symilar: ignore differences due to comments at the end of a line; reflect it in tests

3 files changed, 23 insertions, 9 deletions

diff --git a/checkers/similar.py b/checkers/similar.py
index d8651b5b5..ae008b9be 100644
--- a/checkers/similar.py
+++ b/checkers/similar.py
@@ -139,9 +139,10 @@ def stripped_lines(lines, ignore_comments, ignore_docstrings):
                 if line.endswith(docstring):
                     docstring = None
                 line = ''
-        # XXX cut when a line begins with code but end with a comment
-        if ignore_comments and line.startswith('#'):
-            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
 
@@ -302,7 +303,7 @@ def usage(status=0):
     print "finds copy pasted blocks in a set of files"
     print
     print 'Usage: similar [-d|--duplicates min_duplicated_lines] \
-[--ignore-comments] file1...'
+[-i|--ignore-comments] file1...'
     sys.exit(status)
 
 def run(argv=None):
@@ -310,7 +311,7 @@ def run(argv=None):
     if argv is None:
         argv = sys.argv[1:]
     from getopt import getopt
-    s_opts = 'hd:'
+    s_opts = 'hdi'
     l_opts = ('help', 'duplicates=', 'ignore-comments')
     min_lines = 4
     ignore_comments = False
@@ -320,7 +321,7 @@ def run(argv=None):
             min_lines = int(val)
         elif opt in ('-h', '--help'):
             usage()
-        elif opt == '--ignore-comments':
+        elif opt in ('-i', '--ignore-comments'):
             ignore_comments = True
     if not args:
         usage(1)
diff --git a/test/input/similar1 b/test/input/similar1
index bc881871c..d1604d306 100644
--- a/test/input/similar1
+++ b/test/input/similar1
@@ -6,7 +6,7 @@ see the similar2 file which is almost the
 same file as this one. 
 more than 4
 identical lines should
-be
+be # ignore comments !
 detected
 
 
diff --git a/test/test_similar.py b/test/test_similar.py
index 9b9eb37f9..68aff835d 100644
--- a/test/test_similar.py
+++ b/test/test_similar.py
@@ -11,7 +11,8 @@ SIMILAR2 = join(dirname(abspath(__file__)), 'input', 'similar2')
 
 class SimilarTC(TestCase):
     """test the similar command line utility"""
-    def test(self):
+
+    def test_ignore_comments(self):
         sys.stdout = StringIO()
         try:
             similar.run(['--ignore-comments', SIMILAR1, SIMILAR2])
@@ -31,7 +32,19 @@ class SimilarTC(TestCase):
    
 TOTAL lines=38 duplicates=7 percent=18.42
 """ % (SIMILAR1, SIMILAR2)).strip())
-                          
+
+
+    def test_dont_ignore_comments(self):
+        sys.stdout = StringIO()
+        try:
+            similar.run([SIMILAR1, SIMILAR2])
+            output = sys.stdout.getvalue()
+        finally:
+            sys.stdout = sys.__stdout__
+        self.assertMultiLineEqual(output.strip(), """
+TOTAL lines=38 duplicates=0 percent=0.00
+        """.strip())
+
     def test_help(self):
         sys.stdout = StringIO()
         try: