def test_sort_file():
"""Test md5 sum calculation."""
data_file = create_file(['Ben,US,24', 'Alex,US,25', 'Alex,PT,25'])
out_file = sort_file(data_file)
obs_out = file_2list(out_file)
os.remove(out_file)
assert obs_out == ['Alex,PT,25', 'Alex,US,25', 'Ben,US,24']
def test_sort_file():
"""Test md5 sum calculation."""
data_file = create_file(['Ben,US,24', 'Alex,US,25', 'Alex,PT,25'])
out_file = sort_file(data_file)
obs_out = file_2list(out_file)
os.remove(out_file)
assert obs_out == ['Alex,PT,25', 'Alex,US,25', 'Ben,US,24']
def test_json2csv(test_name, json_data, header_values, row_key, expected):
"""Test json2csv function.
Creates a json file and tests the md5 sum calculation.
"""
json_file = create_file(json_data, 'output.json')
output_json = json2csv(json_file,
"output_json.csv",
header_values=header_values,
row_key=row_key)
obs_out = file_2list(output_json)
os.remove(output_json)
assert obs_out == expected
def test_json2csv():
"""Test json2csv function.
Creates a json file and tests the md5 sum calculation.
"""
json_file = create_file([
"""[ {"User": "******", "Country": "US", "Age": "25"} ]"""],
'output.json')
output_json = json2csv(json_file, "output_json.csv",
header_values=["User", "Country", "Age"])
obs_out = file_2list(output_json)
os.remove(output_json)
assert obs_out == ['User,Country,Age', 'Alex,US,25']
def test_json2csv():
"""Test json2csv function.
Creates a json file and tests the md5 sum calculation.
"""
json_file = create_file([
"""[ {"User": "******", "Country": "US", "Age": "25"} ]"""],
'output.json')
output_json = json2csv(json_file, "output_json.csv",
header_values=["User", "Country", "Age"])
obs_out = file_2list(output_json)
os.remove(output_json)
assert obs_out == ['User,Country,Age', 'Alex,US,25']
def test_xml2csv():
"""Test xml2csv function.
Creates a xml file and tests the md5 sum calculation.
"""
xml_file = create_file([
'<root>', '<row>', '<User>Alex</User>', '<Country>US</Country>',
'<Age>25</Age>', '</row>', '<row>', '<User>Ben</User>',
'<Country>US</Country>', '<Age>24</Age>', '</row>', '</root>'
], 'output.xml')
output_xml = xml2csv(xml_file,
"output_xml.csv",
header_values=["User", "Country", "Age"])
obs_out = file_2list(output_xml)
os.remove(output_xml)
assert obs_out == ['User,Country,Age', 'Alex,US,25', 'Ben,US,24']
def test_xml2csv(test_name, xml_data, header_values, empty_rows, expected):
"""Test xml2csv function.
Creates a xml file and tests the md5 sum calculation.
"""
xml_file = create_file(xml_data, 'output.xml')
input_file = xml_file
outputfile = "output_xml.csv"
output_xml = xml2csv_test(input_file,
outputfile,
header_values,
row_tag="row")
obs_out = file_2list(output_xml)
os.remove(output_xml)
assert obs_out == expected
def test_xml2csv():
"""Test xml2csv function.
Creates a xml file and tests the md5 sum calculation.
"""
xml_file = create_file(['<root>', '<row>',
'<User>Alex</User>',
'<Country>US</Country>',
'<Age>25</Age>', '</row>',
'<row>', '<User>Ben</User>',
'<Country>US</Country>',
'<Age>24</Age>',
'</row>', '</root>'], 'output.xml')
output_xml = xml2csv(xml_file, "output_xml.csv",
header_values=["User", "Country", "Age"])
obs_out = file_2list(output_xml)
os.remove(output_xml)
assert obs_out == ['User,Country,Age', 'Alex,US,25', 'Ben,US,24']
def get_output_as_csv(dataset, engines, tmpdir, db):
"""Install dataset and return the output as a string version of the csv."""
workdir = tmpdir.mkdtemp()
workdir.chdir()
# Since we are writing scripts to the .retriever directory,
# we don't have to change to the main source directory in order
# to have the scripts loaded
script_module = get_script_module(dataset["name"])
script_module.download(engines)
script_module.engine.final_cleanup()
script_module.engine.to_csv()
# get filename and append .csv
csv_file = engines.opts['table_name'].format(db=db, table=dataset["name"])
# csv engine already has the .csv extension
if engines.opts["engine"] != 'csv':
csv_file += '.csv'
obs_out = file_2list(csv_file)
os.chdir(retriever_root_dir)
return obs_out
def get_output_as_csv(dataset, engines, tmpdir, db):
"""Install dataset and return the output as a string version of the csv."""
workdir = tmpdir.mkdtemp()
workdir.chdir()
# Since we are writing scripts to the .retriever directory,
# we don't have to change to the main source directory in order
# to have the scripts loaded
script_module = get_script_module(dataset["name"])
script_module.download(engines)
script_module.engine.final_cleanup()
script_module.engine.to_csv()
# get filename and append .csv
csv_file = engines.opts['table_name'].format(db=db, table=dataset["name"])
# csv engine already has the .csv extension
if engines.opts["engine"] != 'csv':
csv_file += '.csv'
obs_out = file_2list(csv_file)
os.chdir(retriever_root_dir)
return obs_out
