diff options
Diffstat (limited to 'Lib/test/test_tokenize.py')
| -rw-r--r-- | Lib/test/test_tokenize.py | 681 |
1 files changed, 493 insertions, 188 deletions
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py index e59d9c672cf..2ed723b87e1 100644 --- a/Lib/test/test_tokenize.py +++ b/Lib/test/test_tokenize.py @@ -1,126 +1,501 @@ -"""Tests for the tokenize module. +doctests = """ +Tests for the tokenize module. -The tests were originally written in the old Python style, where the -test output was compared to a golden file. This docstring represents -the first steps towards rewriting the entire test as a doctest. + >>> import glob, random, sys -The tests can be really simple. Given a small fragment of source -code, print out a table with the tokens. The ENDMARK is omitted for +The tests can be really simple. Given a small fragment of source +code, print out a table with thokens. The ENDMARK is omitted for brevity. ->>> dump_tokens("1 + 1") -NUMBER '1' (1, 0) (1, 1) -OP '+' (1, 2) (1, 3) -NUMBER '1' (1, 4) (1, 5) - -A comment generates a token here, unlike in the parser module. The -comment token is followed by an NL or a NEWLINE token, depending on -whether the line contains the completion of a statement. - ->>> dump_tokens("if False:\\n" -... " # NL\\n" -... " a = False # NEWLINE\\n") -NAME 'if' (1, 0) (1, 2) -NAME 'False' (1, 3) (1, 8) -OP ':' (1, 8) (1, 9) -NEWLINE '\\n' (1, 9) (1, 10) -COMMENT '# NL' (2, 4) (2, 8) -NL '\\n' (2, 8) (2, 9) -INDENT ' ' (3, 0) (3, 4) -NAME 'a' (3, 4) (3, 5) -OP '=' (3, 9) (3, 10) -NAME 'False' (3, 11) (3, 16) -COMMENT '# NEWLINE' (3, 17) (3, 26) -NEWLINE '\\n' (3, 26) (3, 27) -DEDENT '' (4, 0) (4, 0) - -' # Emacs hint - -There will be a bunch more tests of specific source patterns. - -The tokenize module also defines an untokenize function that should -regenerate the original program text from the tokens. - -There are some standard formatting practices that are easy to get right. - ->>> roundtrip("if x == 1:\\n" -... " print(x)\\n") -if x == 1: - print(x) + >>> dump_tokens("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") + NAME 'if' (1, 0) (1, 2) + NAME 'False' (1, 3) (1, 8) + OP ':' (1, 8) (1, 9) + NEWLINE '\\n' (1, 9) (1, 10) + COMMENT '# NL' (2, 4) (2, 8) + NL '\\n' (2, 8) (2, 9) + INDENT ' ' (3, 0) (3, 4) + NAME 'True' (3, 4) (3, 8) + OP '=' (3, 9) (3, 10) + NAME 'False' (3, 11) (3, 16) + 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 + ... \""" + >>> 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 formattig practises 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 apparent in the expected output. - ->>> roundtrip("if x == 1 : \\n" -... " print(x)\\n") -if x == 1 :\x20\x20 - print(x) - -Comments need to go in the right place. - ->>> roundtrip("if x == 1:\\n" -... " # A comment by itself.\\n" -... " print(x) # Comment here, too.\\n" -... " # Another comment.\\n" -... "after_if = True\\n") -if x == 1: - # A comment by itself. - print(x) # Comment here, too. - # Another comment. -after_if = True - ->>> roundtrip("if (x # The comments need to go in the right place\\n" -... " == 1):\\n" -... " print('x == 1')\\n") -if (x # The comments need to go in the right place - == 1): - print('x == 1') - +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.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 contunuation + + >>> 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") + NUMBER '0xff' (1, 0) (1, 4) + OP '<=' (1, 5) (1, 7) + NUMBER '255' (1, 8) (1, 11) + >>> 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 '2134568' (1, 0) (1, 7) + OP '!=' (1, 8) (1, 10) + NUMBER '01231515' (1, 11) (1, 19) + >>> dump_tokens("(-124561-1) & 0200000000") + OP '(' (1, 0) (1, 1) + OP '-' (1, 1) (1, 2) + NUMBER '124561' (1, 2) (1, 8) + OP '-' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + OP ')' (1, 10) (1, 11) + OP '&' (1, 12) (1, 13) + NUMBER '0200000000' (1, 14) (1, 24) + >>> dump_tokens("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") + NUMBER '0xdeadc0de' (1, 0) (1, 10) + OP '&' (1, 11) (1, 12) + NUMBER '012345' (1, 13) (1, 19) + >>> dump_tokens("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") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '0L' (1, 4) (1, 6) + >>> dump_tokens("x = 0xfffffffffff") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '0xffffffffff (1, 4) (1, 17) + >>> dump_tokens("x = 123141242151251616110l") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '123141242151 (1, 4) (1, 26) + >>> dump_tokens("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") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3.14159' (1, 4) (1, 11) + >>> dump_tokens("x = 314159.") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '314159.' (1, 4) (1, 11) + >>> dump_tokens("x = .314159") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '.314159' (1, 4) (1, 11) + >>> dump_tokens("x = 3e14159") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3e14159' (1, 4) (1, 11) + >>> dump_tokens("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") + 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") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '3.14e159' (1, 4) (1, 12) + +String literals + + >>> dump_tokens("x = ''; y = \\\"\\\"") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING "''" (1, 4) (1, 6) + OP ';' (1, 6) (1, 7) + NAME 'y' (1, 8) (1, 9) + OP '=' (1, 10) (1, 11) + STRING '""' (1, 12) (1, 14) + >>> dump_tokens("x = '\\\"'; y = \\\"'\\\"") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING '\\'"\\'' (1, 4) (1, 7) + OP ';' (1, 7) (1, 8) + NAME 'y' (1, 9) (1, 10) + OP '=' (1, 11) (1, 12) + STRING '"\\'"' (1, 13) (1, 16) + >>> dump_tokens("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'") + 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 = "ABC" + "ABC"') + NAME 'y' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING '"ABC"' (1, 4) (1, 10) + OP '+' (1, 11) (1, 12) + STRING '"ABC"' (1, 13) (1, 19) + >>> dump_tokens("x = r'abc' + r'ABC' + R'ABC' + R'ABC'") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING "r'abc'" (1, 4) (1, 11) + OP '+' (1, 12) (1, 13) + STRING "r'ABC'" (1, 14) (1, 21) + OP '+' (1, 22) (1, 23) + STRING "R'ABC'" (1, 24) (1, 31) + OP '+' (1, 32) (1, 33) + STRING "R'ABC'" (1, 34) (1, 41) + >>> dump_tokens('y = r"abc" + r"ABC" + R"ABC" + R"ABC"') + NAME 'y' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + STRING 'r"abc"' (1, 4) (1, 11) + OP '+' (1, 12) (1, 13) + STRING 'r"ABC"' (1, 14) (1, 21) + OP '+' (1, 22) (1, 23) + STRING 'R"ABC"' (1, 24) (1, 31) + OP '+' (1, 32) (1, 33) + STRING 'R"ABC"' (1, 34) (1, 41) + +Operators + + >>> dump_tokens("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) + NAME 'a' (1, 8) (1, 9) + OP ',' (1, 9) (1, 10) + NAME 'b' (1, 11) (1, 12) + OP ',' (1, 12) (1, 13) + NAME 'c' (1, 14) (1, 15) + OP '=' (1, 15) (1, 16) + NUMBER '2' (1, 16) (1, 17) + OP ',' (1, 17) (1, 18) + NAME 'd' (1, 19) (1, 20) + OP '=' (1, 20) (1, 21) + NUMBER '2' (1, 21) (1, 22) + OP ',' (1, 22) (1, 23) + OP '*' (1, 24) (1, 25) + NAME 'k' (1, 25) (1, 26) + 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") + NAME 'def' (1, 0) (1, 3) + NAME 'd01v_' (1, 4) (1, 9) + OP '(' (1, 9) (1, 10) + NAME 'a' (1, 10) (1, 11) + OP '=' (1, 11) (1, 12) + NUMBER '1' (1, 12) (1, 13) + OP ',' (1, 13) (1, 14) + OP '*' (1, 15) (1, 16) + NAME 'k' (1, 16) (1, 17) + OP ',' (1, 17) (1, 18) + OP '**' (1, 19) (1, 21) + NAME 'w' (1, 21) (1, 22) + 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") + NAME 'if' (1, 0) (1, 2) + NUMBER '1' (1, 3) (1, 4) + OP '<' (1, 5) (1, 6) + NUMBER '1' (1, 7) (1, 8) + OP '>' (1, 9) (1, 10) + NUMBER '1' (1, 11) (1, 12) + OP '==' (1, 13) (1, 15) + NUMBER '1' (1, 16) (1, 17) + OP '>=' (1, 18) (1, 20) + NUMBER '5' (1, 21) (1, 22) + OP '<=' (1, 23) (1, 25) + NUMBER '0x15' (1, 26) (1, 30) + OP '<=' (1, 31) (1, 33) + NUMBER '0x12' (1, 34) (1, 38) + OP '!=' (1, 39) (1, 41) + NUMBER '1' (1, 42) (1, 43) + NAME 'and' (1, 44) (1, 47) + NUMBER '5' (1, 48) (1, 49) + NAME 'in' (1, 50) (1, 52) + NUMBER '1' (1, 53) (1, 54) + NAME 'not' (1, 55) (1, 58) + NAME 'in' (1, 59) (1, 61) + NUMBER '1' (1, 62) (1, 63) + NAME 'is' (1, 64) (1, 66) + NUMBER '1' (1, 67) (1, 68) + NAME 'or' (1, 69) (1, 71) + NUMBER '5' (1, 72) (1, 73) + NAME 'is' (1, 74) (1, 76) + NAME 'not' (1, 77) (1, 80) + NUMBER '1' (1, 81) (1, 82) + OP ':' (1, 82) (1, 83) + NAME 'pass' (1, 84) (1, 88) + +Shift + + >>> dump_tokens("x = 1 << 1 >> 5") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + OP '<<' (1, 6) (1, 8) + 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]") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + OP '-' (1, 6) (1, 7) + NAME 'y' (1, 8) (1, 9) + 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) + +Multiplicative + + >>> dump_tokens("x = 1//1*1/5*12%0x12") + NAME 'x' (1, 0) (1, 1) + OP '=' (1, 2) (1, 3) + NUMBER '1' (1, 4) (1, 5) + OP '//' (1, 5) (1, 7) + NUMBER '1' (1, 7) (1, 8) + OP '*' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + OP '/' (1, 10) (1, 11) + NUMBER '5' (1, 11) (1, 12) + OP '*' (1, 12) (1, 13) + 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") + OP '~' (1, 0) (1, 1) + NUMBER '1' (1, 1) (1, 2) + OP '^' (1, 3) (1, 4) + NUMBER '1' (1, 5) (1, 6) + OP '&' (1, 7) (1, 8) + NUMBER '1' (1, 9) (1, 10) + OP '|' (1, 11) (1, 12) + NUMBER '1' (1, 12) (1, 13) + 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") + OP '-' (1, 0) (1, 1) + NUMBER '1' (1, 1) (1, 2) + OP '*' (1, 2) (1, 3) + NUMBER '1' (1, 3) (1, 4) + OP '/' (1, 4) (1, 5) + NUMBER '1' (1, 5) (1, 6) + OP '+' (1, 6) (1, 7) + NUMBER '1' (1, 7) (1, 8) + OP '*' (1, 8) (1, 9) + NUMBER '1' (1, 9) (1, 10) + OP '//' (1, 10) (1, 12) + NUMBER '1' (1, 12) (1, 13) + OP '-' (1, 14) (1, 15) + OP '-' (1, 16) (1, 17) + OP '-' (1, 17) (1, 18) + OP '-' (1, 18) (1, 19) + 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()") + NAME 'import' (1, 0) (1, 6) + NAME 'sys' (1, 7) (1, 10) + OP ',' (1, 10) (1, 11) + NAME 'time' (1, 12) (1, 16) + NEWLINE '\\n' (1, 16) (1, 17) + NAME 'x' (2, 0) (2, 1) + OP '=' (2, 2) (2, 3) + NAME 'sys' (2, 4) (2, 7) + OP '.' (2, 7) (2, 8) + NAME 'modules' (2, 8) (2, 15) + OP '[' (2, 15) (2, 16) + STRING "'time'" (2, 16) (2, 22) + OP ']' (2, 22) (2, 23) + OP '.' (2, 23) (2, 24) + 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") + OP '@' (1, 0) (1, 1) + NAME 'staticmethod (1, 1) (1, 13) + NEWLINE '\\n' (1, 13) (1, 14) + NAME 'def' (2, 0) (2, 3) + NAME 'foo' (2, 4) (2, 7) + OP '(' (2, 7) (2, 8) + NAME 'x' (2, 8) (2, 9) + OP ',' (2, 9) (2, 10) + NAME 'y' (2, 10) (2, 11) + 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 + + >>> + >>> tempdir = os.path.dirname(f) or os.curdir + >>> testfiles = glob.glob(os.path.join(tempdir, "test*.py")) + >>> if not test_support.is_resource_enabled("compiler"): + ... testfiles = random.sample(testfiles, 10) + ... + >>> for testfile in testfiles: + ... if not roundtrip(open(testfile)): break + ... else: True + True """ -# ' Emacs hint -import os, glob, random, time, sys -import re +from test import test_support +from tokenize import (tokenize, untokenize, generate_tokens, NUMBER, NAME, OP, + STRING, ENDMARKER, tok_name) from io import StringIO -from test.test_support import (verbose, findfile, is_resource_enabled, - TestFailed) -from tokenize import (tokenize, generate_tokens, untokenize, tok_name, - ENDMARKER, NUMBER, NAME, OP, STRING, COMMENT) - -# How much time in seconds can pass before we print a 'Still working' message. -_PRINT_WORKING_MSG_INTERVAL = 5 * 60 - -# Test roundtrip for `untokenize`. `f` is a file path. 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 test_roundtrip(f): - ## print('Testing:', f) - # Get the encoding first - fobj = open(f, encoding="latin-1") - first2lines = fobj.readline() + fobj.readline() - fobj.close() - m = re.search(r"coding:\s*(\S+)", first2lines) - if m: - encoding = m.group(1) - ## print(" coding:", encoding) - else: - encoding = "utf-8" - fobj = open(f, encoding=encoding) - try: - fulltok = list(generate_tokens(fobj.readline)) - finally: - fobj.close() - - t1 = [tok[:2] for tok in fulltok] - newtext = untokenize(t1) - readline = iter(newtext.splitlines(1)).__next__ - t2 = [tok[:2] for tok in generate_tokens(readline)] - if t1 != t2: - raise TestFailed("untokenize() roundtrip failed for %r" % f) +import os def dump_tokens(s): """Print out the tokens in s in a table format. @@ -132,7 +507,7 @@ def dump_tokens(s): if type == ENDMARKER: break type = tok_name[type] - print("%(type)-10.10s %(token)-13.13r %(start)s %(end)s" % locals()) + print("%(type)-10.10s %(token)-13.13r %(start)s %(end)s" % locals()) def roundtrip(s): f = StringIO(s) @@ -177,82 +552,12 @@ def decistmt(s): result.append((toknum, tokval)) return untokenize(result) -def test_main(): - if verbose: - print('starting...') - - next_time = time.time() + _PRINT_WORKING_MSG_INTERVAL - - # Validate the tokenize_tests.txt file. - # This makes sure it compiles, and displays any errors in it. - f = open(findfile('tokenize_tests.txt')) - sf = f.read() - f.close() - cf = compile(sf, 'tokenize_tests.txt', 'exec') - - # This displays the tokenization of tokenize_tests.py to stdout, and - # regrtest.py checks that this equals the expected output (in the - # test/output/ directory). - f = open(findfile('tokenize_tests.txt')) - tokenize(f.readline) - f.close() - - # Now run test_roundtrip() over test_tokenize.py too, and over all - # (if the "compiler" resource is enabled) or a small random sample (if - # "compiler" is not enabled) of the test*.py files. - f = findfile('test_tokenize.py') - if verbose: - print(' round trip: ', f, file=sys.__stdout__) - test_roundtrip(f) - - testdir = os.path.dirname(f) or os.curdir - testfiles = glob.glob(testdir + os.sep + 'test*.py') - if not is_resource_enabled('compiler'): - testfiles = random.sample(testfiles, 10) - - for f in testfiles: - # Print still working message since this test can be really slow - if verbose: - print(' round trip: ', f, file=sys.__stdout__) - if next_time <= time.time(): - next_time = time.time() + _PRINT_WORKING_MSG_INTERVAL - print(' test_main still working, be patient...', file=sys.__stdout__) - sys.__stdout__.flush() - - test_roundtrip(f) - - # Test detecton of IndentationError. - sampleBadText = """\ -def foo(): - bar - baz -""" - - try: - for tok in generate_tokens(StringIO(sampleBadText).readline): - pass - except IndentationError: - pass - else: - raise TestFailed("Did not detect IndentationError:") - - # Run the doctests in this module. - from test import test_tokenize # i.e., this module - from test.test_support import run_doctest - run_doctest(test_tokenize, verbose) - if verbose: - print('finished') +__test__ = {"doctests" : doctests, 'decistmt': decistmt} -def test_rarrow(): - """ - This function exists solely to test the tokenization of the RARROW - operator. - - >>> tokenize(iter(['->']).__next__) #doctest: +NORMALIZE_WHITESPACE - 1,0-1,2:\tOP\t'->' - 2,0-2,0:\tENDMARKER\t'' - """ +def test_main(): + from test import test_tokenize + test_support.run_doctest(test_tokenize, True) if __name__ == "__main__": test_main() |