Revert "Revert "pylint: upgrade to 1.3.1""

third_party/pylint/checkers/similar.py

Index: third_party/pylint/checkers/similar.py
===================================================================
--- third_party/pylint/checkers/similar.py	(revision 293047)
+++ third_party/pylint/checkers/similar.py	(working copy)
@@ -1,5 +1,5 @@
 # pylint: disable=W0622
-# Copyright (c) 2004-2006 LOGILAB S.A. (Paris, FRANCE).
+# 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
@@ -13,11 +13,9 @@
 #
 # 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.,
-# 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 """a similarities / code duplication command line tool and pylint checker
 """
-from __future__ import generators
-
 import sys
 from itertools import izip
 
@@ -27,23 +25,32 @@
 from pylint.checkers import BaseChecker, table_lines_from_stats
 
 
-class Similar:
+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_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):
+    def append_stream(self, streamid, stream, encoding=None):
         """append a file to search for similarities"""
-        stream.seek(0) # XXX may be removed with astng > 0.23
-        self.linesets.append(LineSet(streamid,
-                                     stream.readlines(),
-                                     self.ignore_comments,
-                                     self.ignore_docstrings))
+        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"""
@@ -56,15 +63,15 @@
             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) )
+                    couples.add((lineset1, idx1))
+                    couples.add((lineset2, idx2))
                     break
             else:
-                duplicate.append( set([(lineset1, idx1), (lineset2, idx2)]) )
+                duplicate.append(set([(lineset1, idx1), (lineset2, idx2)]))
         sims = []
         for num, ensembles in no_duplicates.iteritems():
             for couples in ensembles:
-                sims.append( (num, couples) )
+                sims.append((num, couples))
         sims.sort()
         sims.reverse()
         return sims
@@ -80,7 +87,7 @@
                 print "==%s:%s" % (lineset.name, idx)
             # pylint: disable=W0631
             for line in lineset._real_lines[idx:idx+num]:
-                print "  ", line,
+                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" \
@@ -97,10 +104,10 @@
         while index1 < len(lineset1):
             skip = 1
             num = 0
-            for index2 in find( lineset1[index1] ):
+            for index2 in find(lineset1[index1]):
                 non_blank = 0
                 for num, ((_, line1), (_, line2)) in enumerate(
-                    izip(lines1(index1), lines2(index2))):
+                        izip(lines1(index1), lines2(index2))):
                     if line1 != line2:
                         if non_blank > min_lines:
                             yield num, lineset1, index1, lineset2, index2
@@ -125,7 +132,11 @@
                 for sim in self._find_common(lineset, lineset2):
                     yield sim
 
-def stripped_lines(lines, ignore_comments, ignore_docstrings):
+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:
@@ -139,6 +150,9 @@
                 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
@@ -146,14 +160,16 @@
         strippedlines.append(line)
     return strippedlines
 
-class LineSet:
+
+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_docstrings=False, ignore_imports=False):
         self.name = name
         self._real_lines = lines
         self._stripped_lines = stripped_lines(lines, ignore_comments,
-                                              ignore_docstrings)
+                                              ignore_docstrings,
+                                              ignore_imports)
         self._index = self._mk_index()
 
     def __str__(self):
@@ -194,11 +210,12 @@
         index = {}
         for line_no, line in enumerate(self._stripped_lines):
             if line:
-                index.setdefault(line, []).append( line_no )
+                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.')}
@@ -232,14 +249,18 @@
                ('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 = ( ('R0801', 'Duplication', report_similarities), ) # XXX actually a Refactoring message
+    reports = (('RP0801', 'Duplication', report_similarities),)
 
     def __init__(self, linter=None):
         BaseChecker.__init__(self, linter)
@@ -259,6 +280,8 @@
             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"""
@@ -273,7 +296,7 @@
 
         stream must implement the readlines method
         """
-        self.append_stream(self.linter.current_name, node.file_stream)
+        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)"""
@@ -303,18 +326,21 @@
     print "finds copy pasted blocks in a set of files"
     print
     print 'Usage: symilar [-d|--duplicates min_duplicated_lines] \
-[-i|--ignore-comments] file1...'
+[-i|--ignore-comments] [--ignore-docstrings] [--ignore-imports] file1...'
     sys.exit(status)
 
-def run(argv=None):
+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')
+    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'):
@@ -323,12 +349,17 @@
             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)
+    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()
+    Run()