def get_tables(year, month):
from config import InterimCSV
import csv2df.specification as spec
import csv2df.reader as reader
parsed_tables = []
csv_path = InterimCSV(year, month).path
with reader.open_csv(csv_path) as csvfile:
for csv_segment, pdef in reader.Reader(csvfile, spec.SPEC).items():
tables = extract_tables(csv_segment, pdef)
parsed_tables.extend(tables)
return parsed_tables
Yield CSV segments as Row() instances and corresponding
parsing definitons based on *spec* parsing specification.
Args:
spec: parsing specification as spec.Specification() instance
Yields:
Yield CSV segments (list of Row() instances)
and parsing definiton pairs as tuples
"""
for pdef in pdef_segments:
start, end = pdef.get_bounds(self.rows)
csv_segment = self.pop(start, end)
yield csv_segment, pdef
yield self.remaining_rows(), pdef_default
if __name__ == "__main__":
from config import InterimCSV, LATEST_DATE
import csv2df.specification as spec
# print all rows from csvpath
year, month = LATEST_DATE
csv_path = InterimCSV(year, month).path
csvfile = open_csv(csv_path)
reader = Reader(csvfile, spec=spec.SPEC)
for csv_segment, pdef in reader.items():
for row in csv_segment:
print(row)
csvfile.close()
def __init__(self, year, month):
self.year, self.month = year, month
csv_interim = InterimCSV(year, month)
self.dfs = get_dataframes(csv_interim.path)
def test_get_path_property_method_returns_tab_csv(self):
interim_csv = InterimCSV(2015, 5).path
expected_name = 'tab.csv'
assert interim_csv.name == expected_name
def test_get_path_property_method_returns_existing_file(self):
interim_csv = InterimCSV(2015, 5).path
assert interim_csv.exists()
def test_csv_has_no_null_byte():
csv_path = InterimCSV(2015, 2).path
z = csv_path.read_text(encoding='utf-8')
assert "\0" not in z