', 'JF3RQ315BY',
    ],
    'key_2': [
        '162LO154PM', '3ROAV881V2', 'I4T79LP18J', 'WBD36EM6QL', 'DEIODVQU46',
        'KWSJA5WDKQ', 'WX9SVRFO0G', '6UN63WU64G', '3Z89U7XM60', '167CYON6YN',
    ],
    # Test case to make sure we didn't break handling of recursive structures
    'key_3': [
        '162LO154PM', '3ROAV881V2', [1, 2, ['a', 'b', 'c'], 3, 4, 5, 6, 7],
        'KWSJA5WDKQ', 'WX9SVRFO0G', '6UN63WU64G', '3Z89U7XM60', '167CYON6YN',
    ]
}


class CroppingPrettyPrinter(PrettyPrinter):

    def __init__(self, *args, **kwargs):
        self.maxlist = kwargs.pop('maxlist', 6)
        return PrettyPrinter.__init__(self, *args, **kwargs)

    def _format(self, obj, stream, indent, allowance, context, level):
        if isinstance(obj, list):
            # If object is a list, crop a copy of it according to self.maxlist
            # and append an ellipsis
            if len(obj) > self.maxlist:
                cropped_obj = obj[:self.maxlist] + ['...']
                return PrettyPrinter._format(
                    self, cropped_obj, stream, indent,
                    allowance, context, level)

        # Let the original implementation handle anything else
        # Note: No use of super() because PrettyPrinter is an old-style class
        return PrettyPrinter._format(
            self, obj, stream, indent, allowance, context, level)


p = CroppingPrettyPrinter(maxlist=3)
p.pprint(obj)

Output with maxlist=3:

{'key_1': ['EG8XYD9FVN', 'S2WARDCVAO', 'J00YCU55DP', '...'],
 'key_2': ['162LO154PM',
           '3ROAV881V2',
           [1, 2, ['a', 'b', 'c'], '...'],
           '...']}

Output with maxlist=5 (triggers splitting the lists on separate lines):

{'key_1': ['EG8XYD9FVN',
           'S2WARDCVAO',
           'J00YCU55DP',
           'R07BUIF2F7',
           'VGPS1JD0UM',
           '...'],
 'key_2': ['162LO154PM',
           '3ROAV881V2',
           'I4T79LP18J',
           'WBD36EM6QL',
           'DEIODVQU46',
           '...'],
 'key_3': ['162LO154PM',
           '3ROAV881V2',
           [1, 2, ['a', 'b', 'c'], 3, 4, '...'],
           'KWSJA5WDKQ',
           'WX9SVRFO0G',
           '...']}

Notes:

  • This will create copies of lists. Depending on the size of the data structures, this can be very expensive in terms of memory use.
  • This only deals with the special case of lists. Equivalent behavior would have to be implemented for dicts, tuples, sets, frozensets, ... for this class to be of general use.