Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

🐛 The CLI no longer raise an unexpected exception when no encoding has been found #70

Merged
merged 2 commits into from
Jul 23, 2021
Merged

🐛 The CLI no longer raise an unexpected exception when no encoding has been found #70

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
362f3b1
:bug: The CLI no longer raise an unexpected exception when no encodin…
Ousret Jul 23, 2021
5c6b723
:fire: Remove unused import "sep"
Ousret Jul 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
147 changes: 80 additions & 67 deletions charset_normalizer/cli/normalizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,85 +101,98 @@ def cli_detect(argv=None):
explain=args.verbose
)

x_ = []

if len(matches) == 0:
print('Unable to identify originating encoding for "{}". {}'.format(my_file.name, 'Maybe try increasing maximum amount of chaos.' if args.threshold < 1. else ''), file=sys.stderr)
if my_file.closed is False:
my_file.close()
continue

x_ = []
x_.append(
CliDetectionResult(
abspath(my_file.name),
None,
[],
[],
"Unknown",
[],
False,
1.,
0.,
None,
True
)
)
else:

r_ = matches.best()
p_ = r_.first()

x_.append(
CliDetectionResult(
abspath(my_file.name),
p_.encoding,
p_.encoding_aliases,
[cp for cp in p_.could_be_from_charset if cp != p_.encoding],
p_.language,
p_.alphabets,
p_.bom,
p_.percent_chaos,
p_.percent_coherence,
None,
True
r_ = matches.best()
p_ = r_.first()

x_.append(
CliDetectionResult(
abspath(my_file.name),
p_.encoding,
p_.encoding_aliases,
[cp for cp in p_.could_be_from_charset if cp != p_.encoding],
p_.language,
p_.alphabets,
p_.bom,
p_.percent_chaos,
p_.percent_coherence,
None,
True
)
)
)

if len(matches) > 1 and args.alternatives:
for el in matches:
if el != p_:
x_.append(
CliDetectionResult(
abspath(my_file.name),
el.encoding,
el.encoding_aliases,
[cp for cp in el.could_be_from_charset if cp != el.encoding],
el.language,
el.alphabets,
el.bom,
el.percent_chaos,
el.percent_coherence,
None,
False
if len(matches) > 1 and args.alternatives:
for el in matches:
if el != p_:
x_.append(
CliDetectionResult(
abspath(my_file.name),
el.encoding,
el.encoding_aliases,
[cp for cp in el.could_be_from_charset if cp != el.encoding],
el.language,
el.alphabets,
el.bom,
el.percent_chaos,
el.percent_coherence,
None,
False
)
)
)

if args.normalize is True:

if p_.encoding.startswith('utf') is True:
print('"{}" file does not need to be normalized, as it already came from unicode.'.format(my_file.name), file=sys.stderr)
if my_file.closed is False:
my_file.close()
continue
if args.normalize is True:

o_ = my_file.name.split('.') # type: list[str]

if args.replace is False:
o_.insert(-1, p_.encoding)
if my_file.closed is False:
my_file.close()
else:
if args.force is False and query_yes_no(
'Are you sure to normalize "{}" by replacing it ?'.format(my_file.name), 'no') is False:
if p_.encoding.startswith('utf') is True:
print('"{}" file does not need to be normalized, as it already came from unicode.'.format(my_file.name), file=sys.stderr)
if my_file.closed is False:
my_file.close()
continue

try:
x_[0].unicode_path = './{}'.format('.'.join(o_))

with open(x_[0].unicode_path, 'w', encoding='utf-8') as fp:
fp.write(
str(p_)
)
except IOError as e:
print(str(e), file=sys.stderr)
if my_file.closed is False:
my_file.close()
return 2
o_ = my_file.name.split('.') # type: list[str]

if args.replace is False:
o_.insert(-1, p_.encoding)
if my_file.closed is False:
my_file.close()
else:
if args.force is False and query_yes_no(
'Are you sure to normalize "{}" by replacing it ?'.format(my_file.name), 'no') is False:
if my_file.closed is False:
my_file.close()
continue

try:
x_[0].unicode_path = abspath('./{}'.format('.'.join(o_)))

with open(x_[0].unicode_path, 'w', encoding='utf-8') as fp:
fp.write(
str(p_)
)
except IOError as e:
print(str(e), file=sys.stderr)
if my_file.closed is False:
my_file.close()
return 2

if my_file.closed is False:
my_file.close()
Expand Down