diff options
Diffstat (limited to 'Lib/test/test_tokenize.py')
| -rw-r--r-- | Lib/test/test_tokenize.py | 76 |
1 files changed, 68 insertions, 8 deletions
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py index 3b17ca6..5a81a5f 100644 --- a/Lib/test/test_tokenize.py +++ b/Lib/test/test_tokenize.py @@ -4,6 +4,8 @@ from tokenize import (tokenize, _tokenize, untokenize, NUMBER, NAME, OP, open as tokenize_open, Untokenizer) from io import BytesIO from unittest import TestCase, mock +from test.test_grammar import (VALID_UNDERSCORE_LITERALS, + INVALID_UNDERSCORE_LITERALS) import os import token @@ -24,8 +26,7 @@ class TokenizeTest(TestCase): if type == ENDMARKER: break type = tok_name[type] - result.append(" %(type)-10.10s %(token)-13.13r %(start)s %(end)s" % - locals()) + result.append(f" {type:10} {token!r:13} {start} {end}") self.assertEqual(result, [" ENCODING 'utf-8' (0, 0) (0, 0)"] + expected.rstrip().splitlines()) @@ -132,18 +133,18 @@ def k(x): self.check_tokenize("x = 0xfffffffffff", """\ NAME 'x' (1, 0) (1, 1) OP '=' (1, 2) (1, 3) - NUMBER '0xffffffffff (1, 4) (1, 17) + NUMBER '0xfffffffffff' (1, 4) (1, 17) """) self.check_tokenize("x = 123141242151251616110", """\ NAME 'x' (1, 0) (1, 1) OP '=' (1, 2) (1, 3) - NUMBER '123141242151 (1, 4) (1, 25) + NUMBER '123141242151251616110' (1, 4) (1, 25) """) self.check_tokenize("x = -15921590215012591", """\ NAME 'x' (1, 0) (1, 1) OP '=' (1, 2) (1, 3) OP '-' (1, 4) (1, 5) - NUMBER '159215902150 (1, 5) (1, 22) + NUMBER '15921590215012591' (1, 5) (1, 22) """) def test_float(self): @@ -186,6 +187,21 @@ def k(x): NUMBER '3.14e159' (1, 4) (1, 12) """) + def test_underscore_literals(self): + def number_token(s): + f = BytesIO(s.encode('utf-8')) + for toktype, token, start, end, line in tokenize(f.readline): + if toktype == NUMBER: + return token + return 'invalid token' + for lit in VALID_UNDERSCORE_LITERALS: + if '(' in lit: + # this won't work with compound complex inputs + continue + self.assertEqual(number_token(lit), lit) + for lit in INVALID_UNDERSCORE_LITERALS: + self.assertNotEqual(number_token(lit), lit) + def test_string(self): # String literals self.check_tokenize("x = ''; y = \"\"", """\ @@ -307,6 +323,50 @@ def k(x): OP '+' (1, 28) (1, 29) STRING 'RB"abc"' (1, 30) (1, 37) """) + # Check 0, 1, and 2 character string prefixes. + self.check_tokenize(r'"a\ +de\ +fg"', """\ + STRING '"a\\\\\\nde\\\\\\nfg"\' (1, 0) (3, 3) + """) + self.check_tokenize(r'u"a\ +de"', """\ + STRING 'u"a\\\\\\nde"\' (1, 0) (2, 3) + """) + self.check_tokenize(r'rb"a\ +d"', """\ + STRING 'rb"a\\\\\\nd"\' (1, 0) (2, 2) + """) + self.check_tokenize(r'"""a\ +b"""', """\ + STRING '\"\""a\\\\\\nb\"\""' (1, 0) (2, 4) + """) + self.check_tokenize(r'u"""a\ +b"""', """\ + STRING 'u\"\""a\\\\\\nb\"\""' (1, 0) (2, 4) + """) + self.check_tokenize(r'rb"""a\ +b\ +c"""', """\ + STRING 'rb"\""a\\\\\\nb\\\\\\nc"\""' (1, 0) (3, 4) + """) + self.check_tokenize('f"abc"', """\ + STRING 'f"abc"' (1, 0) (1, 6) + """) + self.check_tokenize('fR"a{b}c"', """\ + STRING 'fR"a{b}c"' (1, 0) (1, 9) + """) + self.check_tokenize('f"""abc"""', """\ + STRING 'f\"\"\"abc\"\"\"' (1, 0) (1, 10) + """) + self.check_tokenize(r'f"abc\ +def"', """\ + STRING 'f"abc\\\\\\ndef"' (1, 0) (2, 4) + """) + self.check_tokenize(r'Rf"abc\ +def"', """\ + STRING 'Rf"abc\\\\\\ndef"' (1, 0) (2, 4) + """) def test_function(self): self.check_tokenize("def d22(a, b, c=2, d=2, *k): pass", """\ @@ -505,7 +565,7 @@ def k(x): # Methods self.check_tokenize("@staticmethod\ndef foo(x,y): pass", """\ OP '@' (1, 0) (1, 1) - NAME 'staticmethod (1, 1) (1, 13) + NAME 'staticmethod' (1, 1) (1, 13) NEWLINE '\\n' (1, 13) (1, 14) NAME 'def' (2, 0) (2, 3) NAME 'foo' (2, 4) (2, 7) @@ -1488,10 +1548,10 @@ class TestRoundtrip(TestCase): # Tokenize is broken on test_pep3131.py because regular expressions are # broken on the obscure unicode identifiers in it. *sigh* - # With roundtrip extended to test the 5-tuple mode of untokenize, + # With roundtrip extended to test the 5-tuple mode of untokenize, # 7 more testfiles fail. Remove them also until the failure is diagnosed. - testfiles.remove(os.path.join(tempdir, "test_pep3131.py")) + testfiles.remove(os.path.join(tempdir, "test_unicode_identifiers.py")) for f in ('buffer', 'builtin', 'fileio', 'inspect', 'os', 'platform', 'sys'): testfiles.remove(os.path.join(tempdir, "test_%s.py") % f) |