def smart_text(s, encoding='utf-8', strings_only=False, errors='strict'):
"""Returns a unicode object representing 's'. Treats bytes using the
'encoding' codec.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if isinstance(s, six.text_type):
return s
if strings_only and not isinstance(s, six.string_types):
return s
if not isinstance(s, six.string_types):
if hasattr(s, '__unicode__'):
s = s.__unicode__()
else:
if six.PY3:
if isinstance(s, six.binary_type):
s = six.text_type(s, encoding, errors)
else:
s = six.text_type(s)
else:
s = six.text_type(six.binary_type(s), encoding, errors)
else:
# Note: We use .decode() here, instead of six.text_type(s, encoding,
# errors), so that if s is a SafeBytes, it ends up being a
# SafeText at the end.
s = s.decode(encoding, errors)
return s
def format(self, data):
"""Use this method for formatting data"""
if self.lexer is None:
self.format_text(self.style.get(Token.Text), six.text_type(data))
else:
for token, text in self.lexer.tokenize(data):
self.format_text(self.style.get(token), text)
def lex(self, data):
text = u'%s\n' % six.text_type(data['object']).strip('\n\r')
status = data['status']
if status in self.config:
yield self.config[status], text
else:
yield Token.Failed, text
def lex(self, data):
# Merge statuses into config
if 'statuses' not in self.config:
self.config['statuses'] = HgLexer.config['statuses']
text = u'%s\n' % six.text_type(data['object']).strip('\n\r')
status = data['status']
if status in self.config['statuses']:
token = self.config['statuses'][status]
else:
token = Token.Failed
yield token, text
if token not in (Token.Ok, Token.NoChanges, Token.Changed):
error = data['data']['error'].strip()
if error:
yield Token.Text, indent(error) + '\n'
elif self.config.get('parse', False):
output = data['data']['output'].strip()
if output:
indent_size = self.config.get('indent', 2)
if 'parser' in self.config:
lexer = RegexLexer()
lexer.push_config(self.config['parser'])
for token, text in lexer.tokenize(indent(output, indent_size) + '\n'):
yield token, text
else:
yield Token.Text, indent(output) + '\n'
def lex(self, data):
# Merge statuses into config
if 'statuses' not in self.config:
self.config['statuses'] = HgLexer.config['statuses']
text = u'%s\n' % six.text_type(data['object']).strip('\n\r')
status = data['status']
if status in self.config['statuses']:
token = self.config['statuses'][status]
else:
token = Token.Failed
yield token, text
if token not in (Token.Ok, Token.NoChanges, Token.Changed):
error = data['data']['error'].strip()
if error:
yield Token.Text, indent(error) + '\n'
elif self.config.get('parse', False):
output = data['data']['output'].strip()
if output:
indent_size = self.config.get('indent', 2)
if 'parser' in self.config:
lexer = RegexLexer()
lexer.push_config(self.config['parser'])
for token, text in lexer.tokenize(indent(output, indent_size) + '\n'):
yield token, text
else:
yield Token.Text, indent(output) + '\n'
def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'):
"""Returns a bytes version of 's', encoded as specified in 'encoding'.
If strings_only is True, don't convert (some) non-string-like objects.
"""
if isinstance(s, six.binary_type):
if encoding == 'utf-8':
return s
else:
return s.decode('utf-8', errors).encode(encoding, errors)
if strings_only and not isinstance(s, six.text_type):
return s
if not isinstance(s, six.string_types):
try:
if six.PY3:
return six.text_type(s).encode(encoding)
else:
return six.binary_type(s)
except UnicodeEncodeError:
return six.text_type(s).encode(encoding, errors)
else:
return s.encode(encoding, errors)
