stdout columns to list of dicts - now supporting tabs or whatever and multi-columns

breakout.md

To take any bunch of printed columns from stdout and turn them into lists of dictionaries...

def parse_block(block, headers=True, delimiter=None):
    """Return a list of items for each row.

    If there are headers in the block of text, they will
    be parsed out and a list of dicts will be returned.
    If there are no headers, a list of tuples will be returned.

    If delimiter is None, it is passed to str.split as is,
    which is interpreted to mean "whitespace", such as tabs
    and spaces.
    """
    # remove nullish lines
    lines = [l.strip() for l in block.splitlines() if l.strip()]
    # split first line on whitespace to count the headers
    if not lines:
        return lines
    cols = len(lines[0].split(delimiter))
    # make a list of lists with clean elements of equal length
    breakout = [k.split(delimiter, cols) for k in lines]
    if headers:
        headers, values = breakout[0], breakout[1:]
        return [dict(zip(headers, vals)) for vals in values]
    else:
        return [tuple(vals) for vals in breakout]


machines = """
MACHINE     METADATA
22e994f51ce04e098253d52a91ec4431 role=services
42186fe9d3cc478ea918f381c479d890 environment=staging,role=worker
5cf1ac5803264981830308ffdda1d9a2 role=services
74eb21c316d34b37bd00335974f6b8c2 role=services
9c63be10638b4aa88e548b688b6fc7a2 environment=dev,role=worker
a0fbca206cc043838c0aeddb853769fa environment=staging,role=worker
ae0f612d223b41c0a4865fb5c8d0f4b1 role=services
b098fcfbc0c24e849654328edc28700b environment=dev,role=worker
c1d4cc4c9b4a468bb69409b5c9777bc0 role=services
"""

print parse_block(machines)

[{'MACHINE': '22e994f51ce04e098253d52a91ec4431', 'METADATA': 'role=services'},
 {'MACHINE': '42186fe9d3cc478ea918f381c479d890',
  'METADATA': 'environment=staging,role=worker'},
 {'MACHINE': '5cf1ac5803264981830308ffdda1d9a2', 'METADATA': 'role=services'},
 {'MACHINE': '74eb21c316d34b37bd00335974f6b8c2', 'METADATA': 'role=services'},
 {'MACHINE': '9c63be10638b4aa88e548b688b6fc7a2',
  'METADATA': 'environment=dev,role=worker'},
 {'MACHINE': 'a0fbca206cc043838c0aeddb853769fa',
  'METADATA': 'environment=staging,role=worker'},
 {'MACHINE': 'ae0f612d223b41c0a4865fb5c8d0f4b1', 'METADATA': 'role=services'},
 {'MACHINE': 'b098fcfbc0c24e849654328edc28700b',
  'METADATA': 'environment=dev,role=worker'},
 {'MACHINE': 'c1d4cc4c9b4a468bb69409b5c9777bc0', 'METADATA': 'role=services'}]


foo = """
MACHINE  \t   METADATA  OTHER
22e994f51ce04e098253d52a91ec4431 role=services bar
42186fe9d3cc478ea918f381c479d890 environment=staging,role=worker\t baz
5cf1ac5803264981830308ffdda1d9a2 role=services   \tbing
74eb21c316d34b37bd00335974f6b8c2\t   role=services qux
9c63be10638b4aa88e548b688b6fc7a2 environment=dev,role=worker fred
a0fbca206cc043838c0aeddb853769fa environment=staging,role=worker waldo
ae0f612d223b41c0a4865fb5c8d0f4b1 role=services     xyzzy
b098fcfbc0c24e849654328edc28700b environment=dev,role=worker     thud
c1d4cc4c9b4a468bb69409b5c9777bc0 role=services\t  wobble
"""

print parse_block(foo)
 
 [{'MACHINE': '22e994f51ce04e098253d52a91ec4431',
  'METADATA': 'role=services',
  'OTHER': 'bar'},
 {'MACHINE': '42186fe9d3cc478ea918f381c479d890',
  'METADATA': 'environment=staging,role=worker',
  'OTHER': 'baz'},
 {'MACHINE': '5cf1ac5803264981830308ffdda1d9a2',
  'METADATA': 'role=services',
  'OTHER': 'bing'},
 {'MACHINE': '74eb21c316d34b37bd00335974f6b8c2',
  'METADATA': 'role=services',
  'OTHER': 'qux'},
 {'MACHINE': '9c63be10638b4aa88e548b688b6fc7a2',
  'METADATA': 'environment=dev,role=worker',
  'OTHER': 'fred'},
 {'MACHINE': 'a0fbca206cc043838c0aeddb853769fa',
  'METADATA': 'environment=staging,role=worker',
  'OTHER': 'waldo'},
 {'MACHINE': 'ae0f612d223b41c0a4865fb5c8d0f4b1',
  'METADATA': 'role=services',
  'OTHER': 'xyzzy'},
 {'MACHINE': 'b098fcfbc0c24e849654328edc28700b',
  'METADATA': 'environment=dev,role=worker',
  'OTHER': 'thud'},
 {'MACHINE': 'c1d4cc4c9b4a468bb69409b5c9777bc0',
  'METADATA': 'role=services',
  'OTHER': 'wobble'}]

breakout.py

def parse_block(block, headers=True, delimiter=None):
    """Return a list of items for each row.

    If there are headers in the block of text, they will
    be parsed out and a list of dicts will be returned.
    If there are no headers, a list of tuples will be returned.

    If delimiter is None, it is passed to str.split as is,
    which is interpreted to mean "whitespace", such as tabs
    and spaces.
    """
    # remove nullish lines
    lines = [l.strip() for l in block.splitlines() if l.strip()]
    # split first line on whitespace to count the headers
    if not lines:
        return lines
    cols = len(lines[0].split(delimiter))
    # make a list of lists with clean elements of equal length
    breakout = [k.split(delimiter, cols) for k in lines]
    if headers:
        headers, values = breakout[0], breakout[1:]
        return [dict(zip(headers, vals)) for vals in values]
    else:
        return [tuple(vals) for vals in breakout]


if __name__ == '__main__':

    from pprint import pprint

    machines = """
    MACHINE                          METADATA
    22e994f51ce04e098253d52a91ec4431 role=services
    42186fe9d3cc478ea918f381c479d890 environment=staging,role=worker
    5cf1ac5803264981830308ffdda1d9a2 role=services
    74eb21c316d34b37bd00335974f6b8c2 role=services
    9c63be10638b4aa88e548b688b6fc7a2 environment=dev,role=worker
    a0fbca206cc043838c0aeddb853769fa environment=staging,role=worker
    ae0f612d223b41c0a4865fb5c8d0f4b1 role=services
    b098fcfbc0c24e849654328edc28700b environment=dev,role=worker
    c1d4cc4c9b4a468bb69409b5c9777bc0 role=services
    """
    print('\nInput:\n%s\n' % machines)

    pprint(parse_block(machines))

    foo = """
    MACHINE  \t                      METADATA                   OTHER
    22e994f51ce04e098253d52a91ec4431 role=services bar
    42186fe9d3cc478ea918f381c479d890 environment=staging,role=worker\t baz
    5cf1ac5803264981830308ffdda1d9a2 role=services   \tbing
    74eb21c316d34b37bd00335974f6b8c2\t   role=services qux
    9c63be10638b4aa88e548b688b6fc7a2 environment=dev,role=worker fred
    a0fbca206cc043838c0aeddb853769fa environment=staging,role=worker waldo
    ae0f612d223b41c0a4865fb5c8d0f4b1 role=services     xyzzy
    b098fcfbc0c24e849654328edc28700b environment=dev,role=worker     thud
    c1d4cc4c9b4a468bb69409b5c9777bc0 role=services\t  wobble
    """
    print('\nInput:\n%s\n' % foo)

    pprint(parse_block(foo))

    foo = """
    key0 foo0 bar0
    key1 foo1 bar1
    key2 foo2 bar2
    key3 foo3 bar3
    key4 foo4 bar4
    """
    print('\nInput:\n%s\n' % foo)
    pprint(parse_block(foo, headers=False))