eric: Plugins/CheckerPlugins/Pep8/pep8.py@1843ef6e2656 (annotated)

 # -*- coding: utf-8 -*-
 #
 # pep8.py - Check Python source code formatting, according to PEP 8
 # Copyright (C) 2006 Johann C. Rocholl <johann@rocholl.net>
 #
 # Permission is hereby granted, free of charge, to any person
 # obtaining a copy of this software and associated documentation files
 # (the "Software"), to deal in the Software without restriction,
 # including without limitation the rights to use, copy, modify, merge,
 # publish, distribute, sublicense, and/or sell copies of the Software,
 # and to permit persons to whom the Software is furnished to do so,
 # subject to the following conditions:
 #
 # The above copyright notice and this permission notice shall be
 # included in all copies or substantial portions of the Software.
 #
 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 # EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 # NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 # BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 # ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 # CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 """
 Check Python source code formatting, according to PEP 8:
 http://www.python.org/dev/peps/pep-0008/
 For usage and a list of options, try this:
 $ python pep8.py -h
 This program and its regression test suite live here:
 http://github.com/jcrocholl/pep8
 Groups of errors and warnings:
 E errors
 W warnings
 indentation
 whitespace
 blank lines
 imports
 line length
 deprecation
 statements
 processing errors
 You can add checks to this program by writing plugins. Each plugin is
 a simple function that is called for each line of source code, either
 physical or logical.
 Physical line:
 - Raw line of text from the input file.
 Logical line:
 - Multi-line statements converted to a single line.
 - Stripped left and right.
 - Contents of strings replaced with 'xxx' of same length.
 - Comments removed.
 The check function requests physical or logical lines by the name of
 the first argument:
 def maximum_line_length(physical_line)
 def extraneous_whitespace(logical_line)
 def blank_lines(logical_line, blank_lines, indent_level, line_number)
 The last example above demonstrates how check plugins can request
 additional information with extra arguments. All attributes of the
 Checker object are available. Some examples:
 lines: a list of the raw lines from the input file
 tokens: the tokens that contribute to this logical line
 line_number: line number in the input file
 blank_lines: blank lines before this one
 indent_char: first indentation character in this file (' ' or '\t')
 indent_level: indentation (with tabs expanded to multiples of 8)
 previous_indent_level: indentation on previous line
 previous_logical: previous logical line
 The docstring of each check function shall be the relevant part of
 text from PEP 8. It is printed if the user enables --show-pep8.
 Several docstrings contain examples directly from the PEP 8 document.
 Okay: spam(ham[1], {eggs: 2})
 E201: spam( ham[1], {eggs: 2})
 These examples are verified automatically when pep8.py is run with the
 --doctest option. You can add examples for your own check functions.
 The format is simple: "Okay" or error/warning code followed by colon
 and space, the rest of the line is example source code. If you put 'r'
 before the docstring, you can use \n for newline, \t for tab and \s
 for space.
 """
 #
 # This is a modified version to make the original tabnanny better suitable
 # for being called from within the eric5 IDE. The modifications are as
 # follows:
 #
 # - made messages translatable via Qt
 #
 # Copyright (c) 2011 - 2013 Detlev Offenbach <detlev@die-offenbachs.de>
 #
 __version__ = '0.6.1'
 import os
 import sys
 import re
 import time
 import inspect
 import keyword
 import tokenize
 from optparse import OptionParser
 from fnmatch import fnmatch
 try:
     frozenset
 except NameError:
     from sets import ImmutableSet as frozenset
 from PyQt4.QtCore import QCoreApplication, QT_TRANSLATE_NOOP
 DEFAULT_EXCLUDE = '.svn,CVS,.bzr,.hg,.git'
 DEFAULT_IGNORE = 'E24'
 MAX_LINE_LENGTH = 79
 INDENT_REGEX = re.compile(r'([ \t]*)')
 RAISE_COMMA_REGEX = re.compile(r'raise\s+\w+\s*(,)')
 SELFTEST_REGEX = re.compile(r'(Okay|[EW]\d{3}):\s(.*)')
 ERRORCODE_REGEX = re.compile(r'[EW]\d{3}')
 DOCSTRING_REGEX = re.compile(r'u?r?["\']')
 WHITESPACE_AROUND_OPERATOR_REGEX = \
     re.compile('([^\w\s]*)\s*(\t|  )\s*([^\w\s]*)')
 EXTRANEOUS_WHITESPACE_REGEX = re.compile(r'[[({] | []}),;:]')
 WHITESPACE_AROUND_NAMED_PARAMETER_REGEX = \
     re.compile(r'[()]|\s=[^=]|[^=!<>]=\s')
 WHITESPACE = ' \t'
 BINARY_OPERATORS = frozenset(['**=', '*=', '+=', '-=', '!=', '<>',
     '%=', '^=', '&=', '|=', '==', '/=', '//=', '<=', '>=', '<<=', '>>=',
     '%',  '^',  '&',  '|',  '=',  '/',  '//',  '<',  '>',  '<<'])
 UNARY_OPERATORS = frozenset(['>>', '**', '*', '+', '-'])
 OPERATORS = BINARY_OPERATORS | UNARY_OPERATORS
 SKIP_TOKENS = frozenset([tokenize.COMMENT, tokenize.NL, tokenize.INDENT,
                          tokenize.DEDENT, tokenize.NEWLINE])
 E225NOT_KEYWORDS = (frozenset(keyword.kwlist + ['print']) -
                     frozenset(['False', 'None', 'True']))
 BENCHMARK_KEYS = ('directories', 'files', 'logical lines', 'physical lines')
 options = None
 args = None
 ##############################################################################
 # Helper functions for translated and formatted messages
 ##############################################################################
 pep8_messages = {
     "E101": QT_TRANSLATE_NOOP("pep8",
         "indentation contains mixed spaces and tabs"),
     "E111": QT_TRANSLATE_NOOP("pep8",
         "indentation is not a multiple of four"),
     "E112": QT_TRANSLATE_NOOP("pep8",
         "expected an indented block"),
     "E113": QT_TRANSLATE_NOOP("pep8",
         "unexpected indentation"),
     "W191": QT_TRANSLATE_NOOP("pep8",
         "indentation contains tabs"),
     "E201": QT_TRANSLATE_NOOP("pep8",
         "whitespace after '{0}'"),
     "E202": QT_TRANSLATE_NOOP("pep8",
         "whitespace before '{0}'"),
     "E203": QT_TRANSLATE_NOOP("pep8",
         "whitespace before '{0}'"),
     "E211": QT_TRANSLATE_NOOP("pep8",
         "whitespace before '{0}'"),
     "E221": QT_TRANSLATE_NOOP("pep8",
         "multiple spaces before operator"),
     "E222": QT_TRANSLATE_NOOP("pep8",
         "multiple spaces after operator"),
     "E223": QT_TRANSLATE_NOOP("pep8",
         "tab before operator"),
     "E224": QT_TRANSLATE_NOOP("pep8",
         "tab after operator"),
     "E225": QT_TRANSLATE_NOOP("pep8",
         "missing whitespace around operator"),
     "E231": QT_TRANSLATE_NOOP("pep8",
         "missing whitespace after '{0}'"),
     "E241": QT_TRANSLATE_NOOP("pep8",
         "multiple spaces after '{0}'"),
     "E242": QT_TRANSLATE_NOOP("pep8",
         "tab after '{0}'"),
     "E251": QT_TRANSLATE_NOOP("pep8",
         "no spaces around keyword / parameter equals"),
     "E261": QT_TRANSLATE_NOOP("pep8",
         "at least two spaces before inline comment"),
     "E262": QT_TRANSLATE_NOOP("pep8",
         "inline comment should start with '# '"),
     "W291": QT_TRANSLATE_NOOP("pep8",
         "trailing whitespace"),
     "W292": QT_TRANSLATE_NOOP("pep8",
         "no newline at end of file"),
     "W293": QT_TRANSLATE_NOOP("pep8",
         "blank line contains whitespace"),
     "E301": QT_TRANSLATE_NOOP("pep8",
         "expected 1 blank line, found 0"),
     "E302": QT_TRANSLATE_NOOP("pep8",
         "expected 2 blank lines, found {0}"),
     "E303": QT_TRANSLATE_NOOP("pep8",
         "too many blank lines ({0})"),
     "E304": QT_TRANSLATE_NOOP("pep8",
         "blank lines found after function decorator"),
     "W391": QT_TRANSLATE_NOOP("pep8",
         "blank line at end of file"),
     "E401": QT_TRANSLATE_NOOP("pep8",
         "multiple imports on one line"),
     "E501": QT_TRANSLATE_NOOP("pep8",
         "line too long ({0} characters)"),
     "W601": QT_TRANSLATE_NOOP("pep8",
         ".has_key() is deprecated, use 'in'"),
     "W602": QT_TRANSLATE_NOOP("pep8",
         "deprecated form of raising exception"),
     "W603": QT_TRANSLATE_NOOP("pep8",
         "'<>' is deprecated, use '!='"),
     "W604": QT_TRANSLATE_NOOP("pep8",
         "backticks are deprecated, use 'repr()'"),
     "E701": QT_TRANSLATE_NOOP("pep8",
         "multiple statements on one line (colon)"),
     "E702": QT_TRANSLATE_NOOP("pep8",
         "multiple statements on one line (semicolon)"),
     "E901": QT_TRANSLATE_NOOP("pep8",
         "Token Error: {0}"),
 }
 pep8_messages_sample_args = {
     "E201": ["([{"],
     "E202": ["}])"],
     "E203": [",;:"],
     "E211": ["(["],
     "E231": [",;:"],
     "E241": [",;:"],
     "E242": [",;:"],
     "E302": [1],
     "E303": [3],
     "E501": [85],
 }
 def getMessage(code, *args):
     """
     Function to get a translated and formatted message for a given code.
     @param code message code (string)
     @param args arguments for a formatted message (list)
     @return translated and formatted message (string)
     """
     if code in pep8_messages:
         return code + " " + QCoreApplication.translate("pep8",
             pep8_messages[code]).format(*args)
     else:
         return code + " " + QCoreApplication.translate("pep8",
             "no message for this code defined")
 ##############################################################################
 # Plugins (check functions) for physical lines
 ##############################################################################
 def tabs_or_spaces(physical_line, indent_char):
     r"""
     Never mix tabs and spaces.
     The most popular way of indenting Python is with spaces only.  The
     second-most popular way is with tabs only.  Code indented with a mixture
     of tabs and spaces should be converted to using spaces exclusively.  When
     invoking the Python command line interpreter with the -t option, it issues
     warnings about code that illegally mixes tabs and spaces.  When using -tt
     these warnings become errors.  These options are highly recommended!
     Okay: if a == 0:\n        a = 1\n        b = 1
     E101: if a == 0:\n        a = 1\n\tb = 1
     """
     indent = INDENT_REGEX.match(physical_line).group(1)
     for offset, char in enumerate(indent):
         if char != indent_char:
             return offset, "E101"
 def tabs_obsolete(physical_line):
     r"""
     For new projects, spaces-only are strongly recommended over tabs.  Most
     editors have features that make this easy to do.
     Okay: if True:\n    return
     W191: if True:\n\treturn
     """
     indent = INDENT_REGEX.match(physical_line).group(1)
     if indent.count('\t'):
         return indent.index('\t'), "W191"
 def trailing_whitespace(physical_line):
     r"""
     JCR: Trailing whitespace is superfluous.
     FBM: Except when it occurs as part of a blank line (i.e. the line is
          nothing but whitespace). According to Python docs[1] a line with only
          whitespace is considered a blank line, and is to be ignored. However,
          matching a blank line to its indentation level avoids mistakenly
          terminating a multi-line statement (e.g. class declaration) when
          pasting code into the standard Python interpreter.
          [1] http://docs.python.org/reference/lexical_analysis.html#blank-lines
     The warning returned varies on whether the line itself is blank, for easier
     filtering for those who want to indent their blank lines.
     Okay: spam(1)
     W291: spam(1)\s
     W293: class Foo(object):\n    \n    bang = 12
     """
     physical_line = physical_line.rstrip('\n')    # chr(10), newline
     physical_line = physical_line.rstrip('\r')    # chr(13), carriage return
     physical_line = physical_line.rstrip('\x0c')  # chr(12), form feed, ^L
     stripped = physical_line.rstrip()
     if physical_line != stripped:
         if stripped:
             return len(stripped), "W291"
         else:
             return 0, "W293"
 def trailing_blank_lines(physical_line, lines, line_number):
     r"""
     JCR: Trailing blank lines are superfluous.
     Okay: spam(1)
     W391: spam(1)\n
     """
     if physical_line.strip() == '' and line_number == len(lines):
         return 0, "W391"
 def missing_newline(physical_line):
     """
     JCR: The last line should have a newline.
     """
     if physical_line.rstrip() == physical_line:
         return len(physical_line), "W292"
 def maximum_line_length(physical_line):
     """
     Limit all lines to a maximum of 79 characters.
     There are still many devices around that are limited to 80 character
     lines; plus, limiting windows to 80 characters makes it possible to have
     several windows side-by-side.  The default wrapping on such devices looks
     ugly.  Therefore, please limit all lines to a maximum of 79 characters.
     For flowing long blocks of text (docstrings or comments), limiting the
     length to 72 characters is recommended.
     """
     line = physical_line.rstrip()
     length = len(line)
     try:
         # The line could contain multi-byte characters
         if hasattr(line, 'decode'):   # Python 2 only
             length = len(line.decode('utf-8'))
     except (UnicodeDecodeError, UnicodeEncodeError):
         pass
     if length > MAX_LINE_LENGTH:
         return MAX_LINE_LENGTH, "E501", length
 ##############################################################################
 # Plugins (check functions) for logical lines
 ##############################################################################
 def blank_lines(logical_line, blank_lines, indent_level, line_number,
                 previous_logical, previous_indent_level,
                 blank_lines_before_comment):
     r"""
     Separate top-level function and class definitions with two blank lines.
     Method definitions inside a class are separated by a single blank line.
     Extra blank lines may be used (sparingly) to separate groups of related
     functions.  Blank lines may be omitted between a bunch of related
     one-liners (e.g. a set of dummy implementations).
     Use blank lines in functions, sparingly, to indicate logical sections.
     Okay: def a():\n    pass\n\n\ndef b():\n    pass
     Okay: def a():\n    pass\n\n\n# Foo\n# Bar\n\ndef b():\n    pass
     E301: class Foo:\n    b = 0\n    def bar():\n        pass
     E302: def a():\n    pass\n\ndef b(n):\n    pass
     E303: def a():\n    pass\n\n\n\ndef b(n):\n    pass
     E303: def a():\n\n\n\n    pass
     E304: @decorator\n\ndef a():\n    pass
     """
     if line_number == 1:
         return  # Don't expect blank lines before the first line
     max_blank_lines = max(blank_lines, blank_lines_before_comment)
     if previous_logical.startswith('@'):
         if max_blank_lines:
             return 0, "E304"
     elif (logical_line.startswith('def ') or
           logical_line.startswith('class ') or
           logical_line.startswith('@')):
         if indent_level:
             if not (max_blank_lines or previous_indent_level < indent_level or
                     DOCSTRING_REGEX.match(previous_logical)):
                 return 0, "E301"
         elif max_blank_lines != 2:
             return 0, "E302", max_blank_lines
     elif max_blank_lines > 2 or (indent_level and max_blank_lines == 2):
         return 0, "E303", max_blank_lines
 def extraneous_whitespace(logical_line):
     """
     Avoid extraneous whitespace in the following situations:
     - Immediately inside parentheses, brackets or braces.
     - Immediately before a comma, semicolon, or colon.
     Okay: spam(ham[1], {eggs: 2})
     E201: spam( ham[1], {eggs: 2})
     E201: spam(ham[ 1], {eggs: 2})
     E201: spam(ham[1], { eggs: 2})
     E202: spam(ham[1], {eggs: 2} )
     E202: spam(ham[1 ], {eggs: 2})
     E202: spam(ham[1], {eggs: 2 })
     E203: if x == 4: print x, y; x, y = y , x
     E203: if x == 4: print x, y ; x, y = y, x
     E203: if x == 4 : print x, y; x, y = y, x
     """
     line = logical_line
     for match in EXTRANEOUS_WHITESPACE_REGEX.finditer(line):
         text = match.group()
         char = text.strip()
         found = match.start()
         if text == char + ' ' and char in '([{':
             return found + 1, "E201", char
         if text == ' ' + char and line[found - 1] != ',':
             if char in '}])':
                 return found, "E202", char
             if char in ',;:':
                 return found, "E203", char
 def missing_whitespace(logical_line):
     """
     JCR: Each comma, semicolon or colon should be followed by whitespace.
     Okay: [a, b]
     Okay: (3,)
     Okay: a[1:4]
     Okay: a[:4]
     Okay: a[1:]
     Okay: a[1:4:2]
     E231: ['a','b']
     E231: foo(bar,baz)
     """
     line = logical_line
     for index in range(len(line) - 1):
         char = line[index]
         if char in ',;:' and line[index + 1] not in WHITESPACE:
             before = line[:index]
             if char == ':' and before.count('[') > before.count(']'):
                 continue  # Slice syntax, no space required
             if char == ',' and line[index + 1] == ')':
                 continue  # Allow tuple with only one element: (3,)
             return index, "E231", char
 def indentation(logical_line, previous_logical, indent_char,
                 indent_level, previous_indent_level):
     r"""
     Use 4 spaces per indentation level.
     For really old code that you don't want to mess up, you can continue to
     use 8-space tabs.
     Okay: a = 1
     Okay: if a == 0:\n    a = 1
     E111:   a = 1
     Okay: for item in items:\n    pass
     E112: for item in items:\npass
     Okay: a = 1\nb = 2
     E113: a = 1\n    b = 2
     """
     if indent_char == ' ' and indent_level % 4:
         return 0, "E111"
     indent_expect = previous_logical.endswith(':')
     if indent_expect and indent_level <= previous_indent_level:
         return 0, "E112"
     if indent_level > previous_indent_level and not indent_expect:
         return 0, "E113"
 def whitespace_before_parameters(logical_line, tokens):
     """
     Avoid extraneous whitespace in the following situations:
     - Immediately before the open parenthesis that starts the argument
       list of a function call.
     - Immediately before the open parenthesis that starts an indexing or
       slicing.
     Okay: spam(1)
     E211: spam (1)
     Okay: dict['key'] = list[index]
     E211: dict ['key'] = list[index]
     E211: dict['key'] = list [index]
     """
     prev_type = tokens[0][0]
     prev_text = tokens[0][1]
     prev_end = tokens[0][3]
     for index in range(1, len(tokens)):
         token_type, text, start, end, line = tokens[index]
         if (token_type == tokenize.OP and
             text in '([' and
             start != prev_end and
             (prev_type == tokenize.NAME or prev_text in '}])') and
             # Syntax "class A (B):" is allowed, but avoid it
             (index < 2 or tokens[index - 2][1] != 'class') and
             # Allow "return (a.foo for a in range(5))"
             (not keyword.iskeyword(prev_text))):
             return prev_end, "E211", text
         prev_type = token_type
         prev_text = text
         prev_end = end
 def whitespace_around_operator(logical_line):
     """
     Avoid extraneous whitespace in the following situations:
     - More than one space around an assignment (or other) operator to
       align it with another.
     Okay: a = 12 + 3
     E221: a = 4  + 5
     E222: a = 4 +  5
     E223: a = 4\t+ 5
     E224: a = 4 +\t5
     """
     for match in WHITESPACE_AROUND_OPERATOR_REGEX.finditer(logical_line):
         before, whitespace, after = match.groups()
         tab = whitespace == '\t'
         offset = match.start(2)
         if before in OPERATORS:
             return offset, (tab and "E224" or "E222")
         elif after in OPERATORS:
             return offset, (tab and "E223" or "E221")
 def missing_whitespace_around_operator(logical_line, tokens):
     r"""
     - Always surround these binary operators with a single space on
       either side: assignment (=), augmented assignment (+=, -= etc.),
       comparisons (==, <, >, !=, <>, <=, >=, in, not in, is, is not),
       Booleans (and, or, not).
     - Use spaces around arithmetic operators.
     Okay: i = i + 1
     Okay: submitted += 1
     Okay: x = x * 2 - 1
     Okay: hypot2 = x * x + y * y
     Okay: c = (a + b) * (a - b)
     Okay: foo(bar, key='word', *args, **kwargs)
     Okay: baz(**kwargs)
     Okay: negative = -1
     Okay: spam(-1)
     Okay: alpha[:-i]
     Okay: if not -5 < x < +5:\n    pass
     Okay: lambda *args, **kw: (args, kw)
     E225: i=i+1
     E225: submitted +=1
     E225: x = x*2 - 1
     E225: hypot2 = x*x + y*y
     E225: c = (a+b) * (a-b)
     E225: c = alpha -4
     E225: z = x **y
     """
     parens = 0
     need_space = False
     prev_type = tokenize.OP
     prev_text = prev_end = None
     for token_type, text, start, end, line in tokens:
         if token_type in (tokenize.NL, tokenize.NEWLINE, tokenize.ERRORTOKEN):
             # ERRORTOKEN is triggered by backticks in Python 3000
             continue
         if text in ('(', 'lambda'):
             parens += 1
         elif text == ')':
             parens -= 1
         if need_space:
             if start != prev_end:
                 need_space = False
             elif text == '>' and prev_text == '<':
                 # Tolerate the "<>" operator, even if running Python 3
                 pass
             else:
                 return prev_end, "E225"
         elif token_type == tokenize.OP and prev_end is not None:
             if text == '=' and parens:
                 # Allow keyword args or defaults: foo(bar=None).
                 pass
             elif text in BINARY_OPERATORS:
                 need_space = True
             elif text in UNARY_OPERATORS:
                 # Allow unary operators: -123, -x, +1.
                 # Allow argument unpacking: foo(*args, **kwargs).
                 if prev_type == tokenize.OP:
                     if prev_text in '}])':
                         need_space = True
                 elif prev_type == tokenize.NAME:
                     if prev_text not in E225NOT_KEYWORDS:
                         need_space = True
                 else:
                     need_space = True
             if need_space and start == prev_end:
                 return prev_end, "E225"
         prev_type = token_type
         prev_text = text
         prev_end = end
 def whitespace_around_comma(logical_line):
     """
     Avoid extraneous whitespace in the following situations:
     - More than one space around an assignment (or other) operator to
       align it with another.
     JCR: This should also be applied around comma etc.
     Note: these checks are disabled by default
     Okay: a = (1, 2)
     E241: a = (1,  2)
     E242: a = (1,\t2)
     """
     line = logical_line
     for separator in ',;:':
         found = line.find(separator + '  ')
         if found > -1:
             return found + 1, "E241", separator
         found = line.find(separator + '\t')
         if found > -1:
             return found + 1, "E242", separator
 def whitespace_around_named_parameter_equals(logical_line):
     """
     Don't use spaces around the '=' sign when used to indicate a
     keyword argument or a default parameter value.
     Okay: def complex(real, imag=0.0):
     Okay: return magic(r=real, i=imag)
     Okay: boolean(a == b)
     Okay: boolean(a != b)
     Okay: boolean(a <= b)
     Okay: boolean(a >= b)
     E251: def complex(real, imag = 0.0):
     E251: return magic(r = real, i = imag)
     """
     parens = 0
     for match in WHITESPACE_AROUND_NAMED_PARAMETER_REGEX.finditer(
             logical_line):
         text = match.group()
         if parens and len(text) == 3:
             issue = "E251"
             return match.start(), issue
         if text == '(':
             parens += 1
         elif text == ')':
             parens -= 1
 def whitespace_before_inline_comment(logical_line, tokens):
     """
     Separate inline comments by at least two spaces.
     An inline comment is a comment on the same line as a statement.  Inline
     comments should be separated by at least two spaces from the statement.
     They should start with a # and a single space.
     Okay: x = x + 1  # Increment x
     Okay: x = x + 1    # Increment x
     E261: x = x + 1 # Increment x
     E262: x = x + 1  #Increment x
     E262: x = x + 1  #  Increment x
     """
     prev_end = (0, 0)
     for token_type, text, start, end, line in tokens:
         if token_type == tokenize.NL:
             continue
         if token_type == tokenize.COMMENT:
             if not line[:start[1]].strip():
                 continue
             if prev_end[0] == start[0] and start[1] < prev_end[1] + 2:
                 return (prev_end, "E261")
             if (len(text) > 1 and text.startswith('#  ')
                            or not text.startswith('# ')):
                 return start, "E262"
         else:
             prev_end = end
 def imports_on_separate_lines(logical_line):
     r"""
     Imports should usually be on separate lines.
     Okay: import os\nimport sys
     E401: import sys, os
     Okay: from subprocess import Popen, PIPE
     Okay: from myclas import MyClass
     Okay: from foo.bar.yourclass import YourClass
     Okay: import myclass
     Okay: import foo.bar.yourclass
     """
     line = logical_line
     if line.startswith('import '):
         found = line.find(',')
         if found > -1:
             return found, "E401"
 def compound_statements(logical_line):
     r"""
     Compound statements (multiple statements on the same line) are
     generally discouraged.
     While sometimes it's okay to put an if/for/while with a small body
     on the same line, never do this for multi-clause statements. Also
     avoid folding such long lines!
     Okay: if foo == 'blah':\n    do_blah_thing()
     Okay: do_one()
     Okay: do_two()
     Okay: do_three()
     E701: if foo == 'blah': do_blah_thing()
     E701: for x in lst: total += x
     E701: while t < 10: t = delay()
     E701: if foo == 'blah': do_blah_thing()
     E701: else: do_non_blah_thing()
     E701: try: something()
     E701: finally: cleanup()
     E701: if foo == 'blah': one(); two(); three()
     E702: do_one(); do_two(); do_three()
     """
     line = logical_line
     found = line.find(':')
     if -1 < found < len(line) - 1:
         before = line[:found]
         if (before.count('{') <= before.count('}') and  # {'a': 1} (dict)
             before.count('[') <= before.count(']') and  # [1:2] (slice)
             not re.search(r'\blambda\b', before)):      # lambda x: x
             return found, "E701"
     found = line.find(';')
     if -1 < found:
         return found, "E702"
 def python_3000_has_key(logical_line):
     """
     The {}.has_key() method will be removed in the future version of
     Python. Use the 'in' operation instead, like:
     d = {"a": 1, "b": 2}
     if "b" in d:
         print d["b"]
     """
     pos = logical_line.find('.has_key(')
     if pos > -1:
         return pos, "W601"
 def python_3000_raise_comma(logical_line):
     """
     When raising an exception, use "raise ValueError('message')"
     instead of the older form "raise ValueError, 'message'".
     The paren-using form is preferred because when the exception arguments
     are long or include string formatting, you don't need to use line
     continuation characters thanks to the containing parentheses.  The older
     form will be removed in Python 3000.
     """
     match = RAISE_COMMA_REGEX.match(logical_line)
     if match:
         return match.start(1), "W602"
 def python_3000_not_equal(logical_line):
     """
     != can also be written <>, but this is an obsolete usage kept for
     backwards compatibility only. New code should always use !=.
     The older syntax is removed in Python 3000.
     """
     pos = logical_line.find('<>')
     if pos > -1:
         return pos, "W603"
 def python_3000_backticks(logical_line):
     """
     Backticks are removed in Python 3000.
     Use repr() instead.
     """
     pos = logical_line.find('`')
     if pos > -1:
         return pos, "W604"
 ##############################################################################
 # Helper functions
 ##############################################################################
 if '' == ''.encode():
     # Python 2: implicit encoding.
     def readlines(filename):
         return open(filename).readlines()
 else:
     # Python 3: decode to latin-1.
     # This function is lazy, it does not read the encoding declaration.
     # XXX: use tokenize.detect_encoding()
     def readlines(filename):    # __IGNORE_WARNING__
         return open(filename, encoding='latin-1').readlines()
 def expand_indent(line):
     """
     Return the amount of indentation.
     Tabs are expanded to the next multiple of 8.
     >>> expand_indent('    ')
     >>> expand_indent('\\t')
     >>> expand_indent('    \\t')
     >>> expand_indent('       \\t')
     >>> expand_indent('        \\t')
     """
     result = 0
     for char in line:
         if char == '\t':
             result = result // 8 * 8 + 8
         elif char == ' ':
             result += 1
         else:
             break
     return result
 def mute_string(text):
     """
     Replace contents with 'xxx' to prevent syntax matching.
     >>> mute_string('"abc"')
     '"xxx"'
     >>> mute_string("'''abc'''")
     "'''xxx'''"
     >>> mute_string("r'abc'")
     "r'xxx'"
     """
     start = 1
     end = len(text) - 1
     # String modifiers (e.g. u or r)
     if text.endswith('"'):
         start += text.index('"')
     elif text.endswith("'"):
         start += text.index("'")
     # Triple quotes
     if text.endswith('"""') or text.endswith("'''"):
         start += 2
         end -= 2
     return text[:start] + 'x' * (end - start) + text[end:]
 def message(text):
     """Print a message."""
     # print >> sys.stderr, options.prog + ': ' + text
     # print >> sys.stderr, text
     print(text)
 ##############################################################################
 # Framework to run all checks
 ##############################################################################
 def find_checks(argument_name):
     """
     Find all globally visible functions where the first argument name
     starts with argument_name.
     """
     checks = []
     for name, function in globals().items():
         if not inspect.isfunction(function):
             continue
         args = inspect.getargspec(function)[0]
         if args and args[0].startswith(argument_name):
             codes = ERRORCODE_REGEX.findall(inspect.getdoc(function) or '')
             for code in codes or ['']:
                 if not code or not ignore_code(code):
                     checks.append((name, function, args))
                     break
     checks.sort()
     return checks
 class Checker(object):
     """
     Load a Python source file, tokenize it, check coding style.
     """
     def __init__(self, filename, lines=None):
         self.filename = filename
         if filename is None:
             self.filename = 'stdin'
             self.lines = lines or []
         elif lines is None:
             self.lines = readlines(filename)
         else:
             self.lines = lines
         options.counters['physical lines'] += len(self.lines)
     def readline(self):
         """
         Get the next line from the input buffer.
         """
         self.line_number += 1
         if self.line_number > len(self.lines):
             return ''
         return self.lines[self.line_number - 1]
     def readline_check_physical(self):
         """
         Check and return the next physical line. This method can be
         used to feed tokenize.generate_tokens.
         """
         line = self.readline()
         if line:
             self.check_physical(line)
         return line
     def run_check(self, check, argument_names):
         """
         Run a check plugin.
         """
         arguments = []
         for name in argument_names:
             arguments.append(getattr(self, name))
         return check(*arguments)
     def check_physical(self, line):
         """
         Run all physical checks on a raw input line.
         """
         self.physical_line = line
         if self.indent_char is None and len(line) and line[0] in ' \t':
             self.indent_char = line[0]
         for name, check, argument_names in options.physical_checks:
             result = self.run_check(check, argument_names)
             if result is not None:
                 offset, code = result[:2]
                 args = result[2:]
                 self.report_error_args(self.line_number, offset, code, check,
                     *args)
     def build_tokens_line(self):
         """
         Build a logical line from tokens.
         """
         self.mapping = []
         logical = []
         length = 0
         previous = None
         for token in self.tokens:
             token_type, text = token[0:2]
             if token_type in SKIP_TOKENS:
                 continue
             if token_type == tokenize.STRING:
                 text = mute_string(text)
             if previous:
                 end_line, end = previous[3]
                 start_line, start = token[2]
                 if end_line != start_line:  # different row
                     prev_text = self.lines[end_line - 1][end - 1]
                     if prev_text == ',' or (prev_text not in '{[('
                                             and text not in '}])'):
                         logical.append(' ')
                         length += 1
                 elif end != start:  # different column
                     fill = self.lines[end_line - 1][end:start]
                     logical.append(fill)
                     length += len(fill)
             self.mapping.append((length, token))
             logical.append(text)
             length += len(text)
             previous = token
         self.logical_line = ''.join(logical)
         assert self.logical_line.lstrip() == self.logical_line
         assert self.logical_line.rstrip() == self.logical_line
     def check_logical(self):
         """
         Build a line from tokens and run all logical checks on it.
         """
         options.counters['logical lines'] += 1
         self.build_tokens_line()
         first_line = self.lines[self.mapping[0][1][2][0] - 1]
         indent = first_line[:self.mapping[0][1][2][1]]
         self.previous_indent_level = self.indent_level
         self.indent_level = expand_indent(indent)
         if options.verbose >= 2:
             print(self.logical_line[:80].rstrip())
         for name, check, argument_names in options.logical_checks:
             if options.verbose >= 4:
                 print('   ' + name)
             result = self.run_check(check, argument_names)
             if result is not None:
                 offset, code = result[:2]
                 args = result[2:]
                 if isinstance(offset, tuple):
                     original_number, original_offset = offset
                 else:
                     for token_offset, token in self.mapping:
                         if offset >= token_offset:
                             original_number = token[2][0]
                             original_offset = (token[2][1]
                                                + offset - token_offset)
                 self.report_error_args(original_number, original_offset,
                                        code, check, *args)
         self.previous_logical = self.logical_line
     def check_all(self, expected=None, line_offset=0):
         """
         Run all checks on the input file.
         """
         self.expected = expected or ()
         self.line_offset = line_offset
         self.line_number = 0
         self.file_errors = 0
         self.indent_char = None
         self.indent_level = 0
         self.previous_logical = ''
         self.blank_lines = 0
         self.blank_lines_before_comment = 0
         self.tokens = []
         parens = 0
         try:
             for token in tokenize.generate_tokens(self.readline_check_physical):
                 if options.verbose >= 3:
                     if token[2][0] == token[3][0]:
                         pos = '[%s:%s]' % (token[2][1] or '', token[3][1])
                     else:
                         pos = 'l.%s' % token[3][0]
                     print('l.%s\t%s\t%s\t%r' %
                         (token[2][0], pos, tokenize.tok_name[token[0]], token[1]))
                 self.tokens.append(token)
                 token_type, text = token[0:2]
                 if token_type == tokenize.OP and text in '([{':
                     parens += 1
                 if token_type == tokenize.OP and text in '}])':
                     parens -= 1
                 if token_type == tokenize.NEWLINE and not parens:
                     self.check_logical()
                     self.blank_lines = 0
                     self.blank_lines_before_comment = 0
                     self.tokens = []
                 if token_type == tokenize.NL and not parens:
                     if len(self.tokens) <= 1:
                         # The physical line contains only this token.
                         self.blank_lines += 1
                     self.tokens = []
                 if token_type == tokenize.COMMENT:
                     source_line = token[4]
                     token_start = token[2][1]
                     if source_line[:token_start].strip() == '':
                         self.blank_lines_before_comment = max(self.blank_lines,
                             self.blank_lines_before_comment)
                         self.blank_lines = 0
                     if text.endswith('\n') and not parens:
                         # The comment also ends a physical line.  This works around
                         # Python < 2.6 behaviour, which does not generate NL after
                         # a comment which is on a line by itself.
                         self.tokens = []
         except tokenize.TokenError as err:
             msg, (lnum, pos) = err.args
             self.report_error_args(lnum, pos, "E901", "TokenError", msg)
         return self.file_errors
     def report_error(self, line_number, offset, text, check):
         """
         Report an error, according to options.
         """
         code = text[:4]
         if ignore_code(code):
             return
         if options.quiet == 1 and not self.file_errors:
             message(self.filename)
         if code in options.counters:
             options.counters[code] += 1
         else:
             options.counters[code] = 1
             options.messages[code] = text[5:]
         if options.quiet or code in self.expected:
             # Don't care about expected errors or warnings
             return
         self.file_errors += 1
         if options.counters[code] == 1 or options.repeat:
             message("%s:%s:%d: %s" %
                     (self.filename, self.line_offset + line_number,
                      offset + 1, text))
             if options.show_source:
                 line = self.lines[line_number - 1]
                 message(line.rstrip())
                 message(' ' * offset + '^')
             if options.show_pep8:
                 message(check.__doc__.lstrip('\n').rstrip())
 def input_file(filename):
     """
     Run all checks on a Python source file.
     """
     if options.verbose:
         message('checking ' + filename)
     Checker(filename).check_all()
 def input_dir(dirname, runner=None):
     """
     Check all Python source files in this directory and all subdirectories.
     """
     dirname = dirname.rstrip('/')
     if excluded(dirname):
         return
     if runner is None:
         runner = input_file
     for root, dirs, files in os.walk(dirname):
         if options.verbose:
             message('directory ' + root)
         options.counters['directories'] += 1
         dirs.sort()
         for subdir in dirs:
             if excluded(subdir):
                 dirs.remove(subdir)
-eb5ff61f927b
Added a checker for PEP 8 compliance.

Detlev Offenbach <detlev@die-offenbachs.de>
parents: 
diff
changeset

Mercurial Repositories > eric / annotate

Plugins/CheckerPlugins/Pep8/pep8.py@1843ef6e2656 (annotated)

Plugins/CheckerPlugins/Pep8/pep8.py