def test_from_ISO_8859_1_csv(self):
file = os.path.realpath(this_dir + "/data/area2_yield_ISO-8859-1.csv")
descCSV = CsvDescribe(file)
self.assertEqual(predictCoordinateColumnNames(descCSV.get_column_names()), ['Longitude', 'Latitude'])
df = descCSV.open_pandas_dataframe()
self.assertListEqual(df.columns.to_list(), descCSV.get_column_names())
def test01_csvDescribe_ASCII(self):
csv_desc = CsvDescribe(file_csv)
self.assertEqual(csv_desc.file_encoding, 'ascii')
self.assertEqual(csv_desc.row_count, 13756)
self.assertEqual(csv_desc.column_count, 24)
self.assertEqual(predictCoordinateColumnNames(csv_desc.get_column_names()), ['Lon', 'Lat'])
self.assertTrue(csv_desc.has_column_header)
def test_csvfile_UTF8(self):
csvDesc = CsvDescribe(
os.path.realpath(this_dir + "/data/area2_yield_ISO-8859-1.csv"))
self.assertEqual(csvDesc.file_encoding, 'ISO-8859-1')
self.assertEqual(csvDesc.row_count, 1543)
self.assertEqual(csvDesc.column_count, 18)
self.assertEqual(
predictCoordinateColumnNames(csvDesc.get_column_names()),
['Longitude', 'Latitude'])
self.assertTrue(csvDesc.has_column_header)
def test_csvfile_UTF8(self):
csvDesc = CsvDescribe(os.path.realpath(this_dir + "/data/area2_yield_ISO-8859-1.csv"))
# chardet seems to detect this file as ISO-8869-9, which is described
# as "Largely the same as ISO/IEC 8859-1, replacing the rarely used
# Icelandic letters with Turkish ones."
#self.assertEqual(csvDesc.file_encoding, 'ISO-8859-1')
self.assertEqual(csvDesc.file_encoding, 'ISO-8859-9')
self.assertEqual(csvDesc.row_count, 1543)
self.assertEqual(csvDesc.column_count, 18)
self.assertEqual(predictCoordinateColumnNames(csvDesc.get_column_names()), ['Longitude', 'Latitude'])
self.assertTrue(csvDesc.has_column_header)
self.assertEqual(csvDesc.get_column_names()[-1], csvDesc.get_alias_column_names()[-1])
self.assertNotEqual(csvDesc.get_column_names()[-2], csvDesc.get_alias_column_names()[-2])
self.assertEqual(u'Crop Flw(V)(m\xb3/s)', csvDesc.get_column_names()[-2])
self.assertEqual('CropFlw(V)(m3/s)', csvDesc.get_alias_column_names()[-2])
#check to see if unicode characters exist True if all ascii, false if not
self.assertTrue(all(ord(char) < 128 for char in csvDesc.get_alias_column_names()[-2]))
self.assertFalse(all(ord(char) < 128 for char in csvDesc.get_column_names()[-2]))