Mercurial > hg > Lemuriformes

comparison lemuriformes/json2csv.py @ 15:0d1b8bb1d97b

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
SQL + data related functionality
author Jeff Hammel <k0scist@gmail.com>
date Sun, 10 Dec 2017 17:16:52 -0800
parents
children
comparison
equal deleted inserted replaced
14:756dbd3e391e 15:0d1b8bb1d97b
1 #!/usr/bin/env python
2
3 """
4 convert JSON list of hashes to CSV
5 """
6 # Note: we could use https://docs.python.org/2/library/csv.html#csv.DictWriter
7 # but we're being careful here since we actually want this data structure in code,
8 # not just for de/serialization
9
10
11 import argparse
12 import csv
13 import json
14 import sys
15 from .cast import unify
16 from .cli import ConfigurationParser
17
18
19 def flatten_list_of_dicts(list_of_dicts, header=None):
20 """
21 flattens a list of dicts into a list of lists.
22
23 Returns (header, list_of_lists)
24 """
25
26 if not list_of_dicts:
27 return []
28
29 # sanity
30 keys = list_of_dicts[0].keys()
31 if header:
32 if not set(header).issubset(keys):
33 raise AssertionError("header contains elements not seen in the set: {}".format(', '.format(set(header).difference(keys))))
34 for item in list_of_dicts:
35 # ensure each item has the same keys
36 if set(keys) != set(item.keys()):
37 raise AssertionError("Keys not consistent! {} != {}".format(sorted(keys),
38 sorted(item.keys())))
39
40 if not header:
41 header = keys # to sort?
42
43 # flatten it!
44 retval = []
45 for item in list_of_dicts:
46 retval.append([item[key] for key in header])
47
48 return (header, retval)
49
50
51 def main(args=sys.argv[1:]):
52 """CLI"""
53
54 # parse command line
55 parser = ConfigurationParser(description=__doc__)
56 parser.add_argument('json', type=argparse.FileType('r'),
57 help="JSON file of list of hashes")
58 parser.add_argument('-H', '--header', dest='header', nargs='+',
59 help="use these fields for header")
60 parser.add_argument('-o', '--output', dest='output',
61 type=argparse.FileType('w'), default=sys.stdout,
62 help="path to output, or stdout by default")
63 options = parser.parse_args(args)
64
65 # read
66 data = json.load(options.json)
67
68 # flatten
69 header, flattened = flatten_list_of_dicts(data, header=options.header)
70
71 # write
72 writer = csv.writer(options.output)
73 writer.writerow(header)
74 for row in flattened:
75 writer.writerow([unify(v) for v in row])
76
77 if __name__ == '__main__':
78 main()