scripts: add Python 3 compatibility to spdxcheck.py

"dict.has_key(key)" on dictionaries has been replaced with "key in
dict".  Additionally, when run under Python 3 some files don't decode
with the default encoding (tested with UTF-8).  To handle that, don't
open the file in text mode and decode text line-by-line, ignoring
encoding errors.

This remains compatible with Python 2 and should have no functional
change.

Link: http://lkml.kernel.org/r/20180717190635.29467-1-jcline@redhat.com
Signed-off-by: Jeremy Cline <jcline@redhat.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py
index a6041f2..839e190 100755 (executable)
--- a/scripts/spdxcheck.py
+++ b/scripts/spdxcheck.py
@@ -4,6 +4,7 @@
 
 from argparse import ArgumentParser
 from ply import lex, yacc
+import locale
 import traceback
 import sys
 import git
@@ -102,7 +103,7 @@ class id_parser(object):
                 raise ParserException(tok, 'Invalid License ID')
             self.lastid = id
         elif tok.type == 'EXC':
-            if not self.spdx.exceptions.has_key(id):
+            if id not in self.spdx.exceptions:
                 raise ParserException(tok, 'Invalid Exception ID')
             if self.lastid not in self.spdx.exceptions[id]:
                 raise ParserException(tok, 'Exception not valid for license %s' %self.lastid)
@@ -167,6 +168,7 @@ class id_parser(object):
         self.curline = 0
         try:
             for line in fd:
+                line = line.decode(locale.getpreferredencoding(False), errors='ignore')
                 self.curline += 1
                 if self.curline > maxlines:
                     break
@@ -201,7 +203,8 @@ def scan_git_tree(tree):
             continue
         if not os.path.isfile(el.path):
             continue
-        parser.parse_lines(open(el.path), args.maxlines, el.path)
+        with open(el.path, 'rb') as fd:
+            parser.parse_lines(fd, args.maxlines, el.path)
 
 def scan_git_subtree(tree, path):
     for p in path.strip('/').split('/'):