summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_tokenize.py
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/test/test_tokenize.py')
-rw-r--r--Lib/test/test_tokenize.py589
1 files changed, 460 insertions, 129 deletions
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py
index 489f68f..f9652ce 100644
--- a/Lib/test/test_tokenize.py
+++ b/Lib/test/test_tokenize.py
@@ -1,13 +1,12 @@
doctests = """
Tests for the tokenize module.
- >>> import glob, random, sys
-
The tests can be really simple. Given a small fragment of source
code, print out a table with tokens. The ENDMARK is omitted for
brevity.
>>> dump_tokens("1 + 1")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '1' (1, 0) (1, 1)
OP '+' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -15,6 +14,7 @@ brevity.
>>> dump_tokens("if False:\\n"
... " # NL\\n"
... " True = False # NEWLINE\\n")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'if' (1, 0) (1, 2)
NAME 'False' (1, 3) (1, 8)
OP ':' (1, 8) (1, 9)
@@ -34,32 +34,16 @@ brevity.
... x += 2
... x += 5
... \"""
-
- >>> for tok in generate_tokens(StringIO(indent_error_file).readline): pass
+ >>> readline = BytesIO(indent_error_file.encode('utf-8')).readline
+ >>> for tok in tokenize(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")
+ ... " print(x)\\n")
True
>>> roundtrip("# This is a comment\\n# This also")
@@ -68,26 +52,26 @@ There are some standard formatting practices that are easy to get right.
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.
+two trailing blanks apparent in the expected output.
>>> roundtrip("if x == 1 : \\n"
- ... " print x\\n")
+ ... " print(x)\\n")
True
- >>> f = test_support.findfile("tokenize_tests" + os.extsep + "txt")
- >>> roundtrip(open(f))
+ >>> f = support.findfile("tokenize_tests.txt")
+ >>> roundtrip(open(f, 'rb'))
True
>>> roundtrip("if x == 1:\\n"
... " # A comment by itself.\\n"
- ... " print x # Comment here, too.\\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")
+ ... " print('x==1')\\n")
True
>>> roundtrip("class Test: # A comment here\\n"
@@ -102,8 +86,8 @@ Some error-handling code
>>> roundtrip("try: import somemodule\\n"
... "except ImportError: # comment\\n"
- ... " print 'Can not import' # comment2\\n"
- ... "else: print 'Loaded'\\n")
+ ... " print('Can not import' # comment2\\n)"
+ ... "else: print('Loaded')\\n")
True
Balancing continuation
@@ -123,27 +107,33 @@ Balancing continuation
Ordinary integers and binary operators
>>> dump_tokens("0xff <= 255")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '0xff' (1, 0) (1, 4)
OP '<=' (1, 5) (1, 7)
NUMBER '255' (1, 8) (1, 11)
>>> dump_tokens("0b10 <= 255")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '0b10' (1, 0) (1, 4)
OP '<=' (1, 5) (1, 7)
NUMBER '255' (1, 8) (1, 11)
- >>> dump_tokens("0o123 <= 0123")
+ >>> dump_tokens("0o123 <= 0O123")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '0o123' (1, 0) (1, 5)
OP '<=' (1, 6) (1, 8)
- NUMBER '0123' (1, 9) (1, 13)
- >>> dump_tokens("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")
+ NUMBER '0O123' (1, 9) (1, 14)
+ >>> dump_tokens("1234567 > ~0x15")
+ ENCODING 'utf-8' (0, 0) (0, 0)
+ NUMBER '1234567' (1, 0) (1, 7)
+ OP '>' (1, 8) (1, 9)
+ OP '~' (1, 10) (1, 11)
+ NUMBER '0x15' (1, 11) (1, 15)
+ >>> dump_tokens("2134568 != 1231515")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '2134568' (1, 0) (1, 7)
OP '!=' (1, 8) (1, 10)
- NUMBER '01231515' (1, 11) (1, 19)
- >>> dump_tokens("(-124561-1) & 0200000000")
+ NUMBER '1231515' (1, 11) (1, 18)
+ >>> dump_tokens("(-124561-1) & 200000000")
+ ENCODING 'utf-8' (0, 0) (0, 0)
OP '(' (1, 0) (1, 1)
OP '-' (1, 1) (1, 2)
NUMBER '124561' (1, 2) (1, 8)
@@ -151,17 +141,20 @@ Ordinary integers and binary operators
NUMBER '1' (1, 9) (1, 10)
OP ')' (1, 10) (1, 11)
OP '&' (1, 12) (1, 13)
- NUMBER '0200000000' (1, 14) (1, 24)
+ NUMBER '200000000' (1, 14) (1, 23)
>>> dump_tokens("0xdeadbeef != -1")
+ ENCODING 'utf-8' (0, 0) (0, 0)
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")
+ >>> dump_tokens("0xdeadc0de & 12345")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '0xdeadc0de' (1, 0) (1, 10)
OP '&' (1, 11) (1, 12)
- NUMBER '012345' (1, 13) (1, 19)
+ NUMBER '12345' (1, 13) (1, 18)
>>> dump_tokens("0xFF & 0x15 | 1234")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NUMBER '0xFF' (1, 0) (1, 4)
OP '&' (1, 5) (1, 6)
NUMBER '0x15' (1, 7) (1, 11)
@@ -170,53 +163,64 @@ Ordinary integers and binary operators
Long integers
- >>> dump_tokens("x = 0L")
+ >>> dump_tokens("x = 0")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
- NUMBER '0L' (1, 4) (1, 6)
+ NUMBER '0' (1, 4) (1, 5)
>>> dump_tokens("x = 0xfffffffffff")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '0xffffffffff (1, 4) (1, 17)
- >>> dump_tokens("x = 123141242151251616110l")
+ >>> dump_tokens("x = 123141242151251616110")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
- NUMBER '123141242151 (1, 4) (1, 26)
- >>> dump_tokens("x = -15921590215012591L")
+ NUMBER '123141242151 (1, 4) (1, 25)
+ >>> dump_tokens("x = -15921590215012591")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
OP '-' (1, 4) (1, 5)
- NUMBER '159215902150 (1, 5) (1, 23)
+ NUMBER '159215902150 (1, 5) (1, 22)
Floating point numbers
>>> dump_tokens("x = 3.14159")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3.14159' (1, 4) (1, 11)
>>> dump_tokens("x = 314159.")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '314159.' (1, 4) (1, 11)
>>> dump_tokens("x = .314159")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '.314159' (1, 4) (1, 11)
>>> dump_tokens("x = 3e14159")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3e14159' (1, 4) (1, 11)
>>> dump_tokens("x = 3E123")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3E123' (1, 4) (1, 9)
>>> dump_tokens("x+y = 3e-1230")
+ ENCODING 'utf-8' (0, 0) (0, 0)
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")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '3.14e159' (1, 4) (1, 12)
@@ -224,6 +228,7 @@ Floating point numbers
String literals
>>> dump_tokens("x = ''; y = \\\"\\\"")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING "''" (1, 4) (1, 6)
@@ -232,6 +237,7 @@ String literals
OP '=' (1, 10) (1, 11)
STRING '""' (1, 12) (1, 14)
>>> dump_tokens("x = '\\\"'; y = \\\"'\\\"")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
STRING '\\'"\\'' (1, 4) (1, 7)
@@ -240,72 +246,53 @@ String literals
OP '=' (1, 11) (1, 12)
STRING '"\\'"' (1, 13) (1, 16)
>>> dump_tokens("x = \\\"doesn't \\\"shrink\\\", does it\\\"")
+ ENCODING 'utf-8' (0, 0) (0, 0)
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'")
+ >>> dump_tokens("x = 'abc' + 'ABC'")
+ ENCODING 'utf-8' (0, 0) (0, 0)
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"')
+ STRING "'abc'" (1, 4) (1, 9)
+ OP '+' (1, 10) (1, 11)
+ STRING "'ABC'" (1, 12) (1, 17)
+ >>> dump_tokens('y = "ABC" + "ABC"')
+ ENCODING 'utf-8' (0, 0) (0, 0)
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'")
+ STRING '"ABC"' (1, 4) (1, 9)
+ OP '+' (1, 10) (1, 11)
+ STRING '"ABC"' (1, 12) (1, 17)
+ >>> dump_tokens("x = r'abc' + r'ABC' + R'ABC' + R'ABC'")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
- STRING "ur'abc'" (1, 4) (1, 11)
- OP '+' (1, 12) (1, 13)
- STRING "Ur'ABC'" (1, 14) (1, 21)
- OP '+' (1, 22) (1, 23)
- 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"')
+ STRING "r'abc'" (1, 4) (1, 10)
+ OP '+' (1, 11) (1, 12)
+ STRING "r'ABC'" (1, 13) (1, 19)
+ OP '+' (1, 20) (1, 21)
+ STRING "R'ABC'" (1, 22) (1, 28)
+ OP '+' (1, 29) (1, 30)
+ STRING "R'ABC'" (1, 31) (1, 37)
+ >>> dump_tokens('y = r"abc" + r"ABC" + R"ABC" + R"ABC"')
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'y' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
- STRING 'ur"abc"' (1, 4) (1, 11)
- OP '+' (1, 12) (1, 13)
- STRING 'Ur"ABC"' (1, 14) (1, 21)
- OP '+' (1, 22) (1, 23)
- STRING 'uR"ABC"' (1, 24) (1, 31)
- OP '+' (1, 32) (1, 33)
- STRING 'UR"ABC"' (1, 34) (1, 41)
-
- >>> dump_tokens("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"')
- 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'")
- STRING "br'abc'" (1, 0) (1, 7)
- OP '+' (1, 8) (1, 9)
- STRING "bR'abc'" (1, 10) (1, 17)
- OP '+' (1, 18) (1, 19)
- 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"')
- STRING 'br"abc"' (1, 0) (1, 7)
- OP '+' (1, 8) (1, 9)
- STRING 'bR"abc"' (1, 10) (1, 17)
- OP '+' (1, 18) (1, 19)
- STRING 'Br"abc"' (1, 20) (1, 27)
- OP '+' (1, 28) (1, 29)
- STRING 'BR"abc"' (1, 30) (1, 37)
+ STRING 'r"abc"' (1, 4) (1, 10)
+ OP '+' (1, 11) (1, 12)
+ STRING 'r"ABC"' (1, 13) (1, 19)
+ OP '+' (1, 20) (1, 21)
+ STRING 'R"ABC"' (1, 22) (1, 28)
+ OP '+' (1, 29) (1, 30)
+ STRING 'R"ABC"' (1, 31) (1, 37)
Operators
>>> dump_tokens("def d22(a, b, c=2, d=2, *k): pass")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'def' (1, 0) (1, 3)
NAME 'd22' (1, 4) (1, 7)
OP '(' (1, 7) (1, 8)
@@ -327,6 +314,7 @@ Operators
OP ':' (1, 27) (1, 28)
NAME 'pass' (1, 29) (1, 33)
>>> dump_tokens("def d01v_(a=1, *k, **w): pass")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'def' (1, 0) (1, 3)
NAME 'd01v_' (1, 4) (1, 9)
OP '(' (1, 9) (1, 10)
@@ -347,6 +335,7 @@ 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")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'if' (1, 0) (1, 2)
NUMBER '1' (1, 3) (1, 4)
OP '<' (1, 5) (1, 6)
@@ -383,6 +372,7 @@ Comparison
Shift
>>> dump_tokens("x = 1 << 1 >> 5")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -393,7 +383,8 @@ Shift
Additive
- >>> dump_tokens("x = 1 - y + 15 - 01 + 0x124 + z + a[5]")
+ >>> dump_tokens("x = 1 - y + 15 - 1 + 0x124 + z + a[5]")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -402,20 +393,21 @@ Additive
OP '+' (1, 10) (1, 11)
NUMBER '15' (1, 12) (1, 14)
OP '-' (1, 15) (1, 16)
- NUMBER '01' (1, 17) (1, 19)
- OP '+' (1, 20) (1, 21)
- NUMBER '0x124' (1, 22) (1, 27)
- OP '+' (1, 28) (1, 29)
- NAME 'z' (1, 30) (1, 31)
- OP '+' (1, 32) (1, 33)
- NAME 'a' (1, 34) (1, 35)
- OP '[' (1, 35) (1, 36)
- NUMBER '5' (1, 36) (1, 37)
- OP ']' (1, 37) (1, 38)
+ NUMBER '1' (1, 17) (1, 18)
+ OP '+' (1, 19) (1, 20)
+ NUMBER '0x124' (1, 21) (1, 26)
+ OP '+' (1, 27) (1, 28)
+ NAME 'z' (1, 29) (1, 30)
+ OP '+' (1, 31) (1, 32)
+ NAME 'a' (1, 33) (1, 34)
+ OP '[' (1, 34) (1, 35)
+ NUMBER '5' (1, 35) (1, 36)
+ OP ']' (1, 36) (1, 37)
Multiplicative
>>> dump_tokens("x = 1//1*1/5*12%0x12")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'x' (1, 0) (1, 1)
OP '=' (1, 2) (1, 3)
NUMBER '1' (1, 4) (1, 5)
@@ -433,6 +425,7 @@ Multiplicative
Unary
>>> dump_tokens("~1 ^ 1 & 1 |1 ^ -1")
+ ENCODING 'utf-8' (0, 0) (0, 0)
OP '~' (1, 0) (1, 1)
NUMBER '1' (1, 1) (1, 2)
OP '^' (1, 3) (1, 4)
@@ -445,6 +438,7 @@ Unary
OP '-' (1, 16) (1, 17)
NUMBER '1' (1, 17) (1, 18)
>>> dump_tokens("-1*1/1+1*1//1 - ---1**1")
+ ENCODING 'utf-8' (0, 0) (0, 0)
OP '-' (1, 0) (1, 1)
NUMBER '1' (1, 1) (1, 2)
OP '*' (1, 2) (1, 3)
@@ -468,6 +462,7 @@ Unary
Selector
>>> dump_tokens("import sys, time\\nx = sys.modules['time'].time()")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'import' (1, 0) (1, 6)
NAME 'sys' (1, 7) (1, 10)
OP ',' (1, 10) (1, 11)
@@ -489,6 +484,7 @@ Selector
Methods
>>> dump_tokens("@staticmethod\\ndef foo(x,y): pass")
+ ENCODING 'utf-8' (0, 0) (0, 0)
OP '@' (1, 0) (1, 1)
NAME 'staticmethod (1, 1) (1, 13)
NEWLINE '\\n' (1, 13) (1, 14)
@@ -520,22 +516,27 @@ Two string literals on the same line
Test roundtrip on random python modules.
pass the '-ucpu' option to process the full directory.
- >>>
+ >>> import random
>>> 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"):
+tokenize is broken on test_pep3131.py because regular expressions are broken on
+the obscure unicode identifiers in it. *sigh*
+ >>> testfiles.remove(os.path.join(tempdir, "test_pep3131.py"))
+ >>> if not 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
+ ... if not roundtrip(open(testfile, 'rb')):
+ ... print("Roundtrip failed for file %s" % testfile)
... break
... else: True
True
Evil tabs
+
>>> dump_tokens("def f():\\n\\tif x\\n \\tpass")
+ ENCODING 'utf-8' (0, 0) (0, 0)
NAME 'def' (1, 0) (1, 3)
NAME 'f' (1, 4) (1, 5)
OP '(' (1, 5) (1, 6)
@@ -553,44 +554,77 @@ Evil tabs
Pathological whitespace (http://bugs.python.org/issue16152)
>>> dump_tokens("@ ")
+ ENCODING 'utf-8' (0, 0) (0, 0)
OP '@' (1, 0) (1, 1)
-"""
+Non-ascii identifiers
+
+ >>> dump_tokens("Örter = 'places'\\ngrün = 'green'")
+ ENCODING 'utf-8' (0, 0) (0, 0)
+ NAME 'Örter' (1, 0) (1, 5)
+ OP '=' (1, 6) (1, 7)
+ STRING "'places'" (1, 8) (1, 16)
+ NEWLINE '\\n' (1, 16) (1, 17)
+ NAME 'grün' (2, 0) (2, 4)
+ OP '=' (2, 5) (2, 6)
+ STRING "'green'" (2, 7) (2, 14)
+"""
-from test import test_support
-from tokenize import (untokenize, generate_tokens, NUMBER, NAME, OP,
- STRING, ENDMARKER, tok_name)
-from StringIO import StringIO
-import os
+from test import support
+from tokenize import (tokenize, _tokenize, untokenize, NUMBER, NAME, OP,
+ STRING, ENDMARKER, tok_name, detect_encoding,
+ open as tokenize_open)
+from io import BytesIO
+from unittest import TestCase
+import os, sys, glob
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):
+ f = BytesIO(s.encode('utf-8'))
+ for type, token, start, end, line in tokenize(f.readline):
if type == ENDMARKER:
break
type = tok_name[type]
print("%(type)-10.10s %(token)-13.13r %(start)s %(end)s" % locals())
+def roundtrip(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 = BytesIO(f.encode('utf-8'))
+ try:
+ token_list = list(tokenize(f.readline))
+ finally:
+ f.close()
+ tokens1 = [tok[:2] for tok in token_list]
+ new_bytes = untokenize(tokens1)
+ readline = (line for line in new_bytes.splitlines(1)).__next__
+ tokens2 = [tok[:2] for tok in tokenize(readline)]
+ return tokens1 == tokens2
+
# 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'
+ >>> s = 'print(+21.3e-5*-.1234/81.7)'
>>> decistmt(s)
- "print +Decimal ('21.3e-5')*-Decimal ('.1234')/Decimal ('81.7')"
+ "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
+ we're only showing 11 digits, and the 12th isn't close to 5, the
rest of the output should be platform-independent.
>>> exec(s) #doctest: +ELLIPSIS
- -3.21716034272e-0...7
+ -3.2171603427...e-0...7
Output from calculations with Decimal should be identical across all
platforms.
@@ -598,9 +632,8 @@ def decistmt(s):
>>> exec(decistmt(s))
-3.217160342717258261933904529E-7
"""
-
result = []
- g = generate_tokens(StringIO(s).readline) # tokenize the string
+ g = tokenize(BytesIO(s.encode('utf-8')).readline) # tokenize the string
for toknum, tokval, _, _, _ in g:
if toknum == NUMBER and '.' in tokval: # replace NUMBER tokens
result.extend([
@@ -611,15 +644,313 @@ def decistmt(s):
])
else:
result.append((toknum, tokval))
- return untokenize(result)
+ return untokenize(result).decode('utf-8')
-__test__ = {"doctests" : doctests, 'decistmt': decistmt}
+class TestTokenizerAdheresToPep0263(TestCase):
+ """
+ Test that tokenizer adheres to the coding behaviour stipulated in PEP 0263.
+ """
+ def _testFile(self, filename):
+ path = os.path.join(os.path.dirname(__file__), filename)
+ return roundtrip(open(path, 'rb'))
+
+ def test_utf8_coding_cookie_and_no_utf8_bom(self):
+ f = 'tokenize_tests-utf8-coding-cookie-and-no-utf8-bom-sig.txt'
+ self.assertTrue(self._testFile(f))
+
+ def test_latin1_coding_cookie_and_utf8_bom(self):
+ """
+ As per PEP 0263, if a file starts with a utf-8 BOM signature, the only
+ allowed encoding for the comment is 'utf-8'. The text file used in
+ this test starts with a BOM signature, but specifies latin1 as the
+ coding, so verify that a SyntaxError is raised, which matches the
+ behaviour of the interpreter when it encounters a similar condition.
+ """
+ f = 'tokenize_tests-latin1-coding-cookie-and-utf8-bom-sig.txt'
+ self.assertRaises(SyntaxError, self._testFile, f)
+
+ def test_no_coding_cookie_and_utf8_bom(self):
+ f = 'tokenize_tests-no-coding-cookie-and-utf8-bom-sig-only.txt'
+ self.assertTrue(self._testFile(f))
+
+ def test_utf8_coding_cookie_and_utf8_bom(self):
+ f = 'tokenize_tests-utf8-coding-cookie-and-utf8-bom-sig.txt'
+ self.assertTrue(self._testFile(f))
+
+ def test_bad_coding_cookie(self):
+ self.assertRaises(SyntaxError, self._testFile, 'bad_coding.py')
+ self.assertRaises(SyntaxError, self._testFile, 'bad_coding2.py')
+
+
+class Test_Tokenize(TestCase):
+
+ def test__tokenize_decodes_with_specified_encoding(self):
+ literal = '"ЉЊЈЁЂ"'
+ line = literal.encode('utf-8')
+ first = False
+ def readline():
+ nonlocal first
+ if not first:
+ first = True
+ return line
+ else:
+ return b''
+
+ # skip the initial encoding token and the end token
+ tokens = list(_tokenize(readline, encoding='utf-8'))[1:-1]
+ expected_tokens = [(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"')]
+ self.assertEqual(tokens, expected_tokens,
+ "bytes not decoded with encoding")
+
+ def test__tokenize_does_not_decode_with_encoding_none(self):
+ literal = '"ЉЊЈЁЂ"'
+ first = False
+ def readline():
+ nonlocal first
+ if not first:
+ first = True
+ return literal
+ else:
+ return b''
+
+ # skip the end token
+ tokens = list(_tokenize(readline, encoding=None))[:-1]
+ expected_tokens = [(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"')]
+ self.assertEqual(tokens, expected_tokens,
+ "string not tokenized when encoding is None")
+
+
+class TestDetectEncoding(TestCase):
+
+ def get_readline(self, lines):
+ index = 0
+ def readline():
+ nonlocal index
+ if index == len(lines):
+ raise StopIteration
+ line = lines[index]
+ index += 1
+ return line
+ return readline
+
+ def test_no_bom_no_encoding_cookie(self):
+ lines = (
+ b'# something\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+ self.assertEqual(encoding, 'utf-8')
+ self.assertEqual(consumed_lines, list(lines[:2]))
+
+ def test_bom_no_cookie(self):
+ lines = (
+ b'\xef\xbb\xbf# something\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+ self.assertEqual(encoding, 'utf-8-sig')
+ self.assertEqual(consumed_lines,
+ [b'# something\n', b'print(something)\n'])
+
+ def test_cookie_first_line_no_bom(self):
+ lines = (
+ b'# -*- coding: latin-1 -*-\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+ self.assertEqual(encoding, 'iso-8859-1')
+ self.assertEqual(consumed_lines, [b'# -*- coding: latin-1 -*-\n'])
+
+ def test_matched_bom_and_cookie_first_line(self):
+ lines = (
+ b'\xef\xbb\xbf# coding=utf-8\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+ self.assertEqual(encoding, 'utf-8-sig')
+ self.assertEqual(consumed_lines, [b'# coding=utf-8\n'])
+
+ def test_mismatched_bom_and_cookie_first_line_raises_syntaxerror(self):
+ lines = (
+ b'\xef\xbb\xbf# vim: set fileencoding=ascii :\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ readline = self.get_readline(lines)
+ self.assertRaises(SyntaxError, detect_encoding, readline)
+
+ def test_cookie_second_line_no_bom(self):
+ lines = (
+ b'#! something\n',
+ b'# vim: set fileencoding=ascii :\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+ self.assertEqual(encoding, 'ascii')
+ expected = [b'#! something\n', b'# vim: set fileencoding=ascii :\n']
+ self.assertEqual(consumed_lines, expected)
+
+ def test_matched_bom_and_cookie_second_line(self):
+ lines = (
+ b'\xef\xbb\xbf#! something\n',
+ b'f# coding=utf-8\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ encoding, consumed_lines = detect_encoding(self.get_readline(lines))
+ self.assertEqual(encoding, 'utf-8-sig')
+ self.assertEqual(consumed_lines,
+ [b'#! something\n', b'f# coding=utf-8\n'])
+
+ def test_mismatched_bom_and_cookie_second_line_raises_syntaxerror(self):
+ lines = (
+ b'\xef\xbb\xbf#! something\n',
+ b'# vim: set fileencoding=ascii :\n',
+ b'print(something)\n',
+ b'do_something(else)\n'
+ )
+ readline = self.get_readline(lines)
+ self.assertRaises(SyntaxError, detect_encoding, readline)
+
+ def test_latin1_normalization(self):
+ # See get_normal_name() in tokenizer.c.
+ encodings = ("latin-1", "iso-8859-1", "iso-latin-1", "latin-1-unix",
+ "iso-8859-1-unix", "iso-latin-1-mac")
+ for encoding in encodings:
+ for rep in ("-", "_"):
+ enc = encoding.replace("-", rep)
+ lines = (b"#!/usr/bin/python\n",
+ b"# coding: " + enc.encode("ascii") + b"\n",
+ b"print(things)\n",
+ b"do_something += 4\n")
+ rl = self.get_readline(lines)
+ found, consumed_lines = detect_encoding(rl)
+ self.assertEqual(found, "iso-8859-1")
+
+ def test_syntaxerror_latin1(self):
+ # Issue 14629: need to raise SyntaxError if the first
+ # line(s) have non-UTF-8 characters
+ lines = (
+ b'print("\xdf")', # Latin-1: LATIN SMALL LETTER SHARP S
+ )
+ readline = self.get_readline(lines)
+ self.assertRaises(SyntaxError, detect_encoding, readline)
+
+
+ def test_utf8_normalization(self):
+ # See get_normal_name() in tokenizer.c.
+ encodings = ("utf-8", "utf-8-mac", "utf-8-unix")
+ for encoding in encodings:
+ for rep in ("-", "_"):
+ enc = encoding.replace("-", rep)
+ lines = (b"#!/usr/bin/python\n",
+ b"# coding: " + enc.encode("ascii") + b"\n",
+ b"1 + 3\n")
+ rl = self.get_readline(lines)
+ found, consumed_lines = detect_encoding(rl)
+ self.assertEqual(found, "utf-8")
+
+ def test_short_files(self):
+ readline = self.get_readline((b'print(something)\n',))
+ encoding, consumed_lines = detect_encoding(readline)
+ self.assertEqual(encoding, 'utf-8')
+ self.assertEqual(consumed_lines, [b'print(something)\n'])
+
+ encoding, consumed_lines = detect_encoding(self.get_readline(()))
+ self.assertEqual(encoding, 'utf-8')
+ self.assertEqual(consumed_lines, [])
+
+ readline = self.get_readline((b'\xef\xbb\xbfprint(something)\n',))
+ encoding, consumed_lines = detect_encoding(readline)
+ self.assertEqual(encoding, 'utf-8-sig')
+ self.assertEqual(consumed_lines, [b'print(something)\n'])
+
+ readline = self.get_readline((b'\xef\xbb\xbf',))
+ encoding, consumed_lines = detect_encoding(readline)
+ self.assertEqual(encoding, 'utf-8-sig')
+ self.assertEqual(consumed_lines, [])
+
+ readline = self.get_readline((b'# coding: bad\n',))
+ self.assertRaises(SyntaxError, detect_encoding, readline)
+
+ def test_open(self):
+ filename = support.TESTFN + '.py'
+ self.addCleanup(support.unlink, filename)
+
+ # test coding cookie
+ for encoding in ('iso-8859-15', 'utf-8'):
+ with open(filename, 'w', encoding=encoding) as fp:
+ print("# coding: %s" % encoding, file=fp)
+ print("print('euro:\u20ac')", file=fp)
+ with tokenize_open(filename) as fp:
+ self.assertEqual(fp.encoding, encoding)
+ self.assertEqual(fp.mode, 'r')
+
+ # test BOM (no coding cookie)
+ with open(filename, 'w', encoding='utf-8-sig') as fp:
+ print("print('euro:\u20ac')", file=fp)
+ with tokenize_open(filename) as fp:
+ self.assertEqual(fp.encoding, 'utf-8-sig')
+ self.assertEqual(fp.mode, 'r')
+
+class TestTokenize(TestCase):
+
+ def test_tokenize(self):
+ import tokenize as tokenize_module
+ encoding = object()
+ encoding_used = None
+ def mock_detect_encoding(readline):
+ return encoding, ['first', 'second']
+
+ def mock__tokenize(readline, encoding):
+ nonlocal encoding_used
+ encoding_used = encoding
+ out = []
+ while True:
+ next_line = readline()
+ if next_line:
+ out.append(next_line)
+ continue
+ return out
+
+ counter = 0
+ def mock_readline():
+ nonlocal counter
+ counter += 1
+ if counter == 5:
+ return b''
+ return counter
+
+ orig_detect_encoding = tokenize_module.detect_encoding
+ orig__tokenize = tokenize_module._tokenize
+ tokenize_module.detect_encoding = mock_detect_encoding
+ tokenize_module._tokenize = mock__tokenize
+ try:
+ results = tokenize(mock_readline)
+ self.assertEqual(list(results), ['first', 'second', 1, 2, 3, 4])
+ finally:
+ tokenize_module.detect_encoding = orig_detect_encoding
+ tokenize_module._tokenize = orig__tokenize
+
+ self.assertTrue(encoding_used, encoding)
+
+
+__test__ = {"doctests" : doctests, 'decistmt': decistmt}
def test_main():
from test import test_tokenize
- test_support.run_doctest(test_tokenize, True)
+ support.run_doctest(test_tokenize, True)
+ support.run_unittest(TestTokenizerAdheresToPep0263)
+ support.run_unittest(Test_Tokenize)
+ support.run_unittest(TestDetectEncoding)
+ support.run_unittest(TestTokenize)
if __name__ == "__main__":
test_main()
generated by cgit v0.12 at 2025-12-26 00:01:21 (GMT)