exercism-analysis 0.1.1

data/vendor/python/pylint/checkers/misc.py

@@ -0,0 +1,90 @@
+# pylint: disable=W0511
+# This program is free software; you can redistribute it and/or modify it under
+# the terms of the GNU General Public License as published by the Free Software
+# Foundation; either version 2 of the License, or (at your option) any later
+# version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+""" Copyright (c) 2000-2010 LOGILAB S.A. (Paris, FRANCE).
+ http://www.logilab.fr/ -- mailto:contact@logilab.fr
+
+Check source code is ascii only or has an encoding declaration (PEP 263)
+"""
+
+import re
+
+from pylint.interfaces import IRawChecker
+from pylint.checkers import BaseChecker
+
+
+MSGS = {
+    'W0511': ('%s',
+              'fixme',
+              'Used when a warning note as FIXME or XXX is detected.'),
+    'W0512': ('Cannot decode using encoding "%s", unexpected byte at position %d',
+              'invalid-encoded-data',
+              'Used when a source line cannot be decoded using the specified '
+              'source file encoding.',
+              {'maxversion': (3, 0)}),
+    }
+
+
+class EncodingChecker(BaseChecker):
+    """checks for:
+    * warning notes in the code like FIXME, XXX
+    * encoding issues.
+    """
+    __implements__ = IRawChecker
+
+    # configuration section name
+    name = 'miscellaneous'
+    msgs = MSGS
+
+    options = (('notes',
+                {'type' : 'csv', 'metavar' : '<comma separated values>',
+                 'default' : ('FIXME', 'XXX', 'TODO'),
+                 'help' : 'List of note tags to take in consideration, \
+separated by a comma.'
+                 }),
+               )
+
+    def _check_note(self, notes, lineno, line):
+        match = notes.search(line)
+        if match:
+            self.add_message('fixme', args=line[match.start():-1], line=lineno)
+
+    def _check_encoding(self, lineno, line, file_encoding):
+        try:
+            return unicode(line, file_encoding)
+        except UnicodeDecodeError, ex:
+            self.add_message('invalid-encoded-data', line=lineno,
+                             args=(file_encoding, ex.args[2]))
+
+    def process_module(self, module):
+        """inspect the source file to find encoding problem or fixmes like
+        notes
+        """
+        stream = module.file_stream
+        stream.seek(0) # XXX may be removed with astroid > 0.23
+        if self.config.notes:
+            notes = re.compile('|'.join(self.config.notes))
+        else:
+            notes = None
+        if module.file_encoding:
+            encoding = module.file_encoding
+        else:
+            encoding = 'ascii'
+        for lineno, line in enumerate(stream):
+            line = self._check_encoding(lineno+1, line, encoding)
+            if line is not None and notes:
+                self._check_note(notes, lineno+1, line)
+
+def register(linter):
+    """required method to auto register this checker"""
+    linter.register_checker(EncodingChecker(linter))

data/vendor/python/pylint/checkers/newstyle.py

@@ -0,0 +1,151 @@
+# Copyright (c) 2005-2014 LOGILAB S.A. (Paris, FRANCE).
+# http://www.logilab.fr/ -- mailto:contact@logilab.fr
+#
+# This program is free software; you can redistribute it and/or modify it under
+# the terms of the GNU General Public License as published by the Free Software
+# Foundation; either version 2 of the License, or (at your option) any later
+# version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+"""check for new / old style related problems
+"""
+import sys
+
+import astroid
+
+from pylint.interfaces import IAstroidChecker
+from pylint.checkers import BaseChecker
+from pylint.checkers.utils import check_messages
+
+MSGS = {
+    'E1001': ('Use of __slots__ on an old style class',
+              'slots-on-old-class',
+              'Used when an old style class uses the __slots__ attribute.',
+              {'maxversion': (3, 0)}),
+    'E1002': ('Use of super on an old style class',
+              'super-on-old-class',
+              'Used when an old style class uses the super builtin.',
+              {'maxversion': (3, 0)}),
+    'E1003': ('Bad first argument %r given to super()',
+              'bad-super-call',
+              'Used when another argument than the current class is given as \
+              first argument of the super builtin.'),
+    'E1004': ('Missing argument to super()',
+              'missing-super-argument',
+              'Used when the super builtin didn\'t receive an \
+               argument.',
+              {'maxversion': (3, 0)}),
+    'W1001': ('Use of "property" on an old style class',
+              'property-on-old-class',
+              'Used when PyLint detect the use of the builtin "property" \
+              on an old style class while this is relying on new style \
+              classes features.',
+              {'maxversion': (3, 0)}),
+    'C1001': ('Old-style class defined.',
+              'old-style-class',
+              'Used when a class is defined that does not inherit from another'
+              'class and does not inherit explicitly from "object".',
+              {'maxversion': (3, 0)})
+    }
+
+
+class NewStyleConflictChecker(BaseChecker):
+    """checks for usage of new style capabilities on old style classes and
+    other new/old styles conflicts problems
+    * use of property, __slots__, super
+    * "super" usage
+    """
+
+    __implements__ = (IAstroidChecker,)
+
+    # configuration section name
+    name = 'newstyle'
+    # messages
+    msgs = MSGS
+    priority = -2
+    # configuration options
+    options = ()
+
+    @check_messages('slots-on-old-class', 'old-style-class')
+    def visit_class(self, node):
+        """check __slots__ usage
+        """
+        if '__slots__' in node and not node.newstyle:
+            self.add_message('slots-on-old-class', node=node)
+        # The node type could be class, exception, metaclass, or
+        # interface.  Presumably, the non-class-type nodes would always
+        # have an explicit base class anyway.
+        if not node.bases and node.type == 'class':
+            self.add_message('old-style-class', node=node)
+
+    @check_messages('property-on-old-class')
+    def visit_callfunc(self, node):
+        """check property usage"""
+        parent = node.parent.frame()
+        if (isinstance(parent, astroid.Class) and
+            not parent.newstyle and
+            isinstance(node.func, astroid.Name)):
+            name = node.func.name
+            if name == 'property':
+                self.add_message('property-on-old-class', node=node)
+
+    @check_messages('super-on-old-class', 'bad-super-call', 'missing-super-argument')
+    def visit_function(self, node):
+        """check use of super"""
+        # ignore actual functions or method within a new style class
+        if not node.is_method():
+            return
+        klass = node.parent.frame()
+        for stmt in node.nodes_of_class(astroid.CallFunc):
+            expr = stmt.func
+            if not isinstance(expr, astroid.Getattr):
+                continue
+            call = expr.expr
+            # skip the test if using super
+            if isinstance(call, astroid.CallFunc) and \
+               isinstance(call.func, astroid.Name) and \
+               call.func.name == 'super':
+                if not klass.newstyle:
+                    # super should not be used on an old style class
+                    self.add_message('super-on-old-class', node=node)
+                else:
+                    # super first arg should be the class
+                    if not call.args and sys.version_info[0] == 3:
+                        # unless Python 3
+                        continue
+
+                    try:
+                        supcls = (call.args and call.args[0].infer().next()
+                                  or None)
+                    except astroid.InferenceError:
+                        continue
+
+                    if supcls is None:
+                        self.add_message('missing-super-argument', node=call)
+                        continue
+
+                    if klass is not supcls:
+                        name = None
+                        # if supcls is not YES, then supcls was infered
+                        # and use its name. Otherwise, try to look
+                        # for call.args[0].name
+                        if supcls is not astroid.YES:
+                            name = supcls.name
+                        else:
+                            if hasattr(call.args[0], 'name'):
+                                name = call.args[0].name
+                        if name is not None:
+                            self.add_message('bad-super-call',
+                                             node=call,
+                                             args=(name, ))
+
+
+def register(linter):
+    """required method to auto register this checker """
+    linter.register_checker(NewStyleConflictChecker(linter))

data/vendor/python/pylint/checkers/raw_metrics.py

@@ -0,0 +1,129 @@
+# Copyright (c) 2003-2013 LOGILAB S.A. (Paris, FRANCE).
+# http://www.logilab.fr/ -- mailto:contact@logilab.fr
+#
+# This program is free software; you can redistribute it and/or modify it under
+# the terms of the GNU General Public License as published by the Free Software
+# Foundation; either version 2 of the License, or (at your option) any later
+# version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+""" Copyright (c) 2003-2010 LOGILAB S.A. (Paris, FRANCE).
+ http://www.logilab.fr/ -- mailto:contact@logilab.fr
+
+Raw metrics checker
+"""
+
+import tokenize
+
+# pylint now requires pylint >= 2.2, so this is no longer necessary
+#if not hasattr(tokenize, 'NL'):
+#    raise ValueError("tokenize.NL doesn't exist -- tokenize module too old")
+
+from logilab.common.ureports import Table
+
+from pylint.interfaces import ITokenChecker
+from pylint.utils import EmptyReport
+from pylint.checkers import BaseTokenChecker
+from pylint.reporters import diff_string
+
+def report_raw_stats(sect, stats, old_stats):
+    """calculate percentage of code / doc / comment / empty
+    """
+    total_lines = stats['total_lines']
+    if not total_lines:
+        raise EmptyReport()
+    sect.description = '%s lines have been analyzed' % total_lines
+    lines = ('type', 'number', '%', 'previous', 'difference')
+    for node_type in ('code', 'docstring', 'comment', 'empty'):
+        key = node_type + '_lines'
+        total = stats[key]
+        percent = float(total * 100) / total_lines
+        old = old_stats.get(key, None)
+        if old is not None:
+            diff_str = diff_string(old, total)
+        else:
+            old, diff_str = 'NC', 'NC'
+        lines += (node_type, str(total), '%.2f' % percent,
+                  str(old), diff_str)
+    sect.append(Table(children=lines, cols=5, rheaders=1))
+
+
+class RawMetricsChecker(BaseTokenChecker):
+    """does not check anything but gives some raw metrics :
+    * total number of lines
+    * total number of code lines
+    * total number of docstring lines
+    * total number of comments lines
+    * total number of empty lines
+    """
+
+    __implements__ = (ITokenChecker,)
+
+    # configuration section name
+    name = 'metrics'
+    # configuration options
+    options = ()
+    # messages
+    msgs = {}
+    # reports
+    reports = (('RP0701', 'Raw metrics', report_raw_stats),)
+
+    def __init__(self, linter):
+        BaseTokenChecker.__init__(self, linter)
+        self.stats = None
+
+    def open(self):
+        """init statistics"""
+        self.stats = self.linter.add_stats(total_lines=0, code_lines=0,
+                                           empty_lines=0, docstring_lines=0,
+                                           comment_lines=0)
+
+    def process_tokens(self, tokens):
+        """update stats"""
+        i = 0
+        tokens = list(tokens)
+        while i < len(tokens):
+            i, lines_number, line_type = get_type(tokens, i)
+            self.stats['total_lines'] += lines_number
+            self.stats[line_type] += lines_number
+
+
+JUNK = (tokenize.NL, tokenize.INDENT, tokenize.NEWLINE, tokenize.ENDMARKER)
+
+def get_type(tokens, start_index):
+    """return the line type : docstring, comment, code, empty"""
+    i = start_index
+    tok_type = tokens[i][0]
+    start = tokens[i][2]
+    pos = start
+    line_type = None
+    while i < len(tokens) and tokens[i][2][0] == start[0]:
+        tok_type = tokens[i][0]
+        pos = tokens[i][3]
+        if line_type is None:
+            if tok_type == tokenize.STRING:
+                line_type = 'docstring_lines'
+            elif tok_type == tokenize.COMMENT:
+                line_type = 'comment_lines'
+            elif tok_type in JUNK:
+                pass
+            else:
+                line_type = 'code_lines'
+        i += 1
+    if line_type is None:
+        line_type = 'empty_lines'
+    elif i < len(tokens) and tok_type == tokenize.NEWLINE:
+        i += 1
+    return i, pos[0] - start[0] + 1, line_type
+
+
+def register(linter):
+    """ required method to auto register this checker """
+    linter.register_checker(RawMetricsChecker(linter))
+

data/vendor/python/pylint/checkers/similar.py

@@ -0,0 +1,365 @@
+# pylint: disable=W0622
+# Copyright (c) 2004-2013 LOGILAB S.A. (Paris, FRANCE).
+# http://www.logilab.fr/ -- mailto:contact@logilab.fr
+#
+# This program is free software; you can redistribute it and/or modify it under
+# the terms of the GNU General Public License as published by the Free Software
+# Foundation; either version 2 of the License, or (at your option) any later
+# version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+# FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc.,
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+"""a similarities / code duplication command line tool and pylint checker
+"""
+import sys
+from itertools import izip
+
+from logilab.common.ureports import Table
+
+from pylint.interfaces import IRawChecker
+from pylint.checkers import BaseChecker, table_lines_from_stats
+
+
+class Similar(object):
+    """finds copy-pasted lines of code in a project"""
+
+    def __init__(self, min_lines=4, ignore_comments=False,
+                 ignore_docstrings=False, ignore_imports=False):
+        self.min_lines = min_lines
+        self.ignore_comments = ignore_comments
+        self.ignore_docstrings = ignore_docstrings
+        self.ignore_imports = ignore_imports
+        self.linesets = []
+
+    def append_stream(self, streamid, stream, encoding=None):
+        """append a file to search for similarities"""
+        stream.seek(0) # XXX may be removed with astroid > 0.23
+        if encoding is None:
+            readlines = stream.readlines
+        else:
+            readlines = lambda: [line.decode(encoding) for line in stream]
+        try:
+            self.linesets.append(LineSet(streamid,
+                                         readlines(),
+                                         self.ignore_comments,
+                                         self.ignore_docstrings,
+                                         self.ignore_imports))
+        except UnicodeDecodeError:
+            pass
+
+    def run(self):
+        """start looking for similarities and display results on stdout"""
+        self._display_sims(self._compute_sims())
+
+    def _compute_sims(self):
+        """compute similarities in appended files"""
+        no_duplicates = {}
+        for num, lineset1, idx1, lineset2, idx2 in self._iter_sims():
+            duplicate = no_duplicates.setdefault(num, [])
+            for couples in duplicate:
+                if (lineset1, idx1) in couples or (lineset2, idx2) in couples:
+                    couples.add((lineset1, idx1))
+                    couples.add((lineset2, idx2))
+                    break
+            else:
+                duplicate.append(set([(lineset1, idx1), (lineset2, idx2)]))
+        sims = []
+        for num, ensembles in no_duplicates.iteritems():
+            for couples in ensembles:
+                sims.append((num, couples))
+        sims.sort()
+        sims.reverse()
+        return sims
+
+    def _display_sims(self, sims):
+        """display computed similarities on stdout"""
+        nb_lignes_dupliquees = 0
+        for num, couples in sims:
+            print
+            print num, "similar lines in", len(couples), "files"
+            couples = sorted(couples)
+            for lineset, idx in couples:
+                print "==%s:%s" % (lineset.name, idx)
+            # pylint: disable=W0631
+            for line in lineset._real_lines[idx:idx+num]:
+                print "  ", line.rstrip()
+            nb_lignes_dupliquees += num * (len(couples)-1)
+        nb_total_lignes = sum([len(lineset) for lineset in self.linesets])
+        print "TOTAL lines=%s duplicates=%s percent=%.2f" \
+            % (nb_total_lignes, nb_lignes_dupliquees,
+               nb_lignes_dupliquees*100. / nb_total_lignes)
+
+    def _find_common(self, lineset1, lineset2):
+        """find similarities in the two given linesets"""
+        lines1 = lineset1.enumerate_stripped
+        lines2 = lineset2.enumerate_stripped
+        find = lineset2.find
+        index1 = 0
+        min_lines = self.min_lines
+        while index1 < len(lineset1):
+            skip = 1
+            num = 0
+            for index2 in find(lineset1[index1]):
+                non_blank = 0
+                for num, ((_, line1), (_, line2)) in enumerate(
+                    izip(lines1(index1), lines2(index2))):
+                    if line1 != line2:
+                        if non_blank > min_lines:
+                            yield num, lineset1, index1, lineset2, index2
+                        skip = max(skip, num)
+                        break
+                    if line1:
+                        non_blank += 1
+                else:
+                    # we may have reach the end
+                    num += 1
+                    if non_blank > min_lines:
+                        yield num, lineset1, index1, lineset2, index2
+                    skip = max(skip, num)
+            index1 += skip
+
+    def _iter_sims(self):
+        """iterate on similarities among all files, by making a cartesian
+        product
+        """
+        for idx, lineset in enumerate(self.linesets[:-1]):
+            for lineset2 in self.linesets[idx+1:]:
+                for sim in self._find_common(lineset, lineset2):
+                    yield sim
+
+def stripped_lines(lines, ignore_comments, ignore_docstrings, ignore_imports):
+    """return lines with leading/trailing whitespace and any ignored code
+    features removed
+    """
+
+    strippedlines = []
+    docstring = None
+    for line in lines:
+        line = line.strip()
+        if ignore_docstrings:
+            if not docstring and \
+                   (line.startswith('"""') or line.startswith("'''")):
+                docstring = line[:3]
+                line = line[3:]
+            if docstring:
+                if line.endswith(docstring):
+                    docstring = None
+                line = ''
+        if ignore_imports:
+            if line.startswith("import ") or line.startswith("from "):
+                line = ''
+        if ignore_comments:
+            # XXX should use regex in checkers/format to avoid cutting
+            # at a "#" in a string
+            line = line.split('#', 1)[0].strip()
+        strippedlines.append(line)
+    return strippedlines
+
+
+class LineSet(object):
+    """Holds and indexes all the lines of a single source file"""
+    def __init__(self, name, lines, ignore_comments=False,
+                 ignore_docstrings=False, ignore_imports=False):
+        self.name = name
+        self._real_lines = lines
+        self._stripped_lines = stripped_lines(lines, ignore_comments,
+                                              ignore_docstrings,
+                                              ignore_imports)
+        self._index = self._mk_index()
+
+    def __str__(self):
+        return '<Lineset for %s>' % self.name
+
+    def __len__(self):
+        return len(self._real_lines)
+
+    def __getitem__(self, index):
+        return self._stripped_lines[index]
+
+    def __lt__(self, other):
+        return self.name < other.name
+
+    def __hash__(self):
+        return id(self)
+
+    def enumerate_stripped(self, start_at=0):
+        """return an iterator on stripped lines, starting from a given index
+        if specified, else 0
+        """
+        idx = start_at
+        if start_at:
+            lines = self._stripped_lines[start_at:]
+        else:
+            lines = self._stripped_lines
+        for line in lines:
+            #if line:
+            yield idx, line
+            idx += 1
+
+    def find(self, stripped_line):
+        """return positions of the given stripped line in this set"""
+        return self._index.get(stripped_line, ())
+
+    def _mk_index(self):
+        """create the index for this set"""
+        index = {}
+        for line_no, line in enumerate(self._stripped_lines):
+            if line:
+                index.setdefault(line, []).append(line_no)
+        return index
+
+
+MSGS = {'R0801': ('Similar lines in %s files\n%s',
+                  'duplicate-code',
+                  'Indicates that a set of similar lines has been detected \
+                  among multiple file. This usually means that the code should \
+                  be refactored to avoid this duplication.')}
+
+def report_similarities(sect, stats, old_stats):
+    """make a layout with some stats about duplication"""
+    lines = ['', 'now', 'previous', 'difference']
+    lines += table_lines_from_stats(stats, old_stats,
+                                    ('nb_duplicated_lines',
+                                     'percent_duplicated_lines'))
+    sect.append(Table(children=lines, cols=4, rheaders=1, cheaders=1))
+
+
+# wrapper to get a pylint checker from the similar class
+class SimilarChecker(BaseChecker, Similar):
+    """checks for similarities and duplicated code. This computation may be
+    memory / CPU intensive, so you should disable it if you experiment some
+    problems.
+    """
+
+    __implements__ = (IRawChecker,)
+    # configuration section name
+    name = 'similarities'
+    # messages
+    msgs = MSGS
+    # configuration options
+    # for available dict keys/values see the optik parser 'add_option' method
+    options = (('min-similarity-lines',
+                {'default' : 4, 'type' : "int", 'metavar' : '<int>',
+                 'help' : 'Minimum lines number of a similarity.'}),
+               ('ignore-comments',
+                {'default' : True, 'type' : 'yn', 'metavar' : '<y or n>',
+                 'help': 'Ignore comments when computing similarities.'}
+                ),
+               ('ignore-docstrings',
+                {'default' : True, 'type' : 'yn', 'metavar' : '<y or n>',
+                 'help': 'Ignore docstrings when computing similarities.'}
+                ),
+               ('ignore-imports',
+                {'default' : False, 'type' : 'yn', 'metavar' : '<y or n>',
+                 'help': 'Ignore imports when computing similarities.'}
+                ),
+               )
+    # reports
+    reports = (('RP0801', 'Duplication', report_similarities),)
+
+    def __init__(self, linter=None):
+        BaseChecker.__init__(self, linter)
+        Similar.__init__(self, min_lines=4,
+                         ignore_comments=True, ignore_docstrings=True)
+        self.stats = None
+
+    def set_option(self, optname, value, action=None, optdict=None):
+        """method called to set an option (registered in the options list)
+
+        overridden to report options setting to Similar
+        """
+        BaseChecker.set_option(self, optname, value, action, optdict)
+        if optname == 'min-similarity-lines':
+            self.min_lines = self.config.min_similarity_lines
+        elif optname == 'ignore-comments':
+            self.ignore_comments = self.config.ignore_comments
+        elif optname == 'ignore-docstrings':
+            self.ignore_docstrings = self.config.ignore_docstrings
+        elif optname == 'ignore-imports':
+            self.ignore_imports = self.config.ignore_imports
+
+    def open(self):
+        """init the checkers: reset linesets and statistics information"""
+        self.linesets = []
+        self.stats = self.linter.add_stats(nb_duplicated_lines=0,
+                                           percent_duplicated_lines=0)
+
+    def process_module(self, node):
+        """process a module
+
+        the module's content is accessible via the stream object
+
+        stream must implement the readlines method
+        """
+        self.append_stream(self.linter.current_name, node.file_stream, node.file_encoding)
+
+    def close(self):
+        """compute and display similarities on closing (i.e. end of parsing)"""
+        total = sum([len(lineset) for lineset in self.linesets])
+        duplicated = 0
+        stats = self.stats
+        for num, couples in self._compute_sims():
+            msg = []
+            for lineset, idx in couples:
+                msg.append("==%s:%s" % (lineset.name, idx))
+            msg.sort()
+            # pylint: disable=W0631
+            for line in lineset._real_lines[idx:idx+num]:
+                msg.append(line.rstrip())
+            self.add_message('R0801', args=(len(couples), '\n'.join(msg)))
+            duplicated += num * (len(couples) - 1)
+        stats['nb_duplicated_lines'] = duplicated
+        stats['percent_duplicated_lines'] = total and duplicated * 100. / total
+
+
+def register(linter):
+    """required method to auto register this checker """
+    linter.register_checker(SimilarChecker(linter))
+
+def usage(status=0):
+    """display command line usage information"""
+    print "finds copy pasted blocks in a set of files"
+    print
+    print 'Usage: symilar [-d|--duplicates min_duplicated_lines] \
+[-i|--ignore-comments] [--ignore-docstrings] [--ignore-imports] file1...'
+    sys.exit(status)
+
+def Run(argv=None):
+    """standalone command line access point"""
+    if argv is None:
+        argv = sys.argv[1:]
+    from getopt import getopt
+    s_opts = 'hdi'
+    l_opts = ('help', 'duplicates=', 'ignore-comments', 'ignore-imports',
+              'ignore-docstrings')
+    min_lines = 4
+    ignore_comments = False
+    ignore_docstrings = False
+    ignore_imports = False
+    opts, args = getopt(argv, s_opts, l_opts)
+    for opt, val in opts:
+        if opt in ('-d', '--duplicates'):
+            min_lines = int(val)
+        elif opt in ('-h', '--help'):
+            usage()
+        elif opt in ('-i', '--ignore-comments'):
+            ignore_comments = True
+        elif opt in ('--ignore-docstrings',):
+            ignore_docstrings = True
+        elif opt in ('--ignore-imports',):
+            ignore_imports = True
+    if not args:
+        usage(1)
+    sim = Similar(min_lines, ignore_comments, ignore_docstrings, ignore_imports)
+    for filename in args:
+        sim.append_stream(filename, open(filename))
+    sim.run()
+    sys.exit(0)
+
+if __name__ == '__main__':
+    Run()