[Python-checkins] cpython (merge 2.7 -> 2.7): merge heads
benjamin.peterson
python-checkins at python.org
Tue Oct 6 22:42:56 EDT 2015
https://hg.python.org/cpython/rev/60c44a09c5fc
changeset: 98572:60c44a09c5fc
branch: 2.7
parent: 98571:c46ccfac8763
parent: 98555:7b2af8ee6dfa
user: Benjamin Peterson <benjamin at python.org>
date: Tue Oct 06 19:37:15 2015 -0700
summary:
merge heads
files:
Lib/test/test_tokenize.py | 544 ++++++++++++++-----------
1 files changed, 294 insertions(+), 250 deletions(-)
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
--- a/Lib/test/test_tokenize.py
+++ b/Lib/test/test_tokenize.py
@@ -1,20 +1,42 @@
-doctests = """
-Tests for the tokenize module.
+from test import test_support
+from tokenize import (untokenize, generate_tokens, NUMBER, NAME, OP,
+ STRING, ENDMARKER, tok_name, Untokenizer, tokenize)
+from StringIO import StringIO
+import os
+from unittest import TestCase
- >>> import glob, random, sys
-The tests can be really simple. Given a small fragment of source
-code, print out a table with tokens. The ENDMARKER is omitted for
-brevity.
+class TokenizeTest(TestCase):
+ # Tests for the tokenize module.
- >>> dump_tokens("1 + 1")
+ # The tests can be really simple. Given a small fragment of source
+ # code, print out a table with tokens. The ENDMARKER is omitted for
+ # brevity.
+
+ def check_tokenize(self, s, expected):
+ # Format the tokens in s in a table format.
+ # The ENDMARKER is omitted.
+ result = []
+ f = StringIO(s)
+ for type, token, start, end, line in generate_tokens(f.readline):
+ if type == ENDMARKER:
+ break
+ type = tok_name[type]
+ result.append(" %(type)-10.10s %(token)-13.13r %(start)s %(end)s" %
+ locals())
+ self.assertEqual(result,
+ expected.rstrip().splitlines())
+
+
+ def test_basic(self):
+ self.check_tokenize("1 + 1", """\
NUMBER '1' (1, 0) (1, 1)
OP '+' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
-
- >>> dump_tokens("if False:\\n"
- ... " # NL\\n"
- ... " True = False # NEWLINE\\n")
+ """)
+ self.check_tokenize("if False:\n"
+ " # NL\n"
+ " True = False # NEWLINE\n", """\
NAME 'if' (1, 0) (1, 2)
NAME 'False' (1, 3) (1, 8)
OP ':' (1, 8) (1, 9)
@@ -28,122 +50,48 @@
COMMENT '# NEWLINE' (3, 17) (3, 26)
NEWLINE '\\n' (3, 26) (3, 27)
DEDENT '' (4, 0) (4, 0)
+ """)
- >>> indent_error_file = \"""
- ... def k(x):
- ... x += 2
- ... x += 5
- ... \"""
+ indent_error_file = """\
+def k(x):
+ x += 2
+ x += 5
+"""
+ with self.assertRaisesRegexp(IndentationError,
+ "unindent does not match any "
+ "outer indentation level"):
+ for tok in generate_tokens(StringIO(indent_error_file).readline):
+ pass
- >>> for tok in generate_tokens(StringIO(indent_error_file).readline): pass
- Traceback (most recent call last):
- ...
- IndentationError: unindent does not match any outer indentation level
-
-Test roundtrip for `untokenize`. `f` is an open file or a string. The source
-code in f is tokenized, converted back to source code via tokenize.untokenize(),
-and tokenized again from the latter. The test fails if the second tokenization
-doesn't match the first.
-
- >>> def roundtrip(f):
- ... if isinstance(f, str): f = StringIO(f)
- ... token_list = list(generate_tokens(f.readline))
- ... f.close()
- ... tokens1 = [tok[:2] for tok in token_list]
- ... new_text = untokenize(tokens1)
- ... readline = iter(new_text.splitlines(1)).next
- ... tokens2 = [tok[:2] for tok in generate_tokens(readline)]
- ... return tokens1 == tokens2
- ...
-
-There are some standard formatting practices that are easy to get right.
-
- >>> roundtrip("if x == 1:\\n"
- ... " print x\\n")
- True
-
- >>> roundtrip("# This is a comment\\n# This also")
- True
-
-Some people use different formatting conventions, which makes
-untokenize a little trickier. Note that this test involves trailing
-whitespace after the colon. Note that we use hex escapes to make the
-two trailing blanks apperant in the expected output.
-
- >>> roundtrip("if x == 1 : \\n"
- ... " print x\\n")
- True
-
- >>> f = test_support.findfile("tokenize_tests" + os.extsep + "txt")
- >>> roundtrip(open(f))
- True
-
- >>> roundtrip("if x == 1:\\n"
- ... " # A comment by itself.\\n"
- ... " print x # Comment here, too.\\n"
- ... " # Another comment.\\n"
- ... "after_if = True\\n")
- True
-
- >>> roundtrip("if (x # The comments need to go in the right place\\n"
- ... " == 1):\\n"
- ... " print 'x==1'\\n")
- True
-
- >>> roundtrip("class Test: # A comment here\\n"
- ... " # A comment with weird indent\\n"
- ... " after_com = 5\\n"
- ... " def x(m): return m*5 # a one liner\\n"
- ... " def y(m): # A whitespace after the colon\\n"
- ... " return y*4 # 3-space indent\\n")
- True
-
-Some error-handling code
-
- >>> roundtrip("try: import somemodule\\n"
- ... "except ImportError: # comment\\n"
- ... " print 'Can not import' # comment2\\n"
- ... "else: print 'Loaded'\\n")
- True
-
-Balancing continuation
-
- >>> roundtrip("a = (3,4, \\n"
- ... "5,6)\\n"
- ... "y = [3, 4,\\n"
- ... "5]\\n"
- ... "z = {'a': 5,\\n"
- ... "'b':15, 'c':True}\\n"
- ... "x = len(y) + 5 - a[\\n"
- ... "3] - a[2]\\n"
- ... "+ len(z) - z[\\n"
- ... "'b']\\n")
- True
-
-Ordinary integers and binary operators
-
- >>> dump_tokens("0xff <= 255")
+ def test_int(self):
+ # Ordinary integers and binary operators
+ self.check_tokenize("0xff <= 255", """\
NUMBER '0xff' (1, 0) (1, 4)
OP '<=' (1, 5) (1, 7)
NUMBER '255' (1, 8) (1, 11)
- >>> dump_tokens("0b10 <= 255")
+ """)
+ self.check_tokenize("0b10 <= 255", """\
NUMBER '0b10' (1, 0) (1, 4)
OP '<=' (1, 5) (1, 7)
NUMBER '255' (1, 8) (1, 11)
- >>> dump_tokens("0o123 <= 0123")
+ """)
+ self.check_tokenize("0o123 <= 0123", """\
NUMBER '0o123' (1, 0) (1, 5)
OP '<=' (1, 6) (1, 8)
NUMBER '0123' (1, 9) (1, 13)
- >>> dump_tokens("01234567 > ~0x15")
+ """)
+ self.check_tokenize("01234567 > ~0x15", """\
NUMBER '01234567' (1, 0) (1, 8)
OP '>' (1, 9) (1, 10)
OP '~' (1, 11) (1, 12)
NUMBER '0x15' (1, 12) (1, 16)
- >>> dump_tokens("2134568 != 01231515")
+ """)
+ self.check_tokenize("2134568 != 01231515", """\
NUMBER '2134568' (1, 0) (1, 7)
OP '!=' (1, 8) (1, 10)
NUMBER '01231515' (1, 11) (1, 19)
- >>> dump_tokens("(-124561-1) & 0200000000")
+ """)
+ self.check_tokenize("(-124561-1) & 0200000000", """\
OP '(' (1, 0) (1, 1)
OP '-' (1, 1) (1, 2)
NUMBER '124561' (1, 2) (1, 8)
@@ -152,78 +100,93 @@
OP ')' (1, 10) (1, 11)
OP '&' (1, 12) (1, 13)
NUMBER '0200000000' (1, 14) (1, 24)
- >>> dump_tokens("0xdeadbeef != -1")
+ """)
+ self.check_tokenize("0xdeadbeef != -1", """\
NUMBER '0xdeadbeef' (1, 0) (1, 10)
OP '!=' (1, 11) (1, 13)
OP '-' (1, 14) (1, 15)
NUMBER '1' (1, 15) (1, 16)
- >>> dump_tokens("0xdeadc0de & 012345")
+ """)
+ self.check_tokenize("0xdeadc0de & 012345", """\
NUMBER '0xdeadc0de' (1, 0) (1, 10)
OP '&' (1, 11) (1, 12)
NUMBER '012345' (1, 13) (1, 19)
- >>> dump_tokens("0xFF & 0x15 | 1234")
+ """)
+ self.check_tokenize("0xFF & 0x15 | 1234", """\
NUMBER '0xFF' (1, 0) (1, 4)
OP '&' (1, 5) (1, 6)
NUMBER '0x15' (1, 7) (1, 11)
OP '|' (1, 12) (1, 13)
NUMBER '1234' (1, 14) (1, 18)
+ """)
-Long integers
-
- >>> dump_tokens("x = 0L")
+ def test_long(self):
+ # Long integers
+ self.check_tokenize("x = 0L", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '0L' (1, 4) (1, 6)
- >>> dump_tokens("x = 0xfffffffffff")
+ """)
+ self.check_tokenize("x = 0xfffffffffff", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '0xffffffffff (1, 4) (1, 17)
- >>> dump_tokens("x = 123141242151251616110l")
+ """)
+ self.check_tokenize("x = 123141242151251616110l", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '123141242151 (1, 4) (1, 26)
- >>> dump_tokens("x = -15921590215012591L")
+ """)
+ self.check_tokenize("x = -15921590215012591L", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
OP '-' (1, 4) (1, 5)
NUMBER '159215902150 (1, 5) (1, 23)
+ """)
-Floating point numbers
-
- >>> dump_tokens("x = 3.14159")
+ def test_float(self):
+ # Floating point numbers
+ self.check_tokenize("x = 3.14159", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3.14159' (1, 4) (1, 11)
- >>> dump_tokens("x = 314159.")
+ """)
+ self.check_tokenize("x = 314159.", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '314159.' (1, 4) (1, 11)
- >>> dump_tokens("x = .314159")
+ """)
+ self.check_tokenize("x = .314159", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '.314159' (1, 4) (1, 11)
- >>> dump_tokens("x = 3e14159")
+ """)
+ self.check_tokenize("x = 3e14159", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3e14159' (1, 4) (1, 11)
- >>> dump_tokens("x = 3E123")
+ """)
+ self.check_tokenize("x = 3E123", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3E123' (1, 4) (1, 9)
- >>> dump_tokens("x+y = 3e-1230")
+ """)
+ self.check_tokenize("x+y = 3e-1230", """\
NAME 'x' (1, 0) (1, 1)
OP '+' (1, 1) (1, 2)
NAME 'y' (1, 2) (1, 3)
OP '=' (1, 4) (1, 5)
NUMBER '3e-1230' (1, 6) (1, 13)
- >>> dump_tokens("x = 3.14e159")
+ """)
+ self.check_tokenize("x = 3.14e159", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3.14e159' (1, 4) (1, 12)
+ """)
-String literals
-
- >>> dump_tokens("x = ''; y = \\\"\\\"")
+ def test_string(self):
+ # String literals
+ self.check_tokenize("x = ''; y = \"\"", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING "''" (1, 4) (1, 6)
@@ -231,7 +194,8 @@
NAME 'y' (1, 8) (1, 9)
OP '=' (1, 10) (1, 11)
STRING '""' (1, 12) (1, 14)
- >>> dump_tokens("x = '\\\"'; y = \\\"'\\\"")
+ """)
+ self.check_tokenize("x = '\"'; y = \"'\"", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING '\\'"\\'' (1, 4) (1, 7)
@@ -239,25 +203,29 @@
NAME 'y' (1, 9) (1, 10)
OP '=' (1, 11) (1, 12)
STRING '"\\'"' (1, 13) (1, 16)
- >>> dump_tokens("x = \\\"doesn't \\\"shrink\\\", does it\\\"")
+ """)
+ self.check_tokenize("x = \"doesn't \"shrink\", does it\"", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING '"doesn\\'t "' (1, 4) (1, 14)
NAME 'shrink' (1, 14) (1, 20)
STRING '", does it"' (1, 20) (1, 31)
- >>> dump_tokens("x = u'abc' + U'ABC'")
+ """)
+ self.check_tokenize("x = u'abc' + U'ABC'", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING "u'abc'" (1, 4) (1, 10)
OP '+' (1, 11) (1, 12)
STRING "U'ABC'" (1, 13) (1, 19)
- >>> dump_tokens('y = u"ABC" + U"ABC"')
+ """)
+ self.check_tokenize('y = u"ABC" + U"ABC"', """\
NAME 'y' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING 'u"ABC"' (1, 4) (1, 10)
OP '+' (1, 11) (1, 12)
STRING 'U"ABC"' (1, 13) (1, 19)
- >>> dump_tokens("x = ur'abc' + Ur'ABC' + uR'ABC' + UR'ABC'")
+ """)
+ self.check_tokenize("x = ur'abc' + Ur'ABC' + uR'ABC' + UR'ABC'", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING "ur'abc'" (1, 4) (1, 11)
@@ -267,7 +235,8 @@
STRING "uR'ABC'" (1, 24) (1, 31)
OP '+' (1, 32) (1, 33)
STRING "UR'ABC'" (1, 34) (1, 41)
- >>> dump_tokens('y = ur"abc" + Ur"ABC" + uR"ABC" + UR"ABC"')
+ """)
+ self.check_tokenize('y = ur"abc" + Ur"ABC" + uR"ABC" + UR"ABC"', """\
NAME 'y' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING 'ur"abc"' (1, 4) (1, 11)
@@ -278,15 +247,18 @@
OP '+' (1, 32) (1, 33)
STRING 'UR"ABC"' (1, 34) (1, 41)
- >>> dump_tokens("b'abc' + B'abc'")
+ """)
+ self.check_tokenize("b'abc' + B'abc'", """\
STRING "b'abc'" (1, 0) (1, 6)
OP '+' (1, 7) (1, 8)
STRING "B'abc'" (1, 9) (1, 15)
- >>> dump_tokens('b"abc" + B"abc"')
+ """)
+ self.check_tokenize('b"abc" + B"abc"', """\
STRING 'b"abc"' (1, 0) (1, 6)
OP '+' (1, 7) (1, 8)
STRING 'B"abc"' (1, 9) (1, 15)
- >>> dump_tokens("br'abc' + bR'abc' + Br'abc' + BR'abc'")
+ """)
+ self.check_tokenize("br'abc' + bR'abc' + Br'abc' + BR'abc'", """\
STRING "br'abc'" (1, 0) (1, 7)
OP '+' (1, 8) (1, 9)
STRING "bR'abc'" (1, 10) (1, 17)
@@ -294,7 +266,8 @@
STRING "Br'abc'" (1, 20) (1, 27)
OP '+' (1, 28) (1, 29)
STRING "BR'abc'" (1, 30) (1, 37)
- >>> dump_tokens('br"abc" + bR"abc" + Br"abc" + BR"abc"')
+ """)
+ self.check_tokenize('br"abc" + bR"abc" + Br"abc" + BR"abc"', """\
STRING 'br"abc"' (1, 0) (1, 7)
OP '+' (1, 8) (1, 9)
STRING 'bR"abc"' (1, 10) (1, 17)
@@ -302,10 +275,10 @@
STRING 'Br"abc"' (1, 20) (1, 27)
OP '+' (1, 28) (1, 29)
STRING 'BR"abc"' (1, 30) (1, 37)
+ """)
-Operators
-
- >>> dump_tokens("def d22(a, b, c=2, d=2, *k): pass")
+ def test_function(self):
+ self.check_tokenize("def d22(a, b, c=2, d=2, *k): pass", """\
NAME 'def' (1, 0) (1, 3)
NAME 'd22' (1, 4) (1, 7)
OP '(' (1, 7) (1, 8)
@@ -326,7 +299,8 @@
OP ')' (1, 26) (1, 27)
OP ':' (1, 27) (1, 28)
NAME 'pass' (1, 29) (1, 33)
- >>> dump_tokens("def d01v_(a=1, *k, **w): pass")
+ """)
+ self.check_tokenize("def d01v_(a=1, *k, **w): pass", """\
NAME 'def' (1, 0) (1, 3)
NAME 'd01v_' (1, 4) (1, 9)
OP '(' (1, 9) (1, 10)
@@ -342,11 +316,12 @@
OP ')' (1, 22) (1, 23)
OP ':' (1, 23) (1, 24)
NAME 'pass' (1, 25) (1, 29)
+ """)
-Comparison
-
- >>> dump_tokens("if 1 < 1 > 1 == 1 >= 5 <= 0x15 <= 0x12 != " +
- ... "1 and 5 in 1 not in 1 is 1 or 5 is not 1: pass")
+ def test_comparison(self):
+ # Comparison
+ self.check_tokenize("if 1 < 1 > 1 == 1 >= 5 <= 0x15 <= 0x12 != " +
+ "1 and 5 in 1 not in 1 is 1 or 5 is not 1: pass", """\
NAME 'if' (1, 0) (1, 2)
NUMBER '1' (1, 3) (1, 4)
OP '<' (1, 5) (1, 6)
@@ -379,10 +354,11 @@
NUMBER '1' (1, 81) (1, 82)
OP ':' (1, 82) (1, 83)
NAME 'pass' (1, 84) (1, 88)
+ """)
-Shift
-
- >>> dump_tokens("x = 1 << 1 >> 5")
+ def test_shift(self):
+ # Shift
+ self.check_tokenize("x = 1 << 1 >> 5", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -390,10 +366,11 @@
NUMBER '1' (1, 9) (1, 10)
OP '>>' (1, 11) (1, 13)
NUMBER '5' (1, 14) (1, 15)
+ """)
-Additive
-
- >>> dump_tokens("x = 1 - y + 15 - 01 + 0x124 + z + a[5]")
+ def test_additive(self):
+ # Additive
+ self.check_tokenize("x = 1 - y + 15 - 01 + 0x124 + z + a[5]", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -412,10 +389,11 @@
OP '[' (1, 35) (1, 36)
NUMBER '5' (1, 36) (1, 37)
OP ']' (1, 37) (1, 38)
+ """)
-Multiplicative
-
- >>> dump_tokens("x = 1//1*1/5*12%0x12")
+ def test_multiplicative(self):
+ # Multiplicative
+ self.check_tokenize("x = 1//1*1/5*12%0x12", """\
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -429,10 +407,11 @@
NUMBER '12' (1, 13) (1, 15)
OP '%' (1, 15) (1, 16)
NUMBER '0x12' (1, 16) (1, 20)
+ """)
-Unary
-
- >>> dump_tokens("~1 ^ 1 & 1 |1 ^ -1")
+ def test_unary(self):
+ # Unary
+ self.check_tokenize("~1 ^ 1 & 1 |1 ^ -1", """\
OP '~' (1, 0) (1, 1)
NUMBER '1' (1, 1) (1, 2)
OP '^' (1, 3) (1, 4)
@@ -444,7 +423,8 @@
OP '^' (1, 14) (1, 15)
OP '-' (1, 16) (1, 17)
NUMBER '1' (1, 17) (1, 18)
- >>> dump_tokens("-1*1/1+1*1//1 - ---1**1")
+ """)
+ self.check_tokenize("-1*1/1+1*1//1 - ---1**1", """\
OP '-' (1, 0) (1, 1)
NUMBER '1' (1, 1) (1, 2)
OP '*' (1, 2) (1, 3)
@@ -464,10 +444,12 @@
NUMBER '1' (1, 19) (1, 20)
OP '**' (1, 20) (1, 22)
NUMBER '1' (1, 22) (1, 23)
+ """)
-Selector
-
- >>> dump_tokens("import sys, time\\nx = sys.modules['time'].time()")
+ def test_selector(self):
+ # Selector
+ self.check_tokenize("import sys, time\n"
+ "x = sys.modules['time'].time()", """\
NAME 'import' (1, 0) (1, 6)
NAME 'sys' (1, 7) (1, 10)
OP ',' (1, 10) (1, 11)
@@ -485,10 +467,12 @@
NAME 'time' (2, 24) (2, 28)
OP '(' (2, 28) (2, 29)
OP ')' (2, 29) (2, 30)
+ """)
-Methods
-
- >>> dump_tokens("@staticmethod\\ndef foo(x,y): pass")
+ def test_method(self):
+ # Methods
+ self.check_tokenize("@staticmethod\n"
+ "def foo(x,y): pass", """\
OP '@' (1, 0) (1, 1)
NAME 'staticmethod (1, 1) (1, 13)
NEWLINE '\\n' (1, 13) (1, 14)
@@ -501,41 +485,13 @@
OP ')' (2, 11) (2, 12)
OP ':' (2, 12) (2, 13)
NAME 'pass' (2, 14) (2, 18)
+ """)
-Backslash means line continuation, except for comments
-
- >>> roundtrip("x=1+\\\\n"
- ... "1\\n"
- ... "# This is a comment\\\\n"
- ... "# This also\\n")
- True
- >>> roundtrip("# Comment \\\\nx = 0")
- True
-
-Two string literals on the same line
-
- >>> roundtrip("'' ''")
- True
-
-Test roundtrip on random python modules.
-pass the '-ucpu' option to process the full directory.
-
- >>>
- >>> tempdir = os.path.dirname(f) or os.curdir
- >>> testfiles = glob.glob(os.path.join(tempdir, "test*.py"))
-
- >>> if not test_support.is_resource_enabled("cpu"):
- ... testfiles = random.sample(testfiles, 10)
- ...
- >>> for testfile in testfiles:
- ... if not roundtrip(open(testfile)):
- ... print "Roundtrip failed for file %s" % testfile
- ... break
- ... else: True
- True
-
-Evil tabs
- >>> dump_tokens("def f():\\n\\tif x\\n \\tpass")
+ def test_tabs(self):
+ # Evil tabs
+ self.check_tokenize("def f():\n"
+ "\tif x\n"
+ " \tpass", """\
NAME 'def' (1, 0) (1, 3)
NAME 'f' (1, 4) (1, 5)
OP '(' (1, 5) (1, 6)
@@ -550,56 +506,16 @@
NAME 'pass' (3, 9) (3, 13)
DEDENT '' (4, 0) (4, 0)
DEDENT '' (4, 0) (4, 0)
+ """)
-Pathological whitespace (http://bugs.python.org/issue16152)
- >>> dump_tokens("@ ")
+ def test_pathological_trailing_whitespace(self):
+ # Pathological whitespace (http://bugs.python.org/issue16152)
+ self.check_tokenize("@ ", """\
OP '@' (1, 0) (1, 1)
-"""
+ """)
-from test import test_support
-from tokenize import (untokenize, generate_tokens, NUMBER, NAME, OP,
- STRING, ENDMARKER, tok_name, Untokenizer, tokenize)
-from StringIO import StringIO
-import os
-from unittest import TestCase
-
-def dump_tokens(s):
- """Print out the tokens in s in a table format.
-
- The ENDMARKER is omitted.
- """
- f = StringIO(s)
- for type, token, start, end, line in generate_tokens(f.readline):
- if type == ENDMARKER:
- break
- type = tok_name[type]
- print("%(type)-10.10s %(token)-13.13r %(start)s %(end)s" % locals())
-
-# This is an example from the docs, set up as a doctest.
def decistmt(s):
- """Substitute Decimals for floats in a string of statements.
-
- >>> from decimal import Decimal
- >>> s = 'print +21.3e-5*-.1234/81.7'
- >>> decistmt(s)
- "print +Decimal ('21.3e-5')*-Decimal ('.1234')/Decimal ('81.7')"
-
- The format of the exponent is inherited from the platform C library.
- Known cases are "e-007" (Windows) and "e-07" (not Windows). Since
- we're only showing 12 digits, and the 13th isn't close to 5, the
- rest of the output should be platform-independent.
-
- >>> exec(s) #doctest: +ELLIPSIS
- -3.21716034272e-0...7
-
- Output from calculations with Decimal should be identical across all
- platforms.
-
- >>> exec(decistmt(s))
- -3.217160342717258261933904529E-7
- """
-
result = []
g = generate_tokens(StringIO(s).readline) # tokenize the string
for toknum, tokval, _, _, _ in g:
@@ -614,6 +530,27 @@
result.append((toknum, tokval))
return untokenize(result)
+class TestMisc(TestCase):
+
+ def test_decistmt(self):
+ # Substitute Decimals for floats in a string of statements.
+ # This is an example from the docs.
+
+ from decimal import Decimal
+ s = '+21.3e-5*-.1234/81.7'
+ self.assertEqual(decistmt(s),
+ "+Decimal ('21.3e-5')*-Decimal ('.1234')/Decimal ('81.7')")
+
+ # The format of the exponent is inherited from the platform C library.
+ # Known cases are "e-007" (Windows) and "e-07" (not Windows). Since
+ # we're only showing 12 digits, and the 13th isn't close to 5, the
+ # rest of the output should be platform-independent.
+ self.assertRegexpMatches(str(eval(s)), '-3.21716034272e-0+7')
+
+ # Output from calculations with Decimal should be identical across all
+ # platforms.
+ self.assertEqual(eval(decistmt(s)), Decimal('-3.217160342717258261933904529E-7'))
+
class UntokenizeTest(TestCase):
@@ -651,6 +588,115 @@
class TestRoundtrip(TestCase):
+
+ def check_roundtrip(self, f):
+ """
+ Test roundtrip for `untokenize`. `f` is an open file or a string.
+ The source code in f is tokenized, converted back to source code
+ via tokenize.untokenize(), and tokenized again from the latter.
+ The test fails if the second tokenization doesn't match the first.
+ """
+ if isinstance(f, str): f = StringIO(f)
+ token_list = list(generate_tokens(f.readline))
+ f.close()
+ tokens1 = [tok[:2] for tok in token_list]
+ new_text = untokenize(tokens1)
+ readline = iter(new_text.splitlines(1)).next
+ tokens2 = [tok[:2] for tok in generate_tokens(readline)]
+ self.assertEqual(tokens2, tokens1)
+
+ def test_roundtrip(self):
+ # There are some standard formatting practices that are easy to get right.
+
+ self.check_roundtrip("if x == 1:\n"
+ " print(x)\n")
+
+ # There are some standard formatting practices that are easy to get right.
+
+ self.check_roundtrip("if x == 1:\n"
+ " print x\n")
+ self.check_roundtrip("# This is a comment\n"
+ "# This also")
+
+ # Some people use different formatting conventions, which makes
+ # untokenize a little trickier. Note that this test involves trailing
+ # whitespace after the colon. Note that we use hex escapes to make the
+ # two trailing blanks apperant in the expected output.
+
+ self.check_roundtrip("if x == 1 : \n"
+ " print x\n")
+ fn = test_support.findfile("tokenize_tests" + os.extsep + "txt")
+ with open(fn) as f:
+ self.check_roundtrip(f)
+ self.check_roundtrip("if x == 1:\n"
+ " # A comment by itself.\n"
+ " print x # Comment here, too.\n"
+ " # Another comment.\n"
+ "after_if = True\n")
+ self.check_roundtrip("if (x # The comments need to go in the right place\n"
+ " == 1):\n"
+ " print 'x==1'\n")
+ self.check_roundtrip("class Test: # A comment here\n"
+ " # A comment with weird indent\n"
+ " after_com = 5\n"
+ " def x(m): return m*5 # a one liner\n"
+ " def y(m): # A whitespace after the colon\n"
+ " return y*4 # 3-space indent\n")
+
+ # Some error-handling code
+
+ self.check_roundtrip("try: import somemodule\n"
+ "except ImportError: # comment\n"
+ " print 'Can not import' # comment2\n"
+ "else: print 'Loaded'\n")
+
+ def test_continuation(self):
+ # Balancing continuation
+ self.check_roundtrip("a = (3,4, \n"
+ "5,6)\n"
+ "y = [3, 4,\n"
+ "5]\n"
+ "z = {'a': 5,\n"
+ "'b':15, 'c':True}\n"
+ "x = len(y) + 5 - a[\n"
+ "3] - a[2]\n"
+ "+ len(z) - z[\n"
+ "'b']\n")
+
+ def test_backslash_continuation(self):
+ # Backslash means line continuation, except for comments
+ self.check_roundtrip("x=1+\\\n"
+ "1\n"
+ "# This is a comment\\\n"
+ "# This also\n")
+ self.check_roundtrip("# Comment \\\n"
+ "x = 0")
+
+ def test_string_concatenation(self):
+ # Two string literals on the same line
+ self.check_roundtrip("'' ''")
+
+ def test_random_files(self):
+ # Test roundtrip on random python modules.
+ # pass the '-ucpu' option to process the full directory.
+
+ import glob, random
+ fn = test_support.findfile("tokenize_tests" + os.extsep + "txt")
+ tempdir = os.path.dirname(fn) or os.curdir
+ testfiles = glob.glob(os.path.join(tempdir, "test*.py"))
+
+ if not test_support.is_resource_enabled("cpu"):
+ testfiles = random.sample(testfiles, 10)
+
+ for testfile in testfiles:
+ try:
+ with open(testfile, 'rb') as f:
+ self.check_roundtrip(f)
+ except:
+ print "Roundtrip failed for file %s" % testfile
+ raise
+
+
def roundtrip(self, code):
if isinstance(code, str):
code = code.encode('utf-8')
@@ -667,13 +713,11 @@
self.assertEqual(codelines[1], codelines[2])
-__test__ = {"doctests" : doctests, 'decistmt': decistmt}
-
def test_main():
- from test import test_tokenize
- test_support.run_doctest(test_tokenize, True)
+ test_support.run_unittest(TokenizeTest)
test_support.run_unittest(UntokenizeTest)
test_support.run_unittest(TestRoundtrip)
+ test_support.run_unittest(TestMisc)
if __name__ == "__main__":
test_main()
--
Repository URL: https://hg.python.org/cpython
More information about the Python-checkins
mailing list