Merge pull request #12031 from Carreau/morer-cleanup

remove cast_unicode and add some typings

IPython/core/inputsplitter.py

@@ -1,773 +1,773 b''
 """DEPRECATED: Input handling and transformation machinery.
 
 This module was deprecated in IPython 7.0, in favour of inputtransformer2.
 
 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.
 """
 
 from warnings import warn
 
 warn('IPython.core.inputsplitter is deprecated since IPython 7 in favor of `IPython.core.inputtransformer2`',
      DeprecationWarning)
 
 # 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(r'^\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
     while (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 we've just opened a multiline statement (e.g. 'a = ['), indent more
     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(),
     """
     # A cache for storing the current indentation
     # The first value stores the most recently processed source input
     # The second value is the number of spaces for the current indentation 
     # If self.source matches the first value, the second value is a valid
     # current indentation. Otherwise, the cache is invalid and the indentation
     # must be recalculated.
     _indent_spaces_cache = None, None
     # 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
     # 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._buffer[:] = []
         self.source = ''
         self.code = None
         self._is_complete = False
         self._is_invalid = 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.get_indent_spaces()
             else:
                 return 'complete', None
         finally:
             self.reset()
 
-    def push(self, lines):
+    def push(self, lines:str) -> bool:
         """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.
         """
+        assert isinstance(lines, str)
         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
 
         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.get_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
 
     def get_indent_spaces(self):
         sourcefor, n = self._indent_spaces_cache
         if sourcefor == self.source:
             return n
 
         # self.source always has a trailing newline
         n = find_next_indent(self.source[:-1])
         self._indent_spaces_cache = (self.source, n)
         return n
 
     # Backwards compatibility. I think all code that used .indent_spaces was
     # inside IPython, but we can leave this here until IPython 7 in case any
     # other modules are using it. -TK, November 2017
     indent_spaces = property(get_indent_spaces)
 
     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):
+    def push(self, lines:str) -> bool:
         """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.
         """
-
+        assert isinstance(lines, str)
         # 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')
 
         transformed_lines_list = []
         for line in lines_list:
             transformed = self._transform_line(line)
             if transformed is not None:
                 transformed_lines_list.append(transformed)
 
         if transformed_lines_list:
             transformed_lines = '\n'.join(transformed_lines_list)
             return super(IPythonInputSplitter, self).push(transformed_lines)
         else:
             # Got nothing back from transformers - they must be waiting for
             # more input.
             return False
 
     def _transform_line(self, line):
         """Push a line of input code through the various transformers.
         
         Returns any output from the transformers, or None if a transformer
         is accumulating lines.
         
         Sets self.transformer_accumulating as a side effect.
         """
         def _accumulating(dbg):
             #print(dbg)
             self.transformer_accumulating = True
             return None
 
         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 line
 

IPython/utils/text.py

@@ -1,772 +1,772 b''
 # encoding: utf-8
 """
 Utilities for working with strings and text.
 
 Inheritance diagram:
 
 .. inheritance-diagram:: IPython.utils.text
    :parts: 3
 """
 
 import os
 import re
 import sys
 import textwrap
 from string import Formatter
 from pathlib import Path
 
 from IPython.utils import py3compat
 
 # datetime.strftime date format for ipython
 if sys.platform == 'win32':
     date_format = "%B %d, %Y"
 else:
     date_format = "%B %-d, %Y"
 
 class LSString(str):
     """String derivative with a special access attributes.
 
     These are normal strings, but with the special attributes:
 
         .l (or .list) : value as list (split on newlines).
         .n (or .nlstr): original value (the string itself).
         .s (or .spstr): value as whitespace-separated string.
         .p (or .paths): list of path objects (requires path.py package)
 
     Any values which require transformations are computed only once and
     cached.
 
     Such strings are very useful to efficiently interact with the shell, which
     typically only understands whitespace-separated options for commands."""
 
     def get_list(self):
         try:
             return self.__list
         except AttributeError:
             self.__list = self.split('\n')
             return self.__list
 
     l = list = property(get_list)
 
     def get_spstr(self):
         try:
             return self.__spstr
         except AttributeError:
             self.__spstr = self.replace('\n',' ')
             return self.__spstr
 
     s = spstr = property(get_spstr)
 
     def get_nlstr(self):
         return self
 
     n = nlstr = property(get_nlstr)
 
     def get_paths(self):
         try:
             return self.__paths
         except AttributeError:
             self.__paths = [Path(p) for p in self.split('\n') if os.path.exists(p)]
             return self.__paths
 
     p = paths = property(get_paths)
 
 # FIXME: We need to reimplement type specific displayhook and then add this
 # back as a custom printer. This should also be moved outside utils into the
 # core.
 
 # def print_lsstring(arg):
 #     """ Prettier (non-repr-like) and more informative printer for LSString """
 #     print "LSString (.p, .n, .l, .s available). Value:"
 #     print arg
 #
 #
 # print_lsstring = result_display.register(LSString)(print_lsstring)
 
 
 class SList(list):
     """List derivative with a special access attributes.
 
     These are normal lists, but with the special attributes:
 
     * .l (or .list) : value as list (the list itself).
     * .n (or .nlstr): value as a string, joined on newlines.
     * .s (or .spstr): value as a string, joined on spaces.
     * .p (or .paths): list of path objects (requires path.py package)
 
     Any values which require transformations are computed only once and
     cached."""
 
     def get_list(self):
         return self
 
     l = list = property(get_list)
 
     def get_spstr(self):
         try:
             return self.__spstr
         except AttributeError:
             self.__spstr = ' '.join(self)
             return self.__spstr
 
     s = spstr = property(get_spstr)
 
     def get_nlstr(self):
         try:
             return self.__nlstr
         except AttributeError:
             self.__nlstr = '\n'.join(self)
             return self.__nlstr
 
     n = nlstr = property(get_nlstr)
 
     def get_paths(self):
         try:
             return self.__paths
         except AttributeError:
             self.__paths = [Path(p) for p in self if os.path.exists(p)]
             return self.__paths
 
     p = paths = property(get_paths)
 
     def grep(self, pattern, prune = False, field = None):
         """ Return all strings matching 'pattern' (a regex or callable)
 
         This is case-insensitive. If prune is true, return all items
         NOT matching the pattern.
 
         If field is specified, the match must occur in the specified
         whitespace-separated field.
 
         Examples::
 
             a.grep( lambda x: x.startswith('C') )
             a.grep('Cha.*log', prune=1)
             a.grep('chm', field=-1)
         """
 
         def match_target(s):
             if field is None:
                 return s
             parts = s.split()
             try:
                 tgt = parts[field]
                 return tgt
             except IndexError:
                 return ""
 
         if isinstance(pattern, str):
             pred = lambda x : re.search(pattern, x, re.IGNORECASE)
         else:
             pred = pattern
         if not prune:
             return SList([el for el in self if pred(match_target(el))])
         else:
             return SList([el for el in self if not pred(match_target(el))])
 
     def fields(self, *fields):
         """ Collect whitespace-separated fields from string list
 
         Allows quick awk-like usage of string lists.
 
         Example data (in var a, created by 'a = !ls -l')::
 
             -rwxrwxrwx  1 ville None      18 Dec 14  2006 ChangeLog
             drwxrwxrwx+ 6 ville None       0 Oct 24 18:05 IPython
 
         * ``a.fields(0)`` is ``['-rwxrwxrwx', 'drwxrwxrwx+']``
         * ``a.fields(1,0)`` is ``['1 -rwxrwxrwx', '6 drwxrwxrwx+']``
           (note the joining by space).
         * ``a.fields(-1)`` is ``['ChangeLog', 'IPython']``
 
         IndexErrors are ignored.
 
         Without args, fields() just split()'s the strings.
         """
         if len(fields) == 0:
             return [el.split() for el in self]
 
         res = SList()
         for el in [f.split() for f in self]:
             lineparts = []
 
             for fd in fields:
                 try:
                     lineparts.append(el[fd])
                 except IndexError:
                     pass
             if lineparts:
                 res.append(" ".join(lineparts))
 
         return res
 
     def sort(self,field= None,  nums = False):
         """ sort by specified fields (see fields())
 
         Example::
 
             a.sort(1, nums = True)
 
         Sorts a by second field, in numerical order (so that 21 > 3)
 
         """
 
         #decorate, sort, undecorate
         if field is not None:
             dsu = [[SList([line]).fields(field),  line] for line in self]
         else:
             dsu = [[line,  line] for line in self]
         if nums:
             for i in range(len(dsu)):
                 numstr = "".join([ch for ch in dsu[i][0] if ch.isdigit()])
                 try:
                     n = int(numstr)
                 except ValueError:
                     n = 0
                 dsu[i][0] = n
 
 
         dsu.sort()
         return SList([t[1] for t in dsu])
 
 
 # FIXME: We need to reimplement type specific displayhook and then add this
 # back as a custom printer. This should also be moved outside utils into the
 # core.
 
 # def print_slist(arg):
 #     """ Prettier (non-repr-like) and more informative printer for SList """
 #     print "SList (.p, .n, .l, .s, .grep(), .fields(), sort() available):"
 #     if hasattr(arg,  'hideonce') and arg.hideonce:
 #         arg.hideonce = False
 #         return
 #
 #     nlprint(arg)   # This was a nested list printer, now removed.
 #
 # print_slist = result_display.register(SList)(print_slist)
 
 
 def indent(instr,nspaces=4, ntabs=0, flatten=False):
     """Indent a string a given number of spaces or tabstops.
 
     indent(str,nspaces=4,ntabs=0) -> indent str by ntabs+nspaces.
 
     Parameters
     ----------
 
     instr : basestring
         The string to be indented.
     nspaces : int (default: 4)
         The number of spaces to be indented.
     ntabs : int (default: 0)
         The number of tabs to be indented.
     flatten : bool (default: False)
         Whether to scrub existing indentation.  If True, all lines will be
         aligned to the same indentation.  If False, existing indentation will
         be strictly increased.
 
     Returns
     -------
 
     str|unicode : string indented by ntabs and nspaces.
 
     """
     if instr is None:
         return
     ind = '\t'*ntabs+' '*nspaces
     if flatten:
         pat = re.compile(r'^\s*', re.MULTILINE)
     else:
         pat = re.compile(r'^', re.MULTILINE)
     outstr = re.sub(pat, ind, instr)
     if outstr.endswith(os.linesep+ind):
         return outstr[:-len(ind)]
     else:
         return outstr
 
 
 def list_strings(arg):
     """Always return a list of strings, given a string or list of strings
     as input.
 
     Examples
     --------
     ::
 
         In [7]: list_strings('A single string')
         Out[7]: ['A single string']
 
         In [8]: list_strings(['A single string in a list'])
         Out[8]: ['A single string in a list']
 
         In [9]: list_strings(['A','list','of','strings'])
         Out[9]: ['A', 'list', 'of', 'strings']
     """
 
     if isinstance(arg, str):
         return [arg]
     else:
         return arg
 
 
 def marquee(txt='',width=78,mark='*'):
     """Return the input string centered in a 'marquee'.
 
     Examples
     --------
     ::
 
         In [16]: marquee('A test',40)
         Out[16]: '**************** A test ****************'
 
         In [17]: marquee('A test',40,'-')
         Out[17]: '---------------- A test ----------------'
 
         In [18]: marquee('A test',40,' ')
         Out[18]: '                 A test                 '
 
     """
     if not txt:
         return (mark*width)[:width]
     nmark = (width-len(txt)-2)//len(mark)//2
     if nmark < 0: nmark =0
     marks = mark*nmark
     return '%s %s %s' % (marks,txt,marks)
 
 
 ini_spaces_re = re.compile(r'^(\s+)')
 
 def num_ini_spaces(strng):
     """Return the number of initial spaces in a string"""
 
     ini_spaces = ini_spaces_re.match(strng)
     if ini_spaces:
         return ini_spaces.end()
     else:
         return 0
 
 
 def format_screen(strng):
     """Format a string for screen printing.
 
     This removes some latex-type format codes."""
     # Paragraph continue
     par_re = re.compile(r'\\$',re.MULTILINE)
     strng = par_re.sub('',strng)
     return strng
 
 
 def dedent(text):
     """Equivalent of textwrap.dedent that ignores unindented first line.
 
     This means it will still dedent strings like:
     '''foo
     is a bar
     '''
 
     For use in wrap_paragraphs.
     """
 
     if text.startswith('\n'):
         # text starts with blank line, don't ignore the first line
         return textwrap.dedent(text)
 
     # split first line
     splits = text.split('\n',1)
     if len(splits) == 1:
         # only one line
         return textwrap.dedent(text)
 
     first, rest = splits
     # dedent everything but the first line
     rest = textwrap.dedent(rest)
     return '\n'.join([first, rest])
 
 
 def wrap_paragraphs(text, ncols=80):
     """Wrap multiple paragraphs to fit a specified width.
 
     This is equivalent to textwrap.wrap, but with support for multiple
     paragraphs, as separated by empty lines.
 
     Returns
     -------
 
     list of complete paragraphs, wrapped to fill `ncols` columns.
     """
     paragraph_re = re.compile(r'\n(\s*\n)+', re.MULTILINE)
     text = dedent(text).strip()
     paragraphs = paragraph_re.split(text)[::2] # every other entry is space
     out_ps = []
     indent_re = re.compile(r'\n\s+', re.MULTILINE)
     for p in paragraphs:
         # presume indentation that survives dedent is meaningful formatting,
         # so don't fill unless text is flush.
         if indent_re.search(p) is None:
             # wrap paragraph
             p = textwrap.fill(p, ncols)
         out_ps.append(p)
     return out_ps
 
 
 def long_substr(data):
     """Return the longest common substring in a list of strings.
     
     Credit: http://stackoverflow.com/questions/2892931/longest-common-substring-from-more-than-two-strings-python
     """
     substr = ''
     if len(data) > 1 and len(data[0]) > 0:
         for i in range(len(data[0])):
             for j in range(len(data[0])-i+1):
                 if j > len(substr) and all(data[0][i:i+j] in x for x in data):
                     substr = data[0][i:i+j]
     elif len(data) == 1:
         substr = data[0]
     return substr
 
 
 def strip_email_quotes(text):
     """Strip leading email quotation characters ('>').
 
     Removes any combination of leading '>' interspersed with whitespace that
     appears *identically* in all lines of the input text.
 
     Parameters
     ----------
     text : str
 
     Examples
     --------
 
     Simple uses::
 
         In [2]: strip_email_quotes('> > text')
         Out[2]: 'text'
 
         In [3]: strip_email_quotes('> > text\\n> > more')
         Out[3]: 'text\\nmore'
 
     Note how only the common prefix that appears in all lines is stripped::
 
         In [4]: strip_email_quotes('> > text\\n> > more\\n> more...')
         Out[4]: '> text\\n> more\\nmore...'
 
     So if any line has no quote marks ('>') , then none are stripped from any
     of them ::
     
         In [5]: strip_email_quotes('> > text\\n> > more\\nlast different')
         Out[5]: '> > text\\n> > more\\nlast different'
     """
     lines = text.splitlines()
     matches = set()
     for line in lines:
         prefix = re.match(r'^(\s*>[ >]*)', line)
         if prefix:
             matches.add(prefix.group(1))
         else:
             break
     else:
         prefix = long_substr(list(matches))
         if prefix:
             strip = len(prefix)
             text = '\n'.join([ ln[strip:] for ln in lines])
     return text
 
 def strip_ansi(source):
     """
     Remove ansi escape codes from text.
     
     Parameters
     ----------
     source : str
         Source to remove the ansi from
     """
     return re.sub(r'\033\[(\d|;)+?m', '', source)
 
 
 class EvalFormatter(Formatter):
     """A String Formatter that allows evaluation of simple expressions.
     
     Note that this version interprets a : as specifying a format string (as per
     standard string formatting), so if slicing is required, you must explicitly
     create a slice.
     
     This is to be used in templating cases, such as the parallel batch
     script templates, where simple arithmetic on arguments is useful.
 
     Examples
     --------
     ::
 
         In [1]: f = EvalFormatter()
         In [2]: f.format('{n//4}', n=8)
         Out[2]: '2'
 
         In [3]: f.format("{greeting[slice(2,4)]}", greeting="Hello")
         Out[3]: 'll'
     """
     def get_field(self, name, args, kwargs):
         v = eval(name, kwargs)
         return v, name
 
 #XXX: As of Python 3.4, the format string parsing no longer splits on a colon
 # inside [], so EvalFormatter can handle slicing. Once we only support 3.4 and
 # above, it should be possible to remove FullEvalFormatter.
 
 class FullEvalFormatter(Formatter):
     """A String Formatter that allows evaluation of simple expressions.
     
     Any time a format key is not found in the kwargs,
     it will be tried as an expression in the kwargs namespace.
     
     Note that this version allows slicing using [1:2], so you cannot specify
     a format string. Use :class:`EvalFormatter` to permit format strings.
     
     Examples
     --------
     ::
 
         In [1]: f = FullEvalFormatter()
         In [2]: f.format('{n//4}', n=8)
         Out[2]: '2'
 
         In [3]: f.format('{list(range(5))[2:4]}')
         Out[3]: '[2, 3]'
 
         In [4]: f.format('{3*2}')
         Out[4]: '6'
     """
     # copied from Formatter._vformat with minor changes to allow eval
     # and replace the format_spec code with slicing
-    def vformat(self, format_string, args, kwargs):
+    def vformat(self, format_string:str, args, kwargs)->str:
         result = []
         for literal_text, field_name, format_spec, conversion in \
                 self.parse(format_string):
 
             # output the literal text
             if literal_text:
                 result.append(literal_text)
 
             # if there's a field, output it
             if field_name is not None:
                 # this is some markup, find the object and do
                 # the formatting
 
                 if format_spec:
                     # override format spec, to allow slicing:
                     field_name = ':'.join([field_name, format_spec])
 
                 # eval the contents of the field for the object
                 # to be formatted
                 obj = eval(field_name, kwargs)
 
                 # do any conversion on the resulting object
                 obj = self.convert_field(obj, conversion)
 
                 # format the object and append to the result
                 result.append(self.format_field(obj, ''))
 
-        return ''.join(py3compat.cast_unicode(s) for s in result)
+        return ''.join(result)
 
 
 class DollarFormatter(FullEvalFormatter):
     """Formatter allowing Itpl style $foo replacement, for names and attribute
     access only. Standard {foo} replacement also works, and allows full
     evaluation of its arguments.
 
     Examples
     --------
     ::
 
         In [1]: f = DollarFormatter()
         In [2]: f.format('{n//4}', n=8)
         Out[2]: '2'
 
         In [3]: f.format('23 * 76 is $result', result=23*76)
         Out[3]: '23 * 76 is 1748'
 
         In [4]: f.format('$a or {b}', a=1, b=2)
         Out[4]: '1 or 2'
     """
     _dollar_pattern_ignore_single_quote = re.compile(r"(.*?)\$(\$?[\w\.]+)(?=([^']*'[^']*')*[^']*$)")
     def parse(self, fmt_string):
         for literal_txt, field_name, format_spec, conversion \
                     in Formatter.parse(self, fmt_string):
             
             # Find $foo patterns in the literal text.
             continue_from = 0
             txt = ""
             for m in self._dollar_pattern_ignore_single_quote.finditer(literal_txt):
                 new_txt, new_field = m.group(1,2)
                 # $$foo --> $foo
                 if new_field.startswith("$"):
                     txt += new_txt + new_field
                 else:
                     yield (txt + new_txt, new_field, "", None)
                     txt = ""
                 continue_from = m.end()
             
             # Re-yield the {foo} style pattern
             yield (txt + literal_txt[continue_from:], field_name, format_spec, conversion)
 
 #-----------------------------------------------------------------------------
 # Utils to columnize a list of string
 #-----------------------------------------------------------------------------
 
 def _col_chunks(l, max_rows, row_first=False):
     """Yield successive max_rows-sized column chunks from l."""
     if row_first:
         ncols = (len(l) // max_rows) + (len(l) % max_rows > 0)
         for i in range(ncols):
             yield [l[j] for j in range(i, len(l), ncols)]
     else:
         for i in range(0, len(l), max_rows):
             yield l[i:(i + max_rows)]
 
 
 def _find_optimal(rlist, row_first=False, separator_size=2, displaywidth=80):
     """Calculate optimal info to columnize a list of string"""
     for max_rows in range(1, len(rlist) + 1):
         col_widths = list(map(max, _col_chunks(rlist, max_rows, row_first)))
         sumlength = sum(col_widths)
         ncols = len(col_widths)
         if sumlength + separator_size * (ncols - 1) <= displaywidth:
             break
     return {'num_columns': ncols,
             'optimal_separator_width': (displaywidth - sumlength) // (ncols - 1) if (ncols - 1) else 0,
             'max_rows': max_rows,
             'column_widths': col_widths
             }
 
 
 def _get_or_default(mylist, i, default=None):
     """return list item number, or default if don't exist"""
     if i >= len(mylist):
         return default
     else :
         return mylist[i]
 
 
 def compute_item_matrix(items, row_first=False, empty=None, *args, **kwargs) :
     """Returns a nested list, and info to columnize items
 
     Parameters
     ----------
 
     items
         list of strings to columize
     row_first : (default False)
         Whether to compute columns for a row-first matrix instead of
         column-first (default).
     empty : (default None)
         default value to fill list if needed
     separator_size : int (default=2)
         How much characters will be used as a separation between each columns.
     displaywidth : int (default=80)
         The width of the area onto which the columns should enter
 
     Returns
     -------
 
     strings_matrix
 
         nested list of string, the outer most list contains as many list as
         rows, the innermost lists have each as many element as columns. If the
         total number of elements in `items` does not equal the product of
         rows*columns, the last element of some lists are filled with `None`.
 
     dict_info
         some info to make columnize easier:
 
         num_columns
           number of columns
         max_rows
           maximum number of rows (final number may be less)
         column_widths
           list of with of each columns
         optimal_separator_width
           best separator width between columns
 
     Examples
     --------
     ::
 
         In [1]: l = ['aaa','b','cc','d','eeeee','f','g','h','i','j','k','l']
         In [2]: list, info = compute_item_matrix(l, displaywidth=12)
         In [3]: list
         Out[3]: [['aaa', 'f', 'k'], ['b', 'g', 'l'], ['cc', 'h', None], ['d', 'i', None], ['eeeee', 'j', None]]
         In [4]: ideal = {'num_columns': 3, 'column_widths': [5, 1, 1], 'optimal_separator_width': 2, 'max_rows': 5}
         In [5]: all((info[k] == ideal[k] for k in ideal.keys()))
         Out[5]: True
     """
     info = _find_optimal(list(map(len, items)), row_first, *args, **kwargs)
     nrow, ncol = info['max_rows'], info['num_columns']
     if row_first:
         return ([[_get_or_default(items, r * ncol + c, default=empty) for c in range(ncol)] for r in range(nrow)], info)
     else:
         return ([[_get_or_default(items, c * nrow + r, default=empty) for c in range(ncol)] for r in range(nrow)], info)
 
 
 def columnize(items, row_first=False, separator='  ', displaywidth=80, spread=False):
     """ Transform a list of strings into a single string with columns.
 
     Parameters
     ----------
     items : sequence of strings
         The strings to process.
 
     row_first : (default False)
         Whether to compute columns for a row-first matrix instead of
         column-first (default).
 
     separator : str, optional [default is two spaces]
         The string that separates columns.
 
     displaywidth : int, optional [default is 80]
         Width of the display in number of characters.
 
     Returns
     -------
     The formatted string.
     """
     if not items:
         return '\n'
     matrix, info = compute_item_matrix(items, row_first=row_first, separator_size=len(separator), displaywidth=displaywidth)
     if spread:
         separator = separator.ljust(int(info['optimal_separator_width']))
     fmatrix = [filter(None, x) for x in matrix]
     sjoin = lambda x : separator.join([ y.ljust(w, ' ') for y, w in zip(x, info['column_widths'])])
     return '\n'.join(map(sjoin, fmatrix))+'\n'
 
 
 def get_text_list(list_, last_sep=' and ', sep=", ", wrap_item_with=""):
     """
     Return a string with a natural enumeration of items
 
     >>> get_text_list(['a', 'b', 'c', 'd'])
     'a, b, c and d'
     >>> get_text_list(['a', 'b', 'c'], ' or ')
     'a, b or c'
     >>> get_text_list(['a', 'b', 'c'], ', ')
     'a, b, c'
     >>> get_text_list(['a', 'b'], ' or ')
     'a or b'
     >>> get_text_list(['a'])
     'a'
     >>> get_text_list([])
     ''
     >>> get_text_list(['a', 'b'], wrap_item_with="`")
     '`a` and `b`'
     >>> get_text_list(['a', 'b', 'c', 'd'], " = ", sep=" + ")
     'a + b + c = d'
     """
     if len(list_) == 0:
         return ''
     if wrap_item_with:
         list_ = ['%s%s%s' % (wrap_item_with, item, wrap_item_with) for
                  item in list_]
     if len(list_) == 1:
         return list_[0]
     return '%s%s%s' % (
         sep.join(i for i in list_[:-1]),
         last_sep, list_[-1])