Modify tests to expect unicode. Now all tests pass again.

IPython/config/loader.py

@@ -1,383 +1,384 b''
 # -*- coding: utf-8 -*-
 # coding: utf-8
 """A simple configuration system.
 
 Authors
 -------
 * Brian Granger
 * Fernando Perez
 """
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2008-2009  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.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 import __builtin__
 import os
 import sys
 
 from IPython.external import argparse
 from IPython.utils.path import filefind
 
 #-----------------------------------------------------------------------------
 # Exceptions
 #-----------------------------------------------------------------------------
 
 
 class ConfigError(Exception):
     pass
 
 
 class ConfigLoaderError(ConfigError):
     pass
 
 #-----------------------------------------------------------------------------
 # Argparse fix
 #-----------------------------------------------------------------------------
 
 # Unfortunately argparse by default prints help messages to stderr instead of
 # stdout.  This makes it annoying to capture long help screens at the command
 # line, since one must know how to pipe stderr, which many users don't know how
 # to do.  So we override the print_help method with one that defaults to
 # stdout and use our class instead.
 
 class ArgumentParser(argparse.ArgumentParser):
     """Simple argparse subclass that prints help to stdout by default."""
     
     def print_help(self, file=None):
         if file is None:
             file = sys.stdout
         return super(ArgumentParser, self).print_help(file)
     
     print_help.__doc__ = argparse.ArgumentParser.print_help.__doc__
     
 #-----------------------------------------------------------------------------
 # Config class for holding config information
 #-----------------------------------------------------------------------------
 
 
 class Config(dict):
     """An attribute based dict that can do smart merges."""
 
     def __init__(self, *args, **kwds):
         dict.__init__(self, *args, **kwds)
         # This sets self.__dict__ = self, but it has to be done this way
         # because we are also overriding __setattr__.
         dict.__setattr__(self, '__dict__', self)
 
     def _merge(self, other):
         to_update = {}
         for k, v in other.iteritems():
             if not self.has_key(k):
                 to_update[k] = v
             else: # I have this key
                 if isinstance(v, Config):
                     # Recursively merge common sub Configs
                     self[k]._merge(v)
                 else:
                     # Plain updates for non-Configs
                     to_update[k] = v
 
         self.update(to_update)
 
     def _is_section_key(self, key):
         if key[0].upper()==key[0] and not key.startswith('_'):
             return True
         else:
             return False
 
     def __contains__(self, key):
         if self._is_section_key(key):
             return True
         else:
             return super(Config, self).__contains__(key)
     # .has_key is deprecated for dictionaries.
     has_key = __contains__
 
     def _has_section(self, key):
         if self._is_section_key(key):
             if super(Config, self).__contains__(key):
                 return True
         return False
 
     def copy(self):
         return type(self)(dict.copy(self))
 
     def __copy__(self):
         return self.copy()
 
     def __deepcopy__(self, memo):
         import copy
         return type(self)(copy.deepcopy(self.items()))
 
     def __getitem__(self, key):
         # Because we use this for an exec namespace, we need to delegate
         # the lookup of names in __builtin__ to itself.  This means
         # that you can't have section or attribute names that are 
         # builtins.
         try:
             return getattr(__builtin__, key)
         except AttributeError:
             pass
         if self._is_section_key(key):
             try:
                 return dict.__getitem__(self, key)
             except KeyError:
                 c = Config()
                 dict.__setitem__(self, key, c)
                 return c
         else:
             return dict.__getitem__(self, key)
 
     def __setitem__(self, key, value):
         # Don't allow names in __builtin__ to be modified.
         if hasattr(__builtin__, key):
             raise ConfigError('Config variable names cannot have the same name '
                               'as a Python builtin: %s' % key)
         if self._is_section_key(key):
             if not isinstance(value, Config):
                 raise ValueError('values whose keys begin with an uppercase '
                                  'char must be Config instances: %r, %r' % (key, value))
         else:
             dict.__setitem__(self, key, value)
 
     def __getattr__(self, key):
         try:
             return self.__getitem__(key)
         except KeyError, e:
             raise AttributeError(e)
 
     def __setattr__(self, key, value):
         try:
             self.__setitem__(key, value)
         except KeyError, e:
             raise AttributeError(e)
 
     def __delattr__(self, key):
         try:
             dict.__delitem__(self, key)
         except KeyError, e:
             raise AttributeError(e)
 
 
 #-----------------------------------------------------------------------------
 # Config loading classes
 #-----------------------------------------------------------------------------
 
 
 class ConfigLoader(object):
     """A object for loading configurations from just about anywhere.
     
     The resulting configuration is packaged as a :class:`Struct`.
     
     Notes
     -----
     A :class:`ConfigLoader` does one thing: load a config from a source 
     (file, command line arguments) and returns the data as a :class:`Struct`.
     There are lots of things that :class:`ConfigLoader` does not do.  It does
     not implement complex logic for finding config files.  It does not handle
     default values or merge multiple configs.  These things need to be 
     handled elsewhere.
     """
 
     def __init__(self):
         """A base class for config loaders.
         
         Examples
         --------
         
         >>> cl = ConfigLoader()
         >>> config = cl.load_config()
         >>> config
         {}
         """
         self.clear()
 
     def clear(self):
         self.config = Config()
 
     def load_config(self):
         """Load a config from somewhere, return a :class:`Config` instance.
         
         Usually, this will cause self.config to be set and then returned.
         However, in most cases, :meth:`ConfigLoader.clear` should be called
         to erase any previous state.
         """
         self.clear()
         return self.config
 
 
 class FileConfigLoader(ConfigLoader):
     """A base class for file based configurations.
 
     As we add more file based config loaders, the common logic should go
     here.
     """
     pass
 
 
 class PyFileConfigLoader(FileConfigLoader):
     """A config loader for pure python files.
     
     This calls execfile on a plain python file and looks for attributes
     that are all caps.  These attribute are added to the config Struct.
     """
 
     def __init__(self, filename, path=None):
         """Build a config loader for a filename and path.
 
         Parameters
         ----------
         filename : str
             The file name of the config file.
         path : str, list, tuple
             The path to search for the config file on, or a sequence of
             paths to try in order.
         """
         super(PyFileConfigLoader, self).__init__()
         self.filename = filename
         self.path = path
         self.full_filename = ''
         self.data = None
 
     def load_config(self):
         """Load the config from a file and return it as a Struct."""
         self.clear()
         self._find_file()
         self._read_file_as_dict()
         self._convert_to_config()
         return self.config
 
     def _find_file(self):
         """Try to find the file by searching the paths."""
         self.full_filename = filefind(self.filename, self.path)
 
     def _read_file_as_dict(self):
         """Load the config file into self.config, with recursive loading."""
         # This closure is made available in the namespace that is used
         # to exec the config file.  This allows users to call
         # load_subconfig('myconfig.py') to load config files recursively.
         # It needs to be a closure because it has references to self.path
         # and self.config.  The sub-config is loaded with the same path
         # as the parent, but it uses an empty config which is then merged
         # with the parents.
         def load_subconfig(fname):
             loader = PyFileConfigLoader(fname, self.path)
             try:
                 sub_config = loader.load_config()
             except IOError:
                 # Pass silently if the sub config is not there. This happens
                 # when a user us using a profile, but not the default config.
                 pass
             else:
                 self.config._merge(sub_config)
 
         # Again, this needs to be a closure and should be used in config
         # files to get the config being loaded.
         def get_config():
             return self.config
 
         namespace = dict(load_subconfig=load_subconfig, get_config=get_config)
         fs_encoding = sys.getfilesystemencoding() or 'ascii'
         conf_filename = self.full_filename.encode(fs_encoding)
         execfile(conf_filename, namespace)
 
     def _convert_to_config(self):
         if self.data is None:
             ConfigLoaderError('self.data does not exist')
 
 
 class CommandLineConfigLoader(ConfigLoader):
     """A config loader for command line arguments.
 
     As we add more command line based loaders, the common logic should go
     here.
     """
 
 
 class ArgParseConfigLoader(CommandLineConfigLoader):
 
     def __init__(self, argv=None, *parser_args, **parser_kw):
         """Create a config loader for use with argparse.
 
         Parameters
         ----------
 
         argv : optional, list
           If given, used to read command-line arguments from, otherwise
           sys.argv[1:] is used.
 
         parser_args : tuple
           A tuple of positional arguments that will be passed to the
           constructor of :class:`argparse.ArgumentParser`.
 
         parser_kw : dict
           A tuple of keyword arguments that will be passed to the
           constructor of :class:`argparse.ArgumentParser`.
         """
         super(CommandLineConfigLoader, self).__init__()
         if argv == None:
             argv = sys.argv[1:]
         self.argv = argv
         self.parser_args = parser_args
         self.version = parser_kw.pop("version", None)
         kwargs = dict(argument_default=argparse.SUPPRESS)
         kwargs.update(parser_kw)
         self.parser_kw = kwargs
 
     def load_config(self, args=None):
         """Parse command line arguments and return as a Struct.
 
         Parameters
         ----------
 
         args : optional, list
           If given, a list with the structure of sys.argv[1:] to parse
           arguments from. If not given, the instance's self.argv attribute
           (given at construction time) is used."""
         self.clear()
         if args is None:
             args = self.argv
         self._create_parser()
         self._parse_args(args)
         self._convert_to_config()
         return self.config
 
     def get_extra_args(self):
         if hasattr(self, 'extra_args'):
             return self.extra_args
         else:
             return []
 
     def _create_parser(self):
         self.parser = ArgumentParser(*self.parser_args, **self.parser_kw)
         self._add_arguments()
 
     def _add_arguments(self):
         raise NotImplementedError("subclasses must implement _add_arguments")
 
     def _parse_args(self, args):
         """self.parser->self.parsed_data"""
         # decode sys.argv to support unicode command-line options
         uargs = []
         for a in args:
             if isinstance(a, str):
                 # don't decode if we already got unicode
-                a = a.decode(sys.stdin.encoding)
+                a = a.decode(sys.stdin.encoding or 
+                                            sys.getdefaultencoding())
             uargs.append(a)
         self.parsed_data, self.extra_args = self.parser.parse_known_args(uargs)
 
     def _convert_to_config(self):
         """self.parsed_data->self.config"""
         for k, v in vars(self.parsed_data).iteritems():
             exec_str = 'self.config.' + k + '= v'
             exec exec_str in locals(), globals()
 
 

IPython/core/inputsplitter.py

@@ -1,1009 +1,1009 b''
 """Analysis of text input into executable blocks.
 
 The main class in this module, :class:`InputSplitter`, is designed to break
 input from either interactive, line-by-line environments or block-based ones,
 into standalone blocks that can be executed by Python as 'single' statements
 (thus triggering sys.displayhook).
 
 A companion, :class:`IPythonInputSplitter`, provides the same functionality but
 with full support for the extended IPython syntax (magics, system calls, etc).
 
 For more details, see the class docstring below.
 
 Syntax Transformations
 ----------------------
 
 One of the main jobs of the code in this file is to apply all syntax
 transformations that make up 'the IPython language', i.e. magics, shell
 escapes, etc.  All transformations should be implemented as *fully stateless*
 entities, that simply take one line as their input and return a line.
 Internally for implementation purposes they may be a normal function or a
 callable object, but the only input they receive will be a single line and they
 should only return a line, without holding any data-dependent state between
 calls.
 
 As an example, the EscapedTransformer is a class so we can more clearly group
 together the functionality of dispatching to individual functions based on the
 starting escape character, but the only method for public use is its call
 method.
 
 
 ToDo
 ----
 
 - Should we make push() actually raise an exception once push_accepts_more()
   returns False?
 
 - Naming cleanups.  The tr_* names aren't the most elegant, though now they are
   at least just attributes of a class so not really very exposed.
 
 - Think about the best way to support dynamic things: automagic, autocall,
   macros, etc.
 
 - Think of a better heuristic for the application of the transforms in
   IPythonInputSplitter.push() than looking at the buffer ending in ':'.  Idea:
   track indentation change events (indent, dedent, nothing) and apply them only
   if the indentation went up, but not otherwise.
 
 - Think of the cleanest way for supporting user-specified transformations (the
   user prefilters we had before).
 
 Authors
 -------
 
 * Fernando Perez
 * Brian Granger
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010  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.
 #-----------------------------------------------------------------------------
 from __future__ import print_function
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 # stdlib
 import ast
 import codeop
 import re
 import sys
 
 # IPython modules
 from IPython.utils.text import make_quoted_expr
 
 #-----------------------------------------------------------------------------
 # Globals
 #-----------------------------------------------------------------------------
 
 # The escape sequences that define the syntax transformations IPython will
 # apply to user input.  These can NOT be just changed here: many regular
 # expressions and other parts of the code may use their hardcoded values, and
 # for all intents and purposes they constitute the 'IPython syntax', so they
 # should be considered fixed.
 
 ESC_SHELL  = '!'     # Send line to underlying system shell
 ESC_SH_CAP = '!!'    # Send line to system shell and capture output
 ESC_HELP   = '?'     # Find information about object
 ESC_HELP2  = '??'    # Find extra-detailed information about object
 ESC_MAGIC  = '%'     # Call magic function
 ESC_QUOTE  = ','     # Split args on whitespace, quote each as string and call
 ESC_QUOTE2 = ';'     # Quote all args as a single string, call
 ESC_PAREN  = '/'     # Call first argument with rest of line as arguments
 
 #-----------------------------------------------------------------------------
 # Utilities
 #-----------------------------------------------------------------------------
 
 # FIXME: These are general-purpose utilities that later can be moved to the
 # general ward.  Kept here for now because we're being very strict about test
 # coverage with this code, and this lets us ensure that we keep 100% coverage
 # while developing.
 
 # compiled regexps for autoindent management
 dedent_re = re.compile(r'^\s+raise|^\s+return|^\s+pass')
 ini_spaces_re = re.compile(r'^([ \t\r\f\v]+)')
 
 # regexp to match pure comment lines so we don't accidentally insert 'if 1:'
 # before pure comments
 comment_line_re = re.compile('^\s*\#')
 
 
 def num_ini_spaces(s):
     """Return the number of initial spaces in a string.
 
     Note that tabs are counted as a single space.  For now, we do *not* support
     mixing of tabs and spaces in the user's input.
 
     Parameters
     ----------
     s : string
 
     Returns
     -------
     n : int
     """
 
     ini_spaces = ini_spaces_re.match(s)
     if ini_spaces:
         return ini_spaces.end()
     else:
         return 0
 
 
 def remove_comments(src):
     """Remove all comments from input source.
 
     Note: comments are NOT recognized inside of strings!
 
     Parameters
     ----------
     src : string
       A single or multiline input string.
 
     Returns
     -------
     String with all Python comments removed.
     """
 
     return re.sub('#.*', '', src)
 
 
 def get_input_encoding():
     """Return the default standard input encoding.
 
     If sys.stdin has no encoding, 'ascii' is returned."""
     # There are strange environments for which sys.stdin.encoding is None. We
     # ensure that a valid encoding is returned.
     encoding = getattr(sys.stdin, 'encoding', None)
     if encoding is None:
         encoding = 'ascii'
     return encoding
 
 #-----------------------------------------------------------------------------
 # Classes and functions for normal Python syntax handling
 #-----------------------------------------------------------------------------
 
 # HACK!  This implementation, written by Robert K a while ago using the
 # compiler module, is more robust than the other one below, but it expects its
 # input to be pure python (no ipython syntax).  For now we're using it as a
 # second-pass splitter after the first pass transforms the input to pure
 # python.
 
 def split_blocks(python):
     """ Split multiple lines of code into discrete commands that can be
     executed singly.
 
     Parameters
     ----------
     python : str
         Pure, exec'able Python code.
 
     Returns
     -------
     commands : list of str
         Separate commands that can be exec'ed independently.
     """
     # compiler.parse treats trailing spaces after a newline as a
     # SyntaxError.  This is different than codeop.CommandCompiler, which
     # will compile the trailng spaces just fine.  We simply strip any
     # trailing whitespace off.  Passing a string with trailing whitespace
     # to exec will fail however.  There seems to be some inconsistency in
     # how trailing whitespace is handled, but this seems to work.
     python_ori = python # save original in case we bail on error
     python = python.strip()
 
     # The compiler module will parse the code into an abstract syntax tree.
     # This has a bug with str("a\nb"), but not str("""a\nb""")!!!
     try:
         code_ast = ast.parse(python)
     except:
         return [python_ori]
 
     # Uncomment to help debug the ast tree
     # for n in code_ast.body:
     #     print n.lineno,'->',n
 
     # Each separate command is available by iterating over ast.node. The
     # lineno attribute is the line number (1-indexed) beginning the commands
     # suite.
     # lines ending with ";" yield a Discard Node that doesn't have a lineno
     # attribute.  These nodes can and should be discarded.  But there are
     # other situations that cause Discard nodes that shouldn't be discarded.
     # We might eventually discover other cases where lineno is None and have
     # to put in a more sophisticated test.
     linenos = [x.lineno-1 for x in code_ast.body if x.lineno is not None]
 
     # When we finally get the slices, we will need to slice all the way to
     # the end even though we don't have a line number for it. Fortunately,
     # None does the job nicely.
     linenos.append(None)
 
     # Same problem at the other end: sometimes the ast tree has its
     # first complete statement not starting on line 0. In this case
     # we might miss part of it.  This fixes ticket 266993.  Thanks Gael!
     linenos[0] = 0
 
     lines = python.splitlines()
 
     # Create a list of atomic commands.
     cmds = []
     for i, j in zip(linenos[:-1], linenos[1:]):
         cmd = lines[i:j]
         if cmd:
             cmds.append('\n'.join(cmd)+'\n')
 
     return cmds
 
 
 class InputSplitter(object):
     """An object that can split Python source input in executable blocks.
 
     This object is designed to be used in one of two basic modes:
 
     1. By feeding it python source line-by-line, using :meth:`push`.  In this
        mode, it will return on each push whether the currently pushed code
        could be executed already.  In addition, it provides a method called
        :meth:`push_accepts_more` that can be used to query whether more input
        can be pushed into a single interactive block.
 
     2. By calling :meth:`split_blocks` with a single, multiline Python string,
        that is then split into blocks each of which can be executed
        interactively as a single statement.
 
     This is a simple example of how an interactive terminal-based client can use
     this tool::
 
         isp = InputSplitter()
         while isp.push_accepts_more():
             indent = ' '*isp.indent_spaces
             prompt = '>>> ' + indent
             line = indent + raw_input(prompt)
             isp.push(line)
         print 'Input source was:\n', isp.source_reset(),
     """
     # Number of spaces of indentation computed from input that has been pushed
     # so far.  This is the attributes callers should query to get the current
     # indentation level, in order to provide auto-indent facilities.
     indent_spaces = 0
     # String, indicating the default input encoding.  It is computed by default
     # at initialization time via get_input_encoding(), but it can be reset by a
     # client with specific knowledge of the encoding.
     encoding = ''
     # String where the current full source input is stored, properly encoded.
     # Reading this attribute is the normal way of querying the currently pushed
     # source code, that has been properly encoded.
     source = ''
     # Code object corresponding to the current source.  It is automatically
     # synced to the source, so it can be queried at any time to obtain the code
     # object; it will be None if the source doesn't compile to valid Python.
     code = None
     # Input mode
     input_mode = 'line'
     
     # Private attributes
     
     # List with lines of input accumulated so far
     _buffer = None
     # Command compiler
     _compile = None
     # Mark when input has changed indentation all the way back to flush-left
     _full_dedent = False
     # Boolean indicating whether the current block is complete
     _is_complete = None
     
     def __init__(self, input_mode=None):
         """Create a new InputSplitter instance.
 
         Parameters
         ----------
         input_mode : str
 
           One of ['line', 'cell']; default is 'line'.
 
        The input_mode parameter controls how new inputs are used when fed via
        the :meth:`push` method:
 
        - 'line': meant for line-oriented clients, inputs are appended one at a
          time to the internal buffer and the whole buffer is compiled.
 
        - 'cell': meant for clients that can edit multi-line 'cells' of text at
           a time.  A cell can contain one or more blocks that can be compile in
           'single' mode by Python.  In this mode, each new input new input
           completely replaces all prior inputs.  Cell mode is thus equivalent
           to prepending a full reset() to every push() call.
         """
         self._buffer = []
         self._compile = codeop.CommandCompiler()
         self.encoding = get_input_encoding()
         self.input_mode = InputSplitter.input_mode if input_mode is None \
                           else input_mode
 
     def reset(self):
         """Reset the input buffer and associated state."""
         self.indent_spaces = 0
         self._buffer[:] = []
         self.source = ''
         self.code = None
         self._is_complete = False
         self._full_dedent = False
 
     def source_reset(self):
         """Return the input source and perform a full reset.
         """
         out = self.source
         self.reset()
         return out
 
     def push(self, lines):
         """Push one or more lines of input.
 
         This stores the given lines and returns a status code indicating
         whether the code forms a complete Python block or not.
 
         Any exceptions generated in compilation are swallowed, but if an
         exception was produced, the method returns True.
 
         Parameters
         ----------
         lines : string
           One or more lines of Python input.
         
         Returns
         -------
         is_complete : boolean
           True if the current input source (the result of the current input
         plus prior inputs) forms a complete Python execution block.  Note that
         this value is also stored as a private attribute (_is_complete), so it
         can be queried at any time.
         """
         if self.input_mode == 'cell':
             self.reset()
         
         self._store(lines)
         source = self.source
 
         # Before calling _compile(), reset the code object to None so that if an
         # exception is raised in compilation, we don't mislead by having
         # inconsistent code/source attributes.
         self.code, self._is_complete = None, None
 
         # Honor termination lines properly
         if source.rstrip().endswith('\\'):
             return False
 
         self._update_indent(lines)
         try:
             self.code = self._compile(source)
         # Invalid syntax can produce any of a number of different errors from
         # inside the compiler, so we have to catch them all.  Syntax errors
         # immediately produce a 'ready' block, so the invalid Python can be
         # sent to the kernel for evaluation with possible ipython
         # special-syntax conversion.
         except (SyntaxError, OverflowError, ValueError, TypeError,
                 MemoryError):
             self._is_complete = True
         else:
             # Compilation didn't produce any exceptions (though it may not have
             # given a complete code object)
             self._is_complete = self.code is not None
 
         return self._is_complete
 
     def push_accepts_more(self):
         """Return whether a block of interactive input can accept more input.
 
         This method is meant to be used by line-oriented frontends, who need to
         guess whether a block is complete or not based solely on prior and
         current input lines.  The InputSplitter considers it has a complete
         interactive block and will not accept more input only when either a
         SyntaxError is raised, or *all* of the following are true:
 
         1. The input compiles to a complete statement.
         
         2. The indentation level is flush-left (because if we are indented,
            like inside a function definition or for loop, we need to keep
            reading new input).
           
         3. There is one extra line consisting only of whitespace.
 
         Because of condition #3, this method should be used only by
         *line-oriented* frontends, since it means that intermediate blank lines
         are not allowed in function definitions (or any other indented block).
 
         Block-oriented frontends that have a separate keyboard event to
         indicate execution should use the :meth:`split_blocks` method instead.
 
         If the current input produces a syntax error, this method immediately
         returns False but does *not* raise the syntax error exception, as
         typically clients will want to send invalid syntax to an execution
         backend which might convert the invalid syntax into valid Python via
         one of the dynamic IPython mechanisms.
         """
 
         # With incomplete input, unconditionally accept more
         if not self._is_complete:
             return True
 
         # If we already have complete input and we're flush left, the answer
         # depends.  In line mode, if there hasn't been any indentation,
         # that's it. If we've come back from some indentation, we need
         # the blank final line to finish.
         # In cell mode, we need to check how many blocks the input so far
         # compiles into, because if there's already more than one full
         # independent block of input, then the client has entered full
         # 'cell' mode and is feeding lines that each is complete.  In this
         # case we should then keep accepting. The Qt terminal-like console
         # does precisely this, to provide the convenience of terminal-like
         # input of single expressions, but allowing the user (with a
         # separate keystroke) to switch to 'cell' mode and type multiple
         # expressions in one shot.
         if self.indent_spaces==0:
             if self.input_mode=='line':
                 if not self._full_dedent:
                     return False
             else:
                 nblocks = len(split_blocks(''.join(self._buffer)))
                 if nblocks==1:
                     return False
 
         # When input is complete, then termination is marked by an extra blank
         # line at the end.
         last_line = self.source.splitlines()[-1]
         return bool(last_line and not last_line.isspace())
         
     def split_blocks(self, lines):
         """Split a multiline string into multiple input blocks.
 
         Note: this method starts by performing a full reset().
         
         Parameters
         ----------
         lines : str
           A possibly multiline string.
 
         Returns
         -------
         blocks : list
           A list of strings, each possibly multiline.  Each string corresponds
           to a single block that can be compiled in 'single' mode (unless it
           has a syntax error)."""
 
         # This code is fairly delicate.  If you make any changes here, make
         # absolutely sure that you do run the full test suite and ALL tests
         # pass.
 
         self.reset()
         blocks = []
         
         # Reversed copy so we can use pop() efficiently and consume the input
         # as a stack
         lines = lines.splitlines()[::-1]
         # Outer loop over all input
         while lines:
             #print 'Current lines:', lines  # dbg
             # Inner loop to build each block
             while True:
                 # Safety exit from inner loop
                 if not lines:
                     break
                 # Grab next line but don't push it yet
                 next_line = lines.pop()
                 # Blank/empty lines are pushed as-is
                 if not next_line or next_line.isspace():
                     self.push(next_line)
                     continue
 
                 # Check indentation changes caused by the *next* line
                 indent_spaces, _full_dedent = self._find_indent(next_line)
 
                 # If the next line causes a dedent, it can be for two differnt
                 # reasons: either an explicit de-dent by the user or a
                 # return/raise/pass statement.  These MUST be handled
                 # separately:
                 #
                 # 1. the first case is only detected when the actual explicit
                 # dedent happens, and that would be the *first* line of a *new*
                 # block.  Thus, we must put the line back into the input buffer
                 # so that it starts a new block on the next pass.
                 #
                 # 2. the second case is detected in the line before the actual
                 # dedent happens, so , we consume the line and we can break out
                 # to start a new block.
 
                 # Case 1, explicit dedent causes a break.
                 # Note: check that we weren't on the very last line, else we'll
                 # enter an infinite loop adding/removing the last line.
                 if  _full_dedent and lines and not next_line.startswith(' '):
                     lines.append(next_line)
                     break
                 
                 # Otherwise any line is pushed
                 self.push(next_line)
 
                 # Case 2, full dedent with full block ready:
                 if _full_dedent or \
                        self.indent_spaces==0 and not self.push_accepts_more():
                     break
             # Form the new block with the current source input
             blocks.append(self.source_reset())
             
         #return blocks
         # HACK!!! Now that our input is in blocks but guaranteed to be pure
         # python syntax, feed it back a second time through the AST-based
         # splitter, which is more accurate than ours.
         return split_blocks(''.join(blocks))
 
     #------------------------------------------------------------------------
     # Private interface
     #------------------------------------------------------------------------
 
     def _find_indent(self, line):
         """Compute the new indentation level for a single line.
 
         Parameters
         ----------
         line : str
           A single new line of non-whitespace, non-comment Python input.
           
         Returns
         -------
         indent_spaces : int
           New value for the indent level (it may be equal to self.indent_spaces
         if indentation doesn't change.
 
         full_dedent : boolean
           Whether the new line causes a full flush-left dedent.
         """
         indent_spaces = self.indent_spaces
         full_dedent = self._full_dedent
         
         inisp = num_ini_spaces(line)
         if inisp < indent_spaces:
             indent_spaces = inisp
             if indent_spaces <= 0:
                 #print 'Full dedent in text',self.source # dbg
                 full_dedent = True
 
         if line[-1] == ':':
             indent_spaces += 4
         elif dedent_re.match(line):
             indent_spaces -= 4
             if indent_spaces <= 0:
                 full_dedent = True
 
         # Safety
         if indent_spaces < 0:
             indent_spaces = 0
             #print 'safety' # dbg
             
         return indent_spaces, full_dedent
     
     def _update_indent(self, lines):
         for line in remove_comments(lines).splitlines():
             if line and not line.isspace():
                 self.indent_spaces, self._full_dedent = self._find_indent(line)
 
     def _store(self, lines, buffer=None, store='source'):
         """Store one or more lines of input.
 
         If input lines are not newline-terminated, a newline is automatically
         appended."""
         
         if buffer is None:
             buffer = self._buffer
             
         if lines.endswith('\n'):
             buffer.append(lines)
         else:
             buffer.append(lines+'\n')
         setattr(self, store, self._set_source(buffer))
 
     def _set_source(self, buffer):
         return u''.join(buffer)
 
 
 #-----------------------------------------------------------------------------
 # Functions and classes for IPython-specific syntactic support
 #-----------------------------------------------------------------------------
 
 # RegExp for splitting line contents into pre-char//first word-method//rest.
 # For clarity, each group in on one line.
 
 line_split = re.compile("""
              ^(\s*)              # any leading space
              ([,;/%]|!!?|\?\??)  # escape character or characters
              \s*(%?[\w\.\*]*)    # function/method, possibly with leading %
                                  # to correctly treat things like '?%magic'
              (\s+.*$|$)          # rest of line
              """, re.VERBOSE)
 
 
 def split_user_input(line):
     """Split user input into early whitespace, esc-char, function part and rest.
 
     This is currently handles lines with '=' in them in a very inconsistent
     manner.
 
     Examples
     ========
     >>> split_user_input('x=1')
     ('', '', 'x=1', '')
     >>> split_user_input('?')
     ('', '?', '', '')
     >>> split_user_input('??')
     ('', '??', '', '')
     >>> split_user_input(' ?')
     (' ', '?', '', '')
     >>> split_user_input(' ??')
     (' ', '??', '', '')
     >>> split_user_input('??x')
     ('', '??', 'x', '')
     >>> split_user_input('?x=1')
     ('', '', '?x=1', '')
     >>> split_user_input('!ls')
     ('', '!', 'ls', '')
     >>> split_user_input('  !ls')
     ('  ', '!', 'ls', '')
     >>> split_user_input('!!ls')
     ('', '!!', 'ls', '')
     >>> split_user_input('  !!ls')
     ('  ', '!!', 'ls', '')
     >>> split_user_input(',ls')
     ('', ',', 'ls', '')
     >>> split_user_input(';ls')
     ('', ';', 'ls', '')
     >>> split_user_input('  ;ls')
     ('  ', ';', 'ls', '')
     >>> split_user_input('f.g(x)')
     ('', '', 'f.g(x)', '')
     >>> split_user_input('f.g (x)')
     ('', '', 'f.g', '(x)')
     >>> split_user_input('?%hist')
     ('', '?', '%hist', '')
     >>> split_user_input('?x*')
     ('', '?', 'x*', '')
     """
     match = line_split.match(line)
     if match:
         lspace, esc, fpart, rest = match.groups()
     else:
         # print "match failed for line '%s'" % line
         try:
             fpart, rest = line.split(None, 1)
         except ValueError:
             # print "split failed for line '%s'" % line
             fpart, rest = line,''
         lspace = re.match('^(\s*)(.*)', line).groups()[0]
         esc = ''
 
     # fpart has to be a valid python identifier, so it better be only pure
     # ascii, no unicode:
     try:
         fpart = fpart.encode('ascii')
     except UnicodeEncodeError:
         lspace = unicode(lspace)
         rest = fpart + u' ' + rest
         fpart = u''
 
     #print 'line:<%s>' % line # dbg
     #print 'esc <%s> fpart <%s> rest <%s>' % (esc,fpart.strip(),rest) # dbg
     return lspace, esc, fpart.strip(), rest.lstrip()
 
 
 # The escaped translators ALL receive a line where their own escape has been
 # stripped.  Only '?' is valid at the end of the line, all others can only be
 # placed at the start.
 
 class LineInfo(object):
     """A single line of input and associated info.
 
     This is a utility class that mostly wraps the output of
     :func:`split_user_input` into a convenient object to be passed around
     during input transformations.
 
     Includes the following as properties: 
 
     line
       The original, raw line
 
     lspace
       Any early whitespace before actual text starts.
 
     esc
       The initial esc character (or characters, for double-char escapes like
       '??' or '!!').
     
     fpart
       The 'function part', which is basically the maximal initial sequence
       of valid python identifiers and the '.' character.  This is what is
       checked for alias and magic transformations, used for auto-calling,
       etc.
     
     rest
       Everything else on the line.
     """
     def __init__(self, line):
         self.line = line
         self.lspace, self.esc, self.fpart, self.rest = \
                              split_user_input(line)
 
     def __str__(self):                                                         
         return "LineInfo [%s|%s|%s|%s]" % (self.lspace, self.esc,
                                            self.fpart, self.rest)
 
 
 # Transformations of the special syntaxes that don't rely on an explicit escape
 # character but instead on patterns on the input line
 
 # The core transformations are implemented as standalone functions that can be
 # tested and validated in isolation.  Each of these uses a regexp, we
 # pre-compile these and keep them close to each function definition for clarity
 
 _assign_system_re = re.compile(r'(?P<lhs>(\s*)([\w\.]+)((\s*,\s*[\w\.]+)*))'
                                r'\s*=\s*!\s*(?P<cmd>.*)')
 
 def transform_assign_system(line):
     """Handle the `files = !ls` syntax."""
     m = _assign_system_re.match(line)
     if m is not None:
         cmd = m.group('cmd')
         lhs = m.group('lhs')
         expr = make_quoted_expr(cmd)
         new_line = '%s = get_ipython().getoutput(%s)' % (lhs, expr)
         return new_line
     return line
 
 
 _assign_magic_re = re.compile(r'(?P<lhs>(\s*)([\w\.]+)((\s*,\s*[\w\.]+)*))'
                                r'\s*=\s*%\s*(?P<cmd>.*)')
 
 def transform_assign_magic(line):
     """Handle the `a = %who` syntax."""
     m = _assign_magic_re.match(line)
     if m is not None:
         cmd = m.group('cmd')
         lhs = m.group('lhs')
         expr = make_quoted_expr(cmd)
         new_line = '%s = get_ipython().magic(%s)' % (lhs, expr)
         return new_line
     return line
 
 
 _classic_prompt_re = re.compile(r'^([ \t]*>>> |^[ \t]*\.\.\. )')
 
 def transform_classic_prompt(line):
     """Handle inputs that start with '>>> ' syntax."""
 
     if not line or line.isspace():
         return line
     m = _classic_prompt_re.match(line)
     if m:
         return line[len(m.group(0)):]
     else:
         return line
 
 
 _ipy_prompt_re = re.compile(r'^([ \t]*In \[\d+\]: |^[ \t]*\ \ \ \.\.\.+: )')
 
 def transform_ipy_prompt(line):
     """Handle inputs that start classic IPython prompt syntax."""
 
     if not line or line.isspace():
         return line
     #print 'LINE:  %r' % line # dbg
     m = _ipy_prompt_re.match(line)
     if m:
         #print 'MATCH! %r -> %r' % (line, line[len(m.group(0)):]) # dbg
         return line[len(m.group(0)):]
     else:
         return line
 
 
 class EscapedTransformer(object):
     """Class to transform lines that are explicitly escaped out."""
 
     def __init__(self):
         tr = { ESC_SHELL  : self._tr_system,
                ESC_SH_CAP : self._tr_system2,
                ESC_HELP   : self._tr_help,
                ESC_HELP2  : self._tr_help,
                ESC_MAGIC  : self._tr_magic,
                ESC_QUOTE  : self._tr_quote,
                ESC_QUOTE2 : self._tr_quote2,
                ESC_PAREN  : self._tr_paren }
         self.tr = tr
         
     # Support for syntax transformations that use explicit escapes typed by the
     # user at the beginning of a line
     @staticmethod
     def _tr_system(line_info):
         "Translate lines escaped with: !"
         cmd = line_info.line.lstrip().lstrip(ESC_SHELL)
         return '%sget_ipython().system(%s)' % (line_info.lspace,
                                                make_quoted_expr(cmd))
 
     @staticmethod
     def _tr_system2(line_info):
         "Translate lines escaped with: !!"
         cmd = line_info.line.lstrip()[2:]
         return '%sget_ipython().getoutput(%s)' % (line_info.lspace,
                                                   make_quoted_expr(cmd))
 
     @staticmethod
     def _tr_help(line_info):
         "Translate lines escaped with: ?/??"
         # A naked help line should just fire the intro help screen
         if not line_info.line[1:]:
             return 'get_ipython().show_usage()'
 
         # There may be one or two '?' at the end, move them to the front so that
         # the rest of the logic can assume escapes are at the start
         l_ori = line_info
         line = line_info.line
         if line.endswith('?'):
             line = line[-1] + line[:-1]
         if line.endswith('?'):
             line = line[-1] + line[:-1]
         line_info = LineInfo(line)
 
         # From here on, simply choose which level of detail to get, and
         # special-case the psearch syntax
         pinfo = 'pinfo' # default
         if '*' in line_info.line:
             pinfo = 'psearch'
         elif line_info.esc == '??':
             pinfo = 'pinfo2'
 
-        tpl = '%sget_ipython().magic("%s %s")'
+        tpl = '%sget_ipython().magic(u"%s %s")'
         return tpl % (line_info.lspace, pinfo,
                       ' '.join([line_info.fpart, line_info.rest]).strip())
 
     @staticmethod
     def _tr_magic(line_info):
         "Translate lines escaped with: %"
         tpl = '%sget_ipython().magic(%s)'
         cmd = make_quoted_expr(' '.join([line_info.fpart,
                                          line_info.rest]).strip())
         return tpl % (line_info.lspace, cmd)
 
     @staticmethod
     def _tr_quote(line_info):
         "Translate lines escaped with: ,"
         return '%s%s("%s")' % (line_info.lspace, line_info.fpart,
                              '", "'.join(line_info.rest.split()) )
 
     @staticmethod
     def _tr_quote2(line_info):
         "Translate lines escaped with: ;"
         return '%s%s("%s")' % (line_info.lspace, line_info.fpart,
                                line_info.rest)
 
     @staticmethod
     def _tr_paren(line_info):
         "Translate lines escaped with: /"
         return '%s%s(%s)' % (line_info.lspace, line_info.fpart,
                              ", ".join(line_info.rest.split()))
 
     def __call__(self, line):
         """Class to transform lines that are explicitly escaped out.
 
         This calls the above _tr_* static methods for the actual line
         translations."""
 
         # Empty lines just get returned unmodified
         if not line or line.isspace():
             return line
 
         # Get line endpoints, where the escapes can be
         line_info = LineInfo(line)
 
         # If the escape is not at the start, only '?' needs to be special-cased.
         # All other escapes are only valid at the start
         if not line_info.esc in self.tr:
             if line.endswith(ESC_HELP):
                 return self._tr_help(line_info)
             else:
                 # If we don't recognize the escape, don't modify the line
                 return line
 
         return self.tr[line_info.esc](line_info)
 
 
 # A function-looking object to be used by the rest of the code.  The purpose of
 # the class in this case is to organize related functionality, more than to
 # manage state.
 transform_escaped = EscapedTransformer()
 
 
 class IPythonInputSplitter(InputSplitter):
     """An input splitter that recognizes all of IPython's special syntax."""
 
     # String with raw, untransformed input.
     source_raw = ''
 
     # Private attributes
     
     # List with lines of raw input accumulated so far.
     _buffer_raw = None
 
     def __init__(self, input_mode=None):
         InputSplitter.__init__(self, input_mode)
         self._buffer_raw = []
         
     def reset(self):
         """Reset the input buffer and associated state."""
         InputSplitter.reset(self)
         self._buffer_raw[:] = []
         self.source_raw = ''
 
     def source_raw_reset(self):
         """Return input and raw source and perform a full reset.
         """
         out = self.source
         out_r = self.source_raw
         self.reset()
         return out, out_r
 
     def push(self, lines):
         """Push one or more lines of IPython input.
         """
         if not lines:
             return super(IPythonInputSplitter, self).push(lines)
 
         # We must ensure all input is pure unicode
         if type(lines)==str:
             lines = lines.decode(self.encoding)
 
         lines_list = lines.splitlines()
 
         transforms = [transform_escaped, transform_assign_system,
                       transform_assign_magic, transform_ipy_prompt,
                       transform_classic_prompt]
 
         # Transform logic
         #
         # We only apply the line transformers to the input if we have either no
         # input yet, or complete input, or if the last line of the buffer ends
         # with ':' (opening an indented block).  This prevents the accidental
         # transformation of escapes inside multiline expressions like
         # triple-quoted strings or parenthesized expressions.
         #
         # The last heuristic, while ugly, ensures that the first line of an
         # indented block is correctly transformed.
         #
         # FIXME: try to find a cleaner approach for this last bit.
 
         # If we were in 'block' mode, since we're going to pump the parent
         # class by hand line by line, we need to temporarily switch out to
         # 'line' mode, do a single manual reset and then feed the lines one
         # by one.  Note that this only matters if the input has more than one
         # line.
         changed_input_mode = False
 
         if self.input_mode == 'cell':
             self.reset()
             changed_input_mode = True
             saved_input_mode = 'cell'
             self.input_mode = 'line'
 
         # Store raw source before applying any transformations to it.  Note
         # that this must be done *after* the reset() call that would otherwise
         # flush the buffer.
         self._store(lines, self._buffer_raw, 'source_raw')
         
         try:
             push = super(IPythonInputSplitter, self).push
             for line in lines_list:
                 if self._is_complete or not self._buffer or \
                    (self._buffer and self._buffer[-1].rstrip().endswith(':')):
                     for f in transforms:
                         line = f(line)
 
                 out = push(line)
         finally:
             if changed_input_mode:
                 self.input_mode = saved_input_mode
         return out

IPython/core/tests/test_handlers.py

@@ -1,174 +1,174 b''
 """Tests for input handlers.
 """
 #-----------------------------------------------------------------------------
 # Module imports
 #-----------------------------------------------------------------------------
 
 # third party
 import nose.tools as nt
 
 # our own packages
 from IPython.core import autocall
 from IPython.testing import decorators as dec
 from IPython.testing.globalipapp import get_ipython
 
 #-----------------------------------------------------------------------------
 # Globals
 #-----------------------------------------------------------------------------
 
 # Get the public instance of IPython
 ip = get_ipython()
 
 failures = []
 num_tests = 0
 
 #-----------------------------------------------------------------------------
 # Test functions
 #-----------------------------------------------------------------------------
 
 class CallableIndexable(object):
     def __getitem__(self, idx): return True
     def __call__(self, *args, **kws): return True
 
 
 class Autocallable(autocall.IPyAutocall):
     def __call__(self):
         return "called"
 
 
 def run(tests):
     """Loop through a list of (pre, post) inputs, where pre is the string
     handed to ipython, and post is how that string looks after it's been
     transformed (i.e. ipython's notion of _i)"""
     for pre, post in tests:
         global num_tests
         num_tests += 1        
         ip.runlines(pre)
         ip.runlines('_i')  # Not sure why I need this...
         actual = ip.user_ns['_i']
         if actual != None:
             actual = actual.rstrip('\n')
         if actual != post:
             failures.append('Expected %r to become %r, found %r' % (
                 pre, post, actual))
 
 
 def test_handlers():
     # alias expansion
 
     # We're using 'true' as our syscall of choice because it doesn't
     # write anything to stdout.
 
     # Turn off actual execution of aliases, because it's noisy
     old_system_cmd = ip.system
     ip.system = lambda cmd: None
 
 
     ip.alias_manager.alias_table['an_alias'] = (0, 'true')
     # These are useful for checking a particular recursive alias issue
     ip.alias_manager.alias_table['top'] = (0, 'd:/cygwin/top')
     ip.alias_manager.alias_table['d'] =   (0, 'true')
-    run([("an_alias",    'get_ipython().system("true ")'),     # alias
+    run([("an_alias",    'get_ipython().system(u"true ")'),     # alias
          # Below: recursive aliases should expand whitespace-surrounded
          # chars, *not* initial chars which happen to be aliases:
-         ("top",         'get_ipython().system("d:/cygwin/top ")'),
+         ("top",         'get_ipython().system(u"d:/cygwin/top ")'),
          ])
     ip.system = old_system_cmd
 
     call_idx = CallableIndexable()
     ip.user_ns['call_idx'] = call_idx
 
     # For many of the below, we're also checking that leading whitespace
     # turns off the esc char, which it should unless there is a continuation
     # line.
     run([('"no change"', '"no change"'),             # normal
-         ("!true",       'get_ipython().system("true")'),      # shell_escapes
-         ("!! true",     'get_ipython().magic("sx  true")'),   # shell_escapes + magic
-         ("!!true",      'get_ipython().magic("sx true")'),    # shell_escapes + magic
-         ("%lsmagic",    'get_ipython().magic("lsmagic ")'),   # magic
-         ("lsmagic",     'get_ipython().magic("lsmagic ")'),   # magic
+         ("!true",       'get_ipython().system(u"true")'),      # shell_escapes
+         ("!! true",     'get_ipython().magic(u"sx  true")'),   # shell_escapes + magic
+         ("!!true",      'get_ipython().magic(u"sx true")'),    # shell_escapes + magic
+         ("%lsmagic",    'get_ipython().magic(u"lsmagic ")'),   # magic
+         ("lsmagic",     'get_ipython().magic(u"lsmagic ")'),   # magic
          #("a = b # PYTHON-MODE", '_i'),          # emacs -- avoids _in cache
 
          # post-esc-char whitespace goes inside
-         ("! true",   'get_ipython().system(" true")'),  
+         ("! true",   'get_ipython().system(u" true")'),  
 
          # handle_help
 
          # These are weak tests -- just looking at what the help handlers
          # logs, which is not how it really does its work.  But it still
          # lets us check the key paths through the handler.
 
          ("x=1 # what?", "x=1 # what?"), # no help if valid python
          ])
 
     # multi_line_specials
     ip.prefilter_manager.multi_line_specials = False
     # W/ multi_line_specials off, leading ws kills esc chars/autoexpansion
     run([
         ('if 1:\n    !true',    'if 1:\n    !true'),
         ('if 1:\n    lsmagic',  'if 1:\n    lsmagic'),
         ('if 1:\n    an_alias', 'if 1:\n    an_alias'),
         ])
 
     ip.prefilter_manager.multi_line_specials = True
     # initial indents must be preserved.
     run([
-         ('if 1:\n    !true',    'if 1:\n    get_ipython().system("true")'),
-         ('if 2:\n    lsmagic',  'if 2:\n    get_ipython().magic("lsmagic ")'),
-         ('if 1:\n    an_alias', 'if 1:\n    get_ipython().system("true ")'),
+         ('if 1:\n    !true',    'if 1:\n    get_ipython().system(u"true")'),
+         ('if 2:\n    lsmagic',  'if 2:\n    get_ipython().magic(u"lsmagic ")'),
+         ('if 1:\n    an_alias', 'if 1:\n    get_ipython().system(u"true ")'),
          # Weird one
-         ('if 1:\n    !!true',   'if 1:\n    get_ipython().magic("sx true")'),
+         ('if 1:\n    !!true',   'if 1:\n    get_ipython().magic(u"sx true")'),
 
          # Even with m_l_s on, autocall is off even with special chars
          ('if 1:\n    /fun 1 2', 'if 1:\n    /fun 1 2'), 
          ('if 1:\n    ;fun 1 2', 'if 1:\n    ;fun 1 2'),
          ('if 1:\n    ,fun 1 2', 'if 1:\n    ,fun 1 2'),
          ('if 1:\n    ?fun 1 2', 'if 1:\n    ?fun 1 2'),
          # What about !!  
          ])
 
     # Objects which are instances of IPyAutocall are *always* autocalled
     autocallable = Autocallable()
     ip.user_ns['autocallable'] = autocallable
 
     # auto 
     ip.magic('autocall 0')
     # Only explicit escapes or instances of IPyAutocallable should get
     # expanded
     run([
         ('len "abc"',       'len "abc"'),        
         ('autocallable',    'autocallable()'),     
         (",list 1 2 3",     'list("1", "2", "3")'),
         (";list 1 2 3",     'list("1 2 3")'),      
         ("/len range(1,4)", 'len(range(1,4))'),
         ])
     ip.magic('autocall 1')
     run([
         (",list 1 2 3", 'list("1", "2", "3")'),
         (";list 1 2 3", 'list("1 2 3")'),      
         ("/len range(1,4)", 'len(range(1,4))'),
         ('len "abc"', 'len("abc")'),
         ('len "abc";', 'len("abc");'),  # ; is special -- moves out of parens
         # Autocall is turned off if first arg is [] and the object
         # is both callable and indexable.  Like so:
         ('len [1,2]', 'len([1,2])'),      # len doesn't support __getitem__...
         ('call_idx [1]', 'call_idx [1]'), # call_idx *does*..
         ('call_idx 1', 'call_idx(1)'),
         ('len', 'len '), # only at 2 does it auto-call on single args
         ])
     ip.magic('autocall 2')
     run([
         (",list 1 2 3", 'list("1", "2", "3")'),
         (";list 1 2 3", 'list("1 2 3")'),      
         ("/len range(1,4)", 'len(range(1,4))'),
         ('len "abc"', 'len("abc")'),
         ('len "abc";', 'len("abc");'),
         ('len [1,2]', 'len([1,2])'),   
         ('call_idx [1]', 'call_idx [1]'),
         ('call_idx 1', 'call_idx(1)'),
         # This is what's different:
         ('len', 'len()'), # only at 2 does it auto-call on single args
         ])
     ip.magic('autocall 1')
 
     nt.assert_equals(failures, [])

IPython/core/tests/test_inputsplitter.py

@@ -1,704 +1,704 b''
 # -*- coding: utf-8 -*-
 """Tests for the inputsplitter module.
 
 Authors
 -------
 * Fernando Perez
 * Robert Kern
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010  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.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 # stdlib
 import unittest
 import sys
 
 # Third party
 import nose.tools as nt
 
 # Our own
 from IPython.core import inputsplitter as isp
 
 #-----------------------------------------------------------------------------
 # Semi-complete examples (also used as tests)
 #-----------------------------------------------------------------------------
 
 # Note: at the bottom, there's a slightly more complete version of this that
 # can be useful during development of code here.
 
 def mini_interactive_loop(input_func):
     """Minimal example of the logic of an interactive interpreter loop.
 
     This serves as an example, and it is used by the test system with a fake
     raw_input that simulates interactive input."""
 
     from IPython.core.inputsplitter import InputSplitter
     
     isp = InputSplitter()
     # In practice, this input loop would be wrapped in an outside loop to read
     # input indefinitely, until some exit/quit command was issued.  Here we
     # only illustrate the basic inner loop.
     while isp.push_accepts_more():
         indent = ' '*isp.indent_spaces
         prompt = '>>> ' + indent
         line = indent + input_func(prompt)
         isp.push(line)
 
     # Here we just return input so we can use it in a test suite, but a real
     # interpreter would instead send it for execution somewhere.
     src = isp.source_reset()
     #print 'Input source was:\n', src  # dbg
     return src
 
 #-----------------------------------------------------------------------------
 # Test utilities, just for local use
 #-----------------------------------------------------------------------------
 
 def assemble(block):
     """Assemble a block into multi-line sub-blocks."""
     return ['\n'.join(sub_block)+'\n' for sub_block in block]
 
 
 def pseudo_input(lines):
     """Return a function that acts like raw_input but feeds the input list."""
     ilines = iter(lines)
     def raw_in(prompt):
         try:
             return next(ilines)
         except StopIteration:
             return ''
     return raw_in
 
 #-----------------------------------------------------------------------------
 # Tests
 #-----------------------------------------------------------------------------
 def test_spaces():
     tests = [('', 0),
              (' ', 1),
              ('\n', 0),
              (' \n', 1),
              ('x', 0),
              (' x', 1),
              ('  x',2),
              ('    x',4),
              # Note: tabs are counted as a single whitespace!
              ('\tx', 1),
              ('\t x', 2),
              ]
     
     for s, nsp in tests:
         nt.assert_equal(isp.num_ini_spaces(s), nsp)
 
 
 def test_remove_comments():
     tests = [('text', 'text'),
              ('text # comment', 'text '),
              ('text # comment\n', 'text \n'),
              ('text # comment \n', 'text \n'),
              ('line # c \nline\n','line \nline\n'),
              ('line # c \nline#c2  \nline\nline #c\n\n',
               'line \nline\nline\nline \n\n'),
              ]
 
     for inp, out in tests:
         nt.assert_equal(isp.remove_comments(inp), out)
 
 
 def test_get_input_encoding():
     encoding = isp.get_input_encoding()
     nt.assert_true(isinstance(encoding, basestring))
     # simple-minded check that at least encoding a simple string works with the
     # encoding we got.
     nt.assert_equal('test'.encode(encoding), 'test')
 
 
 class NoInputEncodingTestCase(unittest.TestCase):
     def setUp(self):
         self.old_stdin = sys.stdin
         class X: pass
         fake_stdin = X()
         sys.stdin = fake_stdin
         
     def test(self):
         # Verify that if sys.stdin has no 'encoding' attribute we do the right
         # thing
         enc = isp.get_input_encoding()
         self.assertEqual(enc, 'ascii')
         
     def tearDown(self):
         sys.stdin = self.old_stdin
 
 
 class InputSplitterTestCase(unittest.TestCase):
     def setUp(self):
         self.isp = isp.InputSplitter()
 
     def test_reset(self):
         isp = self.isp
         isp.push('x=1')
         isp.reset()
         self.assertEqual(isp._buffer, [])
         self.assertEqual(isp.indent_spaces, 0)
         self.assertEqual(isp.source, '')
         self.assertEqual(isp.code, None)
         self.assertEqual(isp._is_complete, False)
 
     def test_source(self):
         self.isp._store('1')
         self.isp._store('2')
         self.assertEqual(self.isp.source, '1\n2\n')
         self.assertTrue(len(self.isp._buffer)>0)
         self.assertEqual(self.isp.source_reset(), '1\n2\n')
         self.assertEqual(self.isp._buffer, [])
         self.assertEqual(self.isp.source, '')
         
     def test_indent(self):
         isp = self.isp # shorthand
         isp.push('x=1')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n    x=1')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('y=2\n')
         self.assertEqual(isp.indent_spaces, 0)
 
     def test_indent2(self):
         # In cell mode, inputs must be fed in whole blocks, so skip this test
         if self.isp.input_mode == 'cell': return
 
         isp = self.isp
         isp.push('if 1:')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('    x=1')
         self.assertEqual(isp.indent_spaces, 4)
         # Blank lines shouldn't change the indent level
         isp.push(' '*2)
         self.assertEqual(isp.indent_spaces, 4)
 
     def test_indent3(self):
         # In cell mode, inputs must be fed in whole blocks, so skip this test
         if self.isp.input_mode == 'cell': return
 
         isp = self.isp
         # When a multiline statement contains parens or multiline strings, we
         # shouldn't get confused.
         isp.push("if 1:")
         isp.push("    x = (1+\n    2)")
         self.assertEqual(isp.indent_spaces, 4)
 
     def test_dedent(self):
         isp = self.isp # shorthand
         isp.push('if 1:')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('    pass')
         self.assertEqual(isp.indent_spaces, 0)
         
     def test_push(self):
         isp = self.isp
         self.assertTrue(isp.push('x=1'))
 
     def test_push2(self):
         isp = self.isp
         self.assertFalse(isp.push('if 1:'))
         for line in ['  x=1', '# a comment', '  y=2']:
             self.assertTrue(isp.push(line))
             
     def test_replace_mode(self):
         isp = self.isp
         isp.input_mode = 'cell'
         isp.push('x=1')
         self.assertEqual(isp.source, 'x=1\n')
         isp.push('x=2')
         self.assertEqual(isp.source, 'x=2\n')
 
     def test_push_accepts_more(self):
         isp = self.isp
         isp.push('x=1')
         self.assertFalse(isp.push_accepts_more())
 
     def test_push_accepts_more2(self):
         # In cell mode, inputs must be fed in whole blocks, so skip this test
         if self.isp.input_mode == 'cell': return
 
         isp = self.isp
         isp.push('if 1:')
         self.assertTrue(isp.push_accepts_more())
         isp.push('  x=1')
         self.assertTrue(isp.push_accepts_more())
         isp.push('')
         self.assertFalse(isp.push_accepts_more())
         
     def test_push_accepts_more3(self):
         isp = self.isp
         isp.push("x = (2+\n3)")
         self.assertFalse(isp.push_accepts_more())
 
     def test_push_accepts_more4(self):
         # In cell mode, inputs must be fed in whole blocks, so skip this test
         if self.isp.input_mode == 'cell': return
 
         isp = self.isp
         # When a multiline statement contains parens or multiline strings, we
         # shouldn't get confused.
         # FIXME: we should be able to better handle de-dents in statements like
         # multiline strings and multiline expressions (continued with \ or
         # parens).  Right now we aren't handling the indentation tracking quite
         # correctly with this, though in practice it may not be too much of a
         # problem.  We'll need to see.
         isp.push("if 1:")
         isp.push("    x = (2+")
         isp.push("    3)")
         self.assertTrue(isp.push_accepts_more())
         isp.push("    y = 3")
         self.assertTrue(isp.push_accepts_more())
         isp.push('')
         self.assertFalse(isp.push_accepts_more())
         
     def test_push_accepts_more5(self):
         # In cell mode, inputs must be fed in whole blocks, so skip this test
         if self.isp.input_mode == 'cell': return
 
         isp = self.isp
         isp.push('try:')
         isp.push('    a = 5')
         isp.push('except:')
         isp.push('    raise')
         self.assertTrue(isp.push_accepts_more())
 
     def test_continuation(self):
         isp = self.isp
         isp.push("import os, \\")
         self.assertTrue(isp.push_accepts_more())
         isp.push("sys")
         self.assertFalse(isp.push_accepts_more())
 
     def test_syntax_error(self):
         isp = self.isp
         # Syntax errors immediately produce a 'ready' block, so the invalid
         # Python can be sent to the kernel for evaluation with possible ipython
         # special-syntax conversion.
         isp.push('run foo')
         self.assertFalse(isp.push_accepts_more())
 
     def check_split(self, block_lines, compile=True):
         blocks = assemble(block_lines)
         lines = ''.join(blocks)
         oblock = self.isp.split_blocks(lines)
         self.assertEqual(oblock, blocks)
         if compile:
             for block in blocks:
                 self.isp._compile(block)
 
     def test_split(self):
         # All blocks of input we want to test in a list.  The format for each
         # block is a list of lists, with each inner lists consisting of all the
         # lines (as single-lines) that should make up a sub-block.
 
         # Note: do NOT put here sub-blocks that don't compile, as the
         # check_split() routine makes a final verification pass to check that
         # each sub_block, as returned by split_blocks(), does compile
         # correctly.
         all_blocks = [ [['x=1']],
 
                        [['x=1'],
                         ['y=2']],
 
                        [['x=1',
                          '# a comment'],
                         ['y=11']],
 
                        [['if 1:',
                          '  x=1'],
                         ['y=3']],
 
                        [['def f(x):',
                          '  return x'],
                         ['x=1']],
 
                        [['def f(x):',
                          '  x+=1',
                          '  ',
                          '  return x'],
                         ['x=1']],
 
                        [['def f(x):',
                          '  if x>0:',
                          '    y=1',
                          '  # a comment',
                          '  else:',
                          '    y=4',
                          ' ',
                          '  return y'],
                         ['x=1'],
                         ['if 1:',
                          '  y=11'] ],
                        
                        [['for i in range(10):'
                          '  x=i**2']],
 
                        [['for i in range(10):'
                          '  x=i**2'],
                         ['z = 1']],
 
                        [['"asdf"']],
 
                        [['"asdf"'],
                         ['10'],
                        ],
 
                        [['"""foo',
                          'bar"""']],
                        ]
         for block_lines in all_blocks:
             self.check_split(block_lines)
         
     def test_split_syntax_errors(self):
         # Block splitting with invalid syntax
         all_blocks = [ [['a syntax error']],
             
                        [['x=1',
                          'another syntax error']],
 
                        [['for i in range(10):'
                          '  yet another error']],
                        
                        ]
         for block_lines in all_blocks:
             self.check_split(block_lines, compile=False)
 
     def test_unicode(self):
         self.isp.push(u"Pérez")
         self.isp.push(u'\xc3\xa9')
         self.isp.push(u"u'\xc3\xa9'")
 
 class InteractiveLoopTestCase(unittest.TestCase):
     """Tests for an interactive loop like a python shell.
     """
     def check_ns(self, lines, ns):
         """Validate that the given input lines produce the resulting namespace.
 
         Note: the input lines are given exactly as they would be typed in an
         auto-indenting environment, as mini_interactive_loop above already does
         auto-indenting and prepends spaces to the input.
         """
         src = mini_interactive_loop(pseudo_input(lines))
         test_ns = {}
         exec src in test_ns
         # We can't check that the provided ns is identical to the test_ns,
         # because Python fills test_ns with extra keys (copyright, etc).  But
         # we can check that the given dict is *contained* in test_ns
         for k,v in ns.iteritems():
             self.assertEqual(test_ns[k], v)
         
     def test_simple(self):
         self.check_ns(['x=1'], dict(x=1))
 
     def test_simple2(self):
         self.check_ns(['if 1:', 'x=2'], dict(x=2))
 
     def test_xy(self):
         self.check_ns(['x=1; y=2'], dict(x=1, y=2))
 
     def test_abc(self):
         self.check_ns(['if 1:','a=1','b=2','c=3'], dict(a=1, b=2, c=3))
     
     def test_multi(self):
         self.check_ns(['x =(1+','1+','2)'], dict(x=4))
     
 
 def test_LineInfo():
     """Simple test for LineInfo construction and str()"""
     linfo = isp.LineInfo('  %cd /home')
     nt.assert_equals(str(linfo), 'LineInfo [  |%|cd|/home]')
 
 
 def test_split_user_input():
     """Unicode test - split_user_input already has good doctests"""
     line = u"Pérez Fernando"
     parts = isp.split_user_input(line)
     parts_expected = (u'', u'', u'', line)
     nt.assert_equal(parts, parts_expected)
 
 
 # Transformer tests
 def transform_checker(tests, func):
     """Utility to loop over test inputs"""
     for inp, tr in tests:
         nt.assert_equals(func(inp), tr)
 
 # Data for all the syntax tests in the form of lists of pairs of
 # raw/transformed input.  We store it here as a global dict so that we can use
 # it both within single-function tests and also to validate the behavior of the
 # larger objects
 
 syntax = \
   dict(assign_system =
-       [('a =! ls', 'a = get_ipython().getoutput("ls")'),
-        ('b = !ls', 'b = get_ipython().getoutput("ls")'),
+       [('a =! ls', 'a = get_ipython().getoutput(u"ls")'),
+        ('b = !ls', 'b = get_ipython().getoutput(u"ls")'),
         ('x=1', 'x=1'), # normal input is unmodified
         ('    ','    '),  # blank lines are kept intact
         ],
 
        assign_magic =
-       [('a =% who', 'a = get_ipython().magic("who")'),
-        ('b = %who', 'b = get_ipython().magic("who")'),
+       [('a =% who', 'a = get_ipython().magic(u"who")'),
+        ('b = %who', 'b = get_ipython().magic(u"who")'),
         ('x=1', 'x=1'), # normal input is unmodified
         ('    ','    '),  # blank lines are kept intact
         ],
 
        classic_prompt =
        [('>>> x=1', 'x=1'),
         ('x=1', 'x=1'), # normal input is unmodified
         ('    ', '    '),  # blank lines are kept intact
         ('... ', ''), # continuation prompts
         ],
 
        ipy_prompt =
        [('In [1]: x=1', 'x=1'),
         ('x=1', 'x=1'), # normal input is unmodified
         ('    ','    '),  # blank lines are kept intact
         ('   ....: ', ''), # continuation prompts
         ],
 
        # Tests for the escape transformer to leave normal code alone
        escaped_noesc =
        [ ('    ', '    '),
          ('x=1', 'x=1'),
          ],
 
        # System calls
        escaped_shell =
-       [ ('!ls', 'get_ipython().system("ls")'),
+       [ ('!ls', 'get_ipython().system(u"ls")'),
          # Double-escape shell, this means to capture the output of the
          # subprocess and return it
-         ('!!ls', 'get_ipython().getoutput("ls")'),
+         ('!!ls', 'get_ipython().getoutput(u"ls")'),
          ],
 
        # Help/object info
        escaped_help =
        [ ('?', 'get_ipython().show_usage()'),
-         ('?x1', 'get_ipython().magic("pinfo x1")'),
-         ('??x2', 'get_ipython().magic("pinfo2 x2")'),
-         ('x3?', 'get_ipython().magic("pinfo x3")'),
-         ('x4??', 'get_ipython().magic("pinfo2 x4")'),
-         ('%hist?', 'get_ipython().magic("pinfo %hist")'),
-         ('f*?', 'get_ipython().magic("psearch f*")'),
-         ('ax.*aspe*?', 'get_ipython().magic("psearch ax.*aspe*")'),
+         ('?x1', 'get_ipython().magic(u"pinfo x1")'),
+         ('??x2', 'get_ipython().magic(u"pinfo2 x2")'),
+         ('x3?', 'get_ipython().magic(u"pinfo x3")'),
+         ('x4??', 'get_ipython().magic(u"pinfo2 x4")'),
+         ('%hist?', 'get_ipython().magic(u"pinfo %hist")'),
+         ('f*?', 'get_ipython().magic(u"psearch f*")'),
+         ('ax.*aspe*?', 'get_ipython().magic(u"psearch ax.*aspe*")'),
          ],
 
        # Explicit magic calls
        escaped_magic =
-       [ ('%cd', 'get_ipython().magic("cd")'),
-         ('%cd /home', 'get_ipython().magic("cd /home")'),
-         ('    %magic', '    get_ipython().magic("magic")'),
+       [ ('%cd', 'get_ipython().magic(u"cd")'),
+         ('%cd /home', 'get_ipython().magic(u"cd /home")'),
+         ('    %magic', '    get_ipython().magic(u"magic")'),
          ],
        
        # Quoting with separate arguments
        escaped_quote =
        [ (',f', 'f("")'),
          (',f x', 'f("x")'),
          ('  ,f y', '  f("y")'),
          (',f a b', 'f("a", "b")'),
          ],
        
        # Quoting with single argument
        escaped_quote2 = 
        [ (';f', 'f("")'),
          (';f x', 'f("x")'),
          ('  ;f y', '  f("y")'),
          (';f a b', 'f("a b")'),
          ],
        
        # Simply apply parens
        escaped_paren = 
        [ ('/f', 'f()'),
          ('/f x', 'f(x)'),
          ('  /f y', '  f(y)'),
          ('/f a b', 'f(a, b)'),
          ],
 
        )
 
 # multiline syntax examples.  Each of these should be a list of lists, with
 # each entry itself having pairs of raw/transformed input.  The union (with
 # '\n'.join() of the transformed inputs is what the splitter should produce
 # when fed the raw lines one at a time via push.
 syntax_ml = \
   dict(classic_prompt =
        [ [('>>> for i in range(10):','for i in range(10):'),
           ('...     print i','    print i'),
           ('... ', ''),
           ],
         ],
 
        ipy_prompt =
        [ [('In [24]: for i in range(10):','for i in range(10):'),
           ('   ....:     print i','    print i'),
           ('   ....: ', ''),
           ],
          ],
        )
 
 
 def test_assign_system():
     transform_checker(syntax['assign_system'], isp.transform_assign_system)
 
     
 def test_assign_magic():
     transform_checker(syntax['assign_magic'], isp.transform_assign_magic)
 
 
 def test_classic_prompt():
     transform_checker(syntax['classic_prompt'], isp.transform_classic_prompt)
     for example in syntax_ml['classic_prompt']:
         transform_checker(example, isp.transform_classic_prompt)
     
 
 def test_ipy_prompt():
     transform_checker(syntax['ipy_prompt'], isp.transform_ipy_prompt)
     for example in syntax_ml['ipy_prompt']:
         transform_checker(example, isp.transform_ipy_prompt)
     
 
 def test_escaped_noesc():
     transform_checker(syntax['escaped_noesc'], isp.transform_escaped)
 
 
 def test_escaped_shell():
     transform_checker(syntax['escaped_shell'], isp.transform_escaped)
 
 
 def test_escaped_help():
     transform_checker(syntax['escaped_help'], isp.transform_escaped)
 
 
 def test_escaped_magic():
     transform_checker(syntax['escaped_magic'], isp.transform_escaped)
 
 
 def test_escaped_quote():
     transform_checker(syntax['escaped_quote'], isp.transform_escaped)
 
 
 def test_escaped_quote2():
     transform_checker(syntax['escaped_quote2'], isp.transform_escaped)
 
 
 def test_escaped_paren():
     transform_checker(syntax['escaped_paren'], isp.transform_escaped)
 
 
 class IPythonInputTestCase(InputSplitterTestCase):
     """By just creating a new class whose .isp is a different instance, we
     re-run the same test battery on the new input splitter.
 
     In addition, this runs the tests over the syntax and syntax_ml dicts that
     were tested by individual functions, as part of the OO interface.
 
     It also makes some checks on the raw buffer storage.
     """
 
     def setUp(self):
         self.isp = isp.IPythonInputSplitter(input_mode='line')
 
     def test_syntax(self):
         """Call all single-line syntax tests from the main object"""
         isp = self.isp
         for example in syntax.itervalues():
             for raw, out_t in example:
                 if raw.startswith(' '):
                     continue
                 
                 isp.push(raw)
                 out, out_raw = isp.source_raw_reset()
                 self.assertEqual(out.rstrip(), out_t)
                 self.assertEqual(out_raw.rstrip(), raw.rstrip())
 
     def test_syntax_multiline(self):
         isp = self.isp
         for example in syntax_ml.itervalues():
             out_t_parts = []
             raw_parts = []
             for line_pairs in example:
                 for lraw, out_t_part in line_pairs:
                     isp.push(lraw)
                     out_t_parts.append(out_t_part)
                     raw_parts.append(lraw)
 
                 out, out_raw = isp.source_raw_reset()
                 out_t = '\n'.join(out_t_parts).rstrip()
                 raw = '\n'.join(raw_parts).rstrip()
                 self.assertEqual(out.rstrip(), out_t)
                 self.assertEqual(out_raw.rstrip(), raw)
                 
 
 class BlockIPythonInputTestCase(IPythonInputTestCase):
 
     # Deactivate tests that don't make sense for the block mode
     test_push3 = test_split = lambda s: None
     
     def setUp(self):
         self.isp = isp.IPythonInputSplitter(input_mode='cell')
 
     def test_syntax_multiline(self):
         isp = self.isp
         for example in syntax_ml.itervalues():
             raw_parts = []
             out_t_parts = []
             for line_pairs in example:
                 for raw, out_t_part in line_pairs:
                     raw_parts.append(raw)
                     out_t_parts.append(out_t_part)
 
                 raw = '\n'.join(raw_parts)
                 out_t = '\n'.join(out_t_parts)
 
                 isp.push(raw)
                 out, out_raw = isp.source_raw_reset()
                 # Match ignoring trailing whitespace
                 self.assertEqual(out.rstrip(), out_t.rstrip())
                 self.assertEqual(out_raw.rstrip(), raw.rstrip())
     
 
 #-----------------------------------------------------------------------------
 # Main - use as a script, mostly for developer experiments
 #-----------------------------------------------------------------------------
 
 if __name__ == '__main__':
     # A simple demo for interactive experimentation.  This code will not get
     # picked up by any test suite.
     from IPython.core.inputsplitter import InputSplitter, IPythonInputSplitter
 
     # configure here the syntax to use, prompt and whether to autoindent
     #isp, start_prompt = InputSplitter(), '>>> '
     isp, start_prompt = IPythonInputSplitter(), 'In> '
 
     autoindent = True
     #autoindent = False
     
     try:
         while True:
             prompt = start_prompt
             while isp.push_accepts_more():
                 indent = ' '*isp.indent_spaces
                 if autoindent:
                     line = indent + raw_input(prompt+indent)
                 else:
                     line = raw_input(prompt)
                 isp.push(line)
                 prompt = '... '
 
             # Here we just return input so we can use it in a test suite, but a
             # real interpreter would instead send it for execution somewhere.
             #src = isp.source; raise EOFError # dbg
             src, raw = isp.source_raw_reset()
             print 'Input source was:\n', src
             print 'Raw source was:\n', raw
     except EOFError:
         print 'Bye'

IPython/core/tests/test_iplib.py

@@ -1,271 +1,271 b''
 """Tests for the key interactiveshell module, where the main ipython class is defined.
 """
 #-----------------------------------------------------------------------------
 # Module imports
 #-----------------------------------------------------------------------------
 
 # stdlib
 import os
 import shutil
 import tempfile
 
 # third party
 import nose.tools as nt
 
 # our own packages
 from IPython.testing import decorators as dec
 from IPython.testing.globalipapp import get_ipython
 
 #-----------------------------------------------------------------------------
 # Globals
 #-----------------------------------------------------------------------------
 
 # Get the public instance of IPython
 ip = get_ipython()
 
 #-----------------------------------------------------------------------------
 # Test functions
 #-----------------------------------------------------------------------------
 
 @dec.parametric
 def test_reset():
     """reset must clear most namespaces."""
     # The number of variables in the private user_ns_hidden is not zero, but it
     # should be constant regardless of what we do
     nvars_config_ns = len(ip.user_ns_hidden)
 
     # Check that reset runs without error
     ip.reset()
 
     # Once we've reset it (to clear of any junk that might have been there from
     # other tests, we can count how many variables are in the user's namespace
     nvars_user_ns = len(ip.user_ns)
 
     # Now add a few variables to user_ns, and check that reset clears them
     ip.user_ns['x'] = 1
     ip.user_ns['y'] = 1
     ip.reset()
     
     # Finally, check that all namespaces have only as many variables as we
     # expect to find in them:
     for ns in ip.ns_refs_table:
         if ns is ip.user_ns:
             nvars_expected = nvars_user_ns
         elif ns is ip.user_ns_hidden:
             nvars_expected = nvars_config_ns
         else:
             nvars_expected = 0
             
         yield nt.assert_equals(len(ns), nvars_expected)
 
 
 # Tests for reporting of exceptions in various modes, handling of SystemExit,
 # and %tb functionality.  This is really a mix of testing ultraTB and interactiveshell.
 
 def doctest_tb_plain():
     """
 In [18]: xmode plain
 Exception reporting mode: Plain
 
 In [19]: run simpleerr.py
 Traceback (most recent call last):
   ...line 32, in <module>
     bar(mode)
   ...line 16, in bar
     div0()
   ...line 8, in div0
     x/y
 ZeroDivisionError: integer division or modulo by zero
     """
 
 
 def doctest_tb_context():
     """
 In [3]: xmode context
 Exception reporting mode: Context
 
 In [4]: run simpleerr.py
 ---------------------------------------------------------------------------
 ZeroDivisionError                         Traceback (most recent call last)
 <BLANKLINE>
 ... in <module>()
      30         mode = 'div'
      31 
 ---> 32     bar(mode)
 <BLANKLINE>
 ... in bar(mode)
      14     "bar"
      15     if mode=='div':
 ---> 16         div0()
      17     elif mode=='exit':
      18         try:
 <BLANKLINE>
 ... in div0()
       6     x = 1
       7     y = 0
 ----> 8     x/y
       9 
      10 def sysexit(stat, mode):
 <BLANKLINE>
 ZeroDivisionError: integer division or modulo by zero
 """
 
 
 def doctest_tb_verbose():
     """
 In [5]: xmode verbose
 Exception reporting mode: Verbose
 
 In [6]: run simpleerr.py
 ---------------------------------------------------------------------------
 ZeroDivisionError                         Traceback (most recent call last)
 <BLANKLINE>
 ... in <module>()
      30         mode = 'div'
      31 
 ---> 32     bar(mode)
         global bar = <function bar at ...>
         global mode = 'div'
 <BLANKLINE>
 ... in bar(mode='div')
      14     "bar"
      15     if mode=='div':
 ---> 16         div0()
         global div0 = <function div0 at ...>
      17     elif mode=='exit':
      18         try:
 <BLANKLINE>
 ... in div0()
       6     x = 1
       7     y = 0
 ----> 8     x/y
         x = 1
         y = 0
       9 
      10 def sysexit(stat, mode):
 <BLANKLINE>
 ZeroDivisionError: integer division or modulo by zero
       """
 
 
 def doctest_tb_sysexit():
     """
 In [17]: %xmode plain
 Exception reporting mode: Plain
 
 In [18]: %run simpleerr.py exit
 An exception has occurred, use %tb to see the full traceback.
-SystemExit: (1, 'Mode = exit')
+SystemExit: (1, u'Mode = exit')
 
 In [19]: %run simpleerr.py exit 2
 An exception has occurred, use %tb to see the full traceback.
-SystemExit: (2, 'Mode = exit')
+SystemExit: (2, u'Mode = exit')
 
 In [20]: %tb
 Traceback (most recent call last):
   File ... in <module>
     bar(mode)
   File ... line 22, in bar
     sysexit(stat, mode)
   File ... line 11, in sysexit
     raise SystemExit(stat, 'Mode = %s' % mode)
-SystemExit: (2, 'Mode = exit')
+SystemExit: (2, u'Mode = exit')
 
 In [21]: %xmode context
 Exception reporting mode: Context
 
 In [22]: %tb
 ---------------------------------------------------------------------------
 SystemExit                                Traceback (most recent call last)
 <BLANKLINE>
 ...<module>()
      30         mode = 'div'
      31 
 ---> 32     bar(mode)
 <BLANKLINE>
 ...bar(mode)
      20         except:
      21             stat = 1
 ---> 22         sysexit(stat, mode)
      23     else:
      24         raise ValueError('Unknown mode')
 <BLANKLINE>
 ...sysexit(stat, mode)
       9 
      10 def sysexit(stat, mode):
 ---> 11     raise SystemExit(stat, 'Mode = %s' % mode)
      12 
      13 def bar(mode):
 <BLANKLINE>
-SystemExit: (2, 'Mode = exit')
+SystemExit: (2, u'Mode = exit')
 
 In [23]: %xmode verbose
 Exception reporting mode: Verbose
 
 In [24]: %tb
 ---------------------------------------------------------------------------
 SystemExit                                Traceback (most recent call last)
 <BLANKLINE>
 ... in <module>()
      30         mode = 'div'
      31 
 ---> 32     bar(mode)
         global bar = <function bar at ...>
-        global mode = 'exit'
+        global mode = u'exit'
 <BLANKLINE>
-... in bar(mode='exit')
+... in bar(mode=u'exit')
      20         except:
      21             stat = 1
 ---> 22         sysexit(stat, mode)
         global sysexit = <function sysexit at ...>
         stat = 2
-        mode = 'exit'
+        mode = u'exit'
      23     else:
      24         raise ValueError('Unknown mode')
 <BLANKLINE>
-... in sysexit(stat=2, mode='exit')
+... in sysexit(stat=2, mode=u'exit')
       9 
      10 def sysexit(stat, mode):
 ---> 11     raise SystemExit(stat, 'Mode = %s' % mode)
         global SystemExit = undefined
         stat = 2
-        mode = 'exit'
+        mode = u'exit'
      12 
      13 def bar(mode):
 <BLANKLINE>
-SystemExit: (2, 'Mode = exit')
+SystemExit: (2, u'Mode = exit')
     """
 
 
 def test_runlines():
     import textwrap
     ip.runlines(['a = 10', 'a+=1'])
     ip.runlines('assert a == 11\nassert 1')
 
     nt.assert_equals(ip.user_ns['a'], 11)
     complex = textwrap.dedent("""
     if 1:
         print "hello"
         if 1:
             print "world"
         
     if 2:
         print "foo"
 
     if 3:
         print "bar"
 
     if 4:
         print "bar"
     
     """)
     # Simply verifies that this kind of input is run
     ip.runlines(complex)
     
 
 def test_db():
     """Test the internal database used for variable persistence."""
     ip.db['__unittest_'] = 12
     nt.assert_equals(ip.db['__unittest_'], 12)
     del ip.db['__unittest_']
     assert '__unittest_' not in ip.db

IPython/core/tests/test_run.py

@@ -1,186 +1,186 b''
 """Tests for code execution (%run and related), which is particularly tricky.
 
 Because of how %run manages namespaces, and the fact that we are trying here to
 verify subtle object deletion and reference counting issues, the %run tests
 will be kept in this separate file.  This makes it easier to aggregate in one
 place the tricks needed to handle it; most other magics are much easier to test
 and we do so in a common test_magic file.
 """
 from __future__ import absolute_import
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 import os
 import sys
 import tempfile
 
 import nose.tools as nt
 
 from IPython.testing import decorators as dec
 from IPython.testing import tools as tt
 
 #-----------------------------------------------------------------------------
 # Test functions begin
 #-----------------------------------------------------------------------------
 
 def doctest_refbug():
     """Very nasty problem with references held by multiple runs of a script.
     See: https://bugs.launchpad.net/ipython/+bug/269966
 
     In [1]: _ip.clear_main_mod_cache()
     # random
     
     In [2]: %run refbug
 
     In [3]: call_f()
     lowercased: hello
 
     In [4]: %run refbug
 
     In [5]: call_f()
     lowercased: hello
     lowercased: hello
     """
 
 
 def doctest_run_builtins():
     r"""Check that %run doesn't damage __builtins__.
 
     In [1]: import tempfile
 
     In [2]: bid1 = id(__builtins__)
 
     In [3]: fname = tempfile.mkstemp('.py')[1]
 
     In [3]: f = open(fname,'w')
 
     In [4]: f.write('pass\n')
 
     In [5]: f.flush()
 
     In [6]: t1 = type(__builtins__)
 
     In [7]: %run $fname
 
     In [7]: f.close()
 
     In [8]: bid2 = id(__builtins__)
 
     In [9]: t2 = type(__builtins__)
 
     In [10]: t1 == t2
     Out[10]: True
 
     In [10]: bid1 == bid2
     Out[10]: True
 
     In [12]: try:
        ....:     os.unlink(fname)
        ....: except:
        ....:     pass
        ....: 
     """
 
 def doctest_reset_del():
     """Test that resetting doesn't cause errors in __del__ methods.
 
     In [2]: class A(object):
        ...:     def __del__(self):
        ...:         print str("Hi")
        ...: 
 
     In [3]: a = A()
 
     In [4]: get_ipython().reset()
     Hi
 
     In [5]: 1+1
     Out[5]: 2
     """
 
 # For some tests, it will be handy to organize them in a class with a common
 # setup that makes a temp file
 
 class TestMagicRunPass(tt.TempFileMixin):
 
     def setup(self):
         """Make a valid python temp file."""
         self.mktmp('pass\n')
 
     def run_tmpfile(self):
         _ip = get_ipython()
         # This fails on Windows if self.tmpfile.name has spaces or "~" in it.
         # See below and ticket https://bugs.launchpad.net/bugs/366353
         _ip.magic('run %s' % self.fname)
 
     def test_builtins_id(self):
         """Check that %run doesn't damage __builtins__ """
         _ip = get_ipython()
         # Test that the id of __builtins__ is not modified by %run
         bid1 = id(_ip.user_ns['__builtins__'])
         self.run_tmpfile()
         bid2 = id(_ip.user_ns['__builtins__'])
         tt.assert_equals(bid1, bid2)
 
     def test_builtins_type(self):
         """Check that the type of __builtins__ doesn't change with %run.
         
         However, the above could pass if __builtins__ was already modified to
         be a dict (it should be a module) by a previous use of %run.  So we
         also check explicitly that it really is a module:
         """
         _ip = get_ipython()
         self.run_tmpfile()
         tt.assert_equals(type(_ip.user_ns['__builtins__']),type(sys))
 
     def test_prompts(self):
         """Test that prompts correctly generate after %run"""
         self.run_tmpfile()
         _ip = get_ipython()
         p2 = str(_ip.displayhook.prompt2).strip()
         nt.assert_equals(p2[:3], '...')
 
 
 class TestMagicRunSimple(tt.TempFileMixin):
 
     def test_simpledef(self):
         """Test that simple class definitions work."""
         src = ("class foo: pass\n"
                "def f(): return foo()")
         self.mktmp(src)
         _ip.magic('run %s' % self.fname)
         _ip.runlines('t = isinstance(f(), foo)')
         nt.assert_true(_ip.user_ns['t'])
 
     # We have to skip these in win32 because getoutputerr() crashes,
     # due to the fact that subprocess does not support close_fds when
     # redirecting stdout/err.  So unless someone who knows more tells us how to
     # implement getoutputerr() in win32, we're stuck avoiding these.
     @dec.skip_win32
     def test_obj_del(self):
         """Test that object's __del__ methods are called on exit."""
         
         # This test is known to fail on win32.
         # See ticket https://bugs.launchpad.net/bugs/366334
         src = ("class A(object):\n"
                "    def __del__(self):\n"
                "        print 'object A deleted'\n"
                "a = A()\n")
         self.mktmp(src)
         tt.ipexec_validate(self.fname, 'object A deleted')
 
     @dec.skip_win32
     def test_tclass(self):
         mydir = os.path.dirname(__file__)
         tc = os.path.join(mydir, 'tclass')
         src = ("%%run '%s' C-first\n"
                "%%run '%s' C-second\n") % (tc, tc)
         self.mktmp(src, '.ipy')
         out = """\
-ARGV 1-: ['C-first']
-ARGV 1-: ['C-second']
+ARGV 1-: [u'C-first']
+ARGV 1-: [u'C-second']
 tclass.py: deleting object: C-first
 """
         tt.ipexec_validate(self.fname, out)