Reuse common code for inputsplitter and prefilter.

IPython/core/tests/test_splitinput.py

@@ -0,0 +1,26 b''
+from IPython.core.splitinput import split_user_input
+from IPython.testing import tools as tt
+
+tests = [
+    ('x=1', ('', '', 'x', '=1')),
+    ('?', ('', '?', '', '')),
+    ('??', ('', '??', '', '')),
+    (' ?', (' ', '?', '', '')),
+    (' ??', (' ', '??', '', '')),
+    ('??x', ('', '??', 'x', '')),
+    ('?x=1', ('', '?', 'x', '=1')),
+    ('!ls', ('', '!', 'ls', '')),
+    ('  !ls', ('  ', '!', 'ls', '')),
+    ('!!ls', ('', '!!', 'ls', '')),
+    ('  !!ls', ('  ', '!!', 'ls', '')),
+    (',ls', ('', ',', 'ls', '')),
+    (';ls', ('', ';', 'ls', '')),
+    ('  ;ls', ('  ', ';', 'ls', '')),
+    ('f.g(x)',  ('', '', 'f.g', '(x)')),
+    ('f.g (x)', ('', '', 'f.g', '(x)')),
+    ('?%hist', ('', '?', '%hist', '')),
+    ('?x*', ('', '?', 'x*', '')),
+    ]
+
+def test_split_user_input():
+    return tt.check_pairs(split_user_input, tests)

IPython/core/inputsplitter.py

@@ -1,892 +1,770 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
 import tokenize
 from StringIO import StringIO
 
 # IPython modules
+from IPython.core.splitinput import split_user_input, LineInfo
 from IPython.utils.text import make_quoted_expr
 from IPython.utils.py3compat import cast_unicode
 
 #-----------------------------------------------------------------------------
 # 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('|'.join([
     r'^\s+raise(\s.*)?$', # raise statement (+ space + other stuff, maybe)
     r'^\s+raise\([^\)]*\).*$', # wacky raise with immediate open paren
     r'^\s+return(\s.*)?$', # normal return (+ space + other stuff, maybe)
     r'^\s+return\([^\)]*\).*$', # wacky return with immediate open paren
     r'^\s+pass\s*$' # pass (optionally followed by trailing spaces)
 ]))
 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 has_comment(src):
     """Indicate whether an input line has (i.e. ends in, or is) a comment.
     
     This uses tokenize, so it can distinguish comments from # inside strings.
     
     Parameters
     ----------
     src : string
       A single line input string.
     
     Returns
     -------
     Boolean: True if source has a comment.
     """
     readline = StringIO(src).readline
     toktypes = set()
     try:
         for t in tokenize.generate_tokens(readline):
             toktypes.add(t[0])
     except tokenize.TokenError:
         pass
     return(tokenize.COMMENT in toktypes)
 
 
 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
 #-----------------------------------------------------------------------------
 
 class InputSplitter(object):
     """An object that can accumulate lines of Python source before execution.
 
     This object is designed to be fed python source line-by-line, using
        :meth:`push`. 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.
 
     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, symbol="exec")
         # 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).
 
         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:
                 try:
                     code_ast = ast.parse(u''.join(self._buffer))
                 except Exception:
                     return False
                 else:
                     if len(code_ast.body) == 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())
 
     #------------------------------------------------------------------------
     # 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.rstrip()[-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
 
 
 def _make_help_call(target, esc, lspace, next_input=None):
     """Prepares a pinfo(2)/psearch call from a target name and the escape
     (i.e. ? or ??)"""
     method  = 'pinfo2' if esc == '??' \
                 else 'psearch' if '*' in target \
                 else 'pinfo'
         
     if next_input:
         tpl = '%sget_ipython().magic(u"%s %s", next_input=%s)'
         return tpl % (lspace, method, target, make_quoted_expr(next_input))
     else:
         return '%sget_ipython().magic(u"%s %s")' % (lspace, method, target)
 
 _initial_space_re = re.compile(r'\s*')
 _help_end_re = re.compile(r"""(%?
-                              [a-zA-Z_*][a-zA-Z0-9_*]*       # Variable name
-                              (\.[a-zA-Z_*][a-zA-Z0-9_*]*)*   # .etc.etc
+                              [a-zA-Z_*][\w*]*        # Variable name
+                              (\.[a-zA-Z_*][\w*]*)*   # .etc.etc
                               )
                               (\?\??)$                       # ? or ??""",
                               re.VERBOSE)
 def transform_help_end(line):
     """Translate lines with ?/?? at the end"""
     m = _help_end_re.search(line)
     if m is None or has_comment(line):
         return line
     target = m.group(1)
     esc = m.group(3)
     lspace = _initial_space_re.match(line).group(0)
-    newline = _make_help_call(target, esc, lspace)
     
     # If we're mid-command, put it back on the next prompt for the user.
     next_input = line.rstrip('?') if line.strip() != m.group(0) else None
         
     return _make_help_call(target, esc, lspace, next_input)
 
 
 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,
+        return '%sget_ipython().system(%s)' % (line_info.pre,
                                                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,
+        return '%sget_ipython().getoutput(%s)' % (line_info.pre,
                                                   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()'
         
-        return _make_help_call(line_info.fpart, line_info.esc, line_info.lspace)
+        return _make_help_call(line_info.ifun, line_info.esc, line_info.pre)
 
     @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)
+        cmd = make_quoted_expr(' '.join([line_info.ifun,
+                                        line_info.the_rest]).strip())
+        return tpl % (line_info.pre, 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()) )
+        return '%s%s("%s")' % (line_info.pre, line_info.ifun,
+                             '", "'.join(line_info.the_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)
+        return '%s%s("%s")' % (line_info.pre, line_info.ifun,
+                               line_info.the_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()))
+        return '%s%s(%s)' % (line_info.pre, line_info.ifun,
+                             ", ".join(line_info.the_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 not line_info.esc in self.tr:
             # 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
         lines = cast_unicode(lines, self.encoding)
 
         lines_list = lines.splitlines()
 
         transforms = [transform_ipy_prompt, transform_classic_prompt,
-                      transform_escaped, transform_help_end,
+                      transform_help_end, transform_escaped,
                       transform_assign_system, transform_assign_magic]
 
         # 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/prefilter.py

@@ -1,1015 +1,943 b''
 # encoding: utf-8
 """
 Prefiltering components.
 
 Prefilters transform user input before it is exec'd by Python.  These
 transforms are used to implement additional syntax such as !ls and %magic.
 
 Authors:
 
 * Brian Granger
 * Fernando Perez
 * Dan Milstein
 * Ville Vainio
 """
 
 #-----------------------------------------------------------------------------
 #  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 codeop
 import re
 
 from IPython.core.alias import AliasManager
 from IPython.core.autocall import IPyAutocall
 from IPython.config.configurable import Configurable
 from IPython.core.macro import Macro
-from IPython.core.splitinput import split_user_input
+from IPython.core.splitinput import split_user_input, LineInfo
 from IPython.core import page
 
 from IPython.utils.traitlets import List, Int, Any, Unicode, CBool, Bool, Instance
 from IPython.utils.text import make_quoted_expr
 from IPython.utils.autoattr import auto_attr
 
 #-----------------------------------------------------------------------------
 # Global utilities, errors and constants
 #-----------------------------------------------------------------------------
 
 # Warning, these cannot be changed unless various regular expressions
 # are updated in a number of places.  Not great, but at least we told you.
 ESC_SHELL  = '!'
 ESC_SH_CAP = '!!'
 ESC_HELP   = '?'
 ESC_MAGIC  = '%'
 ESC_QUOTE  = ','
 ESC_QUOTE2 = ';'
 ESC_PAREN  = '/'
 
 
 class PrefilterError(Exception):
     pass
 
 
 # RegExp to identify potential function names
 re_fun_name = re.compile(r'[a-zA-Z_]([a-zA-Z0-9_.]*) *$')
 
 # RegExp to exclude strings with this start from autocalling.  In
 # particular, all binary operators should be excluded, so that if foo is
 # callable, foo OP bar doesn't become foo(OP bar), which is invalid.  The
 # characters '!=()' don't need to be checked for, as the checkPythonChars
 # routine explicitely does so, to catch direct calls and rebindings of
 # existing names.
 
 # Warning: the '-' HAS TO BE AT THE END of the first group, otherwise
 # it affects the rest of the group in square brackets.
 re_exclude_auto = re.compile(r'^[,&^\|\*/\+-]'
                              r'|^is |^not |^in |^and |^or ')
 
 # try to catch also methods for stuff in lists/tuples/dicts: off
 # (experimental). For this to work, the line_split regexp would need
 # to be modified so it wouldn't break things at '['. That line is
 # nasty enough that I shouldn't change it until I can test it _well_.
 #self.re_fun_name = re.compile (r'[a-zA-Z_]([a-zA-Z0-9_.\[\]]*) ?$')
 
 
 # Handler Check Utilities
 def is_shadowed(identifier, ip):
     """Is the given identifier defined in one of the namespaces which shadow
     the alias and magic namespaces?  Note that an identifier is different
     than ifun, because it can not contain a '.' character."""
     # This is much safer than calling ofind, which can change state
     return (identifier in ip.user_ns \
             or identifier in ip.internal_ns \
             or identifier in ip.ns_table['builtin'])
 
 
 #-----------------------------------------------------------------------------
-# The LineInfo class used throughout
-#-----------------------------------------------------------------------------
-
-
-class LineInfo(object):
-    """A single line of input and associated info.
-
-    Includes the following as properties: 
-
-    line
-      The original, raw line
-    
-    continue_prompt
-      Is this line a continuation in a sequence of multiline input?
-    
-    pre
-      The initial esc character or whitespace.
-    
-    pre_char
-      The escape character(s) in pre or the empty string if there isn't one.
-      Note that '!!' is a possible value for pre_char.  Otherwise it will
-      always be a single character.
-    
-    pre_whitespace
-      The leading whitespace from pre if it exists.  If there is a pre_char,
-      this is just ''.
-    
-    ifun
-      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.
-    
-    the_rest
-      Everything else on the line.
-    """
-    def __init__(self, line, continue_prompt):
-        self.line            = line
-        self.continue_prompt = continue_prompt
-        self.pre, self.esc, self.ifun, self.the_rest = split_user_input(line)
-
-        self.pre_char       = self.pre.strip()
-        if self.pre_char:
-            self.pre_whitespace = '' # No whitespace allowd before esc chars
-        else: 
-            self.pre_whitespace = self.pre
-
-        self._oinfo = None
-
-    def ofind(self, ip):
-        """Do a full, attribute-walking lookup of the ifun in the various
-        namespaces for the given IPython InteractiveShell instance.
-
-        Return a dict with keys: found,obj,ospace,ismagic
-
-        Note: can cause state changes because of calling getattr, but should
-        only be run if autocall is on and if the line hasn't matched any
-        other, less dangerous handlers.
-
-        Does cache the results of the call, so can be called multiple times
-        without worrying about *further* damaging state.
-        """
-        if not self._oinfo:
-            # ip.shell._ofind is actually on the Magic class!
-            self._oinfo = ip.shell._ofind(self.ifun)
-        return self._oinfo
-
-    def __str__(self):                                                         
-        return "Lineinfo [%s|%s|%s]" %(self.pre, self.ifun, self.the_rest) 
-
-
-#-----------------------------------------------------------------------------
 # Main Prefilter manager
 #-----------------------------------------------------------------------------
 
 
 class PrefilterManager(Configurable):
     """Main prefilter component.
 
     The IPython prefilter is run on all user input before it is run.  The
     prefilter consumes lines of input and produces transformed lines of 
     input.
 
     The iplementation consists of two phases:
 
     1. Transformers
     2. Checkers and handlers
 
     Over time, we plan on deprecating the checkers and handlers and doing
     everything in the transformers.
 
     The transformers are instances of :class:`PrefilterTransformer` and have
     a single method :meth:`transform` that takes a line and returns a
     transformed line.  The transformation can be accomplished using any
     tool, but our current ones use regular expressions for speed.  We also
     ship :mod:`pyparsing` in :mod:`IPython.external` for use in transformers.
 
     After all the transformers have been run, the line is fed to the checkers,
     which are instances of :class:`PrefilterChecker`.  The line is passed to
     the :meth:`check` method, which either returns `None` or a 
     :class:`PrefilterHandler` instance.  If `None` is returned, the other
     checkers are tried.  If an :class:`PrefilterHandler` instance is returned,
     the line is passed to the :meth:`handle` method of the returned
     handler and no further checkers are tried.
     
     Both transformers and checkers have a `priority` attribute, that determines
     the order in which they are called.  Smaller priorities are tried first.
 
     Both transformers and checkers also have `enabled` attribute, which is
     a boolean that determines if the instance is used.
 
     Users or developers can change the priority or enabled attribute of
     transformers or checkers, but they must call the :meth:`sort_checkers`
     or :meth:`sort_transformers` method after changing the priority.
     """
 
     multi_line_specials = CBool(True, config=True)
     shell = Instance('IPython.core.interactiveshell.InteractiveShellABC')
 
     def __init__(self, shell=None, config=None):
         super(PrefilterManager, self).__init__(shell=shell, config=config)
         self.shell = shell
         self.init_transformers()
         self.init_handlers()
         self.init_checkers()
 
     #-------------------------------------------------------------------------
     # API for managing transformers
     #-------------------------------------------------------------------------
 
     def init_transformers(self):
         """Create the default transformers."""
         self._transformers = []
         for transformer_cls in _default_transformers:
             transformer_cls(
                 shell=self.shell, prefilter_manager=self, config=self.config
             )
 
     def sort_transformers(self):
         """Sort the transformers by priority.
 
         This must be called after the priority of a transformer is changed.
         The :meth:`register_transformer` method calls this automatically.
         """
         self._transformers.sort(key=lambda x: x.priority)
 
     @property
     def transformers(self):
         """Return a list of checkers, sorted by priority."""
         return self._transformers
 
     def register_transformer(self, transformer):
         """Register a transformer instance."""
         if transformer not in self._transformers:
             self._transformers.append(transformer)
             self.sort_transformers()
 
     def unregister_transformer(self, transformer):
         """Unregister a transformer instance."""
         if transformer in self._transformers:
             self._transformers.remove(transformer)
 
     #-------------------------------------------------------------------------
     # API for managing checkers
     #-------------------------------------------------------------------------
 
     def init_checkers(self):
         """Create the default checkers."""
         self._checkers = []
         for checker in _default_checkers:
             checker(
                 shell=self.shell, prefilter_manager=self, config=self.config
             )
 
     def sort_checkers(self):
         """Sort the checkers by priority.
 
         This must be called after the priority of a checker is changed.
         The :meth:`register_checker` method calls this automatically.
         """
         self._checkers.sort(key=lambda x: x.priority)
 
     @property
     def checkers(self):
         """Return a list of checkers, sorted by priority."""
         return self._checkers
 
     def register_checker(self, checker):
         """Register a checker instance."""
         if checker not in self._checkers:
             self._checkers.append(checker)
             self.sort_checkers()
 
     def unregister_checker(self, checker):
         """Unregister a checker instance."""
         if checker in self._checkers:
             self._checkers.remove(checker)
 
     #-------------------------------------------------------------------------
     # API for managing checkers
     #-------------------------------------------------------------------------
 
     def init_handlers(self):
         """Create the default handlers."""
         self._handlers = {}
         self._esc_handlers = {}
         for handler in _default_handlers:
             handler(
                 shell=self.shell, prefilter_manager=self, config=self.config
             )
 
     @property
     def handlers(self):
         """Return a dict of all the handlers."""
         return self._handlers
 
     def register_handler(self, name, handler, esc_strings):
         """Register a handler instance by name with esc_strings."""
         self._handlers[name] = handler
         for esc_str in esc_strings:
             self._esc_handlers[esc_str] = handler
 
     def unregister_handler(self, name, handler, esc_strings):
         """Unregister a handler instance by name with esc_strings."""
         try:
             del self._handlers[name]
         except KeyError:
             pass
         for esc_str in esc_strings:
             h = self._esc_handlers.get(esc_str)
             if h is handler:
                 del self._esc_handlers[esc_str]
 
     def get_handler_by_name(self, name):
         """Get a handler by its name."""
         return self._handlers.get(name)
 
     def get_handler_by_esc(self, esc_str):
         """Get a handler by its escape string."""
         return self._esc_handlers.get(esc_str)
 
     #-------------------------------------------------------------------------
     # Main prefiltering API
     #-------------------------------------------------------------------------
 
     def prefilter_line_info(self, line_info):
         """Prefilter a line that has been converted to a LineInfo object.
 
         This implements the checker/handler part of the prefilter pipe.
         """
         # print "prefilter_line_info: ", line_info
         handler = self.find_handler(line_info)
         return handler.handle(line_info)
 
     def find_handler(self, line_info):
         """Find a handler for the line_info by trying checkers."""
         for checker in self.checkers:
             if checker.enabled:
                 handler = checker.check(line_info)
                 if handler:
                     return handler
         return self.get_handler_by_name('normal')
 
     def transform_line(self, line, continue_prompt):
         """Calls the enabled transformers in order of increasing priority."""
         for transformer in self.transformers:
             if transformer.enabled:
                 line = transformer.transform(line, continue_prompt)
         return line
 
     def prefilter_line(self, line, continue_prompt=False):
         """Prefilter a single input line as text.
 
         This method prefilters a single line of text by calling the
         transformers and then the checkers/handlers.
         """
 
         # print "prefilter_line: ", line, continue_prompt
         # All handlers *must* return a value, even if it's blank ('').
 
         # save the line away in case we crash, so the post-mortem handler can
         # record it
         self.shell._last_input_line = line
 
         if not line:
             # Return immediately on purely empty lines, so that if the user
             # previously typed some whitespace that started a continuation
             # prompt, he can break out of that loop with just an empty line.
             # This is how the default python prompt works.
             return ''
 
         # At this point, we invoke our transformers.
         if not continue_prompt or (continue_prompt and self.multi_line_specials):
             line = self.transform_line(line, continue_prompt)
 
         # Now we compute line_info for the checkers and handlers
         line_info = LineInfo(line, continue_prompt)
         
         # the input history needs to track even empty lines
         stripped = line.strip()
 
         normal_handler = self.get_handler_by_name('normal')
         if not stripped:
             if not continue_prompt:
                 self.shell.displayhook.prompt_count -= 1
 
             return normal_handler.handle(line_info)
 
         # special handlers are only allowed for single line statements
         if continue_prompt and not self.multi_line_specials:
             return normal_handler.handle(line_info)
 
         prefiltered = self.prefilter_line_info(line_info)
         # print "prefiltered line: %r" % prefiltered
         return prefiltered
 
     def prefilter_lines(self, lines, continue_prompt=False):
         """Prefilter multiple input lines of text.
 
         This is the main entry point for prefiltering multiple lines of
         input.  This simply calls :meth:`prefilter_line` for each line of
         input.
 
         This covers cases where there are multiple lines in the user entry,
         which is the case when the user goes back to a multiline history
         entry and presses enter.
         """
         llines = lines.rstrip('\n').split('\n')
         # We can get multiple lines in one shot, where multiline input 'blends'
         # into one line, in cases like recalling from the readline history
         # buffer.  We need to make sure that in such cases, we correctly
         # communicate downstream which line is first and which are continuation
         # ones.
         if len(llines) > 1:
             out = '\n'.join([self.prefilter_line(line, lnum>0)
                              for lnum, line in enumerate(llines) ])
         else:
             out = self.prefilter_line(llines[0], continue_prompt)
             
         return out
 
 #-----------------------------------------------------------------------------
 # Prefilter transformers
 #-----------------------------------------------------------------------------
 
 
 class PrefilterTransformer(Configurable):
     """Transform a line of user input."""
 
     priority = Int(100, config=True)
     # Transformers don't currently use shell or prefilter_manager, but as we
     # move away from checkers and handlers, they will need them.
     shell = Instance('IPython.core.interactiveshell.InteractiveShellABC')
     prefilter_manager = Instance('IPython.core.prefilter.PrefilterManager')
     enabled = Bool(True, config=True)
 
     def __init__(self, shell=None, prefilter_manager=None, config=None):
         super(PrefilterTransformer, self).__init__(
             shell=shell, prefilter_manager=prefilter_manager, config=config
         )
         self.prefilter_manager.register_transformer(self)
 
     def transform(self, line, continue_prompt):
         """Transform a line, returning the new one."""
         return None
 
     def __repr__(self):
         return "<%s(priority=%r, enabled=%r)>" % (
             self.__class__.__name__, self.priority, self.enabled)
 
 
 _assign_system_re = re.compile(r'(?P<lhs>(\s*)([\w\.]+)((\s*,\s*[\w\.]+)*))'
                                r'\s*=\s*!(?P<cmd>.*)')
 
 
 class AssignSystemTransformer(PrefilterTransformer):
     """Handle the `files = !ls` syntax."""
 
     priority = Int(100, config=True)
 
     def transform(self, line, continue_prompt):
         m = _assign_system_re.match(line)
         if m is not None:
             cmd = m.group('cmd')
             lhs = m.group('lhs')
             expr = make_quoted_expr("sc =%s" % cmd)
             new_line = '%s = get_ipython().magic(%s)' % (lhs, expr)
             return new_line
         return line
 
 
 _assign_magic_re = re.compile(r'(?P<lhs>(\s*)([\w\.]+)((\s*,\s*[\w\.]+)*))'
                                r'\s*=\s*%(?P<cmd>.*)')
 
 class AssignMagicTransformer(PrefilterTransformer):
     """Handle the `a = %who` syntax."""
 
     priority = Int(200, config=True)
 
     def transform(self, line, continue_prompt):
         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]*\.\.\. )')
 
 class PyPromptTransformer(PrefilterTransformer):
     """Handle inputs that start with '>>> ' syntax."""
 
     priority = Int(50, config=True)
 
     def transform(self, line, continue_prompt):
 
         if not line or line.isspace() or line.strip() == '...':
             # This allows us to recognize multiple input prompts separated by
             # blank lines and pasted in a single chunk, very common when
             # pasting doctests or long tutorial passages.
             return ''
         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]*\ \ \ \.\.\.+: )')
 
 class IPyPromptTransformer(PrefilterTransformer):
     """Handle inputs that start classic IPython prompt syntax."""
 
     priority = Int(50, config=True)
 
     def transform(self, line, continue_prompt):
 
         if not line or line.isspace() or line.strip() == '...':
             # This allows us to recognize multiple input prompts separated by
             # blank lines and pasted in a single chunk, very common when
             # pasting doctests or long tutorial passages.
             return ''
         m = _ipy_prompt_re.match(line)
         if m:
             return line[len(m.group(0)):]
         else:
             return line
 
 #-----------------------------------------------------------------------------
 # Prefilter checkers
 #-----------------------------------------------------------------------------
 
 
 class PrefilterChecker(Configurable):
     """Inspect an input line and return a handler for that line."""
 
     priority = Int(100, config=True)
     shell = Instance('IPython.core.interactiveshell.InteractiveShellABC')
     prefilter_manager = Instance('IPython.core.prefilter.PrefilterManager')
     enabled = Bool(True, config=True)
 
     def __init__(self, shell=None, prefilter_manager=None, config=None):
         super(PrefilterChecker, self).__init__(
             shell=shell, prefilter_manager=prefilter_manager, config=config
         )
         self.prefilter_manager.register_checker(self)
 
     def check(self, line_info):
         """Inspect line_info and return a handler instance or None."""
         return None
 
     def __repr__(self):
         return "<%s(priority=%r, enabled=%r)>" % (
             self.__class__.__name__, self.priority, self.enabled)
 
 
 class EmacsChecker(PrefilterChecker):
 
     priority = Int(100, config=True)
     enabled = Bool(False, config=True)
 
     def check(self, line_info):
         "Emacs ipython-mode tags certain input lines."
         if line_info.line.endswith('# PYTHON-MODE'):
             return self.prefilter_manager.get_handler_by_name('emacs')
         else:
             return None
 
 
 class ShellEscapeChecker(PrefilterChecker):
 
     priority = Int(200, config=True)
 
     def check(self, line_info):
         if line_info.line.lstrip().startswith(ESC_SHELL):
             return self.prefilter_manager.get_handler_by_name('shell')
 
 
 class MacroChecker(PrefilterChecker):
     
     priority = Int(250, config=True)
     
     def check(self, line_info):
         obj = self.shell.user_ns.get(line_info.ifun)
         if isinstance(obj, Macro):
             return self.prefilter_manager.get_handler_by_name('macro')
         else:
             return None
 
 
 class IPyAutocallChecker(PrefilterChecker):
 
     priority = Int(300, config=True)
 
     def check(self, line_info):
         "Instances of IPyAutocall in user_ns get autocalled immediately"
         obj = self.shell.user_ns.get(line_info.ifun, None)
         if isinstance(obj, IPyAutocall):
             obj.set_ip(self.shell)
             return self.prefilter_manager.get_handler_by_name('auto')
         else:
             return None
 
 
 class MultiLineMagicChecker(PrefilterChecker):
 
     priority = Int(400, config=True)
 
     def check(self, line_info):
         "Allow ! and !! in multi-line statements if multi_line_specials is on"
         # Note that this one of the only places we check the first character of
         # ifun and *not* the pre_char.  Also note that the below test matches
         # both ! and !!.    
         if line_info.continue_prompt \
             and self.prefilter_manager.multi_line_specials:
                 if line_info.esc == ESC_MAGIC:
                     return self.prefilter_manager.get_handler_by_name('magic')
         else:
             return None
 
 
 class EscCharsChecker(PrefilterChecker):
 
     priority = Int(500, config=True)
 
     def check(self, line_info):
         """Check for escape character and return either a handler to handle it,
         or None if there is no escape char."""
         if line_info.line[-1] == ESC_HELP \
                and line_info.esc != ESC_SHELL \
                and line_info.esc != ESC_SH_CAP:
             # the ? can be at the end, but *not* for either kind of shell escape,
             # because a ? can be a vaild final char in a shell cmd
             return self.prefilter_manager.get_handler_by_name('help')
         else:
             if line_info.pre:
                 return None
             # This returns None like it should if no handler exists
             return self.prefilter_manager.get_handler_by_esc(line_info.esc)
 
 
 class AssignmentChecker(PrefilterChecker):
 
     priority = Int(600, config=True)
 
     def check(self, line_info):
         """Check to see if user is assigning to a var for the first time, in
         which case we want to avoid any sort of automagic / autocall games.
     
         This allows users to assign to either alias or magic names true python
         variables (the magic/alias systems always take second seat to true
         python code).  E.g. ls='hi', or ls,that=1,2"""
         if line_info.the_rest:
             if line_info.the_rest[0] in '=,':
                 return self.prefilter_manager.get_handler_by_name('normal')
         else:
             return None
 
 
 class AutoMagicChecker(PrefilterChecker):
 
     priority = Int(700, config=True)
 
     def check(self, line_info):
         """If the ifun is magic, and automagic is on, run it.  Note: normal,
         non-auto magic would already have been triggered via '%' in
         check_esc_chars. This just checks for automagic.  Also, before
         triggering the magic handler, make sure that there is nothing in the
         user namespace which could shadow it."""
         if not self.shell.automagic or not hasattr(self.shell,'magic_'+line_info.ifun):
             return None
 
         # We have a likely magic method.  Make sure we should actually call it.
         if line_info.continue_prompt and not self.prefilter_manager.multi_line_specials:
             return None
 
         head = line_info.ifun.split('.',1)[0]
         if is_shadowed(head, self.shell):
             return None
 
         return self.prefilter_manager.get_handler_by_name('magic')
 
 
 class AliasChecker(PrefilterChecker):
 
     priority = Int(800, config=True)
 
     def check(self, line_info):
         "Check if the initital identifier on the line is an alias."
         # Note: aliases can not contain '.'
         head = line_info.ifun.split('.',1)[0]
         if line_info.ifun not in self.shell.alias_manager \
                or head not in self.shell.alias_manager \
                or is_shadowed(head, self.shell):
             return None
 
         return self.prefilter_manager.get_handler_by_name('alias')
 
 
 class PythonOpsChecker(PrefilterChecker):
 
     priority = Int(900, config=True)
 
     def check(self, line_info):
         """If the 'rest' of the line begins with a function call or pretty much
         any python operator, we should simply execute the line (regardless of
         whether or not there's a possible autocall expansion).  This avoids
         spurious (and very confusing) geattr() accesses."""
         if line_info.the_rest and line_info.the_rest[0] in '!=()<>,+*/%^&|':
             return self.prefilter_manager.get_handler_by_name('normal')
         else:
             return None
 
 
 class AutocallChecker(PrefilterChecker):
 
     priority = Int(1000, config=True)
 
     def check(self, line_info):
         "Check if the initial word/function is callable and autocall is on."
         if not self.shell.autocall:
             return None
 
         oinfo = line_info.ofind(self.shell) # This can mutate state via getattr
         if not oinfo['found']:
             return None
         
         if callable(oinfo['obj']) \
                and (not re_exclude_auto.match(line_info.the_rest)) \
                and re_fun_name.match(line_info.ifun):
             return self.prefilter_manager.get_handler_by_name('auto')
         else:
             return None
 
 
 #-----------------------------------------------------------------------------
 # Prefilter handlers
 #-----------------------------------------------------------------------------
 
 
 class PrefilterHandler(Configurable):
 
     handler_name = Unicode('normal')
     esc_strings = List([])
     shell = Instance('IPython.core.interactiveshell.InteractiveShellABC')
     prefilter_manager = Instance('IPython.core.prefilter.PrefilterManager')
 
     def __init__(self, shell=None, prefilter_manager=None, config=None):
         super(PrefilterHandler, self).__init__(
             shell=shell, prefilter_manager=prefilter_manager, config=config
         )
         self.prefilter_manager.register_handler(
             self.handler_name,
             self,
             self.esc_strings
         )
 
     def handle(self, line_info):
         # print "normal: ", line_info
         """Handle normal input lines. Use as a template for handlers."""
 
         # With autoindent on, we need some way to exit the input loop, and I
         # don't want to force the user to have to backspace all the way to
         # clear the line.  The rule will be in this case, that either two
         # lines of pure whitespace in a row, or a line of pure whitespace but
         # of a size different to the indent level, will exit the input loop.
         line = line_info.line
         continue_prompt = line_info.continue_prompt
 
         if (continue_prompt and
             self.shell.autoindent and
             line.isspace() and
             0 < abs(len(line) - self.shell.indent_current_nsp) <= 2):
             line = ''
 
         return line
 
     def __str__(self):
         return "<%s(name=%s)>" % (self.__class__.__name__, self.handler_name)
 
 
 class AliasHandler(PrefilterHandler):
 
     handler_name = Unicode('alias')
 
     def handle(self, line_info):
         """Handle alias input lines. """
         transformed = self.shell.alias_manager.expand_aliases(line_info.ifun,line_info.the_rest)
         # pre is needed, because it carries the leading whitespace.  Otherwise
         # aliases won't work in indented sections.
         line_out = '%sget_ipython().system(%s)' % (line_info.pre_whitespace,
                                          make_quoted_expr(transformed))
         
         return line_out
 
 
 class ShellEscapeHandler(PrefilterHandler):
 
     handler_name = Unicode('shell')
     esc_strings = List([ESC_SHELL, ESC_SH_CAP])
 
     def handle(self, line_info):
         """Execute the line in a shell, empty return value"""
         magic_handler = self.prefilter_manager.get_handler_by_name('magic')
 
         line = line_info.line
         if line.lstrip().startswith(ESC_SH_CAP):
             # rewrite LineInfo's line, ifun and the_rest to properly hold the
             # call to %sx and the actual command to be executed, so
             # handle_magic can work correctly.  Note that this works even if
             # the line is indented, so it handles multi_line_specials
             # properly.
             new_rest = line.lstrip()[2:]
             line_info.line = '%ssx %s' % (ESC_MAGIC, new_rest)
             line_info.ifun = 'sx'
             line_info.the_rest = new_rest
             return magic_handler.handle(line_info)
         else:
             cmd = line.lstrip().lstrip(ESC_SHELL)
             line_out = '%sget_ipython().system(%s)' % (line_info.pre_whitespace,
                                              make_quoted_expr(cmd))
         return line_out
 
 
 class MacroHandler(PrefilterHandler):
     handler_name = Unicode("macro")
     
     def handle(self, line_info):
         obj = self.shell.user_ns.get(line_info.ifun)
         pre_space = line_info.pre_whitespace
         line_sep = "\n" + pre_space
         return pre_space + line_sep.join(obj.value.splitlines())
 
 
 class MagicHandler(PrefilterHandler):
 
     handler_name = Unicode('magic')
     esc_strings = List([ESC_MAGIC])
 
     def handle(self, line_info):
         """Execute magic functions."""
         ifun    = line_info.ifun
         the_rest = line_info.the_rest
         cmd = '%sget_ipython().magic(%s)' % (line_info.pre_whitespace,
                                    make_quoted_expr(ifun + " " + the_rest))
         return cmd
 
 
 class AutoHandler(PrefilterHandler):
 
     handler_name = Unicode('auto')
     esc_strings = List([ESC_PAREN, ESC_QUOTE, ESC_QUOTE2])
 
     def handle(self, line_info):
         """Handle lines which can be auto-executed, quoting if requested."""
         line    = line_info.line
         ifun    = line_info.ifun
         the_rest = line_info.the_rest
         pre     = line_info.pre
         esc     = line_info.esc
         continue_prompt = line_info.continue_prompt
         obj = line_info.ofind(self)['obj']
         #print 'pre <%s> ifun <%s> rest <%s>' % (pre,ifun,the_rest)  # dbg
 
         # This should only be active for single-line input!
         if continue_prompt:
             return line
 
         force_auto = isinstance(obj, IPyAutocall)
         auto_rewrite = getattr(obj, 'rewrite', True)
         
         if esc == ESC_QUOTE:
             # Auto-quote splitting on whitespace
             newcmd = '%s("%s")' % (ifun,'", "'.join(the_rest.split()) )
         elif esc == ESC_QUOTE2:
             # Auto-quote whole string
             newcmd = '%s("%s")' % (ifun,the_rest)
         elif esc == ESC_PAREN:
             newcmd = '%s(%s)' % (ifun,",".join(the_rest.split()))
         else:
             # Auto-paren.
             # We only apply it to argument-less calls if the autocall
             # parameter is set to 2.  We only need to check that autocall is <
             # 2, since this function isn't called unless it's at least 1.
             if not the_rest and (self.shell.autocall < 2) and not force_auto:
                 newcmd = '%s %s' % (ifun,the_rest)
                 auto_rewrite = False
             else:
                 if not force_auto and the_rest.startswith('['):
                     if hasattr(obj,'__getitem__'):
                         # Don't autocall in this case: item access for an object
                         # which is BOTH callable and implements __getitem__.
                         newcmd = '%s %s' % (ifun,the_rest)
                         auto_rewrite = False
                     else:
                         # if the object doesn't support [] access, go ahead and
                         # autocall
                         newcmd = '%s(%s)' % (ifun.rstrip(),the_rest)
                 elif the_rest.endswith(';'):
                     newcmd = '%s(%s);' % (ifun.rstrip(),the_rest[:-1])
                 else:
                     newcmd = '%s(%s)' % (ifun.rstrip(), the_rest)
 
         if auto_rewrite:
             self.shell.auto_rewrite_input(newcmd)
             
         return newcmd
 
 
 class HelpHandler(PrefilterHandler):
 
     handler_name = Unicode('help')
     esc_strings = List([ESC_HELP])
 
     def handle(self, line_info):
         """Try to get some help for the object.
 
         obj? or ?obj   -> basic information.
         obj?? or ??obj -> more details.
         """
         normal_handler = self.prefilter_manager.get_handler_by_name('normal')
         line = line_info.line
         # We need to make sure that we don't process lines which would be
         # otherwise valid python, such as "x=1 # what?"
         try:
             codeop.compile_command(line)
         except SyntaxError:
             # We should only handle as help stuff which is NOT valid syntax
             if line[0]==ESC_HELP:
                 line = line[1:]
             elif line[-1]==ESC_HELP:
                 line = line[:-1]
             if line:
                 #print 'line:<%r>' % line  # dbg
                 self.shell.magic_pinfo(line_info.ifun)
             else:
                 self.shell.show_usage()
             return '' # Empty string is needed here!
         except:
             raise
             # Pass any other exceptions through to the normal handler
             return normal_handler.handle(line_info)
         else:
             # If the code compiles ok, we should handle it normally
             return normal_handler.handle(line_info)
 
 
 class EmacsHandler(PrefilterHandler):
 
     handler_name = Unicode('emacs')
     esc_strings = List([])
 
     def handle(self, line_info):
         """Handle input lines marked by python-mode."""
 
         # Currently, nothing is done.  Later more functionality can be added
         # here if needed.
 
         # The input cache shouldn't be updated
         return line_info.line
 
 
 #-----------------------------------------------------------------------------
 # Defaults
 #-----------------------------------------------------------------------------
 
 
 _default_transformers = [
     AssignSystemTransformer,
     AssignMagicTransformer,
     PyPromptTransformer,
     IPyPromptTransformer,
 ]
 
 _default_checkers = [
     EmacsChecker,
     ShellEscapeChecker,
     MacroChecker,
     IPyAutocallChecker,
     MultiLineMagicChecker,
     EscCharsChecker,
     AssignmentChecker,
     AutoMagicChecker,
     AliasChecker,
     PythonOpsChecker,
     AutocallChecker
 ]
 
 _default_handlers = [
     PrefilterHandler,
     AliasHandler,
     ShellEscapeHandler,
     MacroHandler,
     MagicHandler,
     AutoHandler,
     HelpHandler,
     EmacsHandler
 ]

IPython/core/splitinput.py

@@ -1,86 +1,138 b''
 # encoding: utf-8
 """
-Simple utility for splitting user input.
+Simple utility for splitting user input. This is used by both inputsplitter and
+prefilter.
 
 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 re
 import sys
 
 from IPython.utils import py3compat
 
 #-----------------------------------------------------------------------------
 # Main function
 #-----------------------------------------------------------------------------
 
-
 # RegExp for splitting line contents into pre-char//first word-method//rest.
 # For clarity, each group in on one line.
 
-# WARNING: update the regexp if the escapes in interactiveshell are changed, as they
-# are hardwired in.
+# WARNING: update the regexp if the escapes in interactiveshell are changed, as
+# they are hardwired in.
 
 # Although it's not solely driven by the regex, note that:
 # ,;/% only trigger if they are the first character on the line
 # ! and !! trigger if they are first char(s) *or* follow an indent 
 # ? triggers as first or last char.
 
-# The four parts of the regex are:
-#  1) pre:     initial whitespace
-#  2) esc:     escape character
-#  3) ifun:    first word/method (mix of \w and '.')
-#  4) the_rest: rest of line (separated from ifun by space if non-empty)
-line_split = re.compile(r'^(\s*)'
-                        r'([,;/%?]|!!?)?'
-                        r'\s*([\w\.]+)'
-                        r'(.*$|$)')
-
-# r'[\w\.]+'
-# r'\s*=\s*%.*'
+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'
+             (.*?$|$)             # rest of line
+             """, re.VERBOSE)
 
 def split_user_input(line, pattern=None):
-    """Split user input into pre-char/whitespace, function part and rest.
-
-    This is currently handles lines with '=' in them in a very inconsistent
-    manner.
+    """Split user input into initial whitespace, escape character, function part
+    and the rest.
     """
     # We need to ensure that the rest of this routine deals only with unicode
     line = py3compat.cast_unicode(line, sys.stdin.encoding or 'utf-8')
         
     if pattern is None:
         pattern = line_split
     match = pattern.match(line)
     if not match:
         # print "match failed for line '%s'" % line
         try:
             ifun, the_rest = line.split(None,1)
         except ValueError:
             # print "split failed for line '%s'" % line
             ifun, the_rest = line, u''
         pre = re.match('^(\s*)(.*)',line).groups()[0]
         esc = ""
     else:
         pre, esc, ifun, the_rest = match.groups()
     
-    if not py3compat.isidentifier(ifun, dotted=True):
-        the_rest = ifun + u' ' + the_rest
-        ifun = u''
-
     #print 'line:<%s>' % line # dbg
     #print 'pre <%s> ifun <%s> rest <%s>' % (pre,ifun.strip(),the_rest) # dbg
-    return pre, esc, ifun.strip(), the_rest.lstrip()
+    return pre, esc or '', ifun.strip(), the_rest.lstrip()
+
+class LineInfo(object):
+    """A single line of input and associated info.
+
+    Includes the following as properties: 
+
+    line
+      The original, raw line
+    
+    continue_prompt
+      Is this line a continuation in a sequence of multiline input?
+    
+    pre
+      Any leading whitespace.
+    
+    esc
+      The escape character(s) in pre or the empty string if there isn't one.
+      Note that '!!' and '??' are possible values for esc. Otherwise it will
+      always be a single character.
+    
+    ifun
+      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. In contrast to Python identifiers, it may start with "%" and contain
+      "*".
+    
+    the_rest
+      Everything else on the line.
+    """
+    def __init__(self, line, continue_prompt=False):
+        self.line            = line
+        self.continue_prompt = continue_prompt
+        self.pre, self.esc, self.ifun, self.the_rest = split_user_input(line)
+
+        self.pre_char       = self.pre.strip()
+        if self.pre_char:
+            self.pre_whitespace = '' # No whitespace allowd before esc chars
+        else: 
+            self.pre_whitespace = self.pre
+
+        self._oinfo = None
+
+    def ofind(self, ip):
+        """Do a full, attribute-walking lookup of the ifun in the various
+        namespaces for the given IPython InteractiveShell instance.
+
+        Return a dict with keys: found,obj,ospace,ismagic
+
+        Note: can cause state changes because of calling getattr, but should
+        only be run if autocall is on and if the line hasn't matched any
+        other, less dangerous handlers.
+
+        Does cache the results of the call, so can be called multiple times
+        without worrying about *further* damaging state.
+        """
+        if not self._oinfo:
+            # ip.shell._ofind is actually on the Magic class!
+            self._oinfo = ip.shell._ofind(self.ifun)
+        return self._oinfo
+
+    def __str__(self):                                                         
+        return "LineInfo [%s|%s|%s|%s]" %(self.pre, self.esc, self.ifun, self.the_rest) 

IPython/core/tests/test_inputsplitter.py

@@ -1,698 +1,698 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
 from IPython.testing import tools as tt
 
 #-----------------------------------------------------------------------------
 # 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),
              ]
     tt.check_pairs(isp.num_ini_spaces, tests)
 
 
 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'),
              ]
     tt.check_pairs(isp.remove_comments, tests)
         
 def test_has_comment():
     tests = [('text', False),
              ('text #comment', True),
              ('text #comment\n', True),
              ('#comment', True),
              ('#comment\n', True),
              ('a = "#string"', False),
              ('a = "#string" # comment', True),
              ('a #comment not "string"', True),
              ]
     tt.check_pairs(isp.has_comment, tests)
 
 
 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(u'test'.encode(encoding), b'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_indent4(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
         # whitespace after ':' should not screw up indent level
         isp.push('if 1: \n    x=1')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('y=2\n')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\t\n    x=1')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('y=2\n')
         self.assertEqual(isp.indent_spaces, 0)
 
     def test_dedent_pass(self):
         isp = self.isp # shorthand
         # should NOT cause dedent
         isp.push('if 1:\n    passes = 5')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('if 1:\n     pass')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n     pass   ')
         self.assertEqual(isp.indent_spaces, 0)
 
     def test_dedent_raise(self):
         isp = self.isp # shorthand
         # should NOT cause dedent
         isp.push('if 1:\n    raised = 4')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('if 1:\n     raise TypeError()')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n     raise')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n     raise      ')
         self.assertEqual(isp.indent_spaces, 0)
 
     def test_dedent_return(self):
         isp = self.isp # shorthand
         # should NOT cause dedent
         isp.push('if 1:\n    returning = 4')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('if 1:\n     return 5 + 493')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n     return')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n     return      ')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('if 1:\n     return(0)')
         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_push3(self):
         isp = self.isp
         isp.push('if True:')
         isp.push('  a = 1')
         self.assertFalse(isp.push('b = [1,'))
             
     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 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)
+    tt.check_pairs(isp.split_user_input, [(line, 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(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(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(u"ls")'),
          # Double-escape shell, this means to capture the output of the
          # subprocess and return it
          ('!!ls', 'get_ipython().getoutput(u"ls")'),
          ],
 
        # Help/object info
        escaped_help =
        [ ('?', 'get_ipython().show_usage()'),
          ('?x1', 'get_ipython().magic(u"pinfo x1")'),
          ('??x2', 'get_ipython().magic(u"pinfo2 x2")'),
          ('?a.*s', 'get_ipython().magic(u"psearch a.*s")'),
          ('?%hist', 'get_ipython().magic(u"pinfo %hist")'),
          ('?abc = qwe', 'get_ipython().magic(u"pinfo abc")'),
          ],
          
       end_help =
       [ ('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*")'),
         ('a = abc?', 'get_ipython().magic(u"pinfo abc", next_input=u"a = abc")'),
         ('a = abc.qe??', 'get_ipython().magic(u"pinfo2 abc.qe", next_input=u"a = abc.qe")'),
         ('a = *.items?', 'get_ipython().magic(u"psearch *.items", next_input=u"a = *.items")'),
         ('plot(a?', 'get_ipython().magic(u"pinfo a", next_input=u"plot(a")'),
         ('a*2 #comment?', 'a*2 #comment?'),
         ],
 
        # Explicit magic calls
        escaped_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)'),
          ],
          
        # Check that we transform prompts before other transforms
        mixed =
        [ ('In [1]: %lsmagic', 'get_ipython().magic(u"lsmagic")'),
          ('>>> %lsmagic', 'get_ipython().magic(u"lsmagic")'),
          ('In [2]: !ls', 'get_ipython().system(u"ls")'),
          ('In [3]: abs?', 'get_ipython().magic(u"pinfo abs")'),
          ('In [4]: b = %who', 'b = get_ipython().magic(u"who")'),
          ],
        )
 
 # 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():
     tt.check_pairs(isp.transform_assign_system, syntax['assign_system'])
 
     
 def test_assign_magic():
     tt.check_pairs(isp.transform_assign_magic, syntax['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_end_help():
     tt.check_pairs(isp.transform_help_end, syntax['end_help'])
 
 def test_escaped_noesc():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_noesc'])
 
 
 def test_escaped_shell():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_shell'])
 
 
 def test_escaped_help():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_help'])
 
 
 def test_escaped_magic():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_magic'])
 
 
 def test_escaped_quote():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_quote'])
 
 
 def test_escaped_quote2():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_quote2'])
 
 
 def test_escaped_paren():
     tt.check_pairs(isp.transform_escaped, syntax['escaped_paren'])
 
 
 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.rstrip(), out_t,
+                        tt.pair_fail_msg.format("inputsplitter",raw, out_t, out))
                 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/testing/tools.py

@@ -1,345 +1,345 b''
 """Generic testing tools that do NOT depend on Twisted.
 
 In particular, this module exposes a set of top-level assert* functions that
 can be used in place of nose.tools.assert* in method generators (the ones in
 nose can not, at least as of nose 0.10.4).
 
 Note: our testing package contains testing.util, which does depend on Twisted
 and provides utilities for tests that manage Deferreds.  All testing support
 tools that only depend on nose, IPython or the standard library should go here
 instead.
 
 
 Authors
 -------
 - Fernando Perez <[e-mail]>
 """
 
 from __future__ import absolute_import
 
 #-----------------------------------------------------------------------------
 #  Copyright (C) 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 os
 import re
 import sys
 import tempfile
 
 from contextlib import contextmanager
 
 try:
     # These tools are used by parts of the runtime, so we make the nose
     # dependency optional at this point.  Nose is a hard dependency to run the
     # test suite, but NOT to use ipython itself.
     import nose.tools as nt
     has_nose = True
 except ImportError:
     has_nose = False
 
 from IPython.config.loader import Config
 from IPython.utils.process import find_cmd, getoutputerror
 from IPython.utils.text import list_strings
 from IPython.utils.io import temp_pyfile
 
 from . import decorators as dec
 from . import skipdoctest
 
 #-----------------------------------------------------------------------------
 # Globals
 #-----------------------------------------------------------------------------
 
 # Make a bunch of nose.tools assert wrappers that can be used in test
 # generators.  This will expose an assert* function for each one in nose.tools.
 
 _tpl = """
 def %(name)s(*a,**kw):
     return nt.%(name)s(*a,**kw)
 """
 
 if has_nose:
     for _x in [a for a in dir(nt) if a.startswith('assert')]:
         exec _tpl % dict(name=_x)
 
 #-----------------------------------------------------------------------------
 # Functions and classes
 #-----------------------------------------------------------------------------
 
 # The docstring for full_path doctests differently on win32 (different path
 # separator) so just skip the doctest there.  The example remains informative.
 doctest_deco = skipdoctest.skip_doctest if sys.platform == 'win32' else dec.null_deco
 
 @doctest_deco
 def full_path(startPath,files):
     """Make full paths for all the listed files, based on startPath.
 
     Only the base part of startPath is kept, since this routine is typically
     used with a script's __file__ variable as startPath.  The base of startPath
     is then prepended to all the listed files, forming the output list.
 
     Parameters
     ----------
       startPath : string
         Initial path to use as the base for the results.  This path is split
       using os.path.split() and only its first component is kept.
 
       files : string or list
         One or more files.
 
     Examples
     --------
 
     >>> full_path('/foo/bar.py',['a.txt','b.txt'])
     ['/foo/a.txt', '/foo/b.txt']
 
     >>> full_path('/foo',['a.txt','b.txt'])
     ['/a.txt', '/b.txt']
 
     If a single file is given, the output is still a list:
     >>> full_path('/foo','a.txt')
     ['/a.txt']
     """
 
     files = list_strings(files)
     base = os.path.split(startPath)[0]
     return [ os.path.join(base,f) for f in files ]
 
 
 def parse_test_output(txt):
     """Parse the output of a test run and return errors, failures.
 
     Parameters
     ----------
     txt : str
       Text output of a test run, assumed to contain a line of one of the
       following forms::
         'FAILED (errors=1)'
         'FAILED (failures=1)'
         'FAILED (errors=1, failures=1)'
 
     Returns
     -------
     nerr, nfail: number of errors and failures.
     """
 
     err_m = re.search(r'^FAILED \(errors=(\d+)\)', txt, re.MULTILINE)
     if err_m:
         nerr = int(err_m.group(1))
         nfail = 0
         return  nerr, nfail
     
     fail_m = re.search(r'^FAILED \(failures=(\d+)\)', txt, re.MULTILINE)
     if fail_m:
         nerr = 0
         nfail = int(fail_m.group(1))
         return  nerr, nfail
 
     both_m = re.search(r'^FAILED \(errors=(\d+), failures=(\d+)\)', txt,
                        re.MULTILINE)
     if both_m:
         nerr = int(both_m.group(1))
         nfail = int(both_m.group(2))
         return  nerr, nfail
     
     # If the input didn't match any of these forms, assume no error/failures
     return 0, 0
 
 
 # So nose doesn't think this is a test
 parse_test_output.__test__ = False
 
 
 def default_argv():
     """Return a valid default argv for creating testing instances of ipython"""
 
     return ['--quick', # so no config file is loaded
             # Other defaults to minimize side effects on stdout
             '--colors=NoColor', '--no-term-title','--no-banner',
             '--autocall=0']
 
 
 def default_config():
     """Return a config object with good defaults for testing."""
     config = Config()
     config.TerminalInteractiveShell.colors = 'NoColor'
     config.TerminalTerminalInteractiveShell.term_title = False,
     config.TerminalInteractiveShell.autocall = 0
     config.HistoryManager.hist_file = tempfile.mktemp(u'test_hist.sqlite')
     config.HistoryManager.db_cache_size = 10000
     return config
 
 
 def ipexec(fname, options=None):
     """Utility to call 'ipython filename'.
 
     Starts IPython witha minimal and safe configuration to make startup as fast
     as possible.
 
     Note that this starts IPython in a subprocess!
 
     Parameters
     ----------
     fname : str
       Name of file to be executed (should have .py or .ipy extension).
 
     options : optional, list
       Extra command-line flags to be passed to IPython.
 
     Returns
     -------
     (stdout, stderr) of ipython subprocess.
     """
     if options is None: options = []
     
     # For these subprocess calls, eliminate all prompt printing so we only see
     # output from script execution
     prompt_opts = [ '--InteractiveShell.prompt_in1=""', 
                     '--InteractiveShell.prompt_in2=""', 
                     '--InteractiveShell.prompt_out=""'
     ]
     cmdargs = ' '.join(default_argv() + prompt_opts + options)
     
     _ip = get_ipython()
     test_dir = os.path.dirname(__file__)
 
     ipython_cmd = find_cmd('ipython')
     # Absolute path for filename
     full_fname = os.path.join(test_dir, fname)
     full_cmd = '%s %s %s' % (ipython_cmd, cmdargs, full_fname)
     #print >> sys.stderr, 'FULL CMD:', full_cmd # dbg
     out = getoutputerror(full_cmd)
     # `import readline` causes 'ESC[?1034h' to be the first output sometimes,
     # so strip that off the front of the first line if it is found
     if out:
         first = out[0]
         m = re.match(r'\x1b\[[^h]+h', first)
         if m:
             # strip initial readline escape
             out = list(out)
             out[0] = first[len(m.group()):]
             out = tuple(out)
     return out
 
 
 def ipexec_validate(fname, expected_out, expected_err='',
                     options=None):
     """Utility to call 'ipython filename' and validate output/error.
 
     This function raises an AssertionError if the validation fails.
 
     Note that this starts IPython in a subprocess!
 
     Parameters
     ----------
     fname : str
       Name of the file to be executed (should have .py or .ipy extension).
 
     expected_out : str
       Expected stdout of the process.
 
     expected_err : optional, str
       Expected stderr of the process.
 
     options : optional, list
       Extra command-line flags to be passed to IPython.
 
     Returns
     -------
     None
     """
 
     import nose.tools as nt
     
     out, err = ipexec(fname)
     #print 'OUT', out  # dbg
     #print 'ERR', err  # dbg
     # If there are any errors, we must check those befor stdout, as they may be
     # more informative than simply having an empty stdout.
     if err:
         if expected_err:
             nt.assert_equals(err.strip(), expected_err.strip())
         else:
             raise ValueError('Running file %r produced error: %r' %
                              (fname, err))
     # If no errors or output on stderr was expected, match stdout
     nt.assert_equals(out.strip(), expected_out.strip())
 
 
 class TempFileMixin(object):
     """Utility class to create temporary Python/IPython files.
 
     Meant as a mixin class for test cases."""
     
     def mktmp(self, src, ext='.py'):
         """Make a valid python temp file."""
         fname, f = temp_pyfile(src, ext)
         self.tmpfile = f
         self.fname = fname
 
     def tearDown(self):
         if hasattr(self, 'tmpfile'):
             # If the tmpfile wasn't made because of skipped tests, like in
             # win32, there's nothing to cleanup.
             self.tmpfile.close()
             try:
                 os.unlink(self.fname)
             except:
                 # On Windows, even though we close the file, we still can't
                 # delete it.  I have no clue why
                 pass
 
-pair_fail_msg = ("Testing function {0}\n\n"
+pair_fail_msg = ("Testing {0}\n\n"
                 "In:\n"
                 "  {1!r}\n"
                 "Expected:\n"
                 "  {2!r}\n"
                 "Got:\n"
                 "  {3!r}\n")
 def check_pairs(func, pairs):
     """Utility function for the common case of checking a function with a 
     sequence of input/output pairs.
     
     Parameters
     ----------
     func : callable
       The function to be tested. Should accept a single argument.
     pairs : iterable
       A list of (input, expected_output) tuples.
     
     Returns
     -------
     None. Raises an AssertionError if any output does not match the expected
     value.
     """
+    name = getattr(func, "func_name", getattr(func, "__name__", "<unknown>"))
     for inp, expected in pairs:
         out = func(inp)
-        assert out == expected, pair_fail_msg.format(func.func_name, inp, expected, out)
+        assert out == expected, pair_fail_msg.format(name, inp, expected, out)
 
 @contextmanager
 def mute_warn():
     from IPython.utils import warn
     save_warn = warn.warn
     warn.warn = lambda *a, **kw: None
     try:
         yield
     finally:
         warn.warn = save_warn
 
 @contextmanager
 def make_tempfile(name):
     """ Create an empty, named, temporary file for the duration of the context.
     """
     f = open(name, 'w')
     f.close()
     try:
         yield
     finally:
         os.unlink(name)
-