def test_null_process(self):
fh = horror_fobj('null.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
row_set.register_processor(null_processor(['null']))
data = list(row_set)
nones = [[x.value is None for x in row] for row in data]
assert_equal(nones[0], [False, True, False, False])
assert_equal(nones[1], [False, False, False, True])
assert_equal(nones[2], [False, True, False, False])
types = type_guess(row_set.sample, strict=True)
expected_types = [
IntegerType(),
IntegerType(),
IntegerType(),
IntegerType()
]
assert_equal(types, expected_types)
row_set.register_processor(types_processor(types))
# after applying the types, '' should become None for int columns
data = list(row_set)
nones = [[x.value is None for x in row] for row in data]
assert_equal(nones[0], [False, True, False, False])
assert_equal(nones[1], [False, False, False, True])
assert_equal(nones[2], [False, True, True, True])
def test_strict_type_guessing_with_large_file(self):
fh = horror_fobj('211.csv')
rows = CSVTableSet(fh).tables[0]
offset, headers = headers_guess(rows.sample)
rows.register_processor(offset_processor(offset + 1))
types = [StringType, IntegerType, DecimalType, DateUtilType]
guessed_types = type_guess(rows.sample, types, True)
assert_equal(len(guessed_types), 96)
assert_equal(guessed_types, [
IntegerType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
IntegerType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), IntegerType(), StringType(), DecimalType(),
DecimalType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
IntegerType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
IntegerType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), StringType(),
StringType(), StringType(), StringType(), DateUtilType(),
DateUtilType(), DateUtilType(), DateUtilType(), StringType(),
StringType(), StringType()])
def test_apply_null_values(self):
fh = horror_fobj('null.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
types = type_guess(row_set.sample, strict=True)
expected_types = [
IntegerType(),
StringType(),
IntegerType(),
StringType()
]
assert_equal(types, expected_types)
row_set.register_processor(types_processor(types))
data = list(row_set)
# treat null as non empty text and 0 as non empty integer
assert [x.empty for x in data[0]] == [False, False, False, False]
assert [x.empty for x in data[1]] == [False, False, False, False]
assert [x.empty for x in data[2]] == [False, False, True, True]
assert [x.empty for x in data[3]] == [False, False, False, False]
assert [x.empty for x in data[4]] == [False, False, False, True]
assert [x.empty for x in data[5]] == [False, False, False, True]
# we expect None for Integers and "" for empty strings in CSV
assert [x.value for x in data[2]] == [3, "null", None, ""], data[2]
def test_file_with_few_strings_among_integers(self):
fh = horror_fobj('mixedGLB.csv')
rows = CSVTableSet(fh).tables[0]
offset, headers = headers_guess(rows.sample)
rows.register_processor(offset_processor(offset + 1))
types = [StringType, IntegerType, DecimalType, DateUtilType]
guessed_types = type_guess(rows.sample, types, True)
assert_equal(len(guessed_types), 19)
print guessed_types
assert_equal(guessed_types, [
IntegerType(),
IntegerType(),
IntegerType(),
IntegerType(),
IntegerType(),
IntegerType(),
StringType(),
StringType(),
StringType(),
StringType(),
StringType(),
StringType(),
StringType(),
StringType(),
StringType(),
StringType(),
IntegerType(),
StringType(),
StringType()
])
def test_non_strict_guessing_handles_padding(self):
csv_file = StringIO.StringIO('''
1, , 2
2, , 1.1
foo, , 1500''')
rows = CSVTableSet(csv_file).tables[0]
guessed_types = type_guess(rows.sample, strict=False)
assert_equal(len(guessed_types), 3)
assert_equal(guessed_types, [IntegerType(), StringType(), DecimalType()])
def test_guessing_uses_first_in_case_of_tie(self):
csv_file = StringIO.StringIO('''
2
1.1
1500''')
rows = CSVTableSet(csv_file).tables[0]
guessed_types = type_guess(
rows.sample, types=[DecimalType, IntegerType], strict=False)
assert_equal(guessed_types, [DecimalType()])
guessed_types = type_guess(
rows.sample, types=[IntegerType, DecimalType], strict=False)
assert_equal(guessed_types, [IntegerType()])
def test_read_type_guess_simple(self):
fh = horror_fobj('simple.csv')
table_set = CSVTableSet(fh)
row_set = table_set.tables[0]
types = type_guess(row_set.sample)
expected_types = [DateType("%Y-%m-%d"), IntegerType(), StringType()]
assert_equal(types, expected_types)
row_set.register_processor(types_processor(types))
data = list(row_set)
header_types = [c.type for c in data[0]]
assert_equal(header_types, [StringType()] * 3)
row_types = [c.type for c in data[2]]
assert_equal(expected_types, row_types)
def test_type_guess(self):
csv_file = StringIO.StringIO('''
1, 2012/2/12, 2, 02 October 2011, yes, 1
2, 2012/2/12, 2, 02 October 2011, true, 1
2.4, 2012/2/12, 1, 1 May 2011, no, 0
foo, bar, 1000, , false, 0
4.3, , 42, 24 October 2012,,
, 2012/2/12, 21, 24 December 2013, true, 1''')
rows = CSVTableSet(csv_file).tables[0]
guessed_types = type_guess(rows.sample)
assert_equal(guessed_types, [
DecimalType(), DateType('%Y/%m/%d'), IntegerType(),
DateType('%d %B %Y'), BoolType(), BoolType()])
def test_type_guess_strict(self):
import locale
locale.setlocale(locale.LC_ALL, 'en_GB.UTF-8')
csv_file = StringIO.StringIO('''
1, 2012/2/12, 2, 2,02 October 2011,"100.234354"
2, 2012/2/12, 1.1, 0,1 May 2011,"100,000,000.12"
foo, bar, 1500, 0,,"NaN"
4, 2012/2/12, 42,"-2,000",24 October 2012,"42"
,,,,,''')
rows = CSVTableSet(csv_file).tables[0]
guessed_types = type_guess(rows.sample, strict=True)
assert_equal(guessed_types, [
StringType(), StringType(),
DecimalType(), IntegerType(), DateType('%d %B %Y'),
DecimalType()])
row_set.register_processor(headers_processor(headers))
row_set.register_processor(offset_processor(offset + 1))
types = type_guess(row_set.sample)
#types = type_guess(row_set.sample, strict=True)
print('guessed types:', types)
# constructing ddl
cols = []
for indx, typ in enumerate(types):
if typ == StringType():
cols.append(" `a%s` string" % (indx))
elif typ == DateType(date_format):
cols.append(" `a%s` date" % (indx))
elif typ == DecimalType():
cols.append(" `a%s` double" % (indx))
elif typ == IntegerType():
cols.append(" `a%s` int" % (indx))
elif typ == BoolType():
cols.append(" `a%s` boolean" % (indx))
else:
raise Exception("A type of column %indx cannot be handled. %s " %
(indx, typ))
cols_str = ",\n".join(cols)
ddl = '''----------------------------------------------------------
CREATE EXTERNAL TABLE IF NOT EXISTS default.%s (
%s
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
WITH SERDEPROPERTIES (
"separatorChar" = "%s",
def helper(value):
return any(i.test(value) for i in IntegerType.instances())
def helper(value):
return any(i.test(value) for i in IntegerType.instances())