def read_data_set(
cls, dirpath: str,
filesystem: FsWrapperBase = FsPathlibWrapper()) -> "DataSet":
"""Reads a DataSet from disk.
A DataSet is given by a directory containing a collection of files,
each of which represents a PublisherDataSet. The name associated to
the DataSet object is the last component of the dirpath.
Args:
dirpath: Directory containing the PublisherDataSets that comprise
this DataSet.
filesystem: The filesystem object that manages all file operations.
Returns:
The DataSet object representing the contents of this directory.
"""
pdf_list = []
for filepath in sorted(filesystem.glob(dirpath, "*")):
if filesystem.is_file(filepath):
with filesystem.open(filepath) as file:
try:
pdf = PublisherData.read_publisher_data(file)
pdf.name = str(filepath)
pdf_list.append(pdf)
except (ValueError, RuntimeError) as e:
raise RuntimeError(
"In publisher file {}".format(filepath)) from e
return cls(pdf_list, filesystem.name(dirpath))
def test_read_and_write_publisher_data(self):
pdf = PublisherData([(1, 0.01), (2, 0.02), (1, 0.04)], "test")
with TemporaryDirectory() as d:
filename = join(d, "pdf_data")
pdf_file = open(filename, "w")
pdf.write_publisher_data(pdf_file)
pdf_file.close()
new_file = open(filename)
new_pdf = PublisherData.read_publisher_data(new_file)
self.assertEqual(new_pdf.max_impressions, 3)
self.assertEqual(new_pdf.max_spend, 0.04)
self.assertEqual(new_pdf.max_reach, 2)
new_file.close()