Matthias Maier <tam...@43-1.org> writes: > This is a different approach to fix the locale dependent encode/decode > problem in common.py utilizing the binary read/write mode [1,2] and > decode/encode with explicit UTF-8 encoding arguments [3].
Why can't we simply pass encoding='utf-8' to open()? > This approach is preferred over the fix in commit d4e5ec877ca because it > is (a) locale independent, and (b) does not depend on the en_US.UTF_8 > locale to be available. > > [1] https://docs.python.org/3.6/library/stdtypes.html#bytes.decode > [2] https://docs.python.org/3.6/library/stdtypes.html#str.encode > [3] https://docs.python.org/3/howto/unicode.html > > Signed-off-by: Arfrever Frehtes Taifersar Arahesis <arfrever....@gmail.com> > Signed-off-by: Matthias Maier <tam...@43-1.org> > --- > scripts/qapi/common.py | 11 ++++++++--- > 1 file changed, 8 insertions(+), 3 deletions(-) > > diff --git a/scripts/qapi/common.py b/scripts/qapi/common.py > index 2462fc0291..44270cd703 100644 > --- a/scripts/qapi/common.py > +++ b/scripts/qapi/common.py > @@ -16,6 +16,7 @@ import errno > import os > import re > import string > +import sys > from collections import OrderedDict > > builtin_types = { > @@ -259,6 +260,8 @@ class QAPISchemaParser(object): > previously_included.append(os.path.abspath(fp.name)) > self.incl_info = incl_info > self.src = fp.read() > + if sys.version_info[0] >= 3: > + self.src = self.src.decode("UTF-8") If I understand 7.2.3. Standard Encodings[*] correctly, the canonical name is "utf-8". Let's use that. Wait, it's the default, no need to pass an argument. > if self.src == '' or self.src[-1] != '\n': > self.src += '\n' > self.cursor = 0 > @@ -340,7 +343,7 @@ class QAPISchemaParser(object): > return None > > try: > - fobj = open(incl_fname, 'r') > + fobj = open(incl_fname, 'rb') > except IOError as e: > raise QAPISemError(info, '%s: %s' % (e.strerror, incl_fname)) > return QAPISchemaParser(fobj, previously_included, info) > @@ -1492,7 +1495,7 @@ class QAPISchemaEvent(QAPISchemaEntity): > class QAPISchema(object): > def __init__(self, fname): > self._fname = fname > - parser = QAPISchemaParser(open(fname, 'r')) > + parser = QAPISchemaParser(open(fname, 'rb')) > exprs = check_exprs(parser.exprs) > self.docs = parser.docs > self._entity_list = [] > @@ -2006,9 +2009,11 @@ class QAPIGen(object): > if e.errno != errno.EEXIST: > raise > fd = os.open(pathname, os.O_RDWR | os.O_CREAT, 0o666) > - f = os.fdopen(fd, 'r+') > + f = os.fdopen(fd, 'r+b') > text = (self._top(fname) + self._preamble + self._body > + self._bottom(fname)) > + if sys.version_info[0] >= 3: > + text = text.encode("UTF-8") Likewise. > oldtext = f.read(len(text) + 1) > if text != oldtext: > f.seek(0) [*] https://docs.python.org/3/library/codecs.html#standard-encodings
