remove sys_version for Python 3

since we're now committed to using Python3, I decided to go through and
clean up the code base to remove paths which depend on sys_version
checks for Python3

IPython/core/debugger.py

@@ -604,7 +604,6 b' class Pdb(OldPdb, object):'
                       ('Globals', self.curframe.f_globals)]
         self.shell.find_line_magic('psource')(arg, namespaces=namespaces)
 
-    if sys.version_info > (3, ):
         def do_where(self, arg):
             """w(here)
             Print a stack trace, with the most recent frame at the bottom.

IPython/core/interactiveshell.py

@@ -187,10 +187,7 b' class ExecutionResult(object):'
             raise self.error_in_exec
 
     def __repr__(self):
-        if sys.version_info > (3,):
             name = self.__class__.__qualname__
-        else:
-            name = self.__class__.__name__
         return '<%s object at %x, execution_count=%s error_before_exec=%s error_in_exec=%s result=%s>' %\
                 (name, id(self), self.execution_count, self.error_before_exec, self.error_in_exec, repr(self.result))
 

IPython/core/tests/test_completer.py

@@ -155,7 +155,6 b' def test_latex_completions():'
 
 
 
[e-mail](sys.version_info[0] >= 3, 'This test only apply on python3')
 def test_back_latex_completion():
     ip = get_ipython()
 
@@ -164,7 +163,6 b' def test_back_latex_completion():'
     nt.assert_equal(len(matches), 1)
     nt.assert_equal(matches[0], '\\beta')
 
[e-mail](sys.version_info[0] >= 3, 'This test only apply on python3')
 def test_back_unicode_completion():
     ip = get_ipython()
     
@@ -173,7 +171,6 b' def test_back_unicode_completion():'
     nt.assert_equal(matches[0], '\\ROMAN NUMERAL FIVE')
 
 
[e-mail](sys.version_info[0] >= 3, 'This test only apply on python3')
 def test_forward_unicode_completion():
     ip = get_ipython()
     
@@ -181,7 +178,6 b' def test_forward_unicode_completion():'
     nt.assert_equal(len(matches), 1)
     nt.assert_equal(matches[0], 'Ⅴ')
 
[e-mail](sys.version_info[0] >= 3, 'This test only apply on python3')
 @dec.knownfailureif(sys.platform == 'win32', 'Fails if there is a C:\\j... path')
 def test_no_ascii_back_completion():
     ip = get_ipython()
@@ -588,7 +584,6 b' def test_dict_key_completion_contexts():'
 
 
 
[e-mail](sys.version_info[0] >= 3, 'This test only applies in Py>=3')
 def test_dict_key_completion_bytes():
     """Test handling of bytes in dict key completion"""
     ip = get_ipython()
@@ -618,7 +613,6 b' def test_dict_key_completion_bytes():'
         nt.assert_not_in("abd", matches)
 
 
[e-mail](sys.version_info[0] < 3, 'This test only applies in Py<3')
 def test_dict_key_completion_unicode_py2():
     """Test handling of unicode in dict key completion"""
     ip = get_ipython()
@@ -679,7 +673,6 b' def test_dict_key_completion_unicode_py2():'
         nt.assert_in(u"d[u'a\u05d0b']", matches)
 
 
[e-mail](sys.version_info[0] >= 3, 'This test only applies in Py>=3')
 def test_dict_key_completion_unicode_py3():
     """Test handling of unicode in dict key completion"""
     ip = get_ipython()

IPython/core/tests/test_interactiveshell.py

@@ -338,19 +338,6 b' class InteractiveShellTestCase(unittest.TestCase):'
         finally:
             trap.hook = save_hook
 
-    @skipif(sys.version_info[0] >= 3, "softspace removed in py3")
-    def test_print_softspace(self):
-        """Verify that softspace is handled correctly when executing multiple
-        statements.
-
-        In [1]: print 1; print 2
-        1
-        2
-
-        In [2]: print 1,; print 2
-        1 2
-        """
-        
     def test_ofind_line_magic(self):
         from IPython.core.magic import register_line_magic
         
@@ -466,22 +453,6 b' class InteractiveShellTestCase(unittest.TestCase):'
             # Reset the custom exception hook
             ip.set_custom_exc((), None)
     
-    @skipif(sys.version_info[0] >= 3, "no differences with __future__ in py3")
-    def test_future_environment(self):
-        "Can we run code with & without the shell's __future__ imports?"
-        ip.run_cell("from __future__ import division")
-        ip.run_cell("a = 1/2", shell_futures=True)
-        self.assertEqual(ip.user_ns['a'], 0.5)
-        ip.run_cell("b = 1/2", shell_futures=False)
-        self.assertEqual(ip.user_ns['b'], 0)
-        
-        ip.compile.reset_compiler_flags()
-        # This shouldn't leak to the shell's compiler
-        ip.run_cell("from __future__ import division \nc=1/2", shell_futures=False)
-        self.assertEqual(ip.user_ns['c'], 0.5)
-        ip.run_cell("d = 1/2", shell_futures=True)
-        self.assertEqual(ip.user_ns['d'], 0)
-
     def test_mktempfile(self):
         filename = ip.mktempfile()
         # Check that we can open the file again on Windows
@@ -509,9 +480,6 b' class InteractiveShellTestCase(unittest.TestCase):'
             raise DerivedInterrupt("foo")
         except KeyboardInterrupt:
             msg = ip.get_exception_only()
-        if sys.version_info[0] <= 2:
-            self.assertEqual(msg, 'DerivedInterrupt: foo\n')
-        else:
             self.assertEqual(msg, 'IPython.core.tests.test_interactiveshell.DerivedInterrupt: foo\n')
 
     def test_inspect_text(self):

IPython/core/tests/test_magic.py

@@ -377,18 +377,6 b' def test_time3():'
                     "run = 0\n"
                     "run += 1")
 
[e-mail](sys.version_info[0] >= 3, "no differences with __future__ in py3")
-def test_time_futures():
-    "Test %time with __future__ environments"
-    ip = get_ipython()
-    ip.autocall = 0
-    ip.run_cell("from __future__ import division")
-    with tt.AssertPrints('0.25'):
-        ip.run_line_magic('time', 'print(1/4)')
-    ip.compile.reset_compiler_flags()
-    with tt.AssertNotPrints('0.25'):
-        ip.run_line_magic('time', 'print(1/4)')
-
 def test_doctest_mode():
     "Toggle doctest_mode twice, it should be a no-op and run without error"
     _ip.magic('doctest_mode')
@@ -573,17 +561,6 b' def test_timeit_return_quiet():'
         res = _ip.run_line_magic('timeit', '-n1 -r1 -q -o 1')
     assert (res is not None)
 
[e-mail](sys.version_info[0] >= 3, "no differences with __future__ in py3")
-def test_timeit_futures():
-    "Test %timeit with __future__ environments"
-    ip = get_ipython()
-    ip.run_cell("from __future__ import division")
-    with tt.AssertPrints('0.25'):
-        ip.run_line_magic('timeit', '-n1 -r1 print(1/4)')
-    ip.compile.reset_compiler_flags()
-    with tt.AssertNotPrints('0.25'):
-        ip.run_line_magic('timeit', '-n1 -r1 print(1/4)')
-
 @dec.skipif(execution.profile is None)
 def test_prun_special_syntax():
     "Test %%prun with IPython special syntax"

IPython/core/tests/test_magic_terminal.py

@@ -57,8 +57,6 b' def check_cpaste(code, should_fail=False):'
     finally:
         sys.stdin = stdin_save
 
-PY31 = sys.version_info[:2] == (3,1)
-
 def test_cpaste():
     """Test cpaste magic"""
 
@@ -77,14 +75,9 b' def test_cpaste():'
                       ],
 
              'fail': ["1 + runf()",
+                      "++ runf()",
              ]}
     
-    # I don't know why this is failing specifically on Python 3.1. I've
-    # checked it manually interactively, but we don't care enough about 3.1
-    # to spend time fiddling with the tests, so we just skip it.
-    if not PY31:
-        tests['fail'].append("++ runf()")
-
     ip.user_ns['runf'] = runf
 
     for code in tests['pass']:

IPython/core/tests/test_oinspect.py

@@ -275,7 +275,6 b' def test_info():'
     nt.assert_equal(i['type_name'], 'type')
     expted_class = str(type(type))  # <class 'type'> (Python 3) or <type 'type'>
     nt.assert_equal(i['base_class'], expted_class)
-    if sys.version_info > (3,):
         nt.assert_regex(i['string_form'], "<class 'IPython.core.tests.test_oinspect.Call'( at 0x[0-9a-f]{1,9})?>")
     fname = __file__
     if fname.endswith(".pyc"):

IPython/core/tests/test_ultratb.py

@@ -313,7 +313,6 b' def r3o2():'
 #----------------------------------------------------------------------------
 
 # module testing (minimal)
-if sys.version_info > (3,):
     def test_handlers():
         def spam(c, d_e):
             (d, e) = d_e

IPython/testing/iptest.py

@@ -45,7 +45,6 b' pjoin = path.join'
 
 # Enable printing all warnings raise by IPython's modules
 warnings.filterwarnings('ignore', message='.*Matplotlib is building the font cache.*', category=UserWarning, module='.*')
-if sys.version_info > (3,0):
     warnings.filterwarnings('error', message='.*', category=ResourceWarning, module='.*')
 warnings.filterwarnings('error', message=".*{'config': True}.*", category=DeprecationWarning, module='IPy.*')
 warnings.filterwarnings('default', message='.*', category=Warning, module='IPy.*')

IPython/testing/skipdoctest.py

@@ -1,26 +1,13 b''
-"""Decorators marks that a doctest should be skipped, for both python 2 and 3.
+"""Decorators marks that a doctest should be skipped.
 
 The IPython.testing.decorators module triggers various extra imports, including
 numpy and sympy if they're present. Since this decorator is used in core parts
 of IPython, it's in a separate module so that running IPython doesn't trigger
 those imports."""
 
-#-----------------------------------------------------------------------------
-#  Copyright (C) 2009-2011  The IPython Development Team
-#
-#  Distributed under the terms of the BSD License.  The full license is in
-#  the file COPYING, distributed as part of this software.
-#-----------------------------------------------------------------------------
+# Copyright (C) IPython Development Team
+# Distributed under the terms of the Modified BSD License.
 
-#-----------------------------------------------------------------------------
-# Imports
-#-----------------------------------------------------------------------------
-
-import sys
-
-#-----------------------------------------------------------------------------
-# Decorators
-#-----------------------------------------------------------------------------
 
 def skip_doctest(f):
     """Decorator - mark a function or method for skipping its doctest.

IPython/utils/tokenize2.py

@@ -1,9 +1,595 b''
-"""Load our patched versions of tokenize.
+"""Patched version of standard library tokenize, to deal with various bugs.
+
+Based on Python 3.2 code.
+
+Patches:
+
+- Gareth Rees' patch for Python issue #12691 (untokenizing)
+  - Except we don't encode the output of untokenize
+  - Python 2 compatible syntax, so that it can be byte-compiled at installation
+- Newlines in comments and blank lines should be either NL or NEWLINE, depending
+  on whether they are in a multi-line statement. Filed as Python issue #17061.
+- Export generate_tokens & TokenError
+- u and rb literals are allowed under Python 3.3 and above.
+
+------------------------------------------------------------------------------
+Tokenization help for Python programs.
+
+tokenize(readline) is a generator that breaks a stream of bytes into
+Python tokens.  It decodes the bytes according to PEP-0263 for
+determining source file encoding.
+
+It accepts a readline-like method which is called repeatedly to get the
+next line of input (or b"" for EOF).  It generates 5-tuples with these
+members:
+
+    the token type (see token.py)
+    the token (a string)
+    the starting (row, column) indices of the token (a 2-tuple of ints)
+    the ending (row, column) indices of the token (a 2-tuple of ints)
+    the original line (string)
+
+It is designed to match the working of the Python tokenizer exactly, except
+that it produces COMMENT tokens for comments and gives type OP for all
+operators.  Additionally, all token lists start with an ENCODING token
+which tells you which encoding was used to decode the bytes stream.
 """
+from __future__ import absolute_import
 
+__author__ = 'Ka-Ping Yee <[e-mail]>'
+__credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, '
+               'Skip Montanaro, Raymond Hettinger, Trent Nelson, '
+               'Michael Foord')
+import builtins
+import re
 import sys
+from token import *
+from codecs import lookup, BOM_UTF8
+import collections
+from io import TextIOWrapper
+cookie_re = re.compile("coding[:=]\s*([-\w.]+)")
+
+import token
+__all__ = token.__all__ + ["COMMENT", "tokenize", "detect_encoding",
+                           "NL", "untokenize", "ENCODING", "TokenInfo"]
+del token
+
+__all__ += ["generate_tokens", "TokenError"]
+
+COMMENT = N_TOKENS
+tok_name[COMMENT] = 'COMMENT'
+NL = N_TOKENS + 1
+tok_name[NL] = 'NL'
+ENCODING = N_TOKENS + 2
+tok_name[ENCODING] = 'ENCODING'
+N_TOKENS += 3
+
+class TokenInfo(collections.namedtuple('TokenInfo', 'type string start end line')):
+    def __repr__(self):
+        annotated_type = '%d (%s)' % (self.type, tok_name[self.type])
+        return ('TokenInfo(type=%s, string=%r, start=%r, end=%r, line=%r)' %
+                self._replace(type=annotated_type))
+
+def group(*choices): return '(' + '|'.join(choices) + ')'
+def any(*choices): return group(*choices) + '*'
+def maybe(*choices): return group(*choices) + '?'
+
+# Note: we use unicode matching for names ("\w") but ascii matching for
+# number literals.
+Whitespace = r'[ \f\t]*'
+Comment = r'#[^\r\n]*'
+Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
+Name = r'\w+'
+
+Hexnumber = r'0[xX][0-9a-fA-F]+'
+Binnumber = r'0[bB][01]+'
+Octnumber = r'0[oO][0-7]+'
+Decnumber = r'(?:0+|[1-9][0-9]*)'
+Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber)
+Exponent = r'[eE][-+]?[0-9]+'
+Pointfloat = group(r'[0-9]+\.[0-9]*', r'\.[0-9]+') + maybe(Exponent)
+Expfloat = r'[0-9]+' + Exponent
+Floatnumber = group(Pointfloat, Expfloat)
+Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]')
+Number = group(Imagnumber, Floatnumber, Intnumber)
+
+if sys.version_info.minor >= 3:
+    StringPrefix = r'(?:[bB][rR]?|[rR][bB]?|[uU])?'
+else:
+    StringPrefix = r'(?:[bB]?[rR]?)?'
+
+# Tail end of ' string.
+Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
+# Tail end of " string.
+Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
+# Tail end of ''' string.
+Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
+# Tail end of """ string.
+Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
+Triple = group(StringPrefix + "'''", StringPrefix + '"""')
+# Single-line ' or " string.
+String = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
+               StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*"')
+
+# Because of leftmost-then-longest match semantics, be sure to put the
+# longest operators first (e.g., if = came before ==, == would get
+# recognized as two instances of =).
+Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"!=",
+                 r"//=?", r"->",
+                 r"[+\-*/%&|^=<>]=?",
+                 r"~")
+
+Bracket = '[][(){}]'
+Special = group(r'\r?\n', r'\.\.\.', r'[:;.,@]')
+Funny = group(Operator, Bracket, Special)
+
+PlainToken = group(Number, Funny, String, Name)
+Token = Ignore + PlainToken
+
+# First (or only) line of ' or " string.
+ContStr = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
+                group("'", r'\\\r?\n'),
+                StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
+                group('"', r'\\\r?\n'))
+PseudoExtras = group(r'\\\r?\n', Comment, Triple)
+PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
+
+def _compile(expr):
+    return re.compile(expr, re.UNICODE)
+
+tokenprog, pseudoprog, single3prog, double3prog = map(
+    _compile, (Token, PseudoToken, Single3, Double3))
+endprogs = {"'": _compile(Single), '"': _compile(Double),
+            "'''": single3prog, '"""': double3prog,
+            "r'''": single3prog, 'r"""': double3prog,
+            "b'''": single3prog, 'b"""': double3prog,
+            "R'''": single3prog, 'R"""': double3prog,
+            "B'''": single3prog, 'B"""': double3prog,
+            "br'''": single3prog, 'br"""': double3prog,
+            "bR'''": single3prog, 'bR"""': double3prog,
+            "Br'''": single3prog, 'Br"""': double3prog,
+            "BR'''": single3prog, 'BR"""': double3prog,
+            'r': None, 'R': None, 'b': None, 'B': None}
+
+triple_quoted = {}
+for t in ("'''", '"""',
+          "r'''", 'r"""', "R'''", 'R"""',
+          "b'''", 'b"""', "B'''", 'B"""',
+          "br'''", 'br"""', "Br'''", 'Br"""',
+          "bR'''", 'bR"""', "BR'''", 'BR"""'):
+    triple_quoted[t] = t
+single_quoted = {}
+for t in ("'", '"',
+          "r'", 'r"', "R'", 'R"',
+          "b'", 'b"', "B'", 'B"',
+          "br'", 'br"', "Br'", 'Br"',
+          "bR'", 'bR"', "BR'", 'BR"' ):
+    single_quoted[t] = t
+
+if sys.version_info.minor >= 3:
+    # Python 3.3
+    for _prefix in ['rb', 'rB', 'Rb', 'RB', 'u', 'U']:
+        _t2 = _prefix+'"""'
+        endprogs[_t2] = double3prog
+        triple_quoted[_t2] = _t2
+        _t1 = _prefix + "'''"
+        endprogs[_t1] = single3prog
+        triple_quoted[_t1] = _t1
+        single_quoted[_prefix+'"'] = _prefix+'"'
+        single_quoted[_prefix+"'"] = _prefix+"'"
+    del _prefix, _t2, _t1
+    endprogs['u'] = None
+    endprogs['U'] = None
+
+del _compile
+
+tabsize = 8
+
+class TokenError(Exception): pass
+
+class StopTokenizing(Exception): pass
+
+
+class Untokenizer:
+
+    def __init__(self):
+        self.tokens = []
+        self.prev_row = 1
+        self.prev_col = 0
+        self.encoding = 'utf-8'
+
+    def add_whitespace(self, tok_type, start):
+        row, col = start
+        assert row >= self.prev_row
+        col_offset = col - self.prev_col
+        if col_offset > 0:
+            self.tokens.append(" " * col_offset)
+        elif row > self.prev_row and tok_type not in (NEWLINE, NL, ENDMARKER):
+            # Line was backslash-continued.
+            self.tokens.append(" ")
+
+    def untokenize(self, tokens):
+        iterable = iter(tokens)
+        for t in iterable:
+            if len(t) == 2:
+                self.compat(t, iterable)
+                break
+            tok_type, token, start, end = t[:4]
+            if tok_type == ENCODING:
+                self.encoding = token
+                continue
+            self.add_whitespace(tok_type, start)
+            self.tokens.append(token)
+            self.prev_row, self.prev_col = end
+            if tok_type in (NEWLINE, NL):
+                self.prev_row += 1
+                self.prev_col = 0
+        return "".join(self.tokens)
+
+    def compat(self, token, iterable):
+        # This import is here to avoid problems when the itertools
+        # module is not built yet and tokenize is imported.
+        from itertools import chain
+        startline = False
+        prevstring = False
+        indents = []
+        toks_append = self.tokens.append
+
+        for tok in chain([token], iterable):
+            toknum, tokval = tok[:2]
+            if toknum == ENCODING:
+                self.encoding = tokval
+                continue
+
+            if toknum in (NAME, NUMBER):
+                tokval += ' '
+
+            # Insert a space between two consecutive strings
+            if toknum == STRING:
+                if prevstring:
+                    tokval = ' ' + tokval
+                prevstring = True
+            else:
+                prevstring = False
+
+            if toknum == INDENT:
+                indents.append(tokval)
+                continue
+            elif toknum == DEDENT:
+                indents.pop()
+                continue
+            elif toknum in (NEWLINE, NL):
+                startline = True
+            elif startline and indents:
+                toks_append(indents[-1])
+                startline = False
+            toks_append(tokval)
+
+
+def untokenize(tokens):
+    """
+    Convert ``tokens`` (an iterable) back into Python source code. Return
+    a bytes object, encoded using the encoding specified by the last
+    ENCODING token in ``tokens``, or UTF-8 if no ENCODING token is found.
+
+    The result is guaranteed to tokenize back to match the input so that
+    the conversion is lossless and round-trips are assured.  The
+    guarantee applies only to the token type and token string as the
+    spacing between tokens (column positions) may change.
+
+    :func:`untokenize` has two modes. If the input tokens are sequences
+    of length 2 (``type``, ``string``) then spaces are added as necessary to
+    preserve the round-trip property.
+
+    If the input tokens are sequences of length 4 or more (``type``,
+    ``string``, ``start``, ``end``), as returned by :func:`tokenize`, then
+    spaces are added so that each token appears in the result at the
+    position indicated by ``start`` and ``end``, if possible.
+    """
+    return Untokenizer().untokenize(tokens)
+
+
+def _get_normal_name(orig_enc):
+    """Imitates get_normal_name in tokenizer.c."""
+    # Only care about the first 12 characters.
+    enc = orig_enc[:12].lower().replace("_", "-")
+    if enc == "utf-8" or enc.startswith("utf-8-"):
+        return "utf-8"
+    if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \
+       enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")):
+        return "iso-8859-1"
+    return orig_enc
+
+def detect_encoding(readline):
+    """
+    The detect_encoding() function is used to detect the encoding that should
+    be used to decode a Python source file.  It requires one argment, readline,
+    in the same way as the tokenize() generator.
+
+    It will call readline a maximum of twice, and return the encoding used
+    (as a string) and a list of any lines (left as bytes) it has read in.
+
+    It detects the encoding from the presence of a utf-8 bom or an encoding
+    cookie as specified in pep-0263.  If both a bom and a cookie are present,
+    but disagree, a SyntaxError will be raised.  If the encoding cookie is an
+    invalid charset, raise a SyntaxError.  Note that if a utf-8 bom is found,
+    'utf-8-sig' is returned.
+
+    If no encoding is specified, then the default of 'utf-8' will be returned.
+    """
+    bom_found = False
+    encoding = None
+    default = 'utf-8'
+    def read_or_stop():
+        try:
+            return readline()
+        except StopIteration:
+            return b''
+
+    def find_cookie(line):
+        try:
+            # Decode as UTF-8. Either the line is an encoding declaration,
+            # in which case it should be pure ASCII, or it must be UTF-8
+            # per default encoding.
+            line_string = line.decode('utf-8')
+        except UnicodeDecodeError:
+            raise SyntaxError("invalid or missing encoding declaration")
+
+        matches = cookie_re.findall(line_string)
+        if not matches:
+            return None
+        encoding = _get_normal_name(matches[0])
+        try:
+            codec = lookup(encoding)
+        except LookupError:
+            # This behaviour mimics the Python interpreter
+            raise SyntaxError("unknown encoding: " + encoding)
+
+        if bom_found:
+            if encoding != 'utf-8':
+                # This behaviour mimics the Python interpreter
+                raise SyntaxError('encoding problem: utf-8')
+            encoding += '-sig'
+        return encoding
+
+    first = read_or_stop()
+    if first.startswith(BOM_UTF8):
+        bom_found = True
+        first = first[3:]
+        default = 'utf-8-sig'
+    if not first:
+        return default, []
+
+    encoding = find_cookie(first)
+    if encoding:
+        return encoding, [first]
+
+    second = read_or_stop()
+    if not second:
+        return default, [first]
+
+    encoding = find_cookie(second)
+    if encoding:
+        return encoding, [first, second]
+
+    return default, [first, second]
+
+
+def open(filename):
+    """Open a file in read only mode using the encoding detected by
+    detect_encoding().
+    """
+    buffer = builtins.open(filename, 'rb')
+    encoding, lines = detect_encoding(buffer.readline)
+    buffer.seek(0)
+    text = TextIOWrapper(buffer, encoding, line_buffering=True)
+    text.mode = 'r'
+    return text
+
+
+def tokenize(readline):
+    """
+    The tokenize() generator requires one argment, readline, which
+    must be a callable object which provides the same interface as the
+    readline() method of built-in file objects.  Each call to the function
+    should return one line of input as bytes.  Alternately, readline
+    can be a callable function terminating with StopIteration:
+        readline = open(myfile, 'rb').__next__  # Example of alternate readline
+
+    The generator produces 5-tuples with these members: the token type; the
+    token string; a 2-tuple (srow, scol) of ints specifying the row and
+    column where the token begins in the source; a 2-tuple (erow, ecol) of
+    ints specifying the row and column where the token ends in the source;
+    and the line on which the token was found.  The line passed is the
+    logical line; continuation lines are included.
 
-if sys.version_info[0] >= 3:
-    from ._tokenize_py3 import *
+    The first token sequence will always be an ENCODING token
+    which tells you which encoding was used to decode the bytes stream.
+    """
+    # This import is here to avoid problems when the itertools module is not
+    # built yet and tokenize is imported.
+    from itertools import chain, repeat
+    encoding, consumed = detect_encoding(readline)
+    rl_gen = iter(readline, b"")
+    empty = repeat(b"")
+    return _tokenize(chain(consumed, rl_gen, empty).__next__, encoding)
+
+
+def _tokenize(readline, encoding):
+    lnum = parenlev = continued = 0
+    numchars = '0123456789'
+    contstr, needcont = '', 0
+    contline = None
+    indents = [0]
+
+    if encoding is not None:
+        if encoding == "utf-8-sig":
+            # BOM will already have been stripped.
+            encoding = "utf-8"
+        yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '')
+    while True:             # loop over lines in stream
+        try:
+            line = readline()
+        except StopIteration:
+            line = b''
+
+        if encoding is not None:
+            line = line.decode(encoding)
+        lnum += 1
+        pos, max = 0, len(line)
+
+        if contstr:                            # continued string
+            if not line:
+                raise TokenError("EOF in multi-line string", strstart)
+            endmatch = endprog.match(line)
+            if endmatch:
+                pos = end = endmatch.end(0)
+                yield TokenInfo(STRING, contstr + line[:end],
+                       strstart, (lnum, end), contline + line)
+                contstr, needcont = '', 0
+                contline = None
+            elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
+                yield TokenInfo(ERRORTOKEN, contstr + line,
+                           strstart, (lnum, len(line)), contline)
+                contstr = ''
+                contline = None
+                continue
+            else:
+                contstr = contstr + line
+                contline = contline + line
+                continue
+
+        elif parenlev == 0 and not continued:  # new statement
+            if not line: break
+            column = 0
+            while pos < max:                   # measure leading whitespace
+                if line[pos] == ' ':
+                    column += 1
+                elif line[pos] == '\t':
+                    column = (column//tabsize + 1)*tabsize
+                elif line[pos] == '\f':
+                    column = 0
+                else:
+                    break
+                pos += 1
+            if pos == max:
+                break
+
+            if line[pos] in '#\r\n':           # skip comments or blank lines
+                if line[pos] == '#':
+                    comment_token = line[pos:].rstrip('\r\n')
+                    nl_pos = pos + len(comment_token)
+                    yield TokenInfo(COMMENT, comment_token,
+                           (lnum, pos), (lnum, pos + len(comment_token)), line)
+                    yield TokenInfo(NEWLINE, line[nl_pos:],
+                           (lnum, nl_pos), (lnum, len(line)), line)
+                else:
+                    yield TokenInfo(NEWLINE, line[pos:],
+                           (lnum, pos), (lnum, len(line)), line)
+                continue
+
+            if column > indents[-1]:           # count indents or dedents
+                indents.append(column)
+                yield TokenInfo(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
+            while column < indents[-1]:
+                if column not in indents:
+                    raise IndentationError(
+                        "unindent does not match any outer indentation level",
+                        ("<tokenize>", lnum, pos, line))
+                indents = indents[:-1]
+                yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line)
+
+        else:                                  # continued statement
+            if not line:
+                raise TokenError("EOF in multi-line statement", (lnum, 0))
+            continued = 0
+
+        while pos < max:
+            pseudomatch = pseudoprog.match(line, pos)
+            if pseudomatch:                                # scan for tokens
+                start, end = pseudomatch.span(1)
+                spos, epos, pos = (lnum, start), (lnum, end), end
+                token, initial = line[start:end], line[start]
+
+                if (initial in numchars or                  # ordinary number
+                    (initial == '.' and token != '.' and token != '...')):
+                    yield TokenInfo(NUMBER, token, spos, epos, line)
+                elif initial in '\r\n':
+                    yield TokenInfo(NL if parenlev > 0 else NEWLINE,
+                           token, spos, epos, line)
+                elif initial == '#':
+                    assert not token.endswith("\n")
+                    yield TokenInfo(COMMENT, token, spos, epos, line)
+                elif token in triple_quoted:
+                    endprog = endprogs[token]
+                    endmatch = endprog.match(line, pos)
+                    if endmatch:                           # all on one line
+                        pos = endmatch.end(0)
+                        token = line[start:pos]
+                        yield TokenInfo(STRING, token, spos, (lnum, pos), line)
+                    else:
+                        strstart = (lnum, start)           # multiple lines
+                        contstr = line[start:]
+                        contline = line
+                        break
+                elif initial in single_quoted or \
+                    token[:2] in single_quoted or \
+                    token[:3] in single_quoted:
+                    if token[-1] == '\n':                  # continued string
+                        strstart = (lnum, start)
+                        endprog = (endprogs[initial] or endprogs[token[1]] or
+                                   endprogs[token[2]])
+                        contstr, needcont = line[start:], 1
+                        contline = line
+                        break
+                    else:                                  # ordinary string
+                        yield TokenInfo(STRING, token, spos, epos, line)
+                elif initial.isidentifier():               # ordinary name
+                    yield TokenInfo(NAME, token, spos, epos, line)
+                elif initial == '\\':                      # continued stmt
+                    continued = 1
+                else:
+                    if initial in '([{':
+                        parenlev += 1
+                    elif initial in ')]}':
+                        parenlev -= 1
+                    yield TokenInfo(OP, token, spos, epos, line)
+            else:
+                yield TokenInfo(ERRORTOKEN, line[pos],
+                           (lnum, pos), (lnum, pos+1), line)
+                pos += 1
+
+    for indent in indents[1:]:                 # pop remaining indent levels
+        yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '')
+    yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '')
+
+
+# An undocumented, backwards compatible, API for all the places in the standard
+# library that expect to be able to use tokenize with strings
+def generate_tokens(readline):
+    return _tokenize(readline, None)
+
+if __name__ == "__main__":
+    # Quick sanity check
+    s = b'''def parseline(self, line):
+            """Parse the line into a command name and a string containing
+            the arguments.  Returns a tuple containing (command, args, line).
+            'command' and 'args' may be None if the line couldn't be parsed.
+            """
+            line = line.strip()
+            if not line:
+                return None, None, line
+            elif line[0] == '?':
+                line = 'help ' + line[1:]
+            elif line[0] == '!':
+                if hasattr(self, 'do_shell'):
+                    line = 'shell ' + line[1:]
 else:
-    from ._tokenize_py2 import *
+                    return None, None, line
+            i, n = 0, len(line)
+            while i < n and line[i] in self.identchars: i = i+1
+            cmd, arg = line[:i], line[i:].strip()
+            return cmd, arg, line
+    '''
+    for tok in tokenize(iter(s.splitlines()).__next__):
+        print(tok)

setup.py

@@ -41,8 +41,6 b' See IPython `README.rst` file for more information:'
     print(error, file=sys.stderr)
     sys.exit(1)
 
-PY3 = (sys.version_info[0] >= 3)
-
 # At least we're on the python version we need, move on.
 
 #-------------------------------------------------------------------------------

tools/github_stats.py

@@ -114,9 +114,6 b' if __name__ == "__main__":'
     print("DEPRECATE: backport_pr.py is deprecated and is is now recommended"
           "to install `ghpro` from PyPI.", file=sys.stderr)
 
-    # deal with unicode
-    if sys.version_info < (3,):
-        sys.stdout = codecs.getwriter('utf8')(sys.stdout)
     
     # Whether to add reST urls for all issues in printout.
     show_urls = True

IPython/utils/_tokenize_py2.py

@@ -1,439 +0,0 b''
-"""Patched version of standard library tokenize, to deal with various bugs.
-
-Patches
-
-- Relevant parts of Gareth Rees' patch for Python issue #12691 (untokenizing),
-  manually applied.
-- Newlines in comments and blank lines should be either NL or NEWLINE, depending
-  on whether they are in a multi-line statement. Filed as Python issue #17061.
-
--------------------------------------------------------------------------------
-Tokenization help for Python programs.
-
-generate_tokens(readline) is a generator that breaks a stream of
-text into Python tokens.  It accepts a readline-like method which is called
-repeatedly to get the next line of input (or "" for EOF).  It generates
-5-tuples with these members:
-
-    the token type (see token.py)
-    the token (a string)
-    the starting (row, column) indices of the token (a 2-tuple of ints)
-    the ending (row, column) indices of the token (a 2-tuple of ints)
-    the original line (string)
-
-It is designed to match the working of the Python tokenizer exactly, except
-that it produces COMMENT tokens for comments and gives type OP for all
-operators
-
-Older entry points
-    tokenize_loop(readline, tokeneater)
-    tokenize(readline, tokeneater=printtoken)
-are the same, except instead of generating tokens, tokeneater is a callback
-function to which the 5 fields described above are passed as 5 arguments,
-each time a new token is found."""
-from __future__ import print_function
-
-__author__ = 'Ka-Ping Yee <[e-mail]>'
-__credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, '
-               'Skip Montanaro, Raymond Hettinger')
-
-import string, re
-from token import *
-
-import token
-__all__ = [x for x in dir(token) if not x.startswith("_")]
-__all__ += ["COMMENT", "tokenize", "generate_tokens", "NL", "untokenize"]
-del x
-del token
-
-__all__ += ["TokenError"]
-
-COMMENT = N_TOKENS
-tok_name[COMMENT] = 'COMMENT'
-NL = N_TOKENS + 1
-tok_name[NL] = 'NL'
-N_TOKENS += 2
-
-def group(*choices): return '(' + '|'.join(choices) + ')'
-def any(*choices): return group(*choices) + '*'
-def maybe(*choices): return group(*choices) + '?'
-
-Whitespace = r'[ \f\t]*'
-Comment = r'#[^\r\n]*'
-Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
-Name = r'[a-zA-Z_]\w*'
-
-Hexnumber = r'0[xX][\da-fA-F]+[lL]?'
-Octnumber = r'(0[oO][0-7]+)|(0[0-7]*)[lL]?'
-Binnumber = r'0[bB][01]+[lL]?'
-Decnumber = r'[1-9]\d*[lL]?'
-Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber)
-Exponent = r'[eE][-+]?\d+'
-Pointfloat = group(r'\d+\.\d*', r'\.\d+') + maybe(Exponent)
-Expfloat = r'\d+' + Exponent
-Floatnumber = group(Pointfloat, Expfloat)
-Imagnumber = group(r'\d+[jJ]', Floatnumber + r'[jJ]')
-Number = group(Imagnumber, Floatnumber, Intnumber)
-
-# Tail end of ' string.
-Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
-# Tail end of " string.
-Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
-# Tail end of ''' string.
-Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
-# Tail end of """ string.
-Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
-Triple = group("[uUbB]?[rR]?'''", '[uUbB]?[rR]?"""')
-# Single-line ' or " string.
-String = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
-               r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*"')
-
-# Because of leftmost-then-longest match semantics, be sure to put the
-# longest operators first (e.g., if = came before ==, == would get
-# recognized as two instances of =).
-Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"<>", r"!=",
-                 r"//=?",
-                 r"[+\-*/%&|^=<>]=?",
-                 r"~")
-
-Bracket = '[][(){}]'
-Special = group(r'\r?\n', r'[:;.,`@]')
-Funny = group(Operator, Bracket, Special)
-
-PlainToken = group(Number, Funny, String, Name)
-Token = Ignore + PlainToken
-
-# First (or only) line of ' or " string.
-ContStr = group(r"[uUbB]?[rR]?'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
-                group("'", r'\\\r?\n'),
-                r'[uUbB]?[rR]?"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
-                group('"', r'\\\r?\n'))
-PseudoExtras = group(r'\\\r?\n', Comment, Triple)
-PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
-
-tokenprog, pseudoprog, single3prog, double3prog = map(
-    re.compile, (Token, PseudoToken, Single3, Double3))
-endprogs = {"'": re.compile(Single), '"': re.compile(Double),
-            "'''": single3prog, '"""': double3prog,
-            "r'''": single3prog, 'r"""': double3prog,
-            "u'''": single3prog, 'u"""': double3prog,
-            "ur'''": single3prog, 'ur"""': double3prog,
-            "R'''": single3prog, 'R"""': double3prog,
-            "U'''": single3prog, 'U"""': double3prog,
-            "uR'''": single3prog, 'uR"""': double3prog,
-            "Ur'''": single3prog, 'Ur"""': double3prog,
-            "UR'''": single3prog, 'UR"""': double3prog,
-            "b'''": single3prog, 'b"""': double3prog,
-            "br'''": single3prog, 'br"""': double3prog,
-            "B'''": single3prog, 'B"""': double3prog,
-            "bR'''": single3prog, 'bR"""': double3prog,
-            "Br'''": single3prog, 'Br"""': double3prog,
-            "BR'''": single3prog, 'BR"""': double3prog,
-            'r': None, 'R': None, 'u': None, 'U': None,
-            'b': None, 'B': None}
-
-triple_quoted = {}
-for t in ("'''", '"""',
-          "r'''", 'r"""', "R'''", 'R"""',
-          "u'''", 'u"""', "U'''", 'U"""',
-          "ur'''", 'ur"""', "Ur'''", 'Ur"""',
-          "uR'''", 'uR"""', "UR'''", 'UR"""',
-          "b'''", 'b"""', "B'''", 'B"""',
-          "br'''", 'br"""', "Br'''", 'Br"""',
-          "bR'''", 'bR"""', "BR'''", 'BR"""'):
-    triple_quoted[t] = t
-single_quoted = {}
-for t in ("'", '"',
-          "r'", 'r"', "R'", 'R"',
-          "u'", 'u"', "U'", 'U"',
-          "ur'", 'ur"', "Ur'", 'Ur"',
-          "uR'", 'uR"', "UR'", 'UR"',
-          "b'", 'b"', "B'", 'B"',
-          "br'", 'br"', "Br'", 'Br"',
-          "bR'", 'bR"', "BR'", 'BR"' ):
-    single_quoted[t] = t
-
-tabsize = 8
-
-class TokenError(Exception): pass
-
-class StopTokenizing(Exception): pass
-
-def printtoken(type, token, srow_scol, erow_ecol, line): # for testing
-    srow, scol = srow_scol
-    erow, ecol = erow_ecol
-    print("%d,%d-%d,%d:\t%s\t%s" % \
-        (srow, scol, erow, ecol, tok_name[type], repr(token)))
-
-def tokenize(readline, tokeneater=printtoken):
-    """
-    The tokenize() function accepts two parameters: one representing the
-    input stream, and one providing an output mechanism for tokenize().
-
-    The first parameter, readline, must be a callable object which provides
-    the same interface as the readline() method of built-in file objects.
-    Each call to the function should return one line of input as a string.
-
-    The second parameter, tokeneater, must also be a callable object. It is
-    called once for each token, with five arguments, corresponding to the
-    tuples generated by generate_tokens().
-    """
-    try:
-        tokenize_loop(readline, tokeneater)
-    except StopTokenizing:
-        pass
-
-# backwards compatible interface
-def tokenize_loop(readline, tokeneater):
-    for token_info in generate_tokens(readline):
-        tokeneater(*token_info)
-
-class Untokenizer:
-
-    def __init__(self):
-        self.tokens = []
-        self.prev_row = 1
-        self.prev_col = 0
-
-    def add_whitespace(self, start):
-        row, col = start
-        assert row >= self.prev_row
-        col_offset = col - self.prev_col
-        if col_offset > 0:
-            self.tokens.append(" " * col_offset)
-        elif row > self.prev_row and tok_type not in (NEWLINE, NL, ENDMARKER):
-            # Line was backslash-continued
-            self.tokens.append(" ")
-
-    def untokenize(self, tokens):
-        iterable = iter(tokens)
-        for t in iterable:
-            if len(t) == 2:
-                self.compat(t, iterable)
-                break
-            tok_type, token, start, end = t[:4]
-            self.add_whitespace(start)
-            self.tokens.append(token)
-            self.prev_row, self.prev_col = end
-            if tok_type in (NEWLINE, NL):
-                self.prev_row += 1
-                self.prev_col = 0
-        return "".join(self.tokens)
-
-    def compat(self, token, iterable):
-        # This import is here to avoid problems when the itertools
-        # module is not built yet and tokenize is imported.
-        from itertools import chain
-        startline = False
-        prevstring = False
-        indents = []
-        toks_append = self.tokens.append
-        for tok in chain([token], iterable):
-            toknum, tokval = tok[:2]
-
-            if toknum in (NAME, NUMBER):
-                tokval += ' '
-
-            # Insert a space between two consecutive strings
-            if toknum == STRING:
-                if prevstring:
-                    tokval = ' ' + tokval
-                prevstring = True
-            else:
-                prevstring = False
-
-            if toknum == INDENT:
-                indents.append(tokval)
-                continue
-            elif toknum == DEDENT:
-                indents.pop()
-                continue
-            elif toknum in (NEWLINE, NL):
-                startline = True
-            elif startline and indents:
-                toks_append(indents[-1])
-                startline = False
-            toks_append(tokval)
-
-def untokenize(iterable):
-    """Transform tokens back into Python source code.
-
-    Each element returned by the iterable must be a token sequence
-    with at least two elements, a token number and token value.  If
-    only two tokens are passed, the resulting output is poor.
-
-    Round-trip invariant for full input:
-        Untokenized source will match input source exactly
-
-    Round-trip invariant for limited intput:
-        # Output text will tokenize the back to the input
-        t1 = [tok[:2] for tok in generate_tokens(f.readline)]
-        newcode = untokenize(t1)
-        readline = iter(newcode.splitlines(1)).next
-        t2 = [tok[:2] for tok in generate_tokens(readline)]
-        assert t1 == t2
-    """
-    ut = Untokenizer()
-    return ut.untokenize(iterable)
-
-def generate_tokens(readline):
-    """
-    The generate_tokens() generator requires one argment, readline, which
-    must be a callable object which provides the same interface as the
-    readline() method of built-in file objects. Each call to the function
-    should return one line of input as a string.  Alternately, readline
-    can be a callable function terminating with StopIteration:
-        readline = open(myfile).next    # Example of alternate readline
-
-    The generator produces 5-tuples with these members: the token type; the
-    token string; a 2-tuple (srow, scol) of ints specifying the row and
-    column where the token begins in the source; a 2-tuple (erow, ecol) of
-    ints specifying the row and column where the token ends in the source;
-    and the line on which the token was found. The line passed is the
-    logical line; continuation lines are included.
-    """
-    lnum = parenlev = continued = 0
-    namechars, numchars = string.ascii_letters + '_', '0123456789'
-    contstr, needcont = '', 0
-    contline = None
-    indents = [0]
-
-    while 1:                                   # loop over lines in stream
-        try:
-            line = readline()
-        except StopIteration:
-            line = ''
-        lnum += 1
-        pos, max = 0, len(line)
-
-        if contstr:                            # continued string
-            if not line:
-                raise TokenError("EOF in multi-line string", strstart)
-            endmatch = endprog.match(line)
-            if endmatch:
-                pos = end = endmatch.end(0)
-                yield (STRING, contstr + line[:end],
-                       strstart, (lnum, end), contline + line)
-                contstr, needcont = '', 0
-                contline = None
-            elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
-                yield (ERRORTOKEN, contstr + line,
-                           strstart, (lnum, len(line)), contline)
-                contstr = ''
-                contline = None
-                continue
-            else:
-                contstr = contstr + line
-                contline = contline + line
-                continue
-
-        elif parenlev == 0 and not continued:  # new statement
-            if not line: break
-            column = 0
-            while pos < max:                   # measure leading whitespace
-                if line[pos] == ' ':
-                    column += 1
-                elif line[pos] == '\t':
-                    column = (column//tabsize + 1)*tabsize
-                elif line[pos] == '\f':
-                    column = 0
-                else:
-                    break
-                pos += 1
-            if pos == max:
-                break
-
-            if line[pos] in '#\r\n':           # skip comments or blank lines
-                if line[pos] == '#':
-                    comment_token = line[pos:].rstrip('\r\n')
-                    nl_pos = pos + len(comment_token)
-                    yield (COMMENT, comment_token,
-                           (lnum, pos), (lnum, pos + len(comment_token)), line)
-                    yield (NEWLINE, line[nl_pos:],
-                           (lnum, nl_pos), (lnum, len(line)), line)
-                else:
-                    yield (NEWLINE, line[pos:],
-                           (lnum, pos), (lnum, len(line)), line)
-                continue
-
-            if column > indents[-1]:           # count indents or dedents
-                indents.append(column)
-                yield (INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
-            while column < indents[-1]:
-                if column not in indents:
-                    raise IndentationError(
-                        "unindent does not match any outer indentation level",
-                        ("<tokenize>", lnum, pos, line))
-                indents = indents[:-1]
-                yield (DEDENT, '', (lnum, pos), (lnum, pos), line)
-
-        else:                                  # continued statement
-            if not line:
-                raise TokenError("EOF in multi-line statement", (lnum, 0))
-            continued = 0
-
-        while pos < max:
-            pseudomatch = pseudoprog.match(line, pos)
-            if pseudomatch:                                # scan for tokens
-                start, end = pseudomatch.span(1)
-                spos, epos, pos = (lnum, start), (lnum, end), end
-                token, initial = line[start:end], line[start]
-
-                if initial in numchars or \
-                   (initial == '.' and token != '.'):      # ordinary number
-                    yield (NUMBER, token, spos, epos, line)
-                elif initial in '\r\n':
-                    yield (NL if parenlev > 0 else NEWLINE,
-                           token, spos, epos, line)
-                elif initial == '#':
-                    assert not token.endswith("\n")
-                    yield (COMMENT, token, spos, epos, line)
-                elif token in triple_quoted:
-                    endprog = endprogs[token]
-                    endmatch = endprog.match(line, pos)
-                    if endmatch:                           # all on one line
-                        pos = endmatch.end(0)
-                        token = line[start:pos]
-                        yield (STRING, token, spos, (lnum, pos), line)
-                    else:
-                        strstart = (lnum, start)           # multiple lines
-                        contstr = line[start:]
-                        contline = line
-                        break
-                elif initial in single_quoted or \
-                    token[:2] in single_quoted or \
-                    token[:3] in single_quoted:
-                    if token[-1] == '\n':                  # continued string
-                        strstart = (lnum, start)
-                        endprog = (endprogs[initial] or endprogs[token[1]] or
-                                   endprogs[token[2]])
-                        contstr, needcont = line[start:], 1
-                        contline = line
-                        break
-                    else:                                  # ordinary string
-                        yield (STRING, token, spos, epos, line)
-                elif initial in namechars:                 # ordinary name
-                    yield (NAME, token, spos, epos, line)
-                elif initial == '\\':                      # continued stmt
-                    continued = 1
-                else:
-                    if initial in '([{':
-                        parenlev += 1
-                    elif initial in ')]}':
-                        parenlev -= 1
-                    yield (OP, token, spos, epos, line)
-            else:
-                yield (ERRORTOKEN, line[pos],
-                           (lnum, pos), (lnum, pos+1), line)
-                pos += 1
-
-    for indent in indents[1:]:                 # pop remaining indent levels
-        yield (DEDENT, '', (lnum, 0), (lnum, 0), '')
-    yield (ENDMARKER, '', (lnum, 0), (lnum, 0), '')
-
-if __name__ == '__main__':                     # testing
-    import sys
-    if len(sys.argv) > 1:
-        tokenize(open(sys.argv[1]).readline)
-    else:
-        tokenize(sys.stdin.readline)

IPython/utils/_tokenize_py3.py

@@ -1,595 +0,0 b''
-"""Patched version of standard library tokenize, to deal with various bugs.
-
-Based on Python 3.2 code.
-
-Patches:
-
-- Gareth Rees' patch for Python issue #12691 (untokenizing)
-  - Except we don't encode the output of untokenize
-  - Python 2 compatible syntax, so that it can be byte-compiled at installation
-- Newlines in comments and blank lines should be either NL or NEWLINE, depending
-  on whether they are in a multi-line statement. Filed as Python issue #17061.
-- Export generate_tokens & TokenError
-- u and rb literals are allowed under Python 3.3 and above.
-
-------------------------------------------------------------------------------
-Tokenization help for Python programs.
-
-tokenize(readline) is a generator that breaks a stream of bytes into
-Python tokens.  It decodes the bytes according to PEP-0263 for
-determining source file encoding.
-
-It accepts a readline-like method which is called repeatedly to get the
-next line of input (or b"" for EOF).  It generates 5-tuples with these
-members:
-
-    the token type (see token.py)
-    the token (a string)
-    the starting (row, column) indices of the token (a 2-tuple of ints)
-    the ending (row, column) indices of the token (a 2-tuple of ints)
-    the original line (string)
-
-It is designed to match the working of the Python tokenizer exactly, except
-that it produces COMMENT tokens for comments and gives type OP for all
-operators.  Additionally, all token lists start with an ENCODING token
-which tells you which encoding was used to decode the bytes stream.
-"""
-from __future__ import absolute_import
-
-__author__ = 'Ka-Ping Yee <[e-mail]>'
-__credits__ = ('GvR, ESR, Tim Peters, Thomas Wouters, Fred Drake, '
-               'Skip Montanaro, Raymond Hettinger, Trent Nelson, '
-               'Michael Foord')
-import builtins
-import re
-import sys
-from token import *
-from codecs import lookup, BOM_UTF8
-import collections
-from io import TextIOWrapper
-cookie_re = re.compile("coding[:=]\s*([-\w.]+)")
-
-import token
-__all__ = token.__all__ + ["COMMENT", "tokenize", "detect_encoding",
-                           "NL", "untokenize", "ENCODING", "TokenInfo"]
-del token
-
-__all__ += ["generate_tokens", "TokenError"]
-
-COMMENT = N_TOKENS
-tok_name[COMMENT] = 'COMMENT'
-NL = N_TOKENS + 1
-tok_name[NL] = 'NL'
-ENCODING = N_TOKENS + 2
-tok_name[ENCODING] = 'ENCODING'
-N_TOKENS += 3
-
-class TokenInfo(collections.namedtuple('TokenInfo', 'type string start end line')):
-    def __repr__(self):
-        annotated_type = '%d (%s)' % (self.type, tok_name[self.type])
-        return ('TokenInfo(type=%s, string=%r, start=%r, end=%r, line=%r)' %
-                self._replace(type=annotated_type))
-
-def group(*choices): return '(' + '|'.join(choices) + ')'
-def any(*choices): return group(*choices) + '*'
-def maybe(*choices): return group(*choices) + '?'
-
-# Note: we use unicode matching for names ("\w") but ascii matching for
-# number literals.
-Whitespace = r'[ \f\t]*'
-Comment = r'#[^\r\n]*'
-Ignore = Whitespace + any(r'\\\r?\n' + Whitespace) + maybe(Comment)
-Name = r'\w+'
-
-Hexnumber = r'0[xX][0-9a-fA-F]+'
-Binnumber = r'0[bB][01]+'
-Octnumber = r'0[oO][0-7]+'
-Decnumber = r'(?:0+|[1-9][0-9]*)'
-Intnumber = group(Hexnumber, Binnumber, Octnumber, Decnumber)
-Exponent = r'[eE][-+]?[0-9]+'
-Pointfloat = group(r'[0-9]+\.[0-9]*', r'\.[0-9]+') + maybe(Exponent)
-Expfloat = r'[0-9]+' + Exponent
-Floatnumber = group(Pointfloat, Expfloat)
-Imagnumber = group(r'[0-9]+[jJ]', Floatnumber + r'[jJ]')
-Number = group(Imagnumber, Floatnumber, Intnumber)
-
-if sys.version_info.minor >= 3:
-    StringPrefix = r'(?:[bB][rR]?|[rR][bB]?|[uU])?'
-else:
-    StringPrefix = r'(?:[bB]?[rR]?)?'
-
-# Tail end of ' string.
-Single = r"[^'\\]*(?:\\.[^'\\]*)*'"
-# Tail end of " string.
-Double = r'[^"\\]*(?:\\.[^"\\]*)*"'
-# Tail end of ''' string.
-Single3 = r"[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*'''"
-# Tail end of """ string.
-Double3 = r'[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*"""'
-Triple = group(StringPrefix + "'''", StringPrefix + '"""')
-# Single-line ' or " string.
-String = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*'",
-               StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*"')
-
-# Because of leftmost-then-longest match semantics, be sure to put the
-# longest operators first (e.g., if = came before ==, == would get
-# recognized as two instances of =).
-Operator = group(r"\*\*=?", r">>=?", r"<<=?", r"!=",
-                 r"//=?", r"->",
-                 r"[+\-*/%&|^=<>]=?",
-                 r"~")
-
-Bracket = '[][(){}]'
-Special = group(r'\r?\n', r'\.\.\.', r'[:;.,@]')
-Funny = group(Operator, Bracket, Special)
-
-PlainToken = group(Number, Funny, String, Name)
-Token = Ignore + PlainToken
-
-# First (or only) line of ' or " string.
-ContStr = group(StringPrefix + r"'[^\n'\\]*(?:\\.[^\n'\\]*)*" +
-                group("'", r'\\\r?\n'),
-                StringPrefix + r'"[^\n"\\]*(?:\\.[^\n"\\]*)*' +
-                group('"', r'\\\r?\n'))
-PseudoExtras = group(r'\\\r?\n', Comment, Triple)
-PseudoToken = Whitespace + group(PseudoExtras, Number, Funny, ContStr, Name)
-
-def _compile(expr):
-    return re.compile(expr, re.UNICODE)
-
-tokenprog, pseudoprog, single3prog, double3prog = map(
-    _compile, (Token, PseudoToken, Single3, Double3))
-endprogs = {"'": _compile(Single), '"': _compile(Double),
-            "'''": single3prog, '"""': double3prog,
-            "r'''": single3prog, 'r"""': double3prog,
-            "b'''": single3prog, 'b"""': double3prog,
-            "R'''": single3prog, 'R"""': double3prog,
-            "B'''": single3prog, 'B"""': double3prog,
-            "br'''": single3prog, 'br"""': double3prog,
-            "bR'''": single3prog, 'bR"""': double3prog,
-            "Br'''": single3prog, 'Br"""': double3prog,
-            "BR'''": single3prog, 'BR"""': double3prog,
-            'r': None, 'R': None, 'b': None, 'B': None}
-
-triple_quoted = {}
-for t in ("'''", '"""',
-          "r'''", 'r"""', "R'''", 'R"""',
-          "b'''", 'b"""', "B'''", 'B"""',
-          "br'''", 'br"""', "Br'''", 'Br"""',
-          "bR'''", 'bR"""', "BR'''", 'BR"""'):
-    triple_quoted[t] = t
-single_quoted = {}
-for t in ("'", '"',
-          "r'", 'r"', "R'", 'R"',
-          "b'", 'b"', "B'", 'B"',
-          "br'", 'br"', "Br'", 'Br"',
-          "bR'", 'bR"', "BR'", 'BR"' ):
-    single_quoted[t] = t
-
-if sys.version_info.minor >= 3:
-    # Python 3.3
-    for _prefix in ['rb', 'rB', 'Rb', 'RB', 'u', 'U']:
-        _t2 = _prefix+'"""'
-        endprogs[_t2] = double3prog
-        triple_quoted[_t2] = _t2
-        _t1 = _prefix + "'''"
-        endprogs[_t1] = single3prog
-        triple_quoted[_t1] = _t1
-        single_quoted[_prefix+'"'] = _prefix+'"'
-        single_quoted[_prefix+"'"] = _prefix+"'"
-    del _prefix, _t2, _t1
-    endprogs['u'] = None
-    endprogs['U'] = None
-
-del _compile
-
-tabsize = 8
-
-class TokenError(Exception): pass
-
-class StopTokenizing(Exception): pass
-
-
-class Untokenizer:
-
-    def __init__(self):
-        self.tokens = []
-        self.prev_row = 1
-        self.prev_col = 0
-        self.encoding = 'utf-8'
-
-    def add_whitespace(self, tok_type, start):
-        row, col = start
-        assert row >= self.prev_row
-        col_offset = col - self.prev_col
-        if col_offset > 0:
-            self.tokens.append(" " * col_offset)
-        elif row > self.prev_row and tok_type not in (NEWLINE, NL, ENDMARKER):
-            # Line was backslash-continued.
-            self.tokens.append(" ")
-
-    def untokenize(self, tokens):
-        iterable = iter(tokens)
-        for t in iterable:
-            if len(t) == 2:
-                self.compat(t, iterable)
-                break
-            tok_type, token, start, end = t[:4]
-            if tok_type == ENCODING:
-                self.encoding = token
-                continue
-            self.add_whitespace(tok_type, start)
-            self.tokens.append(token)
-            self.prev_row, self.prev_col = end
-            if tok_type in (NEWLINE, NL):
-                self.prev_row += 1
-                self.prev_col = 0
-        return "".join(self.tokens)
-
-    def compat(self, token, iterable):
-        # This import is here to avoid problems when the itertools
-        # module is not built yet and tokenize is imported.
-        from itertools import chain
-        startline = False
-        prevstring = False
-        indents = []
-        toks_append = self.tokens.append
-
-        for tok in chain([token], iterable):
-            toknum, tokval = tok[:2]
-            if toknum == ENCODING:
-                self.encoding = tokval
-                continue
-
-            if toknum in (NAME, NUMBER):
-                tokval += ' '
-
-            # Insert a space between two consecutive strings
-            if toknum == STRING:
-                if prevstring:
-                    tokval = ' ' + tokval
-                prevstring = True
-            else:
-                prevstring = False
-
-            if toknum == INDENT:
-                indents.append(tokval)
-                continue
-            elif toknum == DEDENT:
-                indents.pop()
-                continue
-            elif toknum in (NEWLINE, NL):
-                startline = True
-            elif startline and indents:
-                toks_append(indents[-1])
-                startline = False
-            toks_append(tokval)
-
-
-def untokenize(tokens):
-    """
-    Convert ``tokens`` (an iterable) back into Python source code. Return
-    a bytes object, encoded using the encoding specified by the last
-    ENCODING token in ``tokens``, or UTF-8 if no ENCODING token is found.
-
-    The result is guaranteed to tokenize back to match the input so that
-    the conversion is lossless and round-trips are assured.  The
-    guarantee applies only to the token type and token string as the
-    spacing between tokens (column positions) may change.
-
-    :func:`untokenize` has two modes. If the input tokens are sequences
-    of length 2 (``type``, ``string``) then spaces are added as necessary to
-    preserve the round-trip property.
-
-    If the input tokens are sequences of length 4 or more (``type``,
-    ``string``, ``start``, ``end``), as returned by :func:`tokenize`, then
-    spaces are added so that each token appears in the result at the
-    position indicated by ``start`` and ``end``, if possible.
-    """
-    return Untokenizer().untokenize(tokens)
-
-
-def _get_normal_name(orig_enc):
-    """Imitates get_normal_name in tokenizer.c."""
-    # Only care about the first 12 characters.
-    enc = orig_enc[:12].lower().replace("_", "-")
-    if enc == "utf-8" or enc.startswith("utf-8-"):
-        return "utf-8"
-    if enc in ("latin-1", "iso-8859-1", "iso-latin-1") or \
-       enc.startswith(("latin-1-", "iso-8859-1-", "iso-latin-1-")):
-        return "iso-8859-1"
-    return orig_enc
-
-def detect_encoding(readline):
-    """
-    The detect_encoding() function is used to detect the encoding that should
-    be used to decode a Python source file.  It requires one argment, readline,
-    in the same way as the tokenize() generator.
-
-    It will call readline a maximum of twice, and return the encoding used
-    (as a string) and a list of any lines (left as bytes) it has read in.
-
-    It detects the encoding from the presence of a utf-8 bom or an encoding
-    cookie as specified in pep-0263.  If both a bom and a cookie are present,
-    but disagree, a SyntaxError will be raised.  If the encoding cookie is an
-    invalid charset, raise a SyntaxError.  Note that if a utf-8 bom is found,
-    'utf-8-sig' is returned.
-
-    If no encoding is specified, then the default of 'utf-8' will be returned.
-    """
-    bom_found = False
-    encoding = None
-    default = 'utf-8'
-    def read_or_stop():
-        try:
-            return readline()
-        except StopIteration:
-            return b''
-
-    def find_cookie(line):
-        try:
-            # Decode as UTF-8. Either the line is an encoding declaration,
-            # in which case it should be pure ASCII, or it must be UTF-8
-            # per default encoding.
-            line_string = line.decode('utf-8')
-        except UnicodeDecodeError:
-            raise SyntaxError("invalid or missing encoding declaration")
-
-        matches = cookie_re.findall(line_string)
-        if not matches:
-            return None
-        encoding = _get_normal_name(matches[0])
-        try:
-            codec = lookup(encoding)
-        except LookupError:
-            # This behaviour mimics the Python interpreter
-            raise SyntaxError("unknown encoding: " + encoding)
-
-        if bom_found:
-            if encoding != 'utf-8':
-                # This behaviour mimics the Python interpreter
-                raise SyntaxError('encoding problem: utf-8')
-            encoding += '-sig'
-        return encoding
-
-    first = read_or_stop()
-    if first.startswith(BOM_UTF8):
-        bom_found = True
-        first = first[3:]
-        default = 'utf-8-sig'
-    if not first:
-        return default, []
-
-    encoding = find_cookie(first)
-    if encoding:
-        return encoding, [first]
-
-    second = read_or_stop()
-    if not second:
-        return default, [first]
-
-    encoding = find_cookie(second)
-    if encoding:
-        return encoding, [first, second]
-
-    return default, [first, second]
-
-
-def open(filename):
-    """Open a file in read only mode using the encoding detected by
-    detect_encoding().
-    """
-    buffer = builtins.open(filename, 'rb')
-    encoding, lines = detect_encoding(buffer.readline)
-    buffer.seek(0)
-    text = TextIOWrapper(buffer, encoding, line_buffering=True)
-    text.mode = 'r'
-    return text
-
-
-def tokenize(readline):
-    """
-    The tokenize() generator requires one argment, readline, which
-    must be a callable object which provides the same interface as the
-    readline() method of built-in file objects.  Each call to the function
-    should return one line of input as bytes.  Alternately, readline
-    can be a callable function terminating with StopIteration:
-        readline = open(myfile, 'rb').__next__  # Example of alternate readline
-
-    The generator produces 5-tuples with these members: the token type; the
-    token string; a 2-tuple (srow, scol) of ints specifying the row and
-    column where the token begins in the source; a 2-tuple (erow, ecol) of
-    ints specifying the row and column where the token ends in the source;
-    and the line on which the token was found.  The line passed is the
-    logical line; continuation lines are included.
-
-    The first token sequence will always be an ENCODING token
-    which tells you which encoding was used to decode the bytes stream.
-    """
-    # This import is here to avoid problems when the itertools module is not
-    # built yet and tokenize is imported.
-    from itertools import chain, repeat
-    encoding, consumed = detect_encoding(readline)
-    rl_gen = iter(readline, b"")
-    empty = repeat(b"")
-    return _tokenize(chain(consumed, rl_gen, empty).__next__, encoding)
-
-
-def _tokenize(readline, encoding):
-    lnum = parenlev = continued = 0
-    numchars = '0123456789'
-    contstr, needcont = '', 0
-    contline = None
-    indents = [0]
-
-    if encoding is not None:
-        if encoding == "utf-8-sig":
-            # BOM will already have been stripped.
-            encoding = "utf-8"
-        yield TokenInfo(ENCODING, encoding, (0, 0), (0, 0), '')
-    while True:             # loop over lines in stream
-        try:
-            line = readline()
-        except StopIteration:
-            line = b''
-
-        if encoding is not None:
-            line = line.decode(encoding)
-        lnum += 1
-        pos, max = 0, len(line)
-
-        if contstr:                            # continued string
-            if not line:
-                raise TokenError("EOF in multi-line string", strstart)
-            endmatch = endprog.match(line)
-            if endmatch:
-                pos = end = endmatch.end(0)
-                yield TokenInfo(STRING, contstr + line[:end],
-                       strstart, (lnum, end), contline + line)
-                contstr, needcont = '', 0
-                contline = None
-            elif needcont and line[-2:] != '\\\n' and line[-3:] != '\\\r\n':
-                yield TokenInfo(ERRORTOKEN, contstr + line,
-                           strstart, (lnum, len(line)), contline)
-                contstr = ''
-                contline = None
-                continue
-            else:
-                contstr = contstr + line
-                contline = contline + line
-                continue
-
-        elif parenlev == 0 and not continued:  # new statement
-            if not line: break
-            column = 0
-            while pos < max:                   # measure leading whitespace
-                if line[pos] == ' ':
-                    column += 1
-                elif line[pos] == '\t':
-                    column = (column//tabsize + 1)*tabsize
-                elif line[pos] == '\f':
-                    column = 0
-                else:
-                    break
-                pos += 1
-            if pos == max:
-                break
-
-            if line[pos] in '#\r\n':           # skip comments or blank lines
-                if line[pos] == '#':
-                    comment_token = line[pos:].rstrip('\r\n')
-                    nl_pos = pos + len(comment_token)
-                    yield TokenInfo(COMMENT, comment_token,
-                           (lnum, pos), (lnum, pos + len(comment_token)), line)
-                    yield TokenInfo(NEWLINE, line[nl_pos:],
-                           (lnum, nl_pos), (lnum, len(line)), line)
-                else:
-                    yield TokenInfo(NEWLINE, line[pos:],
-                           (lnum, pos), (lnum, len(line)), line)
-                continue
-
-            if column > indents[-1]:           # count indents or dedents
-                indents.append(column)
-                yield TokenInfo(INDENT, line[:pos], (lnum, 0), (lnum, pos), line)
-            while column < indents[-1]:
-                if column not in indents:
-                    raise IndentationError(
-                        "unindent does not match any outer indentation level",
-                        ("<tokenize>", lnum, pos, line))
-                indents = indents[:-1]
-                yield TokenInfo(DEDENT, '', (lnum, pos), (lnum, pos), line)
-
-        else:                                  # continued statement
-            if not line:
-                raise TokenError("EOF in multi-line statement", (lnum, 0))
-            continued = 0
-
-        while pos < max:
-            pseudomatch = pseudoprog.match(line, pos)
-            if pseudomatch:                                # scan for tokens
-                start, end = pseudomatch.span(1)
-                spos, epos, pos = (lnum, start), (lnum, end), end
-                token, initial = line[start:end], line[start]
-
-                if (initial in numchars or                  # ordinary number
-                    (initial == '.' and token != '.' and token != '...')):
-                    yield TokenInfo(NUMBER, token, spos, epos, line)
-                elif initial in '\r\n':
-                    yield TokenInfo(NL if parenlev > 0 else NEWLINE,
-                           token, spos, epos, line)
-                elif initial == '#':
-                    assert not token.endswith("\n")
-                    yield TokenInfo(COMMENT, token, spos, epos, line)
-                elif token in triple_quoted:
-                    endprog = endprogs[token]
-                    endmatch = endprog.match(line, pos)
-                    if endmatch:                           # all on one line
-                        pos = endmatch.end(0)
-                        token = line[start:pos]
-                        yield TokenInfo(STRING, token, spos, (lnum, pos), line)
-                    else:
-                        strstart = (lnum, start)           # multiple lines
-                        contstr = line[start:]
-                        contline = line
-                        break
-                elif initial in single_quoted or \
-                    token[:2] in single_quoted or \
-                    token[:3] in single_quoted:
-                    if token[-1] == '\n':                  # continued string
-                        strstart = (lnum, start)
-                        endprog = (endprogs[initial] or endprogs[token[1]] or
-                                   endprogs[token[2]])
-                        contstr, needcont = line[start:], 1
-                        contline = line
-                        break
-                    else:                                  # ordinary string
-                        yield TokenInfo(STRING, token, spos, epos, line)
-                elif initial.isidentifier():               # ordinary name
-                    yield TokenInfo(NAME, token, spos, epos, line)
-                elif initial == '\\':                      # continued stmt
-                    continued = 1
-                else:
-                    if initial in '([{':
-                        parenlev += 1
-                    elif initial in ')]}':
-                        parenlev -= 1
-                    yield TokenInfo(OP, token, spos, epos, line)
-            else:
-                yield TokenInfo(ERRORTOKEN, line[pos],
-                           (lnum, pos), (lnum, pos+1), line)
-                pos += 1
-
-    for indent in indents[1:]:                 # pop remaining indent levels
-        yield TokenInfo(DEDENT, '', (lnum, 0), (lnum, 0), '')
-    yield TokenInfo(ENDMARKER, '', (lnum, 0), (lnum, 0), '')
-
-
-# An undocumented, backwards compatible, API for all the places in the standard
-# library that expect to be able to use tokenize with strings
-def generate_tokens(readline):
-    return _tokenize(readline, None)
-
-if __name__ == "__main__":
-    # Quick sanity check
-    s = b'''def parseline(self, line):
-            """Parse the line into a command name and a string containing
-            the arguments.  Returns a tuple containing (command, args, line).
-            'command' and 'args' may be None if the line couldn't be parsed.
-            """
-            line = line.strip()
-            if not line:
-                return None, None, line
-            elif line[0] == '?':
-                line = 'help ' + line[1:]
-            elif line[0] == '!':
-                if hasattr(self, 'do_shell'):
-                    line = 'shell ' + line[1:]
-                else:
-                    return None, None, line
-            i, n = 0, len(line)
-            while i < n and line[i] in self.identchars: i = i+1
-            cmd, arg = line[:i], line[i:].strip()
-            return cmd, arg, line
-    '''
-    for tok in tokenize(iter(s.splitlines()).__next__):
-        print(tok)