Improve copyright detection

Strip leading copyright signs from holders

Signed-off-by: Philippe Ombredanne <pombredanne@nexb.com>

Author: pombredanne

src/cluecode/copyrights.py

@@ -3700,6 +3700,7 @@ def is_junk_copyright(s, patterns=COPYRIGHTS_JUNK_PATTERN_MATCHERS):
         "name'",
         "a",
         "moduleauthor",
+        "©",
     ])
 ))
 
@@ -3781,6 +3782,7 @@ def is_junk_copyright(s, patterns=COPYRIGHTS_JUNK_PATTERN_MATCHERS):
         'later',
         '$',
         'current.year',
+        "©",
     ])
 ))
 
@@ -4321,7 +4323,7 @@ def remove_code_comment_markers(s):
     Return ``s`` removing code comments such as C and C++ style comment markers and assimilated
 
     >>> remove_code_comment_markers("\\*#%; /\\/*a*/b/*c\\d#e%f \\*#%; /")
-    'a b c d e f'
+    'a b c\\d e f'
     """
     return (s
         .replace('/*', ' ')

tests/packagedcode/data/debian/copyright/debian-slim-2021-04-07/usr/share/doc/gcc-10-base/copyright-detailed.expected.yml

@@ -2166,7 +2166,7 @@ copyright: |
   Copyright (c) 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019
   Copyright (c) 2009-2019 by the LLVM contributors
   Copyright (c) 1996-2003 Red Hat, Inc.
-  Copyright (c) 2009 Free Software Foundation, Inc. <http://fsf.org/>
+  Copyright (c) 2009 Free Software Foundation, Inc. http://fsf.org
   Copyright (c) 2010 Free Software Foundation, Inc.
   Copyright 2001 by Stephen L. Moshier <moshier@na-net.ornl.gov>
   Copyright (c) 2001 Stephen L. Moshier <moshier@na-net.ornl.gov>

tests/packagedcode/data/debian/copyright/debian-slim-2021-04-07/usr/share/doc/gcc-9-base/copyright-detailed.expected.yml

@@ -2425,7 +2425,7 @@ copyright: |
   Copyright (c) 1986, 1987, 1988, 1989, 1990, 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019
   Copyright (c) 2009-2014 by the LLVM contributors
   Copyright (c) 1996-2003 Red Hat, Inc.
-  Copyright (c) 2009 Free Software Foundation, Inc. <http://fsf.org/>
+  Copyright (c) 2009 Free Software Foundation, Inc. http://fsf.org
   Copyright (c) 2010 Free Software Foundation, Inc.
   Copyright 2001 by Stephen L. Moshier <moshier@na-net.ornl.gov>
   Copyright (c) 2001 Stephen L. Moshier <moshier@na-net.ornl.gov>

tests/packagedcode/data/debian/copyright/debian-slim-2021-04-07/usr/share/doc/libext2fs2/copyright-detailed.expected.yml

@@ -98,7 +98,7 @@ other_license_detections: []
 copyright: |
   Copyright (c) 2003-2007 Theodore Ts'o <tytso@mit.edu>
   Copyright (c) 1997-2003 Yann Dirson <dirson@debian.org>
-  Copyright (c) 2001 Alcove <http://www.alcove.com/>
+  Copyright (c) 2001 Alcove http://www.alcove.com
   Copyright (c) 1997 Klee Dienes
   Copyright (c) 1995-1996 Michael Nonweiler <mrn20@cam.ac.uk>
   Copyright (c) 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008 by Theodore Ts'o

tests/packagedcode/data/debian/copyright/debian-slim-2021-04-07/usr/share/doc/logsave/copyright-detailed.expected.yml

@@ -98,7 +98,7 @@ other_license_detections: []
 copyright: |
   Copyright (c) 2003-2007 Theodore Ts'o <tytso@mit.edu>
   Copyright (c) 1997-2003 Yann Dirson <dirson@debian.org>
-  Copyright (c) 2001 Alcove <http://www.alcove.com/>
+  Copyright (c) 2001 Alcove http://www.alcove.com
   Copyright (c) 1997 Klee Dienes
   Copyright (c) 1995-1996 Michael Nonweiler <mrn20@cam.ac.uk>
   Copyright (c) 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008 by Theodore Ts'o