decodetree: Open files with encoding='utf-8'
When decodetree.py was added in commit 568ae7efae7, QEMU was
using Python 2 which happily reads UTF-8 files in text mode.
Python 3 requires either UTF-8 locale or an explicit encoding
passed to open(). Now that Python 3 is required, explicit
UTF-8 encoding for decodetree source files.
To avoid further problems with the user locale, also explicit
UTF-8 encoding for the generated C files.
Explicit both input/output are plain text by using the 't' mode.
This fixes:
$ /usr/bin/python3 scripts/decodetree.py test.decode
Traceback (most recent call last):
File "scripts/decodetree.py", line 1397, in <module>
main()
File "scripts/decodetree.py", line 1308, in main
parse_file(f, toppat)
File "scripts/decodetree.py", line 994, in parse_file
for line in f:
File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 80:
ordinal not in range(128)
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Suggested-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20210110000240.761122-1-f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
diff --git a/scripts/decodetree.py b/scripts/decodetree.py
index 47aa9ca..4637b63 100644
--- a/scripts/decodetree.py
+++ b/scripts/decodetree.py
@@ -20,6 +20,7 @@
# See the syntax and semantics in docs/devel/decodetree.rst.
#
+import io
import os
import re
import sys
@@ -1304,7 +1305,7 @@
for filename in args:
input_file = filename
- f = open(filename, 'r')
+ f = open(filename, 'rt', encoding='utf-8')
parse_file(f, toppat)
f.close()
@@ -1324,9 +1325,11 @@
prop_size(stree)
if output_file:
- output_fd = open(output_file, 'w')
+ output_fd = open(output_file, 'wt', encoding='utf-8')
else:
- output_fd = sys.stdout
+ output_fd = io.TextIOWrapper(sys.stdout.buffer,
+ encoding=sys.stdout.encoding,
+ errors="ignore")
output_autogen()
for n in sorted(arguments.keys()):
