Calculate indentation based on tokens, not regexes

Closes gh-2913
Closes gh-10268

IPython/core/inputsplitter.py

@@ -1,679 +1,787 b''
 """Input handling and transformation machinery.
 
 The first class in this module, :class:`InputSplitter`, is designed to tell when
 input from a line-oriented frontend is complete and should be executed, and when
 the user should be prompted for another line of code instead. The name 'input
 splitter' is largely for historical reasons.
 
 A companion, :class:`IPythonInputSplitter`, provides the same functionality but
 with full support for the extended IPython syntax (magics, system calls, etc).
 The code to actually do these transformations is in :mod:`IPython.core.inputtransformer`.
 :class:`IPythonInputSplitter` feeds the raw code to the transformers in order
 and stores the results.
 
 For more details, see the class docstrings below.
 """
 
 # Copyright (c) IPython Development Team.
 # Distributed under the terms of the Modified BSD License.
 import ast
 import codeop
+import io
 import re
 import sys
+import tokenize
 import warnings
 
 from IPython.utils.py3compat import cast_unicode
 from IPython.core.inputtransformer import (leading_indent,
                                            classic_prompt,
                                            ipy_prompt,
                                            cellmagic,
                                            assemble_logical_lines,
                                            help_end,
                                            escaped_commands,
                                            assign_from_magic,
                                            assign_from_system,
                                            assemble_python_lines,
                                            )
 
 # These are available in this module for backwards compatibility.
 from IPython.core.inputtransformer import (ESC_SHELL, ESC_SH_CAP, ESC_HELP,
                                         ESC_HELP2, ESC_MAGIC, ESC_MAGIC2,
                                         ESC_QUOTE, ESC_QUOTE2, ESC_PAREN, ESC_SEQUENCES)
 
 #-----------------------------------------------------------------------------
 # 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)
     r'^\s+break\s*$', # break (optionally followed by trailing spaces)
     r'^\s+continue\s*$', # continue (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
 
+# Fake token types for partial_tokenize:
+INCOMPLETE_STRING = tokenize.N_TOKENS
+IN_MULTILINE_STATEMENT = tokenize.N_TOKENS + 1
+
+# The 2 classes below have the same API as TokenInfo, but don't try to look up
+# a token type name that they won't find.
+class IncompleteString:
+    type = exact_type = INCOMPLETE_STRING
+    def __init__(self, s, start, end, line):
+        self.s = s
+        self.start = start
+        self.end = end
+        self.line = line
+
+class InMultilineStatement:
+    type = exact_type = IN_MULTILINE_STATEMENT
+    def __init__(self, pos, line):
+        self.s = ''
+        self.start = self.end = pos
+        self.line = line
+
+def partial_tokens(s):
+    """Iterate over tokens from a possibly-incomplete string of code.
+
+    This adds two special token types: INCOMPLETE_STRING and
+    IN_MULTILINE_STATEMENT. These can only occur as the last token yielded, and
+    represent the two main ways for code to be incomplete.
+    """
+    readline = io.StringIO(s).readline
+    token = tokenize.TokenInfo(tokenize.NEWLINE, '', (1, 0), (1, 0), '')
+    try:
+        for token in tokenize.generate_tokens(readline):
+            yield token
+    except tokenize.TokenError as e:
+        # catch EOF error
+        lines = s.splitlines(keepends=True)
+        end = len(lines), len(lines[-1])
+        if 'multi-line string' in e.args[0]:
+            l, c = start = token.end
+            s = lines[l-1][c:] + ''.join(lines[l:])
+            yield IncompleteString(s, start, end, lines[-1])
+        elif 'multi-line statement' in e.args[0]:
+            yield InMultilineStatement(end, lines[-1])
+        else:
+            raise
+
+def find_next_indent(code):
+    """Find the number of spaces for the next line of indentation"""
+    tokens = list(partial_tokens(code))
+    if tokens[-1].type == tokenize.ENDMARKER:
+        tokens.pop()
+    if not tokens:
+        return 0
+    if tokens[-1].type in {tokenize.DEDENT, tokenize.NEWLINE, tokenize.COMMENT}:
+        tokens.pop()
+
+    if tokens[-1].type == INCOMPLETE_STRING:
+        # Inside a multiline string
+        return 0
+
+    # Find the indents used before
+    prev_indents = [0]
+    def _add_indent(n):
+        if n != prev_indents[-1]:
+            prev_indents.append(n)
+
+    tokiter = iter(tokens)
+    for tok in tokiter:
+        if tok.type in {tokenize.INDENT, tokenize.DEDENT}:
+            _add_indent(tok.end[1])
+        elif (tok.type == tokenize.NL):
+            try:
+                _add_indent(next(tokiter).start[1])
+            except StopIteration:
+                break
+
+    last_indent = prev_indents.pop()
+
+    if tokens[-1].type == IN_MULTILINE_STATEMENT:
+        if tokens[-2].exact_type in {tokenize.LPAR, tokenize.LSQB, tokenize.LBRACE}:
+            return last_indent + 4
+        return last_indent
+
+    if tokens[-1].exact_type == tokenize.COLON:
+        # Line ends with colon - indent
+        return last_indent + 4
+
+    if last_indent:
+        # Examine the last line for dedent cues - statements like return or
+        # raise which normally end a block of code.
+        last_line_starts = 0
+        for i, tok in enumerate(tokens):
+            if tok.type == tokenize.NEWLINE:
+                last_line_starts = i + 1
+
+        last_line_tokens = tokens[last_line_starts:]
+        names = [t.string for t in last_line_tokens if t.type == tokenize.NAME]
+        if names and names[0] in {'raise', 'return', 'pass', 'break', 'continue'}:
+            # Find the most recent indentation less than the current level
+            for indent in reversed(prev_indents):
+                if indent < last_indent:
+                    return indent
+
+    return last_indent
+
+
 def last_blank(src):
     """Determine if the input source ends in a blank.
 
     A blank is either a newline or a line consisting of whitespace.
 
     Parameters
     ----------
     src : string
       A single or multiline string.
     """
     if not src: return False
     ll  = src.splitlines()[-1]
     return (ll == '') or ll.isspace()
 
 
 last_two_blanks_re = re.compile(r'\n\s*\n\s*$', re.MULTILINE)
 last_two_blanks_re2 = re.compile(r'.+\n\s*\n\s+$', re.MULTILINE)
 
 def last_two_blanks(src):
     """Determine if the input source ends in two blanks.
 
     A blank is either a newline or a line consisting of whitespace.
 
     Parameters
     ----------
     src : string
       A single or multiline string.
     """
     if not src: return False
     # The logic here is tricky: I couldn't get a regexp to work and pass all
     # the tests, so I took a different approach: split the source by lines,
     # grab the last two and prepend '###\n' as a stand-in for whatever was in
     # the body before the last two lines.  Then, with that structure, it's
     # possible to analyze with two regexps.  Not the most elegant solution, but
     # it works.  If anyone tries to change this logic, make sure to validate
     # the whole test suite first!
     new_src = '\n'.join(['###\n'] + src.splitlines()[-2:])
     return (bool(last_two_blanks_re.match(new_src)) or
             bool(last_two_blanks_re2.match(new_src)) )
 
 
 def remove_comments(src):
     """Remove all comments from input source.
 
     Note: comments are NOT recognized inside of strings!
 
     Parameters
     ----------
     src : string
       A single or multiline input string.
 
     Returns
     -------
     String with all Python comments removed.
     """
 
     return re.sub('#.*', '', src)
 
 
 def get_input_encoding():
     """Return the default standard input encoding.
 
     If sys.stdin has no encoding, 'ascii' is returned."""
     # There are strange environments for which sys.stdin.encoding is None. We
     # ensure that a valid encoding is returned.
     encoding = getattr(sys.stdin, 'encoding', None)
     if encoding is None:
         encoding = 'ascii'
     return encoding
 
 #-----------------------------------------------------------------------------
 # Classes and functions for normal Python syntax handling
 #-----------------------------------------------------------------------------
 
 class InputSplitter(object):
     r"""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
 
     # 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
     # Boolean indicating whether the current block has an unrecoverable syntax error
     _is_invalid = False
 
     def __init__(self):
         """Create a new InputSplitter instance.
         """
         self._buffer = []
         self._compile = codeop.CommandCompiler()
         self.encoding = get_input_encoding()
 
     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._is_invalid = 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 check_complete(self, source):
         """Return whether a block of code is ready to execute, or should be continued
         
         This is a non-stateful API, and will reset the state of this InputSplitter.
         
         Parameters
         ----------
         source : string
           Python input code, which can be multiline.
         
         Returns
         -------
         status : str
           One of 'complete', 'incomplete', or 'invalid' if source is not a
           prefix of valid code.
         indent_spaces : int or None
           The number of spaces by which to indent the next line of code. If
           status is not 'incomplete', this is None.
         """
         self.reset()
         try:
             self.push(source)
         except SyntaxError:
             # Transformers in IPythonInputSplitter can raise SyntaxError,
             # which push() will not catch.
             return 'invalid', None
         else:
             if self._is_invalid:
                 return 'invalid', None
             elif self.push_accepts_more():
                 return 'incomplete', self.indent_spaces
             else:
                 return 'complete', None
         finally:
             self.reset()
 
     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.
         """
         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
         self._is_invalid = False
 
         # Honor termination lines properly
         if source.endswith('\\\n'):
             return False
 
-        self._update_indent(lines)
+        self._update_indent()
         try:
             with warnings.catch_warnings():
                 warnings.simplefilter('error', SyntaxWarning)
                 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, SyntaxWarning):
             self._is_complete = True
             self._is_invalid = 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 when either:
         
         * A SyntaxError is raised
 
         * The code is complete and consists of a single line or a single
           non-compound statement
 
         * The code is complete and has a blank line at the end
 
         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
         # A syntax error also sets _is_complete to True - see push()
         if not self._is_complete:
             #print("Not complete")  # debug
             return True
         
         # The user can make any (complete) input execute by leaving a blank line
         last_line = self.source.splitlines()[-1]
         if (not last_line) or last_line.isspace():
             #print("Blank line")  # debug
             return False
         
         # If there's just a single line or AST node, and we're flush left, as is
         # the case after a simple statement such as 'a=1', we want to execute it
         # straight away.
         if self.indent_spaces==0:
             if len(self.source.splitlines()) <= 1:
                 return False
             
             try:
                 code_ast = ast.parse(u''.join(self._buffer))
             except Exception:
                 #print("Can't parse AST")  # debug
                 return False
             else:
                 if len(code_ast.body) == 1 and \
                                     not hasattr(code_ast.body[0], 'body'):
                     #print("Simple statement")  # debug
                     return False
 
         # General fallback - accept more code
         return True
 
     #------------------------------------------------------------------------
     # 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 _update_indent(self):
+        # self.source always has a trailing newline
+        self.indent_spaces = find_next_indent(self.source[:-1])
+        self._full_dedent = (self.indent_spaces == 0)
 
     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)
 
 
 class IPythonInputSplitter(InputSplitter):
     """An input splitter that recognizes all of IPython's special syntax."""
 
     # String with raw, untransformed input.
     source_raw = ''
     
     # Flag to track when a transformer has stored input that it hasn't given
     # back yet.
     transformer_accumulating = False
     
     # Flag to track when assemble_python_lines has stored input that it hasn't
     # given back yet.
     within_python_line = False
 
     # Private attributes
 
     # List with lines of raw input accumulated so far.
     _buffer_raw = None
 
     def __init__(self, line_input_checker=True, physical_line_transforms=None,
                     logical_line_transforms=None, python_line_transforms=None):
         super(IPythonInputSplitter, self).__init__()
         self._buffer_raw = []
         self._validate = True
         
         if physical_line_transforms is not None:
             self.physical_line_transforms = physical_line_transforms
         else:
             self.physical_line_transforms = [
                                              leading_indent(),
                                              classic_prompt(),
                                              ipy_prompt(),
                                              cellmagic(end_on_blank_line=line_input_checker),
                                             ]
         
         self.assemble_logical_lines = assemble_logical_lines()
         if logical_line_transforms is not None:
             self.logical_line_transforms = logical_line_transforms
         else:
             self.logical_line_transforms = [
                                             help_end(),
                                             escaped_commands(),
                                             assign_from_magic(),
                                             assign_from_system(),
                                            ]
         
         self.assemble_python_lines = assemble_python_lines()
         if python_line_transforms is not None:
             self.python_line_transforms = python_line_transforms
         else:
             # We don't use any of these at present
             self.python_line_transforms = []
     
     @property
     def transforms(self):
         "Quick access to all transformers."
         return self.physical_line_transforms + \
             [self.assemble_logical_lines] + self.logical_line_transforms + \
             [self.assemble_python_lines]  + self.python_line_transforms
     
     @property
     def transforms_in_use(self):
         """Transformers, excluding logical line transformers if we're in a
         Python line."""
         t = self.physical_line_transforms[:]
         if not self.within_python_line:
             t += [self.assemble_logical_lines] + self.logical_line_transforms
         return t + [self.assemble_python_lines] + self.python_line_transforms
 
     def reset(self):
         """Reset the input buffer and associated state."""
         super(IPythonInputSplitter, self).reset()
         self._buffer_raw[:] = []
         self.source_raw = ''
         self.transformer_accumulating = False
         self.within_python_line = False
 
         for t in self.transforms:
             try:
                 t.reset()
             except SyntaxError:
                 # Nothing that calls reset() expects to handle transformer
                 # errors
                 pass
     
     def flush_transformers(self):
         def _flush(transform, outs):
             """yield transformed lines
             
             always strings, never None
             
             transform: the current transform
             outs: an iterable of previously transformed inputs.
                  Each may be multiline, which will be passed
                  one line at a time to transform.
             """
             for out in outs:
                 for line in out.splitlines():
                     # push one line at a time
                     tmp = transform.push(line)
                     if tmp is not None:
                         yield tmp
             
             # reset the transform
             tmp = transform.reset()
             if tmp is not None:
                 yield tmp
         
         out = []
         for t in self.transforms_in_use:
             out = _flush(t, out)
         
         out = list(out)
         if out:
             self._store('\n'.join(out))
 
     def raw_reset(self):
         """Return raw input only and perform a full reset.
         """
         out = self.source_raw
         self.reset()
         return out
     
     def source_reset(self):
         try:
             self.flush_transformers()
             return self.source
         finally:
             self.reset()
 
     def push_accepts_more(self):
         if self.transformer_accumulating:
             return True
         else:
             return super(IPythonInputSplitter, self).push_accepts_more()
 
     def transform_cell(self, cell):
         """Process and translate a cell of input.
         """
         self.reset()
         try:
             self.push(cell)
             self.flush_transformers()
             return self.source
         finally:
             self.reset()
 
     def push(self, lines):
         """Push one or more lines of IPython input.
 
         This stores the given lines and returns a status code indicating
         whether the code forms a complete Python block or not, after processing
         all input lines for special IPython syntax.
 
         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.
         """
 
         # We must ensure all input is pure unicode
         lines = cast_unicode(lines, self.encoding)
         # ''.splitlines() --> [], but we need to push the empty line to transformers
         lines_list = lines.splitlines()
         if not lines_list:
             lines_list = ['']
 
         # 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')
 
         for line in lines_list:
             out = self.push_line(line)
 
         return out
     
     def push_line(self, line):
         buf = self._buffer
         
         def _accumulating(dbg):
             #print(dbg)
             self.transformer_accumulating = True
             return False
         
         for transformer in self.physical_line_transforms:
             line = transformer.push(line)
             if line is None:
                 return _accumulating(transformer)
         
         if not self.within_python_line:
             line = self.assemble_logical_lines.push(line)
             if line is None:
                 return _accumulating('acc logical line')        
         
             for transformer in self.logical_line_transforms:
                 line = transformer.push(line)
                 if line is None:
                     return _accumulating(transformer)
         
         line = self.assemble_python_lines.push(line)
         if line is None:
             self.within_python_line = True
             return _accumulating('acc python line')
         else:
             self.within_python_line = False
         
         for transformer in self.python_line_transforms:
             line = transformer.push(line)
             if line is None:
                 return _accumulating(transformer)
 
         #print("transformers clear") #debug
         self.transformer_accumulating = False
         return super(IPythonInputSplitter, self).push(line)

IPython/core/tests/test_inputsplitter.py

@@ -1,614 +1,638 b''
 # -*- coding: utf-8 -*-
 """Tests for the inputsplitter module."""
 
 
 # Copyright (c) IPython Development Team.
 # Distributed under the terms of the Modified BSD License.
 
 import unittest
 import sys
 
 import nose.tools as nt
 
 from IPython.core import inputsplitter as isp
 from IPython.core.inputtransformer import InputTransformer
 from IPython.core.tests.test_inputtransformer import syntax, syntax_ml
 from IPython.testing import tools as tt
 from IPython.utils import py3compat
 from IPython.utils.py3compat  import input
 
 #-----------------------------------------------------------------------------
 # 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_get_input_encoding():
     encoding = isp.get_input_encoding()
     nt.assert_true(isinstance(encoding, str))
     # 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.assertEqual(len(self.isp._buffer)>0, True)
         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):
         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):
         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):
         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_break(self):
         isp = self.isp # shorthand
         # should NOT cause dedent
         isp.push('while 1:\n    breaks = 5')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('while 1:\n     break')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('while 1:\n     break   ')
         self.assertEqual(isp.indent_spaces, 0)
 
     def test_dedent_continue(self):
         isp = self.isp # shorthand
         # should NOT cause dedent
         isp.push('while 1:\n    continues = 5')
         self.assertEqual(isp.indent_spaces, 4)
         isp.push('while 1:\n     continue')
         self.assertEqual(isp.indent_spaces, 0)
         isp.push('while 1:\n     continue   ')
         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.assertEqual(isp.push('x=1'), True)
 
     def test_push2(self):
         isp = self.isp
         self.assertEqual(isp.push('if 1:'), False)
         for line in ['  x=1', '# a comment', '  y=2']:
             print(line)
             self.assertEqual(isp.push(line), True)
 
     def test_push3(self):
         isp = self.isp
         isp.push('if True:')
         isp.push('  a = 1')
         self.assertEqual(isp.push('b = [1,'), False)
 
     def test_push_accepts_more(self):
         isp = self.isp
         isp.push('x=1')
         self.assertEqual(isp.push_accepts_more(), False)
 
     def test_push_accepts_more2(self):
         isp = self.isp
         isp.push('if 1:')
         self.assertEqual(isp.push_accepts_more(), True)
         isp.push('  x=1')
         self.assertEqual(isp.push_accepts_more(), True)
         isp.push('')
         self.assertEqual(isp.push_accepts_more(), False)
 
     def test_push_accepts_more3(self):
         isp = self.isp
         isp.push("x = (2+\n3)")
         self.assertEqual(isp.push_accepts_more(), False)
 
     def test_push_accepts_more4(self):
         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.assertEqual(isp.push_accepts_more(), True)
         isp.push("    y = 3")
         self.assertEqual(isp.push_accepts_more(), True)
         isp.push('')
         self.assertEqual(isp.push_accepts_more(), False)
 
     def test_push_accepts_more5(self):
         isp = self.isp
         isp.push('try:')
         isp.push('    a = 5')
         isp.push('except:')
         isp.push('    raise')
         # We want to be able to add an else: block at this point, so it should
         # wait for a blank line.
         self.assertEqual(isp.push_accepts_more(), True)
 
     def test_continuation(self):
         isp = self.isp
         isp.push("import os, \\")
         self.assertEqual(isp.push_accepts_more(), True)
         isp.push("sys")
         self.assertEqual(isp.push_accepts_more(), False)
 
     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.assertEqual(isp.push_accepts_more(), False)
 
     def test_unicode(self):
         self.isp.push(u"Pérez")
         self.isp.push(u'\xc3\xa9')
         self.isp.push(u"u'\xc3\xa9'")
 
     def test_line_continuation(self):
         """ Test issue #2108."""
         isp = self.isp
         # A blank line after a line continuation should not accept more
         isp.push("1 \\\n\n")
         self.assertEqual(isp.push_accepts_more(), False)
         # Whitespace after a \ is a SyntaxError.  The only way to test that
         # here is to test that push doesn't accept more (as with
         # test_syntax_error() above).
         isp.push(r"1 \ ")
         self.assertEqual(isp.push_accepts_more(), False)
         # Even if the line is continuable (c.f. the regular Python
         # interpreter)
         isp.push(r"(1 \ ")
         self.assertEqual(isp.push_accepts_more(), False)
 
     def test_check_complete(self):
         isp = self.isp
         self.assertEqual(isp.check_complete("a = 1"), ('complete', None))
         self.assertEqual(isp.check_complete("for a in range(5):"), ('incomplete', 4))
         self.assertEqual(isp.check_complete("raise = 2"), ('invalid', None))
         self.assertEqual(isp.check_complete("a = [1,\n2,"), ('incomplete', 0))
         self.assertEqual(isp.check_complete("def a():\n x=1\n global x"), ('invalid', None))
 
 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, 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.items():
             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))
 
 
 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()
 
     def test_syntax(self):
         """Call all single-line syntax tests from the main object"""
         isp = self.isp
         for example in syntax.values():
             for raw, out_t in example:
                 if raw.startswith(' '):
                     continue
 
                 isp.push(raw+'\n')
                 out_raw = isp.source_raw
                 out = isp.source_reset()
                 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.values():
             for line_pairs in example:
                 out_t_parts = []
                 raw_parts = []
                 for lraw, out_t_part in line_pairs:
                     if out_t_part is not None:
                         out_t_parts.append(out_t_part)
                     
                     if lraw is not None:
                         isp.push(lraw)
                         raw_parts.append(lraw)
 
                 out_raw = isp.source_raw
                 out = isp.source_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)
 
     def test_syntax_multiline_cell(self):
         isp = self.isp
         for example in syntax_ml.values():
 
             out_t_parts = []
             for line_pairs in example:
                 raw = '\n'.join(r for r, _ in line_pairs if r is not None)
                 out_t = '\n'.join(t for _,t in line_pairs if t is not None)
                 out = isp.transform_cell(raw)
                 # Match ignoring trailing whitespace
                 self.assertEqual(out.rstrip(), out_t.rstrip())
     
     def test_cellmagic_preempt(self):
         isp = self.isp
         for raw, name, line, cell in [
             ("%%cellm a\nIn[1]:", u'cellm', u'a', u'In[1]:'),
             ("%%cellm \nline\n>>> hi", u'cellm', u'', u'line\n>>> hi'),
             (">>> %%cellm \nline\n>>> hi", u'cellm', u'', u'line\nhi'),
             ("%%cellm \n>>> hi", u'cellm', u'', u'>>> hi'),
             ("%%cellm \nline1\nline2", u'cellm', u'', u'line1\nline2'),
             ("%%cellm \nline1\\\\\nline2", u'cellm', u'', u'line1\\\\\nline2'),
         ]:
             expected = "get_ipython().run_cell_magic(%r, %r, %r)" % (
                 name, line, cell
             )
             out = isp.transform_cell(raw)
             self.assertEqual(out.rstrip(), expected.rstrip())
 
     def test_multiline_passthrough(self):
         isp = self.isp
         class CommentTransformer(InputTransformer):
             def __init__(self):
                 self._lines = []
             
             def push(self, line):
                 self._lines.append(line + '#')
             
             def reset(self):
                 text = '\n'.join(self._lines)
                 self._lines = []
                 return text
         
         isp.physical_line_transforms.insert(0, CommentTransformer())
         
         for raw, expected in [
             ("a=5", "a=5#"),
             ("%ls foo", "get_ipython().magic(%r)" % u'ls foo#'),
             ("!ls foo\n%ls bar", "get_ipython().system(%r)\nget_ipython().magic(%r)" % (
                 u'ls foo#', u'ls bar#'
             )),
             ("1\n2\n3\n%ls foo\n4\n5", "1#\n2#\n3#\nget_ipython().magic(%r)\n4#\n5#" % u'ls foo#'),
         ]:
             out = isp.transform_cell(raw)
             self.assertEqual(out.rstrip(), expected.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 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 + input(prompt+indent)
                 else:
                     line = 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
             raw = isp.source_raw
             src = isp.source_reset()
             print('Input source was:\n', src)
             print('Raw source was:\n', raw)
     except EOFError:
         print('Bye')
 
 # Tests for cell magics support
 
 def test_last_blank():
     nt.assert_false(isp.last_blank(''))
     nt.assert_false(isp.last_blank('abc'))
     nt.assert_false(isp.last_blank('abc\n'))
     nt.assert_false(isp.last_blank('abc\na'))
 
     nt.assert_true(isp.last_blank('\n'))
     nt.assert_true(isp.last_blank('\n '))
     nt.assert_true(isp.last_blank('abc\n '))
     nt.assert_true(isp.last_blank('abc\n\n'))
     nt.assert_true(isp.last_blank('abc\nd\n\n'))
     nt.assert_true(isp.last_blank('abc\nd\ne\n\n'))
     nt.assert_true(isp.last_blank('abc \n \n \n\n'))
 
 
 def test_last_two_blanks():
     nt.assert_false(isp.last_two_blanks(''))
     nt.assert_false(isp.last_two_blanks('abc'))
     nt.assert_false(isp.last_two_blanks('abc\n'))
     nt.assert_false(isp.last_two_blanks('abc\n\na'))
     nt.assert_false(isp.last_two_blanks('abc\n \n'))
     nt.assert_false(isp.last_two_blanks('abc\n\n'))
 
     nt.assert_true(isp.last_two_blanks('\n\n'))
     nt.assert_true(isp.last_two_blanks('\n\n '))
     nt.assert_true(isp.last_two_blanks('\n \n'))
     nt.assert_true(isp.last_two_blanks('abc\n\n '))
     nt.assert_true(isp.last_two_blanks('abc\n\n\n'))
     nt.assert_true(isp.last_two_blanks('abc\n\n \n'))
     nt.assert_true(isp.last_two_blanks('abc\n\n \n '))
     nt.assert_true(isp.last_two_blanks('abc\n\n \n \n'))
     nt.assert_true(isp.last_two_blanks('abc\nd\n\n\n'))
     nt.assert_true(isp.last_two_blanks('abc\nd\ne\nf\n\n\n'))
 
 
 class CellMagicsCommon(object):
 
     def test_whole_cell(self):
         src = "%%cellm line\nbody\n"
         out = self.sp.transform_cell(src)
         ref = u"get_ipython().run_cell_magic({u}'cellm', {u}'line', {u}'body')\n"
         nt.assert_equal(out, py3compat.u_format(ref))
     
     def test_cellmagic_help(self):
         self.sp.push('%%cellm?')
         nt.assert_false(self.sp.push_accepts_more())
 
     def tearDown(self):
         self.sp.reset()
 
 
 class CellModeCellMagics(CellMagicsCommon, unittest.TestCase):
     sp = isp.IPythonInputSplitter(line_input_checker=False)
 
     def test_incremental(self):
         sp = self.sp
         sp.push('%%cellm firstline\n')
         nt.assert_true(sp.push_accepts_more()) #1
         sp.push('line2\n')
         nt.assert_true(sp.push_accepts_more()) #2
         sp.push('\n')
         # This should accept a blank line and carry on until the cell is reset
         nt.assert_true(sp.push_accepts_more()) #3
     
     def test_no_strip_coding(self):
         src = '\n'.join([
             '%%writefile foo.py',
             '# coding: utf-8',
             'print(u"üñîçø∂é")',
         ])
         out = self.sp.transform_cell(src)
         nt.assert_in('# coding: utf-8', out)
 
 
 class LineModeCellMagics(CellMagicsCommon, unittest.TestCase):
     sp = isp.IPythonInputSplitter(line_input_checker=True)
 
     def test_incremental(self):
         sp = self.sp
         sp.push('%%cellm line2\n')
         nt.assert_true(sp.push_accepts_more()) #1
         sp.push('\n')
         # In this case, a blank line should end the cell magic
         nt.assert_false(sp.push_accepts_more()) #2
+
+indentation_samples = [
+    ('a = 1', 0),
+    ('for a in b:', 4),
+    ('def f():', 4),
+    ('def f(): #comment', 4),
+    ('a = ":#not a comment"', 0),
+    ('def f():\n    a = 1', 4),
+    ('def f():\n    return 1', 0),
+    ('for a in b:\n'
+     '   if a < 0:'
+     '       continue', 3),
+    ('a = {', 4),
+    ('a = {\n'
+     '     1,', 5),
+    ('b = """123', 0),
+    ('', 0),
+]
+
+def test_find_next_indent():
+    for code, exp in indentation_samples:
+        res = isp.find_next_indent(code)
+        msg = "{!r} != {!r} (expected)\n Code: {!r}".format(res, exp, code)
+        assert res == exp, msg