def get_utf8_string(self):
#_____________________________________________________________________________
assert self.begin <= self.end
if self.begin == self.end:
return "''"
elif self.end - self.begin == 1:
return utf8.unicode_to_pretty_utf8(self.begin)
else:
if self.end == -sys.maxint: end_char = "-oo"
elif self.end == sys.maxint: end_char = "oo"
else: end_char = utf8.unicode_to_pretty_utf8(self.end-1)
return "[" + utf8.unicode_to_pretty_utf8(self.begin) + ", " + end_char + "]"
def get_utf8_string(self):
#_____________________________________________________________________________
assert self.begin <= self.end
if self.begin == self.end:
return "''"
elif self.end - self.begin == 1:
return utf8.unicode_to_pretty_utf8(self.begin)
else:
if self.end == -sys.maxint: end_char = "-oo"
elif self.end == sys.maxint: end_char = "oo"
else: end_char = utf8.unicode_to_pretty_utf8(self.end - 1)
return "[" + utf8.unicode_to_pretty_utf8(
self.begin) + ", " + end_char + "]"
def get_on_skip_range_open(Mode, CloserSequence):
"""For unit tests 'Mode' may actually be a string, so that we do not
have to generate a whole mode just to get the 'on_skip_range_open'
code fragment.
"""
if Mode is None: return ""
txt = ""
if type(Mode) in [str, unicode]:
txt += Mode
elif not Mode.has_code_fragment_list("on_skip_range_open"):
txt += 'QUEX_ERROR_EXIT("\\nLexical analyzer mode \'%s\':\\n"\n' % Mode.name + \
' "End of file occurred before closing skip range delimiter!\\n"' + \
' "The \'on_skip_range_open\' handler has not been specified.");'
else:
closer_string = ""
for letter in CloserSequence:
closer_string += utf8.unicode_to_pretty_utf8(letter).replace(
"'", "")
code, eol_f = action_preparation.get_code(
Mode.get_code_fragment_list("on_skip_range_open"))
txt += "#define Closer \"%s\"\n" % closer_string
txt += code
txt += "#undef Closer\n"
txt += "RETURN;\n"
return txt
def get_character_sequence(Sequence):
txt = ""
comment_txt = ""
for letter in Sequence:
comment_txt += "%s, " % utf8.unicode_to_pretty_utf8(letter)
txt += "0x%X, " % letter
return txt, comment_txt
def get_character_sequence(Sequence):
txt = ""
comment_txt = ""
for letter in Sequence:
comment_txt += "%s, " % utf8.unicode_to_pretty_utf8(letter)
txt += "0x%X, " % letter
return txt, comment_txt
def get_string(self, Option="", Delimiter=", "):
assert Option in ("hex", "dec", "utf8", "")
assert self.end >= self.begin
if Option == "hex": __repr = lambda x: "%04X" % x
elif Option == "utf8": __repr = lambda x: utf8.unicode_to_pretty_utf8(x)
else: __repr = repr
if self.begin == self.end: return "[]"
elif self.end - self.begin == 1: return "[" + __repr(self.begin) + "]"
else: return "[" + __repr(self.begin) + Delimiter + __repr(self.end-1) + "]"
def get_string(self, Option="", Delimiter=", "):
assert Option in ("hex", "dec", "utf8", "")
assert self.end >= self.begin
if Option == "hex": __repr = lambda x: "%04X" % x
elif Option == "utf8":
__repr = lambda x: utf8.unicode_to_pretty_utf8(x)
else:
__repr = repr
if self.begin == self.end: return "[]"
elif self.end - self.begin == 1: return "[" + __repr(self.begin) + "]"
else:
return "[" + __repr(
self.begin) + Delimiter + __repr(self.end - 1) + "]"
