Consolidate utils.pyfile into utils.openpy

IPython/core/ultratb.py

@@ -1,1246 +1,1246 b''
 # -*- coding: utf-8 -*-
 """
 ultratb.py -- Spice up your tracebacks!
 
 * ColorTB
 I've always found it a bit hard to visually parse tracebacks in Python.  The
 ColorTB class is a solution to that problem.  It colors the different parts of a
 traceback in a manner similar to what you would expect from a syntax-highlighting
 text editor.
 
 Installation instructions for ColorTB:
     import sys,ultratb
     sys.excepthook = ultratb.ColorTB()
 
 * VerboseTB
 I've also included a port of Ka-Ping Yee's "cgitb.py" that produces all kinds
 of useful info when a traceback occurs.  Ping originally had it spit out HTML
 and intended it for CGI programmers, but why should they have all the fun?  I
 altered it to spit out colored text to the terminal.  It's a bit overwhelming,
 but kind of neat, and maybe useful for long-running programs that you believe
 are bug-free.  If a crash *does* occur in that type of program you want details.
 Give it a shot--you'll love it or you'll hate it.
 
 Note:
 
   The Verbose mode prints the variables currently visible where the exception
   happened (shortening their strings if too long). This can potentially be
   very slow, if you happen to have a huge data structure whose string
   representation is complex to compute. Your computer may appear to freeze for
   a while with cpu usage at 100%. If this occurs, you can cancel the traceback
   with Ctrl-C (maybe hitting it more than once).
 
   If you encounter this kind of situation often, you may want to use the
   Verbose_novars mode instead of the regular Verbose, which avoids formatting
   variables (but otherwise includes the information and context given by
   Verbose).
 
 
 Installation instructions for ColorTB:
     import sys,ultratb
     sys.excepthook = ultratb.VerboseTB()
 
 Note:  Much of the code in this module was lifted verbatim from the standard
 library module 'traceback.py' and Ka-Ping Yee's 'cgitb.py'.
 
 * Color schemes
 The colors are defined in the class TBTools through the use of the
 ColorSchemeTable class. Currently the following exist:
 
   - NoColor: allows all of this module to be used in any terminal (the color
   escapes are just dummy blank strings).
 
   - Linux: is meant to look good in a terminal like the Linux console (black
   or very dark background).
 
   - LightBG: similar to Linux but swaps dark/light colors to be more readable
   in light background terminals.
 
 You can implement other color schemes easily, the syntax is fairly
 self-explanatory. Please send back new schemes you develop to the author for
 possible inclusion in future releases.
 
 Inheritance diagram:
 
 .. inheritance-diagram:: IPython.core.ultratb
    :parts: 3
 """
 
 #*****************************************************************************
 #       Copyright (C) 2001 Nathaniel Gray <[e-mail]>
 #       Copyright (C) 2001-2004 Fernando Perez <[e-mail]>
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #*****************************************************************************
 
 from __future__ import unicode_literals
 
 import inspect
 import keyword
 import linecache
 import os
 import pydoc
 import re
 import sys
 import time
 import tokenize
 import traceback
 import types
 
 try:                           # Python 2
     generate_tokens = tokenize.generate_tokens
 except AttributeError:         # Python 3
     generate_tokens = tokenize.tokenize
 
 # For purposes of monkeypatching inspect to fix a bug in it.
 from inspect import getsourcefile, getfile, getmodule,\
      ismodule, isclass, ismethod, isfunction, istraceback, isframe, iscode
 
 # IPython's own modules
 # Modified pdb which doesn't damage IPython's readline handling
 from IPython.core import debugger, ipapi
 from IPython.core.display_trap import DisplayTrap
 from IPython.core.excolors import exception_colors
 from IPython.utils import PyColorize
 from IPython.utils import io
+from IPython.utils import openpy
 from IPython.utils import path as util_path
 from IPython.utils import py3compat
-from IPython.utils import pyfile
 from IPython.utils import ulinecache
 from IPython.utils.data import uniq_stable
 from IPython.utils.warn import info, error
 
 # Globals
 # amount of space to put line numbers before verbose tracebacks
 INDENT_SIZE = 8
 
 # Default color scheme.  This is used, for example, by the traceback
 # formatter.  When running in an actual IPython instance, the user's rc.colors
 # value is used, but havinga module global makes this functionality available
 # to users of ultratb who are NOT running inside ipython.
 DEFAULT_SCHEME = 'NoColor'
 
 #---------------------------------------------------------------------------
 # Code begins
 
 # Utility functions
 def inspect_error():
     """Print a message about internal inspect errors.
 
     These are unfortunately quite common."""
 
     error('Internal Python error in the inspect module.\n'
           'Below is the traceback from this internal error.\n')
 
 # This function is a monkeypatch we apply to the Python inspect module. We have
 # now found when it's needed (see discussion on issue gh-1456), and we have a
 # test case (IPython.core.tests.test_ultratb.ChangedPyFileTest) that fails if
 # the monkeypatch is not applied. TK, Aug 2012.
 def findsource(object):
     """Return the entire source file and starting line number for an object.
 
     The argument may be a module, class, method, function, traceback, frame,
     or code object.  The source code is returned as a list of all the lines
     in the file and the line number indexes a line in that list.  An IOError
     is raised if the source code cannot be retrieved.
 
     FIXED version with which we monkeypatch the stdlib to work around a bug."""
 
     file = getsourcefile(object) or getfile(object)
     # If the object is a frame, then trying to get the globals dict from its
     # module won't work. Instead, the frame object itself has the globals
     # dictionary.
     globals_dict = None
     if inspect.isframe(object):
         # XXX: can this ever be false?
         globals_dict = object.f_globals
     else:
         module = getmodule(object, file)
         if module:
             globals_dict = module.__dict__
     lines = linecache.getlines(file, globals_dict)
     if not lines:
         raise IOError('could not get source code')
 
     if ismodule(object):
         return lines, 0
 
     if isclass(object):
         name = object.__name__
         pat = re.compile(r'^(\s*)class\s*' + name + r'\b')
         # make some effort to find the best matching class definition:
         # use the one with the least indentation, which is the one
         # that's most probably not inside a function definition.
         candidates = []
         for i in range(len(lines)):
             match = pat.match(lines[i])
             if match:
                 # if it's at toplevel, it's already the best one
                 if lines[i][0] == 'c':
                     return lines, i
                 # else add whitespace to candidate list
                 candidates.append((match.group(1), i))
         if candidates:
             # this will sort by whitespace, and by line number,
             # less whitespace first
             candidates.sort()
             return lines, candidates[0][1]
         else:
             raise IOError('could not find class definition')
 
     if ismethod(object):
         object = object.im_func
     if isfunction(object):
         object = object.func_code
     if istraceback(object):
         object = object.tb_frame
     if isframe(object):
         object = object.f_code
     if iscode(object):
         if not hasattr(object, 'co_firstlineno'):
             raise IOError('could not find function definition')
         pat = re.compile(r'^(\s*def\s)|(.*(?<!\w)lambda(:|\s))|^(\s*@)')
         pmatch = pat.match
         # fperez - fix: sometimes, co_firstlineno can give a number larger than
         # the length of lines, which causes an error.  Safeguard against that.
         lnum = min(object.co_firstlineno,len(lines))-1
         while lnum > 0:
             if pmatch(lines[lnum]): break
             lnum -= 1
 
         return lines, lnum
     raise IOError('could not find code object')
 
 # Monkeypatch inspect to apply our bugfix.  This code only works with Python >= 2.5
 inspect.findsource = findsource
 
 def fix_frame_records_filenames(records):
     """Try to fix the filenames in each record from inspect.getinnerframes().
 
     Particularly, modules loaded from within zip files have useless filenames
     attached to their code object, and inspect.getinnerframes() just uses it.
     """
     fixed_records = []
     for frame, filename, line_no, func_name, lines, index in records:
         # Look inside the frame's globals dictionary for __file__, which should
         # be better.
         better_fn = frame.f_globals.get('__file__', None)
         if isinstance(better_fn, str):
             # Check the type just in case someone did something weird with
             # __file__. It might also be None if the error occurred during
             # import.
             filename = better_fn
         fixed_records.append((frame, filename, line_no, func_name, lines, index))
     return fixed_records
 
 
 def _fixed_getinnerframes(etb, context=1,tb_offset=0):
     LNUM_POS, LINES_POS, INDEX_POS =  2, 4, 5
 
     records  = fix_frame_records_filenames(inspect.getinnerframes(etb, context))
 
     # If the error is at the console, don't build any context, since it would
     # otherwise produce 5 blank lines printed out (there is no file at the
     # console)
     rec_check = records[tb_offset:]
     try:
         rname = rec_check[0][1]
         if rname == '<ipython console>' or rname.endswith('<string>'):
             return rec_check
     except IndexError:
         pass
 
     aux = traceback.extract_tb(etb)
     assert len(records) == len(aux)
     for i, (file, lnum, _, _) in zip(range(len(records)), aux):
         maybeStart = lnum-1 - context//2
         start =  max(maybeStart, 0)
         end   = start + context
         lines = ulinecache.getlines(file)[start:end]
         buf = list(records[i])
         buf[LNUM_POS] = lnum
         buf[INDEX_POS] = lnum - 1 - start
         buf[LINES_POS] = lines
         records[i] = tuple(buf)
     return records[tb_offset:]
 
 # Helper function -- largely belongs to VerboseTB, but we need the same
 # functionality to produce a pseudo verbose TB for SyntaxErrors, so that they
 # can be recognized properly by ipython.el's py-traceback-line-re
 # (SyntaxErrors have to be treated specially because they have no traceback)
 
 _parser = PyColorize.Parser()
 
 def _format_traceback_lines(lnum, index, lines, Colors, lvals=None,scheme=None):
     numbers_width = INDENT_SIZE - 1
     res = []
     i = lnum - index
 
     # This lets us get fully syntax-highlighted tracebacks.
     if scheme is None:
         ipinst = ipapi.get()
         if ipinst is not None:
             scheme = ipinst.colors
         else:
             scheme = DEFAULT_SCHEME
 
     _line_format = _parser.format2
 
     for line in lines:
         line = py3compat.cast_unicode(line)
 
         new_line, err = _line_format(line, 'str', scheme)
         if not err: line = new_line
 
         if i == lnum:
             # This is the line with the error
             pad = numbers_width - len(str(i))
             if pad >= 3:
                 marker = '-'*(pad-3) + '-> '
             elif pad == 2:
                 marker = '> '
             elif pad == 1:
                 marker = '>'
             else:
                 marker = ''
             num = marker + str(i)
             line = '%s%s%s %s%s' %(Colors.linenoEm, num,
                                    Colors.line, line, Colors.Normal)
         else:
             num = '%*s' % (numbers_width,i)
             line = '%s%s%s %s' %(Colors.lineno, num,
                                  Colors.Normal, line)
 
         res.append(line)
         if lvals and i == lnum:
             res.append(lvals + '\n')
         i = i + 1
     return res
 
 
 #---------------------------------------------------------------------------
 # Module classes
 class TBTools(object):
     """Basic tools used by all traceback printer classes."""
 
     # Number of frames to skip when reporting tracebacks
     tb_offset = 0
 
     def __init__(self, color_scheme='NoColor', call_pdb=False, ostream=None):
         # Whether to call the interactive pdb debugger after printing
         # tracebacks or not
         self.call_pdb = call_pdb
 
         # Output stream to write to.  Note that we store the original value in
         # a private attribute and then make the public ostream a property, so
         # that we can delay accessing io.stdout until runtime.  The way
         # things are written now, the io.stdout object is dynamically managed
         # so a reference to it should NEVER be stored statically.  This
         # property approach confines this detail to a single location, and all
         # subclasses can simply access self.ostream for writing.
         self._ostream = ostream
 
         # Create color table
         self.color_scheme_table = exception_colors()
 
         self.set_colors(color_scheme)
         self.old_scheme = color_scheme  # save initial value for toggles
 
         if call_pdb:
             self.pdb = debugger.Pdb(self.color_scheme_table.active_scheme_name)
         else:
             self.pdb = None
 
     def _get_ostream(self):
         """Output stream that exceptions are written to.
 
         Valid values are:
 
         - None: the default, which means that IPython will dynamically resolve
         to io.stdout.  This ensures compatibility with most tools, including
         Windows (where plain stdout doesn't recognize ANSI escapes).
 
         - Any object with 'write' and 'flush' attributes.
         """
         return io.stdout if self._ostream is None else self._ostream
 
     def _set_ostream(self, val):
         assert val is None or (hasattr(val, 'write') and hasattr(val, 'flush'))
         self._ostream = val
 
     ostream = property(_get_ostream, _set_ostream)
 
     def set_colors(self,*args,**kw):
         """Shorthand access to the color table scheme selector method."""
 
         # Set own color table
         self.color_scheme_table.set_active_scheme(*args,**kw)
         # for convenience, set Colors to the active scheme
         self.Colors = self.color_scheme_table.active_colors
         # Also set colors of debugger
         if hasattr(self,'pdb') and self.pdb is not None:
             self.pdb.set_colors(*args,**kw)
 
     def color_toggle(self):
         """Toggle between the currently active color scheme and NoColor."""
 
         if self.color_scheme_table.active_scheme_name == 'NoColor':
             self.color_scheme_table.set_active_scheme(self.old_scheme)
             self.Colors = self.color_scheme_table.active_colors
         else:
             self.old_scheme = self.color_scheme_table.active_scheme_name
             self.color_scheme_table.set_active_scheme('NoColor')
             self.Colors = self.color_scheme_table.active_colors
 
     def stb2text(self, stb):
         """Convert a structured traceback (a list) to a string."""
         return '\n'.join(stb)
 
     def text(self, etype, value, tb, tb_offset=None, context=5):
         """Return formatted traceback.
 
         Subclasses may override this if they add extra arguments.
         """
         tb_list = self.structured_traceback(etype, value, tb,
                                             tb_offset, context)
         return self.stb2text(tb_list)
 
     def structured_traceback(self, etype, evalue, tb, tb_offset=None,
                              context=5, mode=None):
         """Return a list of traceback frames.
 
         Must be implemented by each class.
         """
         raise NotImplementedError()
 
 
 #---------------------------------------------------------------------------
 class ListTB(TBTools):
     """Print traceback information from a traceback list, with optional color.
 
     Calling requires 3 arguments: (etype, evalue, elist)
     as would be obtained by::
     
       etype, evalue, tb = sys.exc_info()
       if tb:
         elist = traceback.extract_tb(tb)
       else:
         elist = None
 
     It can thus be used by programs which need to process the traceback before
     printing (such as console replacements based on the code module from the
     standard library).
 
     Because they are meant to be called without a full traceback (only a
     list), instances of this class can't call the interactive pdb debugger."""
 
     def __init__(self,color_scheme = 'NoColor', call_pdb=False, ostream=None):
         TBTools.__init__(self, color_scheme=color_scheme, call_pdb=call_pdb,
                          ostream=ostream)
 
     def __call__(self, etype, value, elist):
         self.ostream.flush()
         self.ostream.write(self.text(etype, value, elist))
         self.ostream.write('\n')
 
     def structured_traceback(self, etype, value, elist, tb_offset=None,
                              context=5):
         """Return a color formatted string with the traceback info.
 
         Parameters
         ----------
         etype : exception type
           Type of the exception raised.
 
         value : object
           Data stored in the exception
 
         elist : list
           List of frames, see class docstring for details.
 
         tb_offset : int, optional
           Number of frames in the traceback to skip.  If not given, the
           instance value is used (set in constructor).
 
         context : int, optional
           Number of lines of context information to print.
 
         Returns
         -------
         String with formatted exception.
         """
         tb_offset = self.tb_offset if tb_offset is None else tb_offset
         Colors = self.Colors
         out_list = []
         if elist:
 
             if tb_offset and len(elist) > tb_offset:
                 elist = elist[tb_offset:]
 
             out_list.append('Traceback %s(most recent call last)%s:' %
                                 (Colors.normalEm, Colors.Normal) + '\n')
             out_list.extend(self._format_list(elist))
         # The exception info should be a single entry in the list.
         lines = ''.join(self._format_exception_only(etype, value))
         out_list.append(lines)
 
         # Note: this code originally read:
 
         ## for line in lines[:-1]:
         ##     out_list.append(" "+line)
         ## out_list.append(lines[-1])
 
         # This means it was indenting everything but the last line by a little
         # bit.  I've disabled this for now, but if we see ugliness somewhre we
         # can restore it.
 
         return out_list
 
     def _format_list(self, extracted_list):
         """Format a list of traceback entry tuples for printing.
 
         Given a list of tuples as returned by extract_tb() or
         extract_stack(), return a list of strings ready for printing.
         Each string in the resulting list corresponds to the item with the
         same index in the argument list.  Each string ends in a newline;
         the strings may contain internal newlines as well, for those items
         whose source text line is not None.
 
         Lifted almost verbatim from traceback.py
         """
 
         Colors = self.Colors
         list = []
         for filename, lineno, name, line in extracted_list[:-1]:
             item = '  File %s"%s"%s, line %s%d%s, in %s%s%s\n' % \
                     (Colors.filename, filename, Colors.Normal,
                      Colors.lineno, lineno, Colors.Normal,
                      Colors.name, name, Colors.Normal)
             if line:
                 item += '    %s\n' % line.strip()
             list.append(item)
         # Emphasize the last entry
         filename, lineno, name, line = extracted_list[-1]
         item = '%s  File %s"%s"%s, line %s%d%s, in %s%s%s%s\n' % \
                 (Colors.normalEm,
                  Colors.filenameEm, filename, Colors.normalEm,
                  Colors.linenoEm, lineno, Colors.normalEm,
                  Colors.nameEm, name, Colors.normalEm,
                  Colors.Normal)
         if line:
             item += '%s    %s%s\n' % (Colors.line, line.strip(),
                                             Colors.Normal)
         list.append(item)
         #from pprint import pformat; print 'LISTTB', pformat(list) # dbg
         return list
 
     def _format_exception_only(self, etype, value):
         """Format the exception part of a traceback.
 
         The arguments are the exception type and value such as given by
         sys.exc_info()[:2]. The return value is a list of strings, each ending
         in a newline.  Normally, the list contains a single string; however,
         for SyntaxError exceptions, it contains several lines that (when
         printed) display detailed information about where the syntax error
         occurred.  The message indicating which exception occurred is the
         always last string in the list.
 
         Also lifted nearly verbatim from traceback.py
         """
         have_filedata = False
         Colors = self.Colors
         list = []
         stype = Colors.excName + etype.__name__ + Colors.Normal
         if value is None:
             # Not sure if this can still happen in Python 2.6 and above
             list.append( py3compat.cast_unicode(stype) + '\n')
         else:
             if issubclass(etype, SyntaxError):
                 have_filedata = True
                 #print 'filename is',filename  # dbg
                 if not value.filename: value.filename = "<string>"
                 if value.lineno:
                     lineno = value.lineno
                     textline = ulinecache.getline(value.filename, value.lineno)
                 else:
                     lineno = 'unknown'
                     textline = ''
                 list.append('%s  File %s"%s"%s, line %s%s%s\n' % \
                         (Colors.normalEm,
                          Colors.filenameEm, py3compat.cast_unicode(value.filename), Colors.normalEm,
                          Colors.linenoEm, lineno, Colors.Normal  ))
                 if textline == '':
                     textline = py3compat.cast_unicode(value.text, "utf-8")
 
                 if textline is not None:
                     i = 0
                     while i < len(textline) and textline[i].isspace():
                         i += 1
                     list.append('%s    %s%s\n' % (Colors.line,
                                                   textline.strip(),
                                                   Colors.Normal))
                     if value.offset is not None:
                         s = '    '
                         for c in textline[i:value.offset-1]:
                             if c.isspace():
                                 s += c
                             else:
                                 s += ' '
                         list.append('%s%s^%s\n' % (Colors.caret, s,
                                                    Colors.Normal) )
 
             try:
                 s = value.msg
             except Exception:
                 s = self._some_str(value)
             if s:
                 list.append('%s%s:%s %s\n' % (str(stype), Colors.excName,
                                               Colors.Normal, s))
             else:
                 list.append('%s\n' % str(stype))
 
         # sync with user hooks
         if have_filedata:
             ipinst = ipapi.get()
             if ipinst is not None:
                 ipinst.hooks.synchronize_with_editor(value.filename, value.lineno, 0)
 
         return list
 
     def get_exception_only(self, etype, value):
         """Only print the exception type and message, without a traceback.
 
         Parameters
         ----------
         etype : exception type
         value : exception value
         """
         return ListTB.structured_traceback(self, etype, value, [])
 
 
     def show_exception_only(self, etype, evalue):
         """Only print the exception type and message, without a traceback.
 
         Parameters
         ----------
         etype : exception type
         value : exception value
         """
         # This method needs to use __call__ from *this* class, not the one from
         # a subclass whose signature or behavior may be different
         ostream = self.ostream
         ostream.flush()
         ostream.write('\n'.join(self.get_exception_only(etype, evalue)))
         ostream.flush()
 
     def _some_str(self, value):
         # Lifted from traceback.py
         try:
             return str(value)
         except:
             return '<unprintable %s object>' % type(value).__name__
 
 #----------------------------------------------------------------------------
 class VerboseTB(TBTools):
     """A port of Ka-Ping Yee's cgitb.py module that outputs color text instead
     of HTML.  Requires inspect and pydoc.  Crazy, man.
 
     Modified version which optionally strips the topmost entries from the
     traceback, to be used with alternate interpreters (because their own code
     would appear in the traceback)."""
 
     def __init__(self,color_scheme = 'Linux', call_pdb=False, ostream=None,
                  tb_offset=0, long_header=False, include_vars=True,
                  check_cache=None):
         """Specify traceback offset, headers and color scheme.
 
         Define how many frames to drop from the tracebacks. Calling it with
         tb_offset=1 allows use of this handler in interpreters which will have
         their own code at the top of the traceback (VerboseTB will first
         remove that frame before printing the traceback info)."""
         TBTools.__init__(self, color_scheme=color_scheme, call_pdb=call_pdb,
                          ostream=ostream)
         self.tb_offset = tb_offset
         self.long_header = long_header
         self.include_vars = include_vars
         # By default we use linecache.checkcache, but the user can provide a
         # different check_cache implementation.  This is used by the IPython
         # kernel to provide tracebacks for interactive code that is cached,
         # by a compiler instance that flushes the linecache but preserves its
         # own code cache.
         if check_cache is None:
             check_cache = linecache.checkcache
         self.check_cache = check_cache
 
     def structured_traceback(self, etype, evalue, etb, tb_offset=None,
                              context=5):
         """Return a nice text document describing the traceback."""
 
         tb_offset = self.tb_offset if tb_offset is None else tb_offset
 
         # some locals
         try:
             etype = etype.__name__
         except AttributeError:
             pass
         Colors        = self.Colors   # just a shorthand + quicker name lookup
         ColorsNormal  = Colors.Normal  # used a lot
         col_scheme    = self.color_scheme_table.active_scheme_name
         indent        = ' '*INDENT_SIZE
         em_normal     = '%s\n%s%s' % (Colors.valEm, indent,ColorsNormal)
         undefined     = '%sundefined%s' % (Colors.em, ColorsNormal)
         exc = '%s%s%s' % (Colors.excName,etype,ColorsNormal)
 
         # some internal-use functions
         def text_repr(value):
             """Hopefully pretty robust repr equivalent."""
             # this is pretty horrible but should always return *something*
             try:
                 return pydoc.text.repr(value)
             except KeyboardInterrupt:
                 raise
             except:
                 try:
                     return repr(value)
                 except KeyboardInterrupt:
                     raise
                 except:
                     try:
                         # all still in an except block so we catch
                         # getattr raising
                         name = getattr(value, '__name__', None)
                         if name:
                             # ick, recursion
                             return text_repr(name)
                         klass = getattr(value, '__class__', None)
                         if klass:
                             return '%s instance' % text_repr(klass)
                     except KeyboardInterrupt:
                         raise
                     except:
                         return 'UNRECOVERABLE REPR FAILURE'
         def eqrepr(value, repr=text_repr): return '=%s' % repr(value)
         def nullrepr(value, repr=text_repr): return ''
 
         # meat of the code begins
         try:
             etype = etype.__name__
         except AttributeError:
             pass
 
         if self.long_header:
             # Header with the exception type, python version, and date
             pyver = 'Python ' + sys.version.split()[0] + ': ' + sys.executable
             date = time.ctime(time.time())
 
             head = '%s%s%s\n%s%s%s\n%s' % (Colors.topline, '-'*75, ColorsNormal,
                                            exc, ' '*(75-len(str(etype))-len(pyver)),
                                            pyver, date.rjust(75) )
             head += "\nA problem occured executing Python code.  Here is the sequence of function"\
                     "\ncalls leading up to the error, with the most recent (innermost) call last."
         else:
             # Simplified header
             head = '%s%s%s\n%s%s' % (Colors.topline, '-'*75, ColorsNormal,exc,
                                      'Traceback (most recent call last)'.\
                                                   rjust(75 - len(str(etype)) ) )
         frames = []
         # Flush cache before calling inspect.  This helps alleviate some of the
         # problems with python 2.3's inspect.py.
         ##self.check_cache()
         # Drop topmost frames if requested
         try:
             # Try the default getinnerframes and Alex's: Alex's fixes some
             # problems, but it generates empty tracebacks for console errors
             # (5 blanks lines) where none should be returned.
             #records = inspect.getinnerframes(etb, context)[tb_offset:]
             #print 'python records:', records # dbg
             records = _fixed_getinnerframes(etb, context, tb_offset)
             #print 'alex   records:', records # dbg
         except:
 
             # FIXME: I've been getting many crash reports from python 2.3
             # users, traceable to inspect.py.  If I can find a small test-case
             # to reproduce this, I should either write a better workaround or
             # file a bug report against inspect (if that's the real problem).
             # So far, I haven't been able to find an isolated example to
             # reproduce the problem.
             inspect_error()
             traceback.print_exc(file=self.ostream)
             info('\nUnfortunately, your original traceback can not be constructed.\n')
             return ''
 
         # build some color string templates outside these nested loops
         tpl_link       = '%s%%s%s' % (Colors.filenameEm,ColorsNormal)
         tpl_call       = 'in %s%%s%s%%s%s' % (Colors.vName, Colors.valEm,
                                               ColorsNormal)
         tpl_call_fail  = 'in %s%%s%s(***failed resolving arguments***)%s' % \
                          (Colors.vName, Colors.valEm, ColorsNormal)
         tpl_local_var  = '%s%%s%s' % (Colors.vName, ColorsNormal)
         tpl_global_var = '%sglobal%s %s%%s%s' % (Colors.em, ColorsNormal,
                                                  Colors.vName, ColorsNormal)
         tpl_name_val   = '%%s %s= %%s%s' % (Colors.valEm, ColorsNormal)
         tpl_line       = '%s%%s%s %%s' % (Colors.lineno, ColorsNormal)
         tpl_line_em    = '%s%%s%s %%s%s' % (Colors.linenoEm,Colors.line,
                                             ColorsNormal)
 
         # now, loop over all records printing context and info
         abspath = os.path.abspath
         for frame, file, lnum, func, lines, index in records:
             #print '*** record:',file,lnum,func,lines,index  # dbg
             if not file:
                 file = '?'
             elif not(file.startswith(str("<")) and file.endswith(str(">"))):
                 # Guess that filenames like <string> aren't real filenames, so
                 # don't call abspath on them.                    
                 try:
                     file = abspath(file)
                 except OSError:
                     # Not sure if this can still happen: abspath now works with
                     # file names like <string>
                     pass
             file = py3compat.cast_unicode(file, util_path.fs_encoding)
             link = tpl_link % file
             args, varargs, varkw, locals = inspect.getargvalues(frame)
 
             if func == '?':
                 call = ''
             else:
                 # Decide whether to include variable details or not
                 var_repr = self.include_vars and eqrepr or nullrepr
                 try:
                     call = tpl_call % (func,inspect.formatargvalues(args,
                                                 varargs, varkw,
                                                 locals,formatvalue=var_repr))
                 except KeyError:
                     # This happens in situations like errors inside generator
                     # expressions, where local variables are listed in the
                     # line, but can't be extracted from the frame.  I'm not
                     # 100% sure this isn't actually a bug in inspect itself,
                     # but since there's no info for us to compute with, the
                     # best we can do is report the failure and move on.  Here
                     # we must *not* call any traceback construction again,
                     # because that would mess up use of %debug later on.  So we
                     # simply report the failure and move on.  The only
                     # limitation will be that this frame won't have locals
                     # listed in the call signature.  Quite subtle problem...
                     # I can't think of a good way to validate this in a unit
                     # test, but running a script consisting of:
                     #  dict( (k,v.strip()) for (k,v) in range(10) )
                     # will illustrate the error, if this exception catch is
                     # disabled.
                     call = tpl_call_fail % func
             
             # Don't attempt to tokenize binary files.
             if file.endswith(('.so', '.pyd', '.dll')):
                 frames.append('%s %s\n' % (link,call))
                 continue
             elif file.endswith(('.pyc','.pyo')):
                 # Look up the corresponding source file.
-                file = pyfile.source_from_cache(file)
+                file = openpy.source_from_cache(file)
 
             def linereader(file=file, lnum=[lnum], getline=ulinecache.getline):
                 line = getline(file, lnum[0])
                 lnum[0] += 1
                 return line
 
             # Build the list of names on this line of code where the exception
             # occurred.
             try:
                 names = []
                 name_cont = False
                 
                 for token_type, token, start, end, line in generate_tokens(linereader):
                     # build composite names
                     if token_type == tokenize.NAME and token not in keyword.kwlist:
                         if name_cont:
                             # Continuation of a dotted name
                             try:
                                 names[-1].append(token)
                             except IndexError:
                                 names.append([token])
                             name_cont = False
                         else:
                             # Regular new names.  We append everything, the caller
                             # will be responsible for pruning the list later.  It's
                             # very tricky to try to prune as we go, b/c composite
                             # names can fool us.  The pruning at the end is easy
                             # to do (or the caller can print a list with repeated
                             # names if so desired.
                             names.append([token])
                     elif token == '.':
                         name_cont = True
                     elif token_type == tokenize.NEWLINE:
                         break
                         
             except (IndexError, UnicodeDecodeError):
                 # signals exit of tokenizer
                 pass
             except tokenize.TokenError as msg:
                 _m = ("An unexpected error occurred while tokenizing input\n"
                       "The following traceback may be corrupted or invalid\n"
                       "The error message is: %s\n" % msg)
                 error(_m)
 
             # Join composite names (e.g. "dict.fromkeys")
             names = ['.'.join(n) for n in names]
             # prune names list of duplicates, but keep the right order
             unique_names = uniq_stable(names)
 
             # Start loop over vars
             lvals = []
             if self.include_vars:
                 for name_full in unique_names:
                     name_base = name_full.split('.',1)[0]
                     if name_base in frame.f_code.co_varnames:
                         if name_base in locals:
                             try:
                                 value = repr(eval(name_full,locals))
                             except:
                                 value = undefined
                         else:
                             value = undefined
                         name = tpl_local_var % name_full
                     else:
                         if name_base in frame.f_globals:
                             try:
                                 value = repr(eval(name_full,frame.f_globals))
                             except:
                                 value = undefined
                         else:
                             value = undefined
                         name = tpl_global_var % name_full
                     lvals.append(tpl_name_val % (name,value))
             if lvals:
                 lvals = '%s%s' % (indent,em_normal.join(lvals))
             else:
                 lvals = ''
 
             level = '%s %s\n' % (link,call)
 
             if index is None:
                 frames.append(level)
             else:
                 frames.append('%s%s' % (level,''.join(
                     _format_traceback_lines(lnum,index,lines,Colors,lvals,
                                             col_scheme))))
 
         # Get (safely) a string form of the exception info
         try:
             etype_str,evalue_str = map(str,(etype,evalue))
         except:
             # User exception is improperly defined.
             etype,evalue = str,sys.exc_info()[:2]
             etype_str,evalue_str = map(str,(etype,evalue))
         # ... and format it
         exception = ['%s%s%s: %s' % (Colors.excName, etype_str,
                                      ColorsNormal, py3compat.cast_unicode(evalue_str))]
         if (not py3compat.PY3) and type(evalue) is types.InstanceType:
             try:
                 names = [w for w in dir(evalue) if isinstance(w, basestring)]
             except:
                 # Every now and then, an object with funny inernals blows up
                 # when dir() is called on it.  We do the best we can to report
                 # the problem and continue
                 _m = '%sException reporting error (object with broken dir())%s:'
                 exception.append(_m % (Colors.excName,ColorsNormal))
                 etype_str,evalue_str = map(str,sys.exc_info()[:2])
                 exception.append('%s%s%s: %s' % (Colors.excName,etype_str,
                                      ColorsNormal, py3compat.cast_unicode(evalue_str)))
                 names = []
             for name in names:
                 value = text_repr(getattr(evalue, name))
                 exception.append('\n%s%s = %s' % (indent, name, value))
 
         # vds: >>
         if records:
              filepath, lnum = records[-1][1:3]
              #print "file:", str(file), "linenb", str(lnum) # dbg
              filepath = os.path.abspath(filepath)
              ipinst = ipapi.get()
              if ipinst is not None:
                  ipinst.hooks.synchronize_with_editor(filepath, lnum, 0)
         # vds: <<
 
         # return all our info assembled as a single string
         # return '%s\n\n%s\n%s' % (head,'\n'.join(frames),''.join(exception[0]) )
         return [head] + frames + [''.join(exception[0])]
 
     def debugger(self,force=False):
         """Call up the pdb debugger if desired, always clean up the tb
         reference.
 
         Keywords:
 
           - force(False): by default, this routine checks the instance call_pdb
           flag and does not actually invoke the debugger if the flag is false.
           The 'force' option forces the debugger to activate even if the flag
           is false.
 
         If the call_pdb flag is set, the pdb interactive debugger is
         invoked. In all cases, the self.tb reference to the current traceback
         is deleted to prevent lingering references which hamper memory
         management.
 
         Note that each call to pdb() does an 'import readline', so if your app
         requires a special setup for the readline completers, you'll have to
         fix that by hand after invoking the exception handler."""
 
         if force or self.call_pdb:
             if self.pdb is None:
                 self.pdb = debugger.Pdb(
                     self.color_scheme_table.active_scheme_name)
             # the system displayhook may have changed, restore the original
             # for pdb
             display_trap = DisplayTrap(hook=sys.__displayhook__)
             with display_trap:
                 self.pdb.reset()
                 # Find the right frame so we don't pop up inside ipython itself
                 if hasattr(self,'tb') and self.tb is not None:
                     etb = self.tb
                 else:
                     etb = self.tb = sys.last_traceback
                 while self.tb is not None and self.tb.tb_next is not None:
                     self.tb = self.tb.tb_next
                 if etb and etb.tb_next:
                     etb = etb.tb_next
                 self.pdb.botframe = etb.tb_frame
                 self.pdb.interaction(self.tb.tb_frame, self.tb)
 
         if hasattr(self,'tb'):
             del self.tb
 
     def handler(self, info=None):
         (etype, evalue, etb) = info or sys.exc_info()
         self.tb = etb
         ostream = self.ostream
         ostream.flush()
         ostream.write(self.text(etype, evalue, etb))
         ostream.write('\n')
         ostream.flush()
 
     # Changed so an instance can just be called as VerboseTB_inst() and print
     # out the right info on its own.
     def __call__(self, etype=None, evalue=None, etb=None):
         """This hook can replace sys.excepthook (for Python 2.1 or higher)."""
         if etb is None:
             self.handler()
         else:
             self.handler((etype, evalue, etb))
         try:
             self.debugger()
         except KeyboardInterrupt:
             print "\nKeyboardInterrupt"
 
 #----------------------------------------------------------------------------
 class FormattedTB(VerboseTB, ListTB):
     """Subclass ListTB but allow calling with a traceback.
 
     It can thus be used as a sys.excepthook for Python > 2.1.
 
     Also adds 'Context' and 'Verbose' modes, not available in ListTB.
 
     Allows a tb_offset to be specified. This is useful for situations where
     one needs to remove a number of topmost frames from the traceback (such as
     occurs with python programs that themselves execute other python code,
     like Python shells).  """
 
     def __init__(self, mode='Plain', color_scheme='Linux', call_pdb=False,
                  ostream=None,
                  tb_offset=0, long_header=False, include_vars=False,
                  check_cache=None):
 
         # NEVER change the order of this list. Put new modes at the end:
         self.valid_modes = ['Plain','Context','Verbose']
         self.verbose_modes = self.valid_modes[1:3]
 
         VerboseTB.__init__(self, color_scheme=color_scheme, call_pdb=call_pdb,
                            ostream=ostream, tb_offset=tb_offset,
                            long_header=long_header, include_vars=include_vars,
                            check_cache=check_cache)
 
         # Different types of tracebacks are joined with different separators to
         # form a single string.  They are taken from this dict
         self._join_chars = dict(Plain='', Context='\n', Verbose='\n')
         # set_mode also sets the tb_join_char attribute
         self.set_mode(mode)
 
     def _extract_tb(self,tb):
         if tb:
             return traceback.extract_tb(tb)
         else:
             return None
 
     def structured_traceback(self, etype, value, tb, tb_offset=None, context=5):
         tb_offset = self.tb_offset if tb_offset is None else tb_offset
         mode = self.mode
         if mode in self.verbose_modes:
             # Verbose modes need a full traceback
             return VerboseTB.structured_traceback(
                 self, etype, value, tb, tb_offset, context
             )
         else:
             # We must check the source cache because otherwise we can print
             # out-of-date source code.
             self.check_cache()
             # Now we can extract and format the exception
             elist = self._extract_tb(tb)
             return ListTB.structured_traceback(
                 self, etype, value, elist, tb_offset, context
             )
 
     def stb2text(self, stb):
         """Convert a structured traceback (a list) to a string."""
         return self.tb_join_char.join(stb)
 
 
     def set_mode(self,mode=None):
         """Switch to the desired mode.
 
         If mode is not specified, cycles through the available modes."""
 
         if not mode:
             new_idx = ( self.valid_modes.index(self.mode) + 1 ) % \
                       len(self.valid_modes)
             self.mode = self.valid_modes[new_idx]
         elif mode not in self.valid_modes:
             raise ValueError('Unrecognized mode in FormattedTB: <'+mode+'>\n'
                              'Valid modes: '+str(self.valid_modes))
         else:
             self.mode = mode
         # include variable details only in 'Verbose' mode
         self.include_vars = (self.mode == self.valid_modes[2])
         # Set the join character for generating text tracebacks
         self.tb_join_char = self._join_chars[self.mode]
 
     # some convenient shorcuts
     def plain(self):
         self.set_mode(self.valid_modes[0])
 
     def context(self):
         self.set_mode(self.valid_modes[1])
 
     def verbose(self):
         self.set_mode(self.valid_modes[2])
 
 #----------------------------------------------------------------------------
 class AutoFormattedTB(FormattedTB):
     """A traceback printer which can be called on the fly.
 
     It will find out about exceptions by itself.
 
     A brief example::
 
         AutoTB = AutoFormattedTB(mode = 'Verbose',color_scheme='Linux')
         try:
           ...
         except:
           AutoTB()  # or AutoTB(out=logfile) where logfile is an open file object
     """
 
     def __call__(self,etype=None,evalue=None,etb=None,
                  out=None,tb_offset=None):
         """Print out a formatted exception traceback.
 
         Optional arguments:
           - out: an open file-like object to direct output to.
 
           - tb_offset: the number of frames to skip over in the stack, on a
           per-call basis (this overrides temporarily the instance's tb_offset
           given at initialization time.  """
 
 
         if out is None:
             out = self.ostream
         out.flush()
         out.write(self.text(etype, evalue, etb, tb_offset))
         out.write('\n')
         out.flush()
         # FIXME: we should remove the auto pdb behavior from here and leave
         # that to the clients.
         try:
             self.debugger()
         except KeyboardInterrupt:
             print "\nKeyboardInterrupt"
 
     def structured_traceback(self, etype=None, value=None, tb=None,
                              tb_offset=None, context=5):
         if etype is None:
             etype,value,tb = sys.exc_info()
         self.tb = tb
         return FormattedTB.structured_traceback(
             self, etype, value, tb, tb_offset, context)
 
 #---------------------------------------------------------------------------
 
 # A simple class to preserve Nathan's original functionality.
 class ColorTB(FormattedTB):
     """Shorthand to initialize a FormattedTB in Linux colors mode."""
     def __init__(self,color_scheme='Linux',call_pdb=0):
         FormattedTB.__init__(self,color_scheme=color_scheme,
                              call_pdb=call_pdb)
 
 
 class SyntaxTB(ListTB):
     """Extension which holds some state: the last exception value"""
 
     def __init__(self,color_scheme = 'NoColor'):
         ListTB.__init__(self,color_scheme)
         self.last_syntax_error = None
 
     def __call__(self, etype, value, elist):
         self.last_syntax_error = value
         ListTB.__call__(self,etype,value,elist)
 
     def clear_err_state(self):
         """Return the current error state and clear it"""
         e = self.last_syntax_error
         self.last_syntax_error = None
         return e
 
     def stb2text(self, stb):
         """Convert a structured traceback (a list) to a string."""
         return ''.join(stb)
 
 
 #----------------------------------------------------------------------------
 # module testing (minimal)
 if __name__ == "__main__":
     def spam(c, d_e):
         (d, e) = d_e
         x = c + d
         y = c * d
         foo(x, y)
 
     def foo(a, b, bar=1):
         eggs(a, b + bar)
 
     def eggs(f, g, z=globals()):
         h = f + g
         i = f - g
         return h / i
 
     print ''
     print '*** Before ***'
     try:
         print spam(1, (2, 3))
     except:
         traceback.print_exc()
     print ''
 
     handler = ColorTB()
     print '*** ColorTB ***'
     try:
         print spam(1, (2, 3))
     except:
         handler(*sys.exc_info())
     print ''
 
     handler = VerboseTB()
     print '*** VerboseTB ***'
     try:
         print spam(1, (2, 3))
     except:
         handler(*sys.exc_info())
     print ''
 

IPython/extensions/autoreload.py

@@ -1,509 +1,509 b''
 """IPython extension to reload modules before executing user code.
 
 ``autoreload`` reloads modules automatically before entering the execution of
 code typed at the IPython prompt.
 
 This makes for example the following workflow possible:
 
 .. sourcecode:: ipython
 
    In [1]: %load_ext autoreload
 
    In [2]: %autoreload 2
 
    In [3]: from foo import some_function
 
    In [4]: some_function()
    Out[4]: 42
 
    In [5]: # open foo.py in an editor and change some_function to return 43
 
    In [6]: some_function()
    Out[6]: 43
 
 The module was reloaded without reloading it explicitly, and the object
 imported with ``from foo import ...`` was also updated.
 
 Usage
 =====
 
 The following magic commands are provided:
 
 ``%autoreload``
 
     Reload all modules (except those excluded by ``%aimport``)
     automatically now.
 
 ``%autoreload 0``
 
     Disable automatic reloading.
 
 ``%autoreload 1``
 
     Reload all modules imported with ``%aimport`` every time before
     executing the Python code typed.
 
 ``%autoreload 2``
 
     Reload all modules (except those excluded by ``%aimport``) every
     time before executing the Python code typed.
 
 ``%aimport``
 
     List modules which are to be automatically imported or not to be imported.
 
 ``%aimport foo``
 
     Import module 'foo' and mark it to be autoreloaded for ``%autoreload 1``
 
 ``%aimport -foo``
 
     Mark module 'foo' to not be autoreloaded.
 
 Caveats
 =======
 
 Reloading Python modules in a reliable way is in general difficult,
 and unexpected things may occur. ``%autoreload`` tries to work around
 common pitfalls by replacing function code objects and parts of
 classes previously in the module with new versions. This makes the
 following things to work:
 
 - Functions and classes imported via 'from xxx import foo' are upgraded
   to new versions when 'xxx' is reloaded.
 
 - Methods and properties of classes are upgraded on reload, so that
   calling 'c.foo()' on an object 'c' created before the reload causes
   the new code for 'foo' to be executed.
 
 Some of the known remaining caveats are:
 
 - Replacing code objects does not always succeed: changing a @property
   in a class to an ordinary method or a method to a member variable
   can cause problems (but in old objects only).
 
 - Functions that are removed (eg. via monkey-patching) from a module
   before it is reloaded are not upgraded.
 
 - C extension modules cannot be reloaded, and so cannot be autoreloaded.
 """
 from __future__ import print_function
 
 skip_doctest = True
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2000 Thomas Heller
 #  Copyright (C) 2008 Pauli Virtanen <[e-mail]>
 #  Copyright (C) 2012  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.
 #-----------------------------------------------------------------------------
 #
 # This IPython module is written by Pauli Virtanen, based on the autoreload
 # code by Thomas Heller.
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 import os
 import sys
 import traceback
 import types
 import weakref
 
 try:
     # Reload is not defined by default in Python3.
     reload
 except NameError:
     from imp import reload
 
-from IPython.utils import pyfile
+from IPython.utils import openpy
 from IPython.utils.py3compat import PY3
 
 #------------------------------------------------------------------------------
 # Autoreload functionality
 #------------------------------------------------------------------------------
 
 class ModuleReloader(object):
     enabled = False
     """Whether this reloader is enabled"""
 
     failed = {}
     """Modules that failed to reload: {module: mtime-on-failed-reload, ...}"""
 
     modules = {}
     """Modules specially marked as autoreloadable."""
 
     skip_modules = {}
     """Modules specially marked as not autoreloadable."""
 
     check_all = True
     """Autoreload all modules, not just those listed in 'modules'"""
 
     old_objects = {}
     """(module-name, name) -> weakref, for replacing old code objects"""
 
     def mark_module_skipped(self, module_name):
         """Skip reloading the named module in the future"""
         try:
             del self.modules[module_name]
         except KeyError:
             pass
         self.skip_modules[module_name] = True
 
     def mark_module_reloadable(self, module_name):
         """Reload the named module in the future (if it is imported)"""
         try:
             del self.skip_modules[module_name]
         except KeyError:
             pass
         self.modules[module_name] = True
 
     def aimport_module(self, module_name):
         """Import a module, and mark it reloadable
 
         Returns
         -------
         top_module : module
             The imported module if it is top-level, or the top-level
         top_name : module
             Name of top_module
 
         """
         self.mark_module_reloadable(module_name)
 
         __import__(module_name)
         top_name = module_name.split('.')[0]
         top_module = sys.modules[top_name]
         return top_module, top_name
 
     def check(self, check_all=False):
         """Check whether some modules need to be reloaded."""
 
         if not self.enabled and not check_all:
             return
 
         if check_all or self.check_all:
             modules = sys.modules.keys()
         else:
             modules = self.modules.keys()
 
         for modname in modules:
             m = sys.modules.get(modname, None)
 
             if modname in self.skip_modules:
                 continue
 
             if not hasattr(m, '__file__'):
                 continue
 
             if m.__name__ == '__main__':
                 # we cannot reload(__main__)
                 continue
 
             filename = m.__file__
             path, ext = os.path.splitext(filename)
 
             if ext.lower() == '.py':
-                pyc_filename = pyfile.cache_from_source(filename)
+                pyc_filename = openpy.cache_from_source(filename)
                 py_filename = filename
             else:
                 pyc_filename = filename
                 try:
-                    py_filename = pyfile.source_from_cache(filename)
+                    py_filename = openpy.source_from_cache(filename)
                 except ValueError:
                     continue
 
             try:
                 pymtime = os.stat(py_filename).st_mtime
                 if pymtime <= os.stat(pyc_filename).st_mtime:
                     continue
                 if self.failed.get(py_filename, None) == pymtime:
                     continue
             except OSError:
                 continue
 
             try:
                 superreload(m, reload, self.old_objects)
                 if py_filename in self.failed:
                     del self.failed[py_filename]
             except:
                 print("[autoreload of %s failed: %s]" % (
                         modname, traceback.format_exc(1)), file=sys.stderr)
                 self.failed[py_filename] = pymtime
 
 #------------------------------------------------------------------------------
 # superreload
 #------------------------------------------------------------------------------
 
 if PY3:
     func_attrs = ['__code__', '__defaults__', '__doc__',
                   '__closure__', '__globals__', '__dict__']
 else:
     func_attrs = ['func_code', 'func_defaults', 'func_doc',
                   'func_closure', 'func_globals', 'func_dict']
 
 
 def update_function(old, new):
     """Upgrade the code object of a function"""
     for name in func_attrs:
         try:
             setattr(old, name, getattr(new, name))
         except (AttributeError, TypeError):
             pass
 
 
 def update_class(old, new):
     """Replace stuff in the __dict__ of a class, and upgrade
     method code objects"""
     for key in old.__dict__.keys():
         old_obj = getattr(old, key)
 
         try:
             new_obj = getattr(new, key)
         except AttributeError:
             # obsolete attribute: remove it
             try:
                 delattr(old, key)
             except (AttributeError, TypeError):
                 pass
             continue
 
         if update_generic(old_obj, new_obj): continue
 
         try:
             setattr(old, key, getattr(new, key))
         except (AttributeError, TypeError):
             pass # skip non-writable attributes
 
 
 def update_property(old, new):
     """Replace get/set/del functions of a property"""
     update_generic(old.fdel, new.fdel)
     update_generic(old.fget, new.fget)
     update_generic(old.fset, new.fset)
 
 
 def isinstance2(a, b, typ):
     return isinstance(a, typ) and isinstance(b, typ)
 
 
 UPDATE_RULES = [
     (lambda a, b: isinstance2(a, b, type),
      update_class),
     (lambda a, b: isinstance2(a, b, types.FunctionType),
      update_function),
     (lambda a, b: isinstance2(a, b, property),
      update_property),
 ]
 
 
 if PY3:
     UPDATE_RULES.extend([(lambda a, b: isinstance2(a, b, types.MethodType),
                           lambda a, b: update_function(a.__func__, b.__func__)),
                         ])
 else:
     UPDATE_RULES.extend([(lambda a, b: isinstance2(a, b, types.ClassType),
                           update_class),
                          (lambda a, b: isinstance2(a, b, types.MethodType),
                           lambda a, b: update_function(a.im_func, b.im_func)),
                         ])
 
 
 def update_generic(a, b):
     for type_check, update in UPDATE_RULES:
         if type_check(a, b):
             update(a, b)
             return True
     return False
 
 
 class StrongRef(object):
     def __init__(self, obj):
         self.obj = obj
     def __call__(self):
         return self.obj
 
 
 def superreload(module, reload=reload, old_objects={}):
     """Enhanced version of the builtin reload function.
 
     superreload remembers objects previously in the module, and
 
     - upgrades the class dictionary of every old class in the module
     - upgrades the code object of every old function and method
     - clears the module's namespace before reloading
 
     """
 
     # collect old objects in the module
     for name, obj in module.__dict__.items():
         if not hasattr(obj, '__module__') or obj.__module__ != module.__name__:
             continue
         key = (module.__name__, name)
         try:
             old_objects.setdefault(key, []).append(weakref.ref(obj))
         except TypeError:
             # weakref doesn't work for all types;
             # create strong references for 'important' cases
             if not PY3 and isinstance(obj, types.ClassType):
                 old_objects.setdefault(key, []).append(StrongRef(obj))
 
     # reload module
     try:
         # clear namespace first from old cruft
         old_dict = module.__dict__.copy()
         old_name = module.__name__
         module.__dict__.clear()
         module.__dict__['__name__'] = old_name
         module.__dict__['__loader__'] = old_dict['__loader__']
     except (TypeError, AttributeError, KeyError):
         pass
 
     try:
         module = reload(module)
     except:
         # restore module dictionary on failed reload
         module.__dict__.update(old_dict)
         raise
 
     # iterate over all objects and update functions & classes
     for name, new_obj in module.__dict__.items():
         key = (module.__name__, name)
         if key not in old_objects: continue
 
         new_refs = []
         for old_ref in old_objects[key]:
             old_obj = old_ref()
             if old_obj is None: continue
             new_refs.append(old_ref)
             update_generic(old_obj, new_obj)
 
         if new_refs:
             old_objects[key] = new_refs
         else:
             del old_objects[key]
 
     return module
 
 #------------------------------------------------------------------------------
 # IPython connectivity
 #------------------------------------------------------------------------------
 
 from IPython.core.hooks import TryNext
 from IPython.core.magic import Magics, magics_class, line_magic
 
 @magics_class
 class AutoreloadMagics(Magics):
     def __init__(self, *a, **kw):
         super(AutoreloadMagics, self).__init__(*a, **kw)
         self._reloader = ModuleReloader()
         self._reloader.check_all = False
 
     @line_magic
     def autoreload(self, parameter_s=''):
         r"""%autoreload => Reload modules automatically
 
         %autoreload
         Reload all modules (except those excluded by %aimport) automatically
         now.
 
         %autoreload 0
         Disable automatic reloading.
 
         %autoreload 1
         Reload all modules imported with %aimport every time before executing
         the Python code typed.
 
         %autoreload 2
         Reload all modules (except those excluded by %aimport) every time
         before executing the Python code typed.
 
         Reloading Python modules in a reliable way is in general
         difficult, and unexpected things may occur. %autoreload tries to
         work around common pitfalls by replacing function code objects and
         parts of classes previously in the module with new versions. This
         makes the following things to work:
 
         - Functions and classes imported via 'from xxx import foo' are upgraded
           to new versions when 'xxx' is reloaded.
 
         - Methods and properties of classes are upgraded on reload, so that
           calling 'c.foo()' on an object 'c' created before the reload causes
           the new code for 'foo' to be executed.
 
         Some of the known remaining caveats are:
 
         - Replacing code objects does not always succeed: changing a @property
           in a class to an ordinary method or a method to a member variable
           can cause problems (but in old objects only).
 
         - Functions that are removed (eg. via monkey-patching) from a module
           before it is reloaded are not upgraded.
 
         - C extension modules cannot be reloaded, and so cannot be
           autoreloaded.
 
         """
         if parameter_s == '':
             self._reloader.check(True)
         elif parameter_s == '0':
             self._reloader.enabled = False
         elif parameter_s == '1':
             self._reloader.check_all = False
             self._reloader.enabled = True
         elif parameter_s == '2':
             self._reloader.check_all = True
             self._reloader.enabled = True
 
     @line_magic
     def aimport(self, parameter_s='', stream=None):
         """%aimport => Import modules for automatic reloading.
 
         %aimport
         List modules to automatically import and not to import.
 
         %aimport foo
         Import module 'foo' and mark it to be autoreloaded for %autoreload 1
 
         %aimport -foo
         Mark module 'foo' to not be autoreloaded for %autoreload 1
         """
         modname = parameter_s
         if not modname:
             to_reload = self._reloader.modules.keys()
             to_reload.sort()
             to_skip = self._reloader.skip_modules.keys()
             to_skip.sort()
             if stream is None:
                 stream = sys.stdout
             if self._reloader.check_all:
                 stream.write("Modules to reload:\nall-except-skipped\n")
             else:
                 stream.write("Modules to reload:\n%s\n" % ' '.join(to_reload))
             stream.write("\nModules to skip:\n%s\n" % ' '.join(to_skip))
         elif modname.startswith('-'):
             modname = modname[1:]
             self._reloader.mark_module_skipped(modname)
         else:
             top_module, top_name = self._reloader.aimport_module(modname)
 
             # Inject module to user namespace
             self.shell.push({top_name: top_module})
 
     def pre_run_code_hook(self, ip):
         if not self._reloader.enabled:
             raise TryNext
         try:
             self._reloader.check()
         except:
             pass
 
 
 def load_ipython_extension(ip):
     """Load the extension in IPython."""
     auto_reload = AutoreloadMagics(ip)
     ip.register_magics(auto_reload)
     ip.set_hook('pre_run_code_hook', auto_reload.pre_run_code_hook)

IPython/utils/openpy.py

@@ -1,219 +1,239 b''
 """
 Tools to open .py files as Unicode, using the encoding specified within the file,
 as per PEP 263.
 
 Much of the code is taken from the tokenize module in Python 3.2.
 """
 from __future__ import absolute_import
 
 import io
 from io import TextIOWrapper, BytesIO
+import os.path
 import re
 
 cookie_re = re.compile(ur"coding[:=]\s*([-\w.]+)", re.UNICODE)
 cookie_comment_re = re.compile(ur"^\s*#.*coding[:=]\s*([-\w.]+)", re.UNICODE)
 
 try:
     # Available in Python 3
     from tokenize import detect_encoding
 except ImportError:
     from codecs import lookup, BOM_UTF8
     
     # Copied from Python 3.2 tokenize
     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
     
     # Copied from Python 3.2 tokenize
     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:
                 line_string = line.decode('ascii')
             except UnicodeDecodeError:
                 return None
 
             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 codec.name != '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]
 
 try:
     # Available in Python 3.2 and above.
     from tokenize import open
 except ImportError:
     # Copied from Python 3.2 tokenize
     def open(filename):
         """Open a file in read only mode using the encoding detected by
         detect_encoding().
         """
         buffer = io.open(filename, 'rb')   # Tweaked to use io.open for Python 2
         encoding, lines = detect_encoding(buffer.readline)
         buffer.seek(0)
         text = TextIOWrapper(buffer, encoding, line_buffering=True)
         text.mode = 'r'
         return text   
 
 def source_to_unicode(txt, errors='replace', skip_encoding_cookie=True):
     """Converts a bytes string with python source code to unicode.
 
     Unicode strings are passed through unchanged. Byte strings are checked
     for the python source file encoding cookie to determine encoding.
     txt can be either a bytes buffer or a string containing the source
     code.
     """
     if isinstance(txt, unicode):
         return txt
     if isinstance(txt, bytes):
         buffer = BytesIO(txt)
     else:
         buffer = txt
     try:
         encoding, _ = detect_encoding(buffer.readline)
     except SyntaxError:
         encoding = "ascii"
     buffer.seek(0)
     text = TextIOWrapper(buffer, encoding, errors=errors, line_buffering=True)
     text.mode = 'r'
     if skip_encoding_cookie:
         return u"".join(strip_encoding_cookie(text))
     else:
         return text.read()
 
 def strip_encoding_cookie(filelike):
     """Generator to pull lines from a text-mode file, skipping the encoding
     cookie if it is found in the first two lines.
     """
     it = iter(filelike)
     try:
         first = next(it)
         if not cookie_comment_re.match(first):
             yield first
         second = next(it)
         if not cookie_comment_re.match(second):
             yield second
     except StopIteration:
         return
     
     for line in it:
         yield line
 
 def read_py_file(filename, skip_encoding_cookie=True):
     """Read a Python file, using the encoding declared inside the file.
     
     Parameters
     ----------
     filename : str
       The path to the file to read.
     skip_encoding_cookie : bool
       If True (the default), and the encoding declaration is found in the first
       two lines, that line will be excluded from the output - compiling a
       unicode string with an encoding declaration is a SyntaxError in Python 2.
     
     Returns
     -------
     A unicode string containing the contents of the file.
     """
     with open(filename) as f:   # the open function defined in this module.
         if skip_encoding_cookie:
             return "".join(strip_encoding_cookie(f))
         else:
             return f.read()
 
 def read_py_url(url, errors='replace', skip_encoding_cookie=True):
     """Read a Python file from a URL, using the encoding declared inside the file.
     
     Parameters
     ----------
     url : str
       The URL from which to fetch the file.
     errors : str
       How to handle decoding errors in the file. Options are the same as for
       bytes.decode(), but here 'replace' is the default.
     skip_encoding_cookie : bool
       If True (the default), and the encoding declaration is found in the first
       two lines, that line will be excluded from the output - compiling a
       unicode string with an encoding declaration is a SyntaxError in Python 2.
     
     Returns
     -------
     A unicode string containing the contents of the file.
     """
     from urllib import urlopen  # Deferred import for faster start
     response = urlopen(url)
     buffer = io.BytesIO(response.read())
     return source_to_unicode(buffer, errors, skip_encoding_cookie)
 
 def _list_readline(x):
     """Given a list, returns a readline() function that returns the next element
     with each call.
     """
     x = iter(x)
     def readline():
         return next(x)
     return readline
+
+# Code for going between .py files and cached .pyc files ----------------------
+
+try:    # Python 3.2, see PEP 3147
+    from imp import source_from_cache, cache_from_source
+except ImportError:
+    # Python <= 3.1: .pyc files go next to .py
+    def source_from_cache(path):
+        basename, ext = os.path.splitext(path)
+        if ext not in ('.pyc', '.pyo'):
+            raise ValueError('Not a cached Python file extension', ext)
+        # Should we look for .pyw files?
+        return basename + '.py'
+    
+    def cache_from_source(path, debug_override=None):
+        if debug_override is None:
+            debug_override = __debug__
+        basename, ext = os.path.splitext(path)
+        return basename + '.pyc' if debug_override else '.pyo'