diff options
Diffstat (limited to 'Lib/test/test_csv.py')
| -rw-r--r-- | Lib/test/test_csv.py | 265 |
1 files changed, 185 insertions, 80 deletions
diff --git a/Lib/test/test_csv.py b/Lib/test/test_csv.py index 55796a2..83f8cb3 100644 --- a/Lib/test/test_csv.py +++ b/Lib/test/test_csv.py @@ -197,6 +197,17 @@ class Test_Csv(unittest.TestCase): fileobj.seek(0) self.assertEqual(fileobj.read(), "a,b\r\nc,d\r\n") + @support.cpython_only + def test_writerows_legacy_strings(self): + import _testcapi + + c = _testcapi.unicode_legacy_string('a') + with TemporaryFile("w+", newline='') as fileobj: + writer = csv.writer(fileobj) + writer.writerows([[c]]) + fileobj.seek(0) + self.assertEqual(fileobj.read(), "a\r\n") + def _read_test(self, input, expect, **kwargs): reader = csv.reader(input, **kwargs) result = list(reader) @@ -559,6 +570,18 @@ class TestDictFields(unittest.TestCase): fileobj = StringIO() self.assertRaises(TypeError, csv.DictWriter, fileobj) + def test_write_fields_not_in_fieldnames(self): + with TemporaryFile("w+", newline='') as fileobj: + writer = csv.DictWriter(fileobj, fieldnames = ["f1", "f2", "f3"]) + # Of special note is the non-string key (issue 19449) + with self.assertRaises(ValueError) as cx: + writer.writerow({"f4": 10, "f2": "spam", 1: "abc"}) + exception = str(cx.exception) + self.assertIn("fieldnames", exception) + self.assertIn("'f4'", exception) + self.assertNotIn("'f2'", exception) + self.assertIn("1", exception) + def test_read_dict_fields(self): with TemporaryFile("w+") as fileobj: fileobj.write("1,2,abc\r\n") @@ -724,6 +747,7 @@ class TestDialectValidity(unittest.TestCase): lineterminator = '\r\n' quoting = csv.QUOTE_NONE d = mydialect() + self.assertEqual(d.quoting, csv.QUOTE_NONE) mydialect.quoting = None self.assertRaises(csv.Error, mydialect) @@ -732,12 +756,21 @@ class TestDialectValidity(unittest.TestCase): mydialect.quoting = csv.QUOTE_ALL mydialect.quotechar = '"' d = mydialect() + self.assertEqual(d.quoting, csv.QUOTE_ALL) + self.assertEqual(d.quotechar, '"') + self.assertTrue(d.doublequote) mydialect.quotechar = "''" - self.assertRaises(csv.Error, mydialect) + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"quotechar" must be an 1-character string') mydialect.quotechar = 4 - self.assertRaises(csv.Error, mydialect) + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"quotechar" must be string, not int') def test_delimiter(self): class mydialect(csv.Dialect): @@ -748,12 +781,31 @@ class TestDialectValidity(unittest.TestCase): lineterminator = '\r\n' quoting = csv.QUOTE_NONE d = mydialect() + self.assertEqual(d.delimiter, ";") mydialect.delimiter = ":::" - self.assertRaises(csv.Error, mydialect) + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"delimiter" must be an 1-character string') + + mydialect.delimiter = "" + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"delimiter" must be an 1-character string') + + mydialect.delimiter = b"," + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"delimiter" must be string, not bytes') mydialect.delimiter = 4 - self.assertRaises(csv.Error, mydialect) + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"delimiter" must be string, not int') def test_lineterminator(self): class mydialect(csv.Dialect): @@ -764,12 +816,30 @@ class TestDialectValidity(unittest.TestCase): lineterminator = '\r\n' quoting = csv.QUOTE_NONE d = mydialect() + self.assertEqual(d.lineterminator, '\r\n') mydialect.lineterminator = ":::" d = mydialect() + self.assertEqual(d.lineterminator, ":::") mydialect.lineterminator = 4 - self.assertRaises(csv.Error, mydialect) + with self.assertRaises(csv.Error) as cm: + mydialect() + self.assertEqual(str(cm.exception), + '"lineterminator" must be a string') + + def test_invalid_chars(self): + def create_invalid(field_name, value): + class mydialect(csv.Dialect): + pass + setattr(mydialect, field_name, value) + d = mydialect() + + for field_name in ("delimiter", "escapechar", "quotechar"): + self.assertRaises(csv.Error, create_invalid, field_name, "") + self.assertRaises(csv.Error, create_invalid, field_name, "abc") + self.assertRaises(csv.Error, create_invalid, field_name, b'x') + self.assertRaises(csv.Error, create_invalid, field_name, 5) class TestSniffer(unittest.TestCase): @@ -785,7 +855,7 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back 'Tommy''s Place':'Blue Island':'IL':'12/28/02':'Blue Sunday/White Crow' 'Stonecutters ''Seafood'' and Chop House':'Lemont':'IL':'12/19/02':'Week Back' """ - header = '''\ + header1 = '''\ "venue","city","state","date","performers" ''' sample3 = '''\ @@ -804,10 +874,35 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back sample6 = "a|b|c\r\nd|e|f\r\n" sample7 = "'a'|'b'|'c'\r\n'd'|e|f\r\n" +# Issue 18155: Use a delimiter that is a special char to regex: + + header2 = '''\ +"venue"+"city"+"state"+"date"+"performers" +''' + sample8 = """\ +Harry's+ Arlington Heights+ IL+ 2/1/03+ Kimi Hayes +Shark City+ Glendale Heights+ IL+ 12/28/02+ Prezence +Tommy's Place+ Blue Island+ IL+ 12/28/02+ Blue Sunday/White Crow +Stonecutters Seafood and Chop House+ Lemont+ IL+ 12/19/02+ Week Back +""" + sample9 = """\ +'Harry''s'+ Arlington Heights'+ 'IL'+ '2/1/03'+ 'Kimi Hayes' +'Shark City'+ Glendale Heights'+' IL'+ '12/28/02'+ 'Prezence' +'Tommy''s Place'+ Blue Island'+ 'IL'+ '12/28/02'+ 'Blue Sunday/White Crow' +'Stonecutters ''Seafood'' and Chop House'+ 'Lemont'+ 'IL'+ '12/19/02'+ 'Week Back' +""" + def test_has_header(self): sniffer = csv.Sniffer() self.assertEqual(sniffer.has_header(self.sample1), False) - self.assertEqual(sniffer.has_header(self.header+self.sample1), True) + self.assertEqual(sniffer.has_header(self.header1 + self.sample1), + True) + + def test_has_header_regex_special_delimiter(self): + sniffer = csv.Sniffer() + self.assertEqual(sniffer.has_header(self.sample8), False) + self.assertEqual(sniffer.has_header(self.header2 + self.sample8), + True) def test_sniff(self): sniffer = csv.Sniffer() @@ -841,86 +936,96 @@ Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back dialect = sniffer.sniff(self.sample7) self.assertEqual(dialect.delimiter, "|") self.assertEqual(dialect.quotechar, "'") + dialect = sniffer.sniff(self.sample8) + self.assertEqual(dialect.delimiter, '+') + dialect = sniffer.sniff(self.sample9) + self.assertEqual(dialect.delimiter, '+') + self.assertEqual(dialect.quotechar, "'") def test_doublequote(self): sniffer = csv.Sniffer() - dialect = sniffer.sniff(self.header) + dialect = sniffer.sniff(self.header1) + self.assertFalse(dialect.doublequote) + dialect = sniffer.sniff(self.header2) self.assertFalse(dialect.doublequote) dialect = sniffer.sniff(self.sample2) self.assertTrue(dialect.doublequote) + dialect = sniffer.sniff(self.sample8) + self.assertFalse(dialect.doublequote) + dialect = sniffer.sniff(self.sample9) + self.assertTrue(dialect.doublequote) -if not hasattr(sys, "gettotalrefcount"): - if support.verbose: print("*** skipping leakage tests ***") -else: - class NUL: - def write(s, *args): - pass - writelines = write - - class TestLeaks(unittest.TestCase): - def test_create_read(self): - delta = 0 - lastrc = sys.gettotalrefcount() - for i in range(20): - gc.collect() - self.assertEqual(gc.garbage, []) - rc = sys.gettotalrefcount() - csv.reader(["a,b,c\r\n"]) - csv.reader(["a,b,c\r\n"]) - csv.reader(["a,b,c\r\n"]) - delta = rc-lastrc - lastrc = rc - # if csv.reader() leaks, last delta should be 3 or more - self.assertEqual(delta < 3, True) - - def test_create_write(self): - delta = 0 - lastrc = sys.gettotalrefcount() - s = NUL() - for i in range(20): - gc.collect() - self.assertEqual(gc.garbage, []) - rc = sys.gettotalrefcount() - csv.writer(s) - csv.writer(s) - csv.writer(s) - delta = rc-lastrc - lastrc = rc - # if csv.writer() leaks, last delta should be 3 or more - self.assertEqual(delta < 3, True) - - def test_read(self): - delta = 0 - rows = ["a,b,c\r\n"]*5 - lastrc = sys.gettotalrefcount() - for i in range(20): - gc.collect() - self.assertEqual(gc.garbage, []) - rc = sys.gettotalrefcount() - rdr = csv.reader(rows) - for row in rdr: - pass - delta = rc-lastrc - lastrc = rc - # if reader leaks during read, delta should be 5 or more - self.assertEqual(delta < 5, True) - - def test_write(self): - delta = 0 - rows = [[1,2,3]]*5 - s = NUL() - lastrc = sys.gettotalrefcount() - for i in range(20): - gc.collect() - self.assertEqual(gc.garbage, []) - rc = sys.gettotalrefcount() - writer = csv.writer(s) - for row in rows: - writer.writerow(row) - delta = rc-lastrc - lastrc = rc - # if writer leaks during write, last delta should be 5 or more - self.assertEqual(delta < 5, True) +class NUL: + def write(s, *args): + pass + writelines = write + +@unittest.skipUnless(hasattr(sys, "gettotalrefcount"), + 'requires sys.gettotalrefcount()') +class TestLeaks(unittest.TestCase): + def test_create_read(self): + delta = 0 + lastrc = sys.gettotalrefcount() + for i in range(20): + gc.collect() + self.assertEqual(gc.garbage, []) + rc = sys.gettotalrefcount() + csv.reader(["a,b,c\r\n"]) + csv.reader(["a,b,c\r\n"]) + csv.reader(["a,b,c\r\n"]) + delta = rc-lastrc + lastrc = rc + # if csv.reader() leaks, last delta should be 3 or more + self.assertEqual(delta < 3, True) + + def test_create_write(self): + delta = 0 + lastrc = sys.gettotalrefcount() + s = NUL() + for i in range(20): + gc.collect() + self.assertEqual(gc.garbage, []) + rc = sys.gettotalrefcount() + csv.writer(s) + csv.writer(s) + csv.writer(s) + delta = rc-lastrc + lastrc = rc + # if csv.writer() leaks, last delta should be 3 or more + self.assertEqual(delta < 3, True) + + def test_read(self): + delta = 0 + rows = ["a,b,c\r\n"]*5 + lastrc = sys.gettotalrefcount() + for i in range(20): + gc.collect() + self.assertEqual(gc.garbage, []) + rc = sys.gettotalrefcount() + rdr = csv.reader(rows) + for row in rdr: + pass + delta = rc-lastrc + lastrc = rc + # if reader leaks during read, delta should be 5 or more + self.assertEqual(delta < 5, True) + + def test_write(self): + delta = 0 + rows = [[1,2,3]]*5 + s = NUL() + lastrc = sys.gettotalrefcount() + for i in range(20): + gc.collect() + self.assertEqual(gc.garbage, []) + rc = sys.gettotalrefcount() + writer = csv.writer(s) + for row in rows: + writer.writerow(row) + delta = rc-lastrc + lastrc = rc + # if writer leaks during write, last delta should be 5 or more + self.assertEqual(delta < 5, True) class TestUnicode(unittest.TestCase): |