Improve copyright detection

 * correct detection for genivi #17
 * other refeinments and new tests

Signed-off-by: Philippe Ombredanne <[email protected]>

Author: pombredanne

src/cluecode/copyrights.py

@@ -722,6 +722,13 @@ def detect(location):
     #copyright notice (3dfx Interactive, Inc. 1999), (notice is JUNK)
     COPYRIGHT: {<COPY> <JUNK> <COMPANY> <YR-RANGE>}       #2620
 
+    # Copyright (C) <2013>, GENIVI Alliance, Inc.
+    COPYRIGHT: {<COPYRIGHT2> <ANDCO>}       #2625
+
+    #  copyright C 1988 by the Institute of Electrical and Electronics Engineers, Inc.
+    COPYRIGHT: {<COPY> <PN> <YR-RANGE> <BY> <COMPANY> }       #2630
+
+
 # Authors
     AUTH: {<AUTH2>+ <BY>}        #2640
     AUTHOR: {<AUTH>+ <NN>? <COMPANY|NAME|YR-RANGE>* <BY>? <EMAIL>+}        #2650
@@ -969,6 +976,7 @@ def is_junk(c):
         '(c) if you bring a patent claim against any contributor',
         'copyright-check writable-files m4-check author_mark_check',
         # 'copyrighting it yourself or claiming authorship'
+        "copyright of uc berkeley's berkeley software distribution",
     ])
     return c.lower() in junk
 
@@ -1203,6 +1211,7 @@ def strip_markup(text):
     html_tag_regex = re.compile(
         r'<'
         r'[(--)\?\!\%\/]?'
+        r'[a-zA-Z#\"\=\s\.\;\:\%\&?!,\+\*\-_\/]+'
         r'[a-zA-Z0-9#\"\=\s\.\;\:\%\&?!,\+\*\-_\/]+'
         r'\/?>',
         re.MULTILINE | re.UNICODE

tests/cluecode/test_copyrights.py

@@ -518,7 +518,7 @@ def test_copyright_chameleon_assembly(self):
     def test_copyright_co_cust(self):
         test_file = self.get_test_loc('copyrights/copyright_co_cust-copyright_java.java')
         expected = [
-            'Copyright (c) 2009 Company Customer Identity Hidden',
+            'Copyright (c) 2009 <p> Company Customer Identity Hidden',
         ]
         check_detection(expected, test_file)
 
@@ -3441,7 +3441,7 @@ def test_copyright_regents_complex(self):
         ]
         check_detection(expected, test_file)
 
-    @expectedFailure
+    #@expectedFailure
     def test_copyright_regents_license(self):
         test_file = self.get_test_loc('copyrights/copyright_regents_license-LICENSE')
         expected = [
@@ -4072,24 +4072,14 @@ def test_copyright_rim(self):
         check_detection(expected, test_lines)
 
     def test_copyright_sinica(self):
-        test_lines = ['''
-            #  Copyright (c) 1999 Computer Systems and Communication Lab,
-            #                    Institute of Information Science, Academia Sinica.
-
-            some junk
-        ''']
-        expected = ['Copyright (c) 1999 Computer Systems']
-        check_detection(expected, test_lines)
-
-    @expectedFailure
-    def test_copyright_sinica_correct(self):
-        test_lines = ['''
+        test_lines = '''
             #  Copyright (c) 1999 Computer Systems and Communication Lab,
             #                    Institute of Information Science, Academia Sinica.
 
             some junk
-        ''']
+        '''.splitlines()
         expected = ['Copyright (c) 1999 Computer Systems and Communication Lab, Institute of Information Science, Academia Sinica.']
+
         check_detection(expected, test_lines)
 
     def test_copyright_copr1(self):
@@ -4203,3 +4193,29 @@ def test_copyright_word_in_html(self):
             u'Copyright (c) 2010 Nokia Corporation and/or its subsidiary(-ies)',
         ]
         check_detection(expected, test_lines)
+
+    def test_copyright_with_date_in_angle_brackets(self):
+        test_lines = '''
+         * Copyright (C) <2013>, GENIVI Alliance, Inc.
+         * Author: [email protected]
+        '''.splitlines(False)
+        expected = [
+            u'Copyright (c) <2013> , GENIVI Alliance, Inc.',
+        ]
+        check_detection(expected, test_lines, what='copyrights')
+        expected = [
+            u'[email protected]',
+        ]
+        check_detection(expected, test_lines, what='authors')
+
+    def test_copyright_with_zoo(self):
+        test_lines = '''
+             *  Download Upload Messaging Manager
+             *
+             *  Copyright (C) 2012-2013  Open-RnD Sp. z o.o. All rights reserved.
+             * @verbatim
+        '''.splitlines(False)
+        expected = [
+            u'Copyright (c) 2012-2013 Open-RnD Sp.',
+        ]
+        check_detection(expected, test_lines, what='copyrights')