def _FormatMessage(item, lang):
"""Format a single <message> element."""
message = item.ws_at_start + item.Translate(lang) + item.ws_at_end
# Output message with non-ascii chars escaped as octal numbers C's grammar
# allows escaped hexadecimal numbers to be infinite, but octal is always of
# the form \OOO. Python 3 doesn't support string-escape, so we have to jump
# through some hoops here via codecs.escape_encode.
# This basically does:
# - message - the starting string
# - message.encode(...) - convert to bytes
# - codecs.escape_encode(...) - convert non-ASCII bytes to \x## escapes
# - (...).decode() - convert bytes back to a string
message = codecs.escape_encode(message.encode('utf-8'))[0].decode('utf-8')
# an escaped char is (\xHH)+ but only if the initial
# backslash is not escaped.
not_a_backslash = r"(^|[^\\])" # beginning of line or a non-backslash char
escaped_backslashes = not_a_backslash + r"(\\\\)*"
hex_digits = r"((\\x)[0-9a-f]{2})+"
two_digit_hex_num = re.compile(r"(?P<escaped_backslashes>%s)(?P<hex>%s)" %
(escaped_backslashes, hex_digits))
message = two_digit_hex_num.sub(_HexToOct, message)
# unescape \ (convert \\ back to \)
message = message.replace('\\\\', '\\')
message = message.replace('"', '\\"')
message = util.LINEBREAKS.sub(r'\\n', message)
name_attr = item.GetTextualIds()[0]
return '\n case %s:\n return "%s";' % (name_attr, message)
def _FormatMessage(item, lang):
"""Format a single <message> element."""
message = item.ws_at_start + item.Translate(lang) + item.ws_at_end
# output message with non-ascii chars escaped as octal numbers
# C's grammar allows escaped hexadecimal numbers to be infinite,
# but octal is always of the form \OOO
message = message.encode('utf-8').encode('string_escape')
# an escaped char is (\xHH)+ but only if the initial
# backslash is not escaped.
not_a_backslash = r"(^|[^\\])" # beginning of line or a non-backslash char
escaped_backslashes = not_a_backslash + r"(\\\\)*"
hex_digits = r"((\\x)[0-9a-f]{2})+"
two_digit_hex_num = re.compile(
r"(?P<escaped_backslashes>%s)(?P<hex>%s)"
% (escaped_backslashes, hex_digits))
message = two_digit_hex_num.sub(_HexToOct, message)
# unescape \ (convert \\ back to \)
message = message.replace('\\\\', '\\')
message = message.replace('"', '\\"')
message = util.LINEBREAKS.sub(r'\\n', message)
name_attr = item.GetTextualIds()[0]
return '\n case %s:\n return "%s";' % (name_attr, message)
def _FormatMessage(item, lang):
"""Format a single <message> element."""
message = item.ws_at_start + item.Translate(lang) + item.ws_at_end
# output message with non-ascii chars escaped as octal numbers
# C's grammar allows escaped hexadecimal numbers to be infinite,
# but octal is always of the form \OOO
message = message.encode('utf-8').encode('string_escape')
# an escaped char is (\xHH)+ but only if the initial
# backslash is not escaped.
not_a_backslash = r"(^|[^\\])" # beginning of line or a non-backslash char
escaped_backslashes = not_a_backslash + r"(\\\\)*"
hex_digits = r"((\\x)[0-9a-f]{2})+"
two_digit_hex_num = re.compile(
r"(?P<escaped_backslashes>%s)(?P<hex>%s)"
% (escaped_backslashes, hex_digits))
message = two_digit_hex_num.sub(_HexToOct, message)
# unescape \ (convert \\ back to \)
message = message.replace('\\\\', '\\')
message = message.replace('"', '\\"')
message = util.LINEBREAKS.sub(r'\\n', message)
name_attr = item.GetTextualIds()[0]
return '\n case %s:\n return "%s";' % (name_attr, message)