def covid19Transformer(self):
if self == InputFileFactory.CONFIRMED_US:
return Covid19USTransformer()
elif self == InputFileFactory.CONFIRMED_GLOBAL:
return Covid19GlobalTransformer()
else:
return None
def test_process_line(self):
t1 = Covid19USTransformer()
self.assertEqual(0, len(t1._colsToRead))
self.assertEqual(0, len(t1._dateList))
self.assertEqual(0, len(t1._objColl))
t1.processLine(self._header.split(','), True)
self.assertEqual(72, len(t1._colsToRead))
self.assertEqual(69, len(t1._dateList))
self.assertEqual(0, len(t1._objColl))
for line in self._inputListFromFile:
lineAsList = TestCovid19USTransformer._createListFromCSVLine(line)
t1.processLine(lineAsList, False)
self.assertEqual(72, len(t1._colsToRead))
self.assertEqual(69, len(t1._dateList))
self.assertEqual(len(self._inputListFromFile), len(t1._objColl))
i = 0
for obj in t1.getCollection():
self.assertEqual(str(self._verificationObjects[i]), str(obj))
# print('{0}: {1}'.format(i, str(obj)))
i = i + 1
self.assertEqual(72, len(t1._colsToRead))
self.assertEqual(69, len(t1._dateList))
self.assertEqual(len(self._inputListFromFile), len(t1._objColl))
def test3():
t1 = Covid19USTransformer()
self.assertEqual(0, len(t1._colsToRead))
t1.processHeader(['abc'])
self.assertEqual(0, len(t1._colsToRead))
t1.processHeader(['iso3'])
self.assertEqual(1, len(t1._colsToRead))
t1.processHeader(['iso3', 'Province_State'])
self.assertEqual(2, len(t1._colsToRead))
t1.processHeader(['iso3', 'Province_State', 'abracadabra'])
self.assertEqual(2, len(t1._colsToRead))
self.assertEqual(0, len(t1._dateList))
def test_add_to_collection(self):
t1 = Covid19USTransformer()
self.assertEqual(0, len(t1._objColl))
t1.processHeader(self._header.split(','))
colList = t1.listOfIndexesOfColumnsToRead()
for line in self._inputListFromFile:
lineAsList = TestCovid19USTransformer._createListFromCSVLine(line)
rawDataList = []
for col in colList:
rawDataList.append(lineAsList[col])
t1.addToCollection(t1.createObject(tuple(rawDataList)))
self.assertEqual(len(self._inputListFromFile), len(t1._objColl))
i = 0
for obj in t1._objColl:
self.assertEqual(str(self._verificationObjects[i]), str(obj))
i = i + 1
def test_create_object(self):
t1 = Covid19USTransformer()
headerAsTuple = tuple(self._header.split(','))
firstDatePos = headerAsTuple.index('Combined_Key') + 1
numDateCols = len(headerAsTuple) - firstDatePos
t1.processHeader(self._header.split(','))
colList = t1.listOfIndexesOfColumnsToRead()
self.assertEqual(numDateCols + 3, len(colList))
for i in range(0, len(self._inputListFromFile)):
line = self._inputListFromFile[i]
lineAsList = TestCovid19USTransformer._createListFromCSVLine(line)
# print("xx = ", str(lineAsList))
rawDataList = []
for col in colList:
rawDataList.append(lineAsList[col])
# print(str(tuple(rawDataList)))
o1 = t1.createObject(tuple(rawDataList))
self.assertIsNotNone(o1)
self.assertEqual(str(self._verificationObjects[i]), str(o1))
i = i + 1
def test4():
t1 = Covid19USTransformer()
self.assertEqual(0, len(t1._colsToRead))
# '"UID,iso2,iso3,code3,FIPS,Admin2,Province_State,Country_Region,Lat,Long_,Combined_Key,1/22/2020...'
# Before 'Combined_Key'. 'Combined_Key' is index #10.
t1.processHeader(self._header.split(',')[:10])
self.assertEqual(3, len(t1._colsToRead))
self.assertEqual(0, len(t1._dateList))
# Include 'Combined_Key'. 'Combined_Key' is index #10.
t1.processHeader(self._header.split(',')[:11])
self.assertEqual(3, len(t1._colsToRead))
self.assertEqual(0, len(t1._dateList))
# # Include date after 'Combined_Key'.
t1.processHeader(self._header.split(',')[:12])
self.assertEqual(4, len(t1._colsToRead))
self.assertEqual(1, len(t1._dateList))
t1.processHeader(self._header.split(',')[:13])
self.assertEqual(5, len(t1._colsToRead))
self.assertEqual(2, len(t1._dateList))
# All date columns.
t1.processHeader(self._header.split(','))
self.assertEqual(72, len(t1._colsToRead))
self.assertEqual(69, len(t1._dateList))
def test_columns_to_read(self):
t1 = Covid19USTransformer()
colAsTuple = tuple(self._header.split(','))
t1.processHeader(colAsTuple)
self.assertEqual(0, len(t1._objColl))
headerAsTuple = tuple(self._header.split(','))
firstDatePos = headerAsTuple.index('Combined_Key') + 1
self.assertTrue(firstDatePos > 1)
numDateCols = len(headerAsTuple) - firstDatePos
self.assertTrue(numDateCols > 0)
l1 = t1.listOfIndexesOfColumnsToRead()
self.assertEqual(numDateCols + 3, len(l1))
self.assertEqual(0, len(t1._objColl))
self.assertEqual(numDateCols, len(t1._dateList))
l1AsTuple = tuple(l1)
countryCol = headerAsTuple.index('iso3')
self.assertTrue(countryCol >= 0)
self.assertTrue(l1AsTuple.index(countryCol) >= 0)
stateCol = headerAsTuple.index('Province_State')
self.assertTrue(stateCol >= 0)
self.assertTrue(l1AsTuple.index(stateCol) >= 0)
countyCol = headerAsTuple.index('Admin2')
self.assertTrue(countyCol >= 0)
self.assertTrue(l1AsTuple.index(countyCol) >= 0)
# Check all date column header numbers are included.
for i in range(firstDatePos, len(headerAsTuple)):
self.assertTrue(l1AsTuple.index(i) >= 0)
self.assertEqual(tuple(self._dateList), tuple(t1._dateList))
def test2():
t1 = Covid19USTransformer()
self.assertEqual(0, len(t1._colsToRead))
t1.processHeader([])
self.assertEqual(0, len(t1._colsToRead))
self.assertEqual(0, len(t1._dateList))