tools/asn2wrs.py: handle windows-1252 encoding

The RRC ASN.1 definitions resulted in a decode error in Python because
the file is encoded as windows-1252 instead of UTF-8. This patch makes
the tool more forgiving in handling windows-1252 encodings.

Tested with Python 2.6.9, 2.7.10, 3.4.3.

Change-Id: I9c9269e1065c98b8bcfb57ab4bfd21d5e183a656
Reviewed-on: https://code.wireshark.org/review/9133
Reviewed-by: Pascal Quantin <pascal.quantin@gmail.com>
Reviewed-by: Peter Wu <peter@lekensteyn.nl>

1 files changed, 12 insertions, 3 deletions

diff --git a/tools/asn2wrs.py b/tools/asn2wrs.py
index 55bb537953..a319961084 100755
--- a/tools/asn2wrs.py
+++ b/tools/asn2wrs.py
@@ -7977,9 +7977,18 @@ def eth_main():
         input_file = fn
         lexer.lineno = 1
         if (ectx.srcdir): fn = ectx.srcdir + '/' + fn
-        f = open (fn, "r")
-        ast.extend(yacc.parse(f.read(), lexer=lexer, debug=pd))
-        f.close ()
+        # Read ASN.1 definition, trying one of the common encodings.
+        data = open(fn, "rb").read()
+        for encoding in ('utf-8', 'windows-1252'):
+            try:
+                data = data.decode(encoding)
+                break
+            except:
+                warnings.warn_explicit("Decoding %s as %s failed, trying next." % (fn, encoding), UserWarning, '', 0)
+        # Py2 compat, name.translate in eth_output_hf_arr fails with unicode
+        if not isinstance(data, str):
+            data = data.encode('utf-8')
+        ast.extend(yacc.parse(data, lexer=lexer, debug=pd))
     ectx.eth_clean()
     if (ectx.merge_modules):  # common output for all module
         ectx.eth_clean()