def __snap_repetition_range(the_state_machine, stream):
"""Snaps a string that represents a repetition range. The following
syntaxes are supported:
'?' one or none repetition
'+' one or arbitrary repetition
'*' arbitrary repetition (even zero)
'{n}' exactly 'n' repetitions
'{m,n}' from 'm' to 'n' repetitions
'{n,}' arbitrary, but at least 'n' repetitions
"""
assert the_state_machine.__class__.__name__ == "StateMachine", \
"received object of type '%s'" % the_state_machine.__class__.__name__ + "\n" + \
repr(the_state_machine)
position_0 = stream.tell()
x = stream.read(1)
if x == "+": result = repeat.do(the_state_machine, 1)
elif x == "*": result = repeat.do(the_state_machine)
elif x == "?": result = repeat.do(the_state_machine, 0, 1)
elif x == "{":
repetition_range_str = __snap_until(stream, "}")
if len(repetition_range_str) and not repetition_range_str[0].isdigit():
# no repetition range, so everything remains as it is
stream.seek(position_0)
return the_state_machine
try:
if repetition_range_str.find(",") == -1:
# no ',' thus "match exactly a certain number":
# e.g. {4} = match exactly four repetitions
number = int(repetition_range_str)
result = repeat.do(the_state_machine, number, number)
return result
# a range of numbers is given
fields = repetition_range_str.split(",")
fields = map(lambda x: x.strip(), fields)
number_1 = int(fields[0].strip())
if fields[1] == "": number_2 = -1 # e.g. {2,}
else: number_2 = int(fields[1].strip()) # e.g. {2,5}
# produce repeated state machine
result = repeat.do(the_state_machine, number_1, number_2)
return result
except:
raise RegularExpressionException("error while parsing repetition range expression '%s'" \
% repetition_range_str)
else:
# no repetition range, so everything remains as it is
stream.seek(position_0)
return the_state_machine
return result
def __snap_repetition_range(the_state_machine, stream):
"""Snaps a string that represents a repetition range. The following
syntaxes are supported:
'?' one or none repetition
'+' one or arbitrary repetition
'*' arbitrary repetition (even zero)
'{n}' exactly 'n' repetitions
'{m,n}' from 'm' to 'n' repetitions
'{n,}' arbitrary, but at least 'n' repetitions
"""
assert the_state_machine.__class__.__name__ == "StateMachine", \
"received object of type '%s'" % the_state_machine.__class__.__name__ + "\n" + \
repr(the_state_machine)
position_0 = stream.tell()
x = stream.read(1)
if x == "+": result = repeat.do(the_state_machine, 1)
elif x == "*": result = repeat.do(the_state_machine)
elif x == "?": result = repeat.do(the_state_machine, 0, 1)
elif x == "{":
repetition_range_str = __snap_until(stream, "}")
if len(repetition_range_str) and not repetition_range_str[0].isdigit():
# no repetition range, so everything remains as it is
stream.seek(position_0)
return the_state_machine
try:
if repetition_range_str.find(",") == -1:
# no ',' thus "match exactly a certain number":
# e.g. {4} = match exactly four repetitions
number = int(repetition_range_str)
result = repeat.do(the_state_machine, number, number)
return result
# a range of numbers is given
fields = repetition_range_str.split(",")
fields = map(lambda x: x.strip(), fields)
number_1 = int(fields[0].strip())
if fields[1] == "": number_2 = -1 # e.g. {2,}
else: number_2 = int(fields[1].strip()) # e.g. {2,5}
# produce repeated state machine
result = repeat.do(the_state_machine, number_1, number_2)
return result
except:
raise RegularExpressionException("error while parsing repetition range expression '%s'" \
% repetition_range_str)
else:
# no repetition range, so everything remains as it is
stream.seek(position_0)
return the_state_machine
return result
def do(SM_A, SM_B):
"""\NotIn{P Q} = \NotBegin{P \Any*(Q+)}
"""
all_star = repeat.do(special.get_any(), min_repetition_n=0)
sm_b_repeated = repeat.do(SM_B, min_repetition_n=1)
tmp = sequentialize.do([all_star, sm_b_repeated],
MountToFirstStateMachineF=True,
CloneRemainingStateMachinesF=True)
tmp = beautifier.do(tmp)
# There might be many paths which have no hope to reach acceptance
tmp.clean_up()
return complement_begin.do(SM_A, tmp)
def do(SM_A, SM_B):
"""\NotIn{P Q} = \NotBegin{P \Any*(Q+)}
"""
all_star = repeat.do(special.get_any(), min_repetition_n=0)
sm_b_repeated = repeat.do(SM_B, min_repetition_n=1)
tmp = sequentialize.do([all_star, sm_b_repeated],
MountToFirstStateMachineF=True,
CloneRemainingStateMachinesF=True)
tmp = beautifier.do(tmp)
# There might be many paths which have no hope to reach acceptance
tmp.clean_up()
return complement_begin.do(SM_A, tmp)
def __parse_option(fh, new_mode):
def get_pattern_object(SM):
if not SM.is_DFA_compliant(): result = nfa_to_dfa.do(SM)
else: result = SM
result = hopcroft.do(result, CreateNewStateMachineF=False)
return Pattern(result, AllowStateMachineTrafoF=True)
identifier = read_option_start(fh)
if identifier is None: return False
verify_word_in_list(identifier, mode_option_info_db.keys(),
"mode option", fh.name, get_current_line_info_number(fh))
if identifier == "skip":
# A skipper 'eats' characters at the beginning of a pattern that belong
# to a specified set of characters. A useful application is most probably
# the whitespace skipper '[ \t\n]'. The skipper definition allows quex to
# implement a very effective way to skip these regions.
pattern_str, trigger_set = regular_expression.parse_character_set(fh, PatternStringF=True)
skip_whitespace(fh)
if fh.read(1) != ">":
error_msg("missing closing '>' for mode option '%s'." % identifier, fh)
if trigger_set.is_empty():
error_msg("Empty trigger set for skipper." % identifier, fh)
# TriggerSet skipping is implemented the following way: As soon as one element of the
# trigger set appears, the state machine enters the 'trigger set skipper section'.
# Enter the skipper as if the opener pattern was a normal pattern and the 'skipper' is the action.
# NOTE: The correspondent CodeFragment for skipping is created in 'implement_skippers(...)'
pattern_sm = StateMachine()
pattern_sm.add_transition(pattern_sm.init_state_index, trigger_set, AcceptanceF=True)
# Skipper code is to be generated later
action = GeneratedCode(skip_character_set.do,
FileName = fh.name,
LineN = get_current_line_info_number(fh))
action.data["character_set"] = trigger_set
new_mode.add_match(pattern_str, action, get_pattern_object(pattern_sm),
Comment=E_SpecialPatterns.SKIP)
return True
elif identifier in ["skip_range", "skip_nested_range"]:
# A non-nesting skipper can contain a full fledged regular expression as opener,
# since it only effects the trigger. Not so the nested range skipper-see below.
# -- opener
skip_whitespace(fh)
if identifier == "skip_nested_range":
# Nested range state machines only accept 'strings' not state machines
opener_str, opener_sequence = __parse_string(fh, "Opener pattern for 'skip_nested_range'")
opener_sm = StateMachine.from_sequence(opener_sequence)
else:
opener_str, opener_pattern = regular_expression.parse(fh)
opener_sm = opener_pattern.sm
# For 'range skipping' the opener sequence is not needed, only the opener state
# machine is webbed into the pattern matching state machine.
opener_sequence = None
skip_whitespace(fh)
# -- closer
closer_str, closer_sequence = __parse_string(fh, "Closing pattern for 'skip_range' or 'skip_nested_range'")
skip_whitespace(fh)
if fh.read(1) != ">":
error_msg("missing closing '>' for mode option '%s'" % identifier, fh)
# Skipper code is to be generated later
generator_function, comment = {
"skip_range": (skip_range.do, E_SpecialPatterns.SKIP_RANGE),
"skip_nested_range": (skip_nested_range.do, E_SpecialPatterns.SKIP_NESTED_RANGE),
}[identifier]
action = GeneratedCode(generator_function,
FileName = fh.name,
LineN = get_current_line_info_number(fh))
action.data["opener_sequence"] = opener_sequence
action.data["closer_sequence"] = closer_sequence
action.data["mode_name"] = new_mode.name
new_mode.add_match(opener_str, action, get_pattern_object(opener_sm), Comment=comment)
return True
elif identifier == "indentation":
value = indentation_setup.do(fh)
# Enter 'Newline' and 'Suppressed Newline' as matches into the engine.
# Similar to skippers, the indentation count is then triggered by the newline.
# -- Suppressed Newline = Suppressor followed by Newline,
# then newline does not trigger indentation counting.
suppressed_newline_pattern_str = ""
if value.newline_suppressor_state_machine.get() is not None:
suppressed_newline_pattern_str = \
"(" + value.newline_suppressor_state_machine.pattern_string() + ")" \
+ "(" + value.newline_state_machine.pattern_string() + ")"
suppressed_newline_sm = \
sequentialize.do([value.newline_suppressor_state_machine.get(),
value.newline_state_machine.get()])
FileName = value.newline_suppressor_state_machine.file_name
LineN = value.newline_suppressor_state_machine.line_n
# Go back to start.
code = UserCodeFragment("goto %s;" % get_label("$start", U=True), FileName, LineN)
new_mode.add_match(suppressed_newline_pattern_str, code,
get_pattern_object(suppressed_newline_sm),
Comment=E_SpecialPatterns.SUPPRESSED_INDENTATION_NEWLINE)
# When there is an empty line, then there shall be no indentation count on it.
# Here comes the trick:
#
# Let newline
# be defined as: newline ([space]* newline])*
#
# This way empty lines are eating away before the indentation count is activated.
# -- 'space'
x0 = StateMachine()
x0.add_transition(x0.init_state_index, value.indentation_count_character_set(),
AcceptanceF=True)
# -- '[space]*'
x1 = repeat.do(x0)
# -- '[space]* newline'
x2 = sequentialize.do([x1, value.newline_state_machine.get()])
# -- '([space]* newline)*'
x3 = repeat.do(x2)
# -- 'newline ([space]* newline)*'
x4 = sequentialize.do([value.newline_state_machine.get(), x3])
# -- nfa to dfa; hopcroft optimization
sm = beautifier.do(x4)
FileName = value.newline_state_machine.file_name
LineN = value.newline_state_machine.line_n
action = GeneratedCode(indentation_counter.do, FileName, LineN)
action.data["indentation_setup"] = value
new_mode.add_match(value.newline_state_machine.pattern_string(), action,
get_pattern_object(sm),
Comment=E_SpecialPatterns.INDENTATION_NEWLINE)
# Announce the mode to which the setup belongs
value.set_containing_mode_name(new_mode.name)
else:
value = read_option_value(fh)
# The 'verify_word_in_list()' call must have ensured that the following holds
assert mode_option_info_db.has_key(identifier)
# Is the option of the appropriate value?
option_info = mode_option_info_db[identifier]
if option_info.domain is not None and value not in option_info.domain:
error_msg("Tried to set value '%s' for option '%s'. " % (value, identifier) + \
"Though, possible for this option are only: %s." % repr(option_info.domain)[1:-1], fh)
# Finally, set the option
new_mode.add_option(identifier, value)
return True
def __parse_option(fh, new_mode):
def get_pattern_object(SM):
if not SM.is_DFA_compliant(): result = nfa_to_dfa.do(SM)
else: result = SM
result = hopcroft.do(result, CreateNewStateMachineF=False)
return Pattern(result, AllowStateMachineTrafoF=True)
identifier = read_option_start(fh)
if identifier is None: return False
verify_word_in_list(identifier, mode_option_info_db.keys(), "mode option",
fh.name, get_current_line_info_number(fh))
if identifier == "skip":
# A skipper 'eats' characters at the beginning of a pattern that belong
# to a specified set of characters. A useful application is most probably
# the whitespace skipper '[ \t\n]'. The skipper definition allows quex to
# implement a very effective way to skip these regions.
pattern_str, trigger_set = regular_expression.parse_character_set(
fh, PatternStringF=True)
skip_whitespace(fh)
if fh.read(1) != ">":
error_msg("missing closing '>' for mode option '%s'." % identifier,
fh)
if trigger_set.is_empty():
error_msg("Empty trigger set for skipper." % identifier, fh)
# TriggerSet skipping is implemented the following way: As soon as one element of the
# trigger set appears, the state machine enters the 'trigger set skipper section'.
# Enter the skipper as if the opener pattern was a normal pattern and the 'skipper' is the action.
# NOTE: The correspondent CodeFragment for skipping is created in 'implement_skippers(...)'
pattern_sm = StateMachine()
pattern_sm.add_transition(pattern_sm.init_state_index,
trigger_set,
AcceptanceF=True)
# Skipper code is to be generated later
action = GeneratedCode(skip_character_set.do,
FileName=fh.name,
LineN=get_current_line_info_number(fh))
action.data["character_set"] = trigger_set
new_mode.add_match(pattern_str,
action,
get_pattern_object(pattern_sm),
Comment=E_SpecialPatterns.SKIP)
return True
elif identifier in ["skip_range", "skip_nested_range"]:
# A non-nesting skipper can contain a full fledged regular expression as opener,
# since it only effects the trigger. Not so the nested range skipper-see below.
# -- opener
skip_whitespace(fh)
if identifier == "skip_nested_range":
# Nested range state machines only accept 'strings' not state machines
opener_str, opener_sequence = __parse_string(
fh, "Opener pattern for 'skip_nested_range'")
opener_sm = StateMachine.from_sequence(opener_sequence)
else:
opener_str, opener_pattern = regular_expression.parse(fh)
opener_sm = opener_pattern.sm
# For 'range skipping' the opener sequence is not needed, only the opener state
# machine is webbed into the pattern matching state machine.
opener_sequence = None
skip_whitespace(fh)
# -- closer
closer_str, closer_sequence = __parse_string(
fh, "Closing pattern for 'skip_range' or 'skip_nested_range'")
skip_whitespace(fh)
if fh.read(1) != ">":
error_msg("missing closing '>' for mode option '%s'" % identifier,
fh)
# Skipper code is to be generated later
generator_function, comment = {
"skip_range": (skip_range.do, E_SpecialPatterns.SKIP_RANGE),
"skip_nested_range":
(skip_nested_range.do, E_SpecialPatterns.SKIP_NESTED_RANGE),
}[identifier]
action = GeneratedCode(generator_function,
FileName=fh.name,
LineN=get_current_line_info_number(fh))
action.data["opener_sequence"] = opener_sequence
action.data["closer_sequence"] = closer_sequence
action.data["mode_name"] = new_mode.name
new_mode.add_match(opener_str,
action,
get_pattern_object(opener_sm),
Comment=comment)
return True
elif identifier == "indentation":
value = indentation_setup.do(fh)
# Enter 'Newline' and 'Suppressed Newline' as matches into the engine.
# Similar to skippers, the indentation count is then triggered by the newline.
# -- Suppressed Newline = Suppressor followed by Newline,
# then newline does not trigger indentation counting.
suppressed_newline_pattern_str = ""
if value.newline_suppressor_state_machine.get() is not None:
suppressed_newline_pattern_str = \
"(" + value.newline_suppressor_state_machine.pattern_string() + ")" \
+ "(" + value.newline_state_machine.pattern_string() + ")"
suppressed_newline_sm = \
sequentialize.do([value.newline_suppressor_state_machine.get(),
value.newline_state_machine.get()])
FileName = value.newline_suppressor_state_machine.file_name
LineN = value.newline_suppressor_state_machine.line_n
# Go back to start.
code = UserCodeFragment("goto %s;" % get_label("$start", U=True),
FileName, LineN)
new_mode.add_match(
suppressed_newline_pattern_str,
code,
get_pattern_object(suppressed_newline_sm),
Comment=E_SpecialPatterns.SUPPRESSED_INDENTATION_NEWLINE)
# When there is an empty line, then there shall be no indentation count on it.
# Here comes the trick:
#
# Let newline
# be defined as: newline ([space]* newline])*
#
# This way empty lines are eating away before the indentation count is activated.
# -- 'space'
x0 = StateMachine()
x0.add_transition(x0.init_state_index,
value.indentation_count_character_set(),
AcceptanceF=True)
# -- '[space]*'
x1 = repeat.do(x0)
# -- '[space]* newline'
x2 = sequentialize.do([x1, value.newline_state_machine.get()])
# -- '([space]* newline)*'
x3 = repeat.do(x2)
# -- 'newline ([space]* newline)*'
x4 = sequentialize.do([value.newline_state_machine.get(), x3])
# -- nfa to dfa; hopcroft optimization
sm = beautifier.do(x4)
FileName = value.newline_state_machine.file_name
LineN = value.newline_state_machine.line_n
action = GeneratedCode(indentation_counter.do, FileName, LineN)
action.data["indentation_setup"] = value
new_mode.add_match(value.newline_state_machine.pattern_string(),
action,
get_pattern_object(sm),
Comment=E_SpecialPatterns.INDENTATION_NEWLINE)
# Announce the mode to which the setup belongs
value.set_containing_mode_name(new_mode.name)
else:
value = read_option_value(fh)
# The 'verify_word_in_list()' call must have ensured that the following holds
assert mode_option_info_db.has_key(identifier)
# Is the option of the appropriate value?
option_info = mode_option_info_db[identifier]
if option_info.domain is not None and value not in option_info.domain:
error_msg("Tried to set value '%s' for option '%s'. " % (value, identifier) + \
"Though, possible for this option are only: %s." % repr(option_info.domain)[1:-1], fh)
# Finally, set the option
new_mode.add_option(identifier, value)
return True