def get_literal(character, is_case_insensitive):
if is_case_insensitive and not suppress_case_insensitive:
lowercase = character.lower()
uppercase = character.upper()
if lowercase != uppercase:
return Regex.Literal([(ord(lowercase), ord(lowercase)),
(ord(uppercase), ord(uppercase))])
return Regex.Literal([(ord(character), ord(character))])
def parse_character_class(self):
"""
Parse a character class ([...]) expression from the string at its current index.
@return: a Regex.Literal object representing the characters
"""
characters = self.parse_character_class_expression()
return Regex.Literal([i for i in characters])
def visit_literal(self, literal):
new_literal = Regex.Literal([])
new_literal.characters = literal.characters
self.stack.append(new_literal)
def parse_literal(self, suppress_case_insensitive=False):
"""
Parse a single character from the string, from its current index into a literal expression
@return: a Regex.Literal or Regex.LiteralExcept object representing the character.
"""
def get_literal(character, is_case_insensitive):
if is_case_insensitive and not suppress_case_insensitive:
lowercase = character.lower()
uppercase = character.upper()
if lowercase != uppercase:
return Regex.Literal([(ord(lowercase), ord(lowercase)),
(ord(uppercase), ord(uppercase))])
return Regex.Literal([(ord(character), ord(character))])
if self.get_next_if(u'.'):
return Regex.Literal([(1, 0x10FFFF)])
elif self.get_next_if(u'\\'):
if self.get_next_if(u'w'):
return Regex.Literal(
[Parser.lowercase, Parser.uppercase, Parser.underscore])
elif self.get_next_if(u'W'):
return Regex.LiteralExcept(
[Parser.lowercase, Parser.uppercase, Parser.underscore])
elif self.get_next_if(u'r'):
return Regex.Literal([Parser.carriage_return])
elif self.get_next_if(u'n'):
return Regex.Literal([Parser.line_feed])
elif self.get_next_if(u't'):
return Regex.Literal([Parser.tab])
elif self.get_next_if(u's'):
return Regex.Literal([Parser.space])
elif self.get_next_if(u'd'):
return Regex.Literal([Parser.digits])
elif self.get_next_if(u'v'):
return Regex.Literal([Parser.vertical_tab])
elif self.get_next_if(u'f'):
return Regex.Literal([Parser.form_feed])
elif self.get_next_if(u'x'):
codepoint = self.parse_hex_digits(2)
return Regex.Literal([(codepoint, codepoint)])
elif self.get_next_if(u'p'):
coverage = self.parse_unicode_expression()
return Regex.Literal(coverage)
elif self.get_next_if(u'N'):
coverage = self.parse_unicode_name()
return Regex.Literal(coverage)
elif self.get_next_if(u'P'):
coverage = self.parse_unicode_expression()
return Regex.LiteralExcept(coverage)
elif self.get_next_if(u'u'):
codepoint = self.parse_hex_digits(4)
return Regex.Literal([(codepoint, codepoint)])
elif self.get_next_if(u'U'):
codepoint = self.parse_hex_digits(6)
return Regex.Literal([(codepoint, codepoint)])
else:
return get_literal(self.get_next(), self.is_case_insensitive)
else:
character = self.get_next()
if character in Parser.closing:
raise RegexParserExpected("character", self.text,
self.index - 1)
elif character in Parser.special:
raise RegexParserInvalidCharacter(character)
return get_literal(character, self.is_case_insensitive)
