File size: 5,622 Bytes
06555b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
import sys
import json
import shutil
import pathlib
import argparse
import subprocess
from colorama import init, Fore, Style
from csvw import CSVW, TableGroup
from csvw.db import Database
from csvw.utils import metadata2markdown
def parsed_args(desc, args, *argspecs):
if args is None: # pragma: no cover
parser = argparse.ArgumentParser(description=desc)
for kw, kwargs in argspecs:
parser.add_argument(*kw, **kwargs)
return parser.parse_args()
return args
def exit(ret, test=False):
if test:
return ret
sys.exit(ret) # pragma: no cover
def csvwdescribe(args=None, test=False):
frictionless = shutil.which('frictionless')
if not frictionless: # pragma: no cover
raise ValueError('The frictionless command must be installed for this functionality!\n'
'Run `pip install frictionless` and try again.')
args = parsed_args(
"Describe a (set of) CSV file(s) with basic CSVW metadata.",
args,
(['--delimiter'], dict(default=None)),
(['csv'], dict(nargs='+', help="CSV files to describe as CSVW TableGroup")),
)
fargs = ['describe', '--json']
if args.delimiter:
fargs.extend(['--dialect', '{"delimiter": "%s"}' % args.delimiter])
onefile = False
if len(args.csv) == 1 and '*' not in args.csv[0]:
onefile = True
# Make sure we infer a tabular-data schema even if the file suffix does not suggest a CSV
# file.
fargs.extend(['--format', 'csv'])
else:
fargs.extend(['--type', 'package'])
dp = json.loads(subprocess.check_output([frictionless] + fargs + args.csv))
if onefile:
dp = dict(resources=[dp], profile='data-package')
tg = TableGroup.from_frictionless_datapackage(dp)
print(json.dumps(tg.asdict(), indent=4))
return exit(0, test=test)
def csvwvalidate(args=None, test=False):
init()
args = parsed_args(
"Validate a (set of) CSV file(s) described by CSVW metadata.",
args,
(['url'], dict(help='URL or local path to CSV or JSON metadata file.')),
(['-v', '--verbose'], dict(action='store_true', default=False)),
)
ret = 0
try:
csvw = CSVW(args.url, validate=True)
if csvw.is_valid:
print(Style.BRIGHT + Fore.GREEN + 'OK')
else:
ret = 1
print(Style.BRIGHT + Fore.RED + 'FAIL')
if args.verbose:
for w in csvw.warnings:
print(Style.DIM + str(w.message))
except ValueError as e:
ret = 2
print(Style.BRIGHT + Fore.RED + 'FAIL')
if args.verbose:
print(Style.DIM + Fore.BLUE + str(e))
return exit(ret, test=test)
def csvw2datasette(args=None, test=False):
args = parsed_args(
"Convert CSVW to data for datasette (https://datasette.io/).",
args,
(['url'], dict(help='URL or local path to CSV or JSON metadata file.')),
(['-o', '--outdir'], dict(type=pathlib.Path, default=pathlib.Path('.'))),
)
dbname, mdname = 'datasette.db', 'datasette-metadata.json'
csvw = CSVW(args.url)
db = Database(csvw.tablegroup, fname=args.outdir / dbname)
db.write_from_tg()
md = {}
for k in ['title', 'description', 'license']:
if 'dc:{}'.format(k) in csvw.common_props:
md[k] = csvw.common_props['dc:{}'.format(k)]
# FIXME: flesh out, see https://docs.datasette.io/en/stable/metadata.html
args.outdir.joinpath(mdname).write_text(json.dumps(md, indent=4))
print("""Run
datasette {} --metadata {}
and open your browser at
http://localhost:8001/
to browse the data.
""".format(args.outdir / dbname, args.outdir / mdname))
return exit(0, test=test)
def csvw2json(args=None, test=False):
args = parsed_args(
"Convert CSVW to JSON, see https://w3c.github.io/csvw/csv2json/",
args,
(['url'], dict(help='URL or local path to CSV or JSON metadata file.')),
)
csvw = CSVW(args.url)
print(json.dumps(csvw.to_json(), indent=4))
return exit(0, test=test)
def csvw2sqlite(args=None, test=False): # pragma: no cover
args = parsed_args(
"Convert CSVW to JSON, see https://w3c.github.io/csvw/csv2json/",
args,
(
['url'],
dict(help='URL or local path to CSVW metadata file describing a TableGroup.\n\n'
'Note that not all valid CSVW datasets can be converted to SQLite. One '
'limitation is that all tables which are referenced by foreign keys must '
'have a primary key.')),
(
['output'],
dict(help='Path for the generated SQLite database file.')),
)
tg = TableGroup.from_file(args.url)
db = Database(tg, args.output)
db.write_from_tg(_force=True)
return exit(0, test=test)
def csvw2markdown(args=None, test=False):
args = parsed_args(
"Convert CSVW to JSON, see https://w3c.github.io/csvw/csv2json/",
args,
(
['url'],
dict(help='URL or local path to CSVW metadata file describing a TableGroup.\n\n'
'Note that not all valid CSVW datasets can be converted to SQLite. One '
'limitation is that all tables which are referenced by foreign keys must '
'have a primary key.')),
)
tg = TableGroup.from_file(args.url)
print(metadata2markdown(tg, link_files=True))
return exit(0, test=test)
if __name__ == '__main__': # pragma: no cover
csvw2json()
|