def from_json(cls, local_path, header=None, line_delimited=False):
"""
Create a ``parsons table`` from a json file
`Args:`
local_path: list
A JSON formatted local path, url or ftp. If this is a
file path that ends in ".gz", the file will be decompressed first.
header: list
List of columns to use for the destination table. If omitted, columns will
be inferred from the initial data in the file.
line_delimited: bool
Whether the file is line-delimited JSON (with a row on each line), or a proper
JSON file.
`Returns:`
Parsons Table
See :ref:`parsons-table` for output options.
"""
if line_delimited:
if files.is_gzip_path(local_path):
open_fn = gzip.open
else:
open_fn = open
with open_fn(local_path, 'r') as file:
rows = [json.loads(line) for line in file]
return cls(rows)
else:
return cls(petl.fromjson(local_path, header=header))
def to_json(self, local_path=None, temp_file_compression=None, line_delimited=False):
"""
Outputs table to a JSON file
.. warning::
If a file already exists at the given location, it will be
overwritten.
`Args:`
local_path: str
The path to write the JSON locally. If it ends in ".gz", it will be
compressed first. If not specified, a temporary file will be created and returned,
and that file will be removed automatically when the script is done running.
temp_file_compression: str
If a temp file is requested (ie. no ``local_path`` is specified), the compression
type for that file. Currently "None" and "gzip" are supported.
If a ``local_path`` is specified, this argument is ignored.
line_delimited: bool
Whether the file will be line-delimited JSON (with a row on each line), or a proper
JSON file.
`Returns:`
str
The path of the new file
"""
if not local_path:
suffix = '.json' + files.suffix_for_compression_type(temp_file_compression)
local_path = files.create_temp_file(suffix=suffix)
# Note we don't use the much simpler petl.tojson(), since that method reads the whole
# table into memory before writing to file.
if files.is_gzip_path(local_path):
open_fn = gzip.open
mode = 'w+t'
else:
open_fn = open
mode = 'w'
with open_fn(local_path, mode) as file:
if not line_delimited:
file.write('[')
i = 0
for row in self:
if i:
if not line_delimited:
file.write(',')
file.write('\n')
i += 1
json.dump(row, file)
if not line_delimited:
file.write(']')
return local_path
def test_is_gzip_path():
assert files.is_gzip_path('some/file.gz')
assert not files.is_gzip_path('some/file')
assert not files.is_gzip_path('some/file.csv')
