return 'ast.PLex.Section1.Options.BoolOption({0:s})'.format(', '.join(params))
# GENERATE END
+ class Caseless(BoolOption):
+ # GENERATE ELEMENT() BEGIN
+ def __init__(
+ self,
+ tag = 'PLex_Section1_Options_Caseless',
+ attrib = {},
+ text = '',
+ children = [],
+ value = False
+ ):
+ PLex.Section1.Options.BoolOption.__init__(
+ self,
+ tag,
+ attrib,
+ text,
+ children,
+ value
+ )
+ def copy(self, factory = None):
+ result = PLex.Section1.Options.BoolOption.copy(
+ self,
+ Caseless if factory is None else factory
+ )
+ return result
+ def __repr__(self):
+ params = []
+ self.repr_serialize(params)
+ return 'ast.PLex.Section1.Options.Caseless({0:s})'.format(', '.join(params))
+ # GENERATE END
+ def post_process(self, section):
+ section.caseless = self.value
+
+ class Default(BoolOption):
+ # GENERATE ELEMENT() BEGIN
+ def __init__(
+ self,
+ tag = 'PLex_Section1_Options_Default',
+ attrib = {},
+ text = '',
+ children = [],
+ value = False
+ ):
+ PLex.Section1.Options.BoolOption.__init__(
+ self,
+ tag,
+ attrib,
+ text,
+ children,
+ value
+ )
+ def copy(self, factory = None):
+ result = PLex.Section1.Options.BoolOption.copy(
+ self,
+ Default if factory is None else factory
+ )
+ return result
+ def __repr__(self):
+ params = []
+ self.repr_serialize(params)
+ return 'ast.PLex.Section1.Options.Default({0:s})'.format(', '.join(params))
+ # GENERATE END
+ def post_process(self, section):
+ section.default = self.value
+
class ECS(BoolOption):
# GENERATE ELEMENT() BEGIN
def __init__(
def post_process(self, section):
section.reject = self.value
+ class Stack(BoolOption):
+ # GENERATE ELEMENT() BEGIN
+ def __init__(
+ self,
+ tag = 'PLex_Section1_Options_Stack',
+ attrib = {},
+ text = '',
+ children = [],
+ value = False
+ ):
+ PLex.Section1.Options.BoolOption.__init__(
+ self,
+ tag,
+ attrib,
+ text,
+ children,
+ value
+ )
+ def copy(self, factory = None):
+ result = PLex.Section1.Options.BoolOption.copy(
+ self,
+ Stack if factory is None else factory
+ )
+ return result
+ def __repr__(self):
+ params = []
+ self.repr_serialize(params)
+ return 'ast.PLex.Section1.Options.Stack({0:s})'.format(', '.join(params))
+ # GENERATE END
+ def post_process(self, section):
+ section.stack = self.value
+
+ class StdInit(BoolOption):
+ # GENERATE ELEMENT() BEGIN
+ def __init__(
+ self,
+ tag = 'PLex_Section1_Options_StdInit',
+ attrib = {},
+ text = '',
+ children = [],
+ value = False
+ ):
+ PLex.Section1.Options.BoolOption.__init__(
+ self,
+ tag,
+ attrib,
+ text,
+ children,
+ value
+ )
+ def copy(self, factory = None):
+ result = PLex.Section1.Options.BoolOption.copy(
+ self,
+ StdInit if factory is None else factory
+ )
+ return result
+ def __repr__(self):
+ params = []
+ self.repr_serialize(params)
+ return 'ast.PLex.Section1.Options.StdInit({0:s})'.format(', '.join(params))
+ # GENERATE END
+ def post_process(self, section):
+ section.std_init = self.value
+
+
class YYMore(BoolOption):
# GENERATE ELEMENT() BEGIN
def __init__(
def post_process(self, section):
section.yymore = self.value
+ class YYTopState(BoolOption):
+ # GENERATE ELEMENT() BEGIN
+ def __init__(
+ self,
+ tag = 'PLex_Section1_Options_YYTopState',
+ attrib = {},
+ text = '',
+ children = [],
+ value = False
+ ):
+ PLex.Section1.Options.BoolOption.__init__(
+ self,
+ tag,
+ attrib,
+ text,
+ children,
+ value
+ )
+ def copy(self, factory = None):
+ result = PLex.Section1.Options.BoolOption.copy(
+ self,
+ YYTopState if factory is None else factory
+ )
+ return result
+ def __repr__(self):
+ params = []
+ self.repr_serialize(params)
+ return 'ast.PLex.Section1.Options.YYTopState({0:s})'.format(', '.join(params))
+ # GENERATE END
+ def post_process(self, section):
+ section.yy_top_state = self.value
+
class YYWrap(BoolOption):
# GENERATE ELEMENT() BEGIN
def __init__(
)
)
- # GENERATE ELEMENT(bool ecs, bool meta_ecs, bool reject, bool yymore, bool yywrap) BEGIN
+ # GENERATE ELEMENT(bool caseless, bool default, bool ecs, bool meta_ecs, bool reject, bool stack, bool std_init, bool yymore, bool yy_top_state, bool yywrap) BEGIN
def __init__(
self,
tag = 'PLex_Section1',
text = '',
children = [],
code_blocks_text = [],
+ caseless = False,
+ default = False,
ecs = False,
meta_ecs = False,
reject = False,
+ stack = False,
+ std_init = False,
yymore = False,
+ yy_top_state = False,
yywrap = False
):
PLex.Section1Or2.__init__(
children,
code_blocks_text
)
+ self.caseless = (
+ element.deserialize_bool(caseless)
+ if isinstance(caseless, str) else
+ caseless
+ )
+ self.default = (
+ element.deserialize_bool(default)
+ if isinstance(default, str) else
+ default
+ )
self.ecs = (
element.deserialize_bool(ecs)
if isinstance(ecs, str) else
if isinstance(reject, str) else
reject
)
+ self.stack = (
+ element.deserialize_bool(stack)
+ if isinstance(stack, str) else
+ stack
+ )
+ self.std_init = (
+ element.deserialize_bool(std_init)
+ if isinstance(std_init, str) else
+ std_init
+ )
self.yymore = (
element.deserialize_bool(yymore)
if isinstance(yymore, str) else
yymore
)
+ self.yy_top_state = (
+ element.deserialize_bool(yy_top_state)
+ if isinstance(yy_top_state, str) else
+ yy_top_state
+ )
self.yywrap = (
element.deserialize_bool(yywrap)
if isinstance(yywrap, str) else
)
def serialize(self, ref_list):
PLex.Section1Or2.serialize(self, ref_list)
+ self.set('caseless', element.serialize_bool(self.caseless))
+ self.set('default', element.serialize_bool(self.default))
self.set('ecs', element.serialize_bool(self.ecs))
self.set('meta_ecs', element.serialize_bool(self.meta_ecs))
self.set('reject', element.serialize_bool(self.reject))
+ self.set('stack', element.serialize_bool(self.stack))
+ self.set('std_init', element.serialize_bool(self.std_init))
self.set('yymore', element.serialize_bool(self.yymore))
+ self.set('yy_top_state', element.serialize_bool(self.yy_top_state))
self.set('yywrap', element.serialize_bool(self.yywrap))
def deserialize(self, ref_list):
PLex.Section1Or2.deserialize(self, ref_list)
+ self.caseless = element.deserialize_bool(self.get('caseless', 'false'))
+ self.default = element.deserialize_bool(self.get('default', 'false'))
self.ecs = element.deserialize_bool(self.get('ecs', 'false'))
self.meta_ecs = element.deserialize_bool(self.get('meta_ecs', 'false'))
self.reject = element.deserialize_bool(self.get('reject', 'false'))
+ self.stack = element.deserialize_bool(self.get('stack', 'false'))
+ self.std_init = element.deserialize_bool(self.get('std_init', 'false'))
self.yymore = element.deserialize_bool(self.get('yymore', 'false'))
+ self.yy_top_state = element.deserialize_bool(self.get('yy_top_state', 'false'))
self.yywrap = element.deserialize_bool(self.get('yywrap', 'false'))
def copy(self, factory = None):
result = PLex.Section1Or2.copy(
self,
Section1 if factory is None else factory
)
+ result.caseless = self.caseless
+ result.default = self.default
result.ecs = self.ecs
result.meta_ecs = self.meta_ecs
result.reject = self.reject
+ result.stack = self.stack
+ result.std_init = self.std_init
result.yymore = self.yymore
+ result.yy_top_state = self.yy_top_state
result.yywrap = self.yywrap
return result
def repr_serialize(self, params):
PLex.Section1Or2.repr_serialize(self, params)
+ if self.caseless != False:
+ params.append(
+ 'caseless = {0:s}'.format(repr(self.caseless))
+ )
+ if self.default != False:
+ params.append(
+ 'default = {0:s}'.format(repr(self.default))
+ )
if self.ecs != False:
params.append(
'ecs = {0:s}'.format(repr(self.ecs))
params.append(
'reject = {0:s}'.format(repr(self.reject))
)
+ if self.stack != False:
+ params.append(
+ 'stack = {0:s}'.format(repr(self.stack))
+ )
+ if self.std_init != False:
+ params.append(
+ 'std_init = {0:s}'.format(repr(self.std_init))
+ )
if self.yymore != False:
params.append(
'yymore = {0:s}'.format(repr(self.yymore))
)
+ if self.yy_top_state != False:
+ params.append(
+ 'yy_top_state = {0:s}'.format(repr(self.yy_top_state))
+ )
if self.yywrap != False:
params.append(
'yywrap = {0:s}'.format(repr(self.yywrap))
inclusive_start_conditions,
parent_start_conditions
):
+ self.caseless = False
+ self.default = True
self.ecs = False
self.meta_ecs = False
self.reject = True
+ self.stack = True
+ self.std_init = True
self.yymore = True
+ self.yy_top_state = True
self.yywrap = True
PLex.Section1Or2.post_process(
self,
if not self[1].bol:
plex.start_conditions[i].rules.append(self[1])
plex.start_conditions[i].bol_rules.append(self[1])
- self[1][0].post_process() # regex
- self[1][1].post_process() # trailing context regex
+ self[1][0].post_process(
+ caseless = plex[0].caseless
+ ) # regex
+ self[1][1].post_process(
+ caseless = plex[0].caseless
+ ) # trailing context regex
self[1].action = len(plex.actions_text)
plex.actions_text.append(self[2][0] if len(self) > 2 else PLex.Text()) # fix this later
else:
children = [
k[1]
],
- group_index = k.action
+ index = k.action
)
]
)
character_set = [0, 0x100]
),
regex.RegexGroup(
- group_index = self.default_action,
children = [
regex.RegexEmpty()
- ]
+ ],
+ index = self.default_action
)
]
)
'PLex_Section1_Options': PLex.Section1.Options,
'PLex_Section1_Options_Option': PLex.Section1.Options.Option,
'PLex_Section1_Options_BoolOption': PLex.Section1.Options.BoolOption,
+ 'PLex_Section1_Options_Caseless': PLex.Section1.Options.Caseless,
+ 'PLex_Section1_Options_Default': PLex.Section1.Options.Default,
'PLex_Section1_Options_ECS': PLex.Section1.Options.ECS,
'PLex_Section1_Options_MetaECS': PLex.Section1.Options.MetaECS,
'PLex_Section1_Options_Reject': PLex.Section1.Options.Reject,
+ 'PLex_Section1_Options_Stack': PLex.Section1.Options.Stack,
+ 'PLex_Section1_Options_StdInit': PLex.Section1.Options.StdInit,
'PLex_Section1_Options_YYMore': PLex.Section1.Options.YYMore,
+ 'PLex_Section1_Options_YYTopState': PLex.Section1.Options.YYTopState,
'PLex_Section1_Options_YYWrap': PLex.Section1.Options.YYWrap,
'PLex_Section1_StartConditions': PLex.Section1.StartConditions,
'PLex_Section2': PLex.Section2,
self.repr_serialize(params)
return 'regex.Regex({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
+ def post_process(self, group_index = 0, caseless = False):
for i in self:
- group_index = i.post_process(group_index) #, rule_name_to_character_set)
+ group_index = i.post_process(group_index, caseless)
return group_index
- def to_groups(self, groups):
+ def add_to_groups(self, groups):
for i in self:
- i.to_groups(groups)
+ i.add_to_groups(groups)
def to_nfa_state(self, _nfa, next_state):
raise NotImplementedException
def add_to_nfa(self, _nfa):
_nfa.start_state.append(self.to_nfa_state(_nfa, 0))
- #def to_lr1_symbols(self, n_terminals, symbols, lookaheads, group_bounds):
- # group_count = 0
- # for i in self:
- # group_count += (
- # i.to_lr1_symbols(n_terminals, symbols, lookaheads, group_bounds)
- # )
- # return group_count # count of groups or ungrouped characters
class RegexNone(Regex):
# GENERATE ELEMENT() BEGIN
self.repr_serialize(params)
return 'regex.RegexCharacter({0:s})'.format(', '.join(params))
# GENERATE END
+ def post_process(self, group_index = 0, caseless = False):
+ group_index = Regex.post_process(self, group_index, caseless)
+ if caseless:
+ temp = bisect_set.bisect_set_and(
+ self.character_set,
+ [0x41, 0x5b, 0x61, 0x7b]
+ )
+ self.character_set = bisect_set.bisect_set_or(
+ self.character_set,
+ [i ^ 0x20 for i in temp if i >= 0x60] +
+ [i ^ 0x20 for i in temp if i < 0x60]
+ )
+ return group_index
def to_nfa_state(self, _nfa, next_state):
new_state = len(_nfa.states)
_nfa.states.append((nfa.NFA.STATE_CHARACTER, self.character_set, next_state))
return new_state
- #def to_lr1_symbols(self, n_terminals, symbols, lookaheads, group_bounds):
- # terminal_set = []
- # nonterminal_set = []
- # i = 0
- # while i < len(self.character_set):
- # [j, k] = self.character_set[i:i + 2]
- # if k > n_terminals:
- # if j < n_terminals:
- # terminal_set.extend([j, n_terminals])
- # nonterminal_set.extend([0, k - n_terminals])
- # i += 2
- # while i < len(self.character_set):
- # [j, k] = self.character_set[i:i + 2]
- # nonterminal_set.extend([j - n_terminals, k - n_terminals])
- # i += 2
- # break
- # terminal_set.extend([j, k])
- # i += 2
- # symbols.append((terminal_set, nonterminal_set))
- # lookaheads.append(([], False)) # initial_set, can_be_empty
- # return 1 # count of groups or ungrouped characters
+
+class RegexCharacterLiteral(RegexCharacter):
+ # GENERATE ELEMENT() BEGIN
+ def __init__(
+ self,
+ tag = 'RegexCharacterLiteral',
+ attrib = {},
+ text = '',
+ children = [],
+ character_set = []
+ ):
+ RegexCharacter.__init__(
+ self,
+ tag,
+ attrib,
+ text,
+ children,
+ character_set
+ )
+ def copy(self, factory = None):
+ result = RegexCharacter.copy(
+ self,
+ RegexCharacterLiteral if factory is None else factory
+ )
+ return result
+ def __repr__(self):
+ params = []
+ self.repr_serialize(params)
+ return 'regex.RegexCharacterLiteral({0:s})'.format(', '.join(params))
+ # GENERATE END
+ def post_process(self, group_index = 1, caseless = False):
+ group_index = RegexCharacter.post_process(self, group_index, False)
+ if caseless:
+ temp = bisect_set.bisect_set_and(
+ self.character_set,
+ [0x41, 0x5b, 0x61, 0x7b]
+ )
+ self.character_set = bisect_set.bisect_set_or(
+ self.character_set,
+ [i ^ 0x20 for i in temp if i >= 0x60] +
+ [i ^ 0x20 for i in temp if i < 0x60]
+ )
+ return group_index
class RegexCharacterRange(RegexCharacter):
# GENERATE ELEMENT() BEGIN
self.repr_serialize(params)
return 'regex.RegexCharacterRange({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
- group_index = RegexCharacter.post_process(self, group_index) #, rule_name_to_character_set)
+ def post_process(self, group_index = 0, caseless = False):
+ group_index = RegexCharacter.post_process(self, group_index, False)
self.character_set = [self[0].character_set[0], self[1].character_set[-1]]
+ if caseless:
+ temp = bisect_set.bisect_set_and(
+ self.character_set,
+ [0x41, 0x5b, 0x61, 0x7b]
+ )
+ self.character_set = bisect_set.bisect_set_or(
+ self.character_set,
+ [i ^ 0x20 for i in temp if i >= 0x60] +
+ [i ^ 0x20 for i in temp if i < 0x60]
+ )
return group_index
class RegexCharacterOr(RegexCharacter):
self.repr_serialize(params)
return 'regex.RegexCharacterOr({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
- group_index = RegexCharacter.post_process(self, group_index) #, rule_name_to_character_set)
+ def post_process(self, group_index = 0, caseless = False):
+ group_index = RegexCharacter.post_process(self, group_index, caseless)
self.character_set = bisect_set.bisect_set_or(self[0].character_set, self[1].character_set)
return group_index
self.repr_serialize(params)
return 'regex.RegexCharacterAnd({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
- group_index = RegexCharacter.post_process(self, group_index) #, rule_name_to_character_set)
+ def post_process(self, group_index = 0, caseless = False):
+ group_index = RegexCharacter.post_process(self, group_index, caseless)
self.character_set = bisect_set.bisect_set_and(self[0].character_set, self[1].character_set)
return group_index
self.repr_serialize(params)
return 'regex.RegexCharacterNot({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
- group_index = RegexCharacter.post_process(self, group_index) #, rule_name_to_character_set)
+ def post_process(self, group_index = 0, caseless = False):
+ group_index = RegexCharacter.post_process(self, group_index, caseless)
self.character_set = bisect_set.bisect_set_not(self[0].character_set)
return group_index
-#class RegexCharacterRule(RegexCharacter):
-# # GENERATE ELEMENT(str rule_name) BEGIN
-# def __init__(
-# self,
-# tag = 'RegexCharacterRule',
-# attrib = {},
-# text = '',
-# children = [],
-# character_set = [],
-# rule_name = ''
-# ):
-# RegexCharacter.__init__(
-# self,
-# tag,
-# attrib,
-# text,
-# children,
-# character_set
-# )
-# self.rule_name = rule_name
-# def serialize(self, ref_list, indent = 0):
-# RegexCharacter.serialize(self, ref_list, indent)
-# self.set('rule_name', element.serialize_str(self.rule_name))
-# def deserialize(self, ref_list):
-# RegexCharacter.deserialize(self, ref_list)
-# self.rule_name = element.deserialize_str(self.get('rule_name', ''))
-# def copy(self, factory = None):
-# result = RegexCharacter.copy(
-# self,
-# RegexCharacterRule if factory is None else factory
-# )
-# result.rule_name = self.rule_name
-# return result
-# def repr_serialize(self, params):
-# RegexCharacter.repr_serialize(self, params)
-# if self.rule_name != '':
-# params.append(
-# 'rule_name = {0:s}'.format(repr(self.rule_name))
-# )
-# def __repr__(self):
-# params = []
-# self.repr_serialize(params)
-# return 'regex.RegexCharacterRule({0:s})'.format(', '.join(params))
-# # GENERATE END
-# def post_process(self, group_index = 0, rule_name_to_character_set = None):
-# if rule_name_to_character_set is not None:
-# self.character_set = rule_name_to_character_set[self.rule_name]
-# return RegexCharacter.post_process(self, group_index, rule_name_to_character_set)
-
class RegexOr(Regex):
# GENERATE ELEMENT() BEGIN
def __init__(
self.repr_serialize(params)
return 'regex.RegexRepeat({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
+ def post_process(self, group_index = 0, caseless = False):
# total hack which will be done in a Python action in future
if len(self) >= 2:
assert self[1].tag == 'Number'
self.count1 = self.count0
del self[1:]
# end total hack
- return Regex.post_process(self, group_index) #, rule_name_to_character_set)
+ return Regex.post_process(self, group_index, caseless)
def to_nfa_state(self, _nfa, next_state):
count0 = self.count0
count1 = self.count1
return 'regex.RegexGroup.Attribute({0:s})'.format(', '.join(params))
# GENERATE END
- # GENERATE ELEMENT(int group_index, str group_name, list(ref) group_attributes) BEGIN
+ # GENERATE ELEMENT(int index, str name, list(ref) attributes) BEGIN
def __init__(
self,
tag = 'RegexGroup',
attrib = {},
text = '',
children = [],
- group_index = -1,
- group_name = '',
- group_attributes = []
+ index = -1,
+ name = '',
+ attributes = []
):
Regex.__init__(
self,
text,
children
)
- self.group_index = (
- element.deserialize_int(group_index)
- if isinstance(group_index, str) else
- group_index
+ self.index = (
+ element.deserialize_int(index)
+ if isinstance(index, str) else
+ index
)
- self.group_name = group_name
- self.group_attributes = group_attributes
+ self.name = name
+ self.attributes = attributes
def serialize(self, ref_list):
Regex.serialize(self, ref_list)
- self.set('group_index', element.serialize_int(self.group_index))
- self.set('group_name', element.serialize_str(self.group_name))
+ self.set('index', element.serialize_int(self.index))
+ self.set('name', element.serialize_str(self.name))
self.set(
- 'group_attributes',
- ' '.join([element.serialize_ref(i, ref_list) for i in self.group_attributes])
+ 'attributes',
+ ' '.join([element.serialize_ref(i, ref_list) for i in self.attributes])
)
def deserialize(self, ref_list):
Regex.deserialize(self, ref_list)
- self.group_index = element.deserialize_int(self.get('group_index', '-1'))
- self.group_name = element.deserialize_str(self.get('group_name', ''))
- self.group_attributes = [
+ self.index = element.deserialize_int(self.get('index', '-1'))
+ self.name = element.deserialize_str(self.get('name', ''))
+ self.attributes = [
element.deserialize_ref(i, ref_list)
- for i in self.get('group_attributes', '').split()
+ for i in self.get('attributes', '').split()
]
def copy(self, factory = None):
result = Regex.copy(
self,
RegexGroup if factory is None else factory
)
- result.group_index = self.group_index
- result.group_name = self.group_name
- result.group_attributes = self.group_attributes
+ result.index = self.index
+ result.name = self.name
+ result.attributes = self.attributes
return result
def repr_serialize(self, params):
Regex.repr_serialize(self, params)
- if self.group_index != -1:
+ if self.index != -1:
params.append(
- 'group_index = {0:s}'.format(repr(self.group_index))
+ 'index = {0:s}'.format(repr(self.index))
)
- if self.group_name != '':
+ if self.name != '':
params.append(
- 'group_name = {0:s}'.format(repr(self.group_name))
+ 'name = {0:s}'.format(repr(self.name))
)
- if len(self.group_attributes):
+ if len(self.attributes):
params.append(
- 'group_attributes = [{0:s}]'.format(
- ', '.join([repr(i) for i in self.group_attributes])
+ 'attributes = [{0:s}]'.format(
+ ', '.join([repr(i) for i in self.attributes])
)
)
def __repr__(self):
self.repr_serialize(params)
return 'regex.RegexGroup({0:s})'.format(', '.join(params))
# GENERATE END
- def post_process(self, group_index = 0): #, rule_name_to_character_set = None):
+ def post_process(self, group_index = 0, caseless = False):
# total hack which will be done in a Python action in future
if len(self) >= 2:
assert self[0].tag == 'GroupName'
- self.group_name = self[0].text[1:-1]
+ self.name = self[0].text[1:-1]
del self[:1]
# end total hack
- self.group_index = group_index
+ self.index = group_index
group_index += 1
- return Regex.post_process(self, group_index) #, rule_name_to_character_set)
- def to_groups(self, groups):
- assert len(groups) == self.group_index
+ return Regex.post_process(self, group_index, caseless)
+ def add_to_groups(self, groups):
+ assert len(groups) == self.index
groups.append(
- (self.group_name, {i.name: i.value for i in self.group_attributes})
+ (self.name, {i.name: i.value for i in self.attributes})
)
- return Regex.to_groups(self, groups)
+ return Regex.add_to_groups(self, groups)
def to_nfa_state(self, _nfa, next_state):
mark_state = len(_nfa.states)
- _nfa.states.append((nfa.NFA.STATE_MARK, self.group_index * 2 + 1, next_state))
+ _nfa.states.append((nfa.NFA.STATE_MARK, self.index * 2 + 1, next_state))
child_state = self[0].to_nfa_state(_nfa, mark_state)
if child_state == -1:
return -1
new_state = len(_nfa.states)
- _nfa.states.append((nfa.NFA.STATE_MARK, self.group_index * 2, child_state))
+ _nfa.states.append((nfa.NFA.STATE_MARK, self.index * 2, child_state))
return new_state
- #def to_lr1_symbols(self, n_terminals, symbols, lookaheads, group_bounds):
- # group_start = len(symbols)
- # assert self.group_index == len(group_bounds)
- # group_bounds.append(None)
- # group_count = Regex.to_lr1_symbols(
- # self,
- # n_terminals,
- # symbols,
- # lookaheads,
- # group_bounds
- # )
- # group_bounds[self.group_index] = (
- # group_start,
- # group_count,
- # self.group_name,
- # {i.name: i.value for i in self.group_attributes}
- # )
- # return 1 # count of groups or ungrouped characters
# GENERATE FACTORY(element.Element) BEGIN
tag_to_class = {
'RegexNone': RegexNone,
'RegexEmpty': RegexEmpty,
'RegexCharacter': RegexCharacter,
+ 'RegexCharacterLiteral': RegexCharacterLiteral,
'RegexCharacterRange': RegexCharacterRange,
'RegexCharacterOr': RegexCharacterOr,
'RegexCharacterAnd': RegexCharacterAnd,
return tag_to_class.get(tag, element.Element)(tag, attrib, *args, **kwargs)
# GENERATE END
-if __name__ == '__main__':
- import sys
- import xml.etree.ElementTree
-
- regex = RegexAnd(children = [RegexRepeat(children = [RegexCharacterNot(
-children = [RegexCharacter()], character_set = [0, 256])]), RegexGroup(children = [
-RegexOr(children = [RegexOr(children = [RegexOr(children = [RegexGroup(children
-= [RegexRepeat(children = [RegexCharacter(character_set = [9, 14, 32, 33])],
-one_or_more = True)], group_index = 1, group_name = 'Whitespace'), RegexGroup(
-children = [RegexRepeat(children = [RegexCharacter(character_set = [48, 58])],
-one_or_more = True)], group_index = 2, group_name = 'Number')]), RegexGroup(
-children = [RegexSequence(children = [RegexSequence(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacter(character_set = [102, 103])]),
-RegexCharacter(character_set = [111, 112])]), RegexCharacter(character_set = [114, 115])]
-)], group_index = 3, group_name = 'For')]), RegexGroup(children = [
-RegexSequence(children = [RegexCharacter(character_set = [65, 91, 95, 96, 97, 123]),
-RegexRepeat(children = [RegexCharacter(character_set = [48, 58, 65, 91, 95, 96, 97,
-123])])])], group_index = 4, group_name = 'Identifier')])], group_index = 0)])
- #sys.stdout.write(
- # wrap_repr(
- # ' regex = {0:s}'.format(repr(regex).replace('regex.', '')),
- # 79
- # )
- #)
-
- _nfa = regex.to_nfa()
- #sys.stdout.write(
- # wrap_repr(
- # ' _nfa = {0:s}'.format(repr(_nfa).replace('regex.', '')),
- # 79
- # )
- #)
-
- text = ' id 99id id99 for forex '
- i = 0
- while i < len(text):
- print('text "{0:s}"'.format(text[i:i + 72].replace('\n', '$')))
- thread = _nfa.match_text(text, i)
- if thread is None:
- print('no match')
- break
- i = thread[0] # end position of overall match
- group_start = [-1 for j in range(len(_nfa.groups))]
- group_end = [-1 for j in range(len(_nfa.groups))]
- while thread is not None:
- pos, mark, thread = thread
- group = mark >> 1
- if (mark & 1) == 0:
- group_start[group] = pos
- print(
- 'group {0:d} name "{1:s}" text "{2:s}"'.format(
- group,
- _nfa.groups[group][0],
- text[group_start[group]:group_end[group]].replace('\n', '$')
- )
- )
- else:
- group_end[group] = pos
-
- dfa = _nfa.to_dfa()
- #sys.stdout.write(
- # wrap_repr(
- # ' dfa = {0:s}'.format(repr(dfa).replace('regex.', '')),
- # 79
- # )
- #)
-
- text = ' id 99id id99 for forex '
- i = 0
- while i < len(text):
- print('text "{0:s}"'.format(text[i:i + 72].replace('\n', '$')))
- thread = dfa.match_text(text, i)
- if thread is None:
- print('no match')
- break
- i = thread[0] # end position of overall match
- group_start = [-1 for j in range(len(dfa.groups))]
- group_end = [-1 for j in range(len(dfa.groups))]
- while thread is not None:
- pos, mark, thread = thread
- group = mark >> 1
- if (mark & 1) == 0:
- group_start[group] = pos
- print(
- 'group {0:d} name "{1:s}" text "{2:s}"'.format(
- group,
- dfa.groups[group][0],
- text[group_start[group]:group_end[group]].replace('\n', '$')
- )
- )
- else:
- group_end[group] = pos
-
- grammar = Grammar(children = [Grammar.Production(children = [RegexSequence(
-children = [RegexSequence(children = [RegexEmpty(), RegexCharacterRule(character_set
-= [288, 295], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [
-259, 262], rule_name = 'expr0')])], nonterminal = 0), Grammar.Production(
-children = [RegexSequence(children = [RegexEmpty(), RegexCharacterRule(character_set
-= [262, 265], rule_name = 'expr1')])], nonterminal = 1), Grammar.Production(
-children = [RegexSequence(children = [RegexEmpty(), RegexGroup(children = [
-RegexSequence(children = [RegexSequence(children = [RegexSequence(children = [
-RegexSequence(children = [RegexEmpty(), RegexCharacterRule(character_set = [259, 262
-], rule_name = 'expr0')]), RegexCharacter(character_set = [43, 44])]),
-RegexCharacterRule(character_set = [288, 295], rule_name = 'whitespace_opt')]),
-RegexCharacterRule(character_set = [262, 265], rule_name = 'expr1')])], group_index
-= 0, group_name = 'Add')])], nonterminal = 2), Grammar.Production(children = [
-RegexSequence(children = [RegexEmpty(), RegexGroup(children = [RegexSequence(
-children = [RegexSequence(children = [RegexSequence(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacterRule(character_set = [259, 262], rule_name =
-'expr0')]), RegexCharacter(character_set = [45, 46])]), RegexCharacterRule(character_set
-= [288, 295], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [
-262, 265], rule_name = 'expr1')])], group_index = 0, group_name = 'Subtract')])
-], nonterminal = 3), Grammar.Production(children = [RegexSequence(children = [
-RegexEmpty(), RegexCharacterRule(character_set = [265, 268], rule_name = 'expr2')])
-], nonterminal = 4), Grammar.Production(children = [RegexSequence(children = [
-RegexEmpty(), RegexGroup(children = [RegexSequence(children = [RegexSequence(
-children = [RegexSequence(children = [RegexSequence(children = [RegexEmpty(),
-RegexCharacterRule(character_set = [262, 265], rule_name = 'expr1')]),
-RegexCharacter(character_set = [42, 43])]), RegexCharacterRule(character_set = [288, 295
-], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [265, 268],
-rule_name = 'expr2')])], group_index = 0, group_name = 'Multiply')])],
-nonterminal = 5), Grammar.Production(children = [RegexSequence(children = [
-RegexEmpty(), RegexGroup(children = [RegexSequence(children = [RegexSequence(
-children = [RegexSequence(children = [RegexSequence(children = [RegexEmpty(),
-RegexCharacterRule(character_set = [262, 265], rule_name = 'expr1')]),
-RegexCharacter(character_set = [47, 48])]), RegexCharacterRule(character_set = [288, 295
-], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [265, 268],
-rule_name = 'expr2')])], group_index = 0, group_name = 'Divide')])],
-nonterminal = 6), Grammar.Production(children = [RegexSequence(children = [
-RegexSequence(children = [RegexEmpty(), RegexGroup(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name =
-'number')])], group_index = 0, group_name = 'Number')]), RegexCharacterRule(
-character_set = [288, 295], rule_name = 'whitespace_opt')])], nonterminal = 7),
-Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
-RegexGroup(children = [RegexSequence(children = [RegexSequence(children = [
-RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [45, 46])]),
-RegexCharacterRule(character_set = [288, 295], rule_name = 'whitespace_opt')]),
-RegexCharacterRule(character_set = [265, 268], rule_name = 'expr2')])], group_index
-= 0, group_name = 'Negate')])], nonterminal = 8), Grammar.Production(children =
-[RegexSequence(children = [RegexSequence(children = [RegexSequence(children = [
-RegexSequence(children = [RegexSequence(children = [RegexEmpty(),
-RegexCharacter(character_set = [40, 41])]), RegexCharacterRule(character_set = [288, 295
-], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [259, 262],
-rule_name = 'expr0')]), RegexCharacter(character_set = [41, 42])]),
-RegexCharacterRule(character_set = [288, 295], rule_name = 'whitespace_opt')])],
-nonterminal = 9), Grammar.Production(children = [RegexSequence(children = [
-RegexEmpty(), RegexCharacter(character_set = [48, 49])])], nonterminal = 10),
-Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
-RegexCharacter(character_set = [49, 50])])], nonterminal = 11), Grammar.Production(
-children = [RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [
-50, 51])])], nonterminal = 12), Grammar.Production(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacter(character_set = [51, 52])])], nonterminal =
-13), Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
-RegexCharacter(character_set = [52, 53])])], nonterminal = 14), Grammar.Production(
-children = [RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [
-53, 54])])], nonterminal = 15), Grammar.Production(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacter(character_set = [54, 55])])], nonterminal =
-16), Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
-RegexCharacter(character_set = [55, 56])])], nonterminal = 17), Grammar.Production(
-children = [RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [
-56, 57])])], nonterminal = 18), Grammar.Production(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacter(character_set = [57, 58])])], nonterminal =
-19), Grammar.Production(children = [RegexSequence(children = [RegexSequence(
-children = [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name =
-'number')]), RegexCharacter(character_set = [48, 49])])], nonterminal = 20),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [49, 50])])], nonterminal = 21),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [50, 51])])], nonterminal = 22),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [51, 52])])], nonterminal = 23),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [52, 53])])], nonterminal = 24),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [53, 54])])], nonterminal = 25),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [54, 55])])], nonterminal = 26),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [55, 56])])], nonterminal = 27),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [56, 57])])], nonterminal = 28),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
-)]), RegexCharacter(character_set = [57, 58])])], nonterminal = 29),
-Grammar.Production(children = [RegexEmpty()], nonterminal = 30),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
-'whitespace_opt')]), RegexCharacter(character_set = [9, 10])])], nonterminal = 31),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
-'whitespace_opt')]), RegexCharacter(character_set = [10, 11])])], nonterminal = 32),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
-'whitespace_opt')]), RegexCharacter(character_set = [11, 12])])], nonterminal = 33),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
-'whitespace_opt')]), RegexCharacter(character_set = [12, 13])])], nonterminal = 34),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
-'whitespace_opt')]), RegexCharacter(character_set = [13, 14])])], nonterminal = 35),
-Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
-= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
-'whitespace_opt')]), RegexCharacter(character_set = [32, 33])])], nonterminal = 36)
-], n_terminals = 258)
- #sys.stdout.write(
- # wrap_repr(
- # ' grammar = {0:s}'.format(repr(grammar).replace('regex.', '')),
- # 79
- # )
- #)
-
- lr1 = grammar.to_lr1()
- #sys.stdout.write(
- # wrap_repr(
- # ' lr1 = {0:s}'.format(repr(lr1).replace('regex.', '')),
- # 79
- # )
- #)
-
- lr1.parse_text('(13 + 5 * 6) * 2', 0)
- root = element.Element('root', text = '(13 + 5 * 6) * 2')
- lr1.parse_yychunk(root, 0, 0, element.Element, iter([]))
- xml.etree.ElementTree.dump(root)
-
- clr1 = lr1.to_clr1()
- #sys.stdout.write(
- # wrap_repr(
- # ' clr1 = {0:s}'.format(repr(clr1).replace('regex.', '')),
- # 79
- # )
- #)
-
- clr1.parse_text('(13 + 5 * 6) * 2', 0)
- root = element.Element('root', text = '(13 + 5 * 6) * 2')
- clr1.parse_yychunk(root, 0, 0, element.Element, iter([]))
- xml.etree.ElementTree.dump(root)
-
- lalr1 = lr1.to_lalr1()
- #sys.stdout.write(
- # wrap_repr(
- # ' lalr1 = {0:s}'.format(repr(lalr1).replace('regex.', '')),
- # 79
- # )
- #)
-
- lalr1.parse_text('(13 + 5 * 6) * 2', 0)
- root = element.Element('root', text = '(13 + 5 * 6) * 2')
- lalr1.parse_yychunk(root, 0, 0, element.Element, iter([]))
- xml.etree.ElementTree.dump(root)
+# some of this should be moved into grammar.py:
+#if __name__ == '__main__':
+# import sys
+# import xml.etree.ElementTree
+#
+# regex = RegexAnd(children = [RegexRepeat(children = [RegexCharacterNot(
+#children = [RegexCharacter()], character_set = [0, 256])]), RegexGroup(children = [
+#RegexOr(children = [RegexOr(children = [RegexOr(children = [RegexGroup(children
+#= [RegexRepeat(children = [RegexCharacter(character_set = [9, 14, 32, 33])],
+#one_or_more = True)], group_index = 1, group_name = 'Whitespace'), RegexGroup(
+#children = [RegexRepeat(children = [RegexCharacter(character_set = [48, 58])],
+#one_or_more = True)], group_index = 2, group_name = 'Number')]), RegexGroup(
+#children = [RegexSequence(children = [RegexSequence(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacter(character_set = [102, 103])]),
+#RegexCharacter(character_set = [111, 112])]), RegexCharacter(character_set = [114, 115])]
+#)], group_index = 3, group_name = 'For')]), RegexGroup(children = [
+#RegexSequence(children = [RegexCharacter(character_set = [65, 91, 95, 96, 97, 123]),
+#RegexRepeat(children = [RegexCharacter(character_set = [48, 58, 65, 91, 95, 96, 97,
+#123])])])], group_index = 4, group_name = 'Identifier')])], group_index = 0)])
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' regex = {0:s}'.format(repr(regex).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# _nfa = regex.to_nfa()
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' _nfa = {0:s}'.format(repr(_nfa).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# text = ' id 99id id99 for forex '
+# i = 0
+# while i < len(text):
+# print('text "{0:s}"'.format(text[i:i + 72].replace('\n', '$')))
+# thread = _nfa.match_text(text, i)
+# if thread is None:
+# print('no match')
+# break
+# i = thread[0] # end position of overall match
+# group_start = [-1 for j in range(len(_nfa.groups))]
+# group_end = [-1 for j in range(len(_nfa.groups))]
+# while thread is not None:
+# pos, mark, thread = thread
+# group = mark >> 1
+# if (mark & 1) == 0:
+# group_start[group] = pos
+# print(
+# 'group {0:d} name "{1:s}" text "{2:s}"'.format(
+# group,
+# _nfa.groups[group][0],
+# text[group_start[group]:group_end[group]].replace('\n', '$')
+# )
+# )
+# else:
+# group_end[group] = pos
+#
+# dfa = _nfa.to_dfa()
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' dfa = {0:s}'.format(repr(dfa).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# text = ' id 99id id99 for forex '
+# i = 0
+# while i < len(text):
+# print('text "{0:s}"'.format(text[i:i + 72].replace('\n', '$')))
+# thread = dfa.match_text(text, i)
+# if thread is None:
+# print('no match')
+# break
+# i = thread[0] # end position of overall match
+# group_start = [-1 for j in range(len(dfa.groups))]
+# group_end = [-1 for j in range(len(dfa.groups))]
+# while thread is not None:
+# pos, mark, thread = thread
+# group = mark >> 1
+# if (mark & 1) == 0:
+# group_start[group] = pos
+# print(
+# 'group {0:d} name "{1:s}" text "{2:s}"'.format(
+# group,
+# dfa.groups[group][0],
+# text[group_start[group]:group_end[group]].replace('\n', '$')
+# )
+# )
+# else:
+# group_end[group] = pos
+#
+# grammar = Grammar(children = [Grammar.Production(children = [RegexSequence(
+#children = [RegexSequence(children = [RegexEmpty(), RegexCharacterRule(character_set
+#= [288, 295], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [
+#259, 262], rule_name = 'expr0')])], nonterminal = 0), Grammar.Production(
+#children = [RegexSequence(children = [RegexEmpty(), RegexCharacterRule(character_set
+#= [262, 265], rule_name = 'expr1')])], nonterminal = 1), Grammar.Production(
+#children = [RegexSequence(children = [RegexEmpty(), RegexGroup(children = [
+#RegexSequence(children = [RegexSequence(children = [RegexSequence(children = [
+#RegexSequence(children = [RegexEmpty(), RegexCharacterRule(character_set = [259, 262
+#], rule_name = 'expr0')]), RegexCharacter(character_set = [43, 44])]),
+#RegexCharacterRule(character_set = [288, 295], rule_name = 'whitespace_opt')]),
+#RegexCharacterRule(character_set = [262, 265], rule_name = 'expr1')])], group_index
+#= 0, group_name = 'Add')])], nonterminal = 2), Grammar.Production(children = [
+#RegexSequence(children = [RegexEmpty(), RegexGroup(children = [RegexSequence(
+#children = [RegexSequence(children = [RegexSequence(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacterRule(character_set = [259, 262], rule_name =
+#'expr0')]), RegexCharacter(character_set = [45, 46])]), RegexCharacterRule(character_set
+#= [288, 295], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [
+#262, 265], rule_name = 'expr1')])], group_index = 0, group_name = 'Subtract')])
+#], nonterminal = 3), Grammar.Production(children = [RegexSequence(children = [
+#RegexEmpty(), RegexCharacterRule(character_set = [265, 268], rule_name = 'expr2')])
+#], nonterminal = 4), Grammar.Production(children = [RegexSequence(children = [
+#RegexEmpty(), RegexGroup(children = [RegexSequence(children = [RegexSequence(
+#children = [RegexSequence(children = [RegexSequence(children = [RegexEmpty(),
+#RegexCharacterRule(character_set = [262, 265], rule_name = 'expr1')]),
+#RegexCharacter(character_set = [42, 43])]), RegexCharacterRule(character_set = [288, 295
+#], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [265, 268],
+#rule_name = 'expr2')])], group_index = 0, group_name = 'Multiply')])],
+#nonterminal = 5), Grammar.Production(children = [RegexSequence(children = [
+#RegexEmpty(), RegexGroup(children = [RegexSequence(children = [RegexSequence(
+#children = [RegexSequence(children = [RegexSequence(children = [RegexEmpty(),
+#RegexCharacterRule(character_set = [262, 265], rule_name = 'expr1')]),
+#RegexCharacter(character_set = [47, 48])]), RegexCharacterRule(character_set = [288, 295
+#], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [265, 268],
+#rule_name = 'expr2')])], group_index = 0, group_name = 'Divide')])],
+#nonterminal = 6), Grammar.Production(children = [RegexSequence(children = [
+#RegexSequence(children = [RegexEmpty(), RegexGroup(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name =
+#'number')])], group_index = 0, group_name = 'Number')]), RegexCharacterRule(
+#character_set = [288, 295], rule_name = 'whitespace_opt')])], nonterminal = 7),
+#Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
+#RegexGroup(children = [RegexSequence(children = [RegexSequence(children = [
+#RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [45, 46])]),
+#RegexCharacterRule(character_set = [288, 295], rule_name = 'whitespace_opt')]),
+#RegexCharacterRule(character_set = [265, 268], rule_name = 'expr2')])], group_index
+#= 0, group_name = 'Negate')])], nonterminal = 8), Grammar.Production(children =
+#[RegexSequence(children = [RegexSequence(children = [RegexSequence(children = [
+#RegexSequence(children = [RegexSequence(children = [RegexEmpty(),
+#RegexCharacter(character_set = [40, 41])]), RegexCharacterRule(character_set = [288, 295
+#], rule_name = 'whitespace_opt')]), RegexCharacterRule(character_set = [259, 262],
+#rule_name = 'expr0')]), RegexCharacter(character_set = [41, 42])]),
+#RegexCharacterRule(character_set = [288, 295], rule_name = 'whitespace_opt')])],
+#nonterminal = 9), Grammar.Production(children = [RegexSequence(children = [
+#RegexEmpty(), RegexCharacter(character_set = [48, 49])])], nonterminal = 10),
+#Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
+#RegexCharacter(character_set = [49, 50])])], nonterminal = 11), Grammar.Production(
+#children = [RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [
+#50, 51])])], nonterminal = 12), Grammar.Production(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacter(character_set = [51, 52])])], nonterminal =
+#13), Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
+#RegexCharacter(character_set = [52, 53])])], nonterminal = 14), Grammar.Production(
+#children = [RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [
+#53, 54])])], nonterminal = 15), Grammar.Production(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacter(character_set = [54, 55])])], nonterminal =
+#16), Grammar.Production(children = [RegexSequence(children = [RegexEmpty(),
+#RegexCharacter(character_set = [55, 56])])], nonterminal = 17), Grammar.Production(
+#children = [RegexSequence(children = [RegexEmpty(), RegexCharacter(character_set = [
+#56, 57])])], nonterminal = 18), Grammar.Production(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacter(character_set = [57, 58])])], nonterminal =
+#19), Grammar.Production(children = [RegexSequence(children = [RegexSequence(
+#children = [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name =
+#'number')]), RegexCharacter(character_set = [48, 49])])], nonterminal = 20),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [49, 50])])], nonterminal = 21),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [50, 51])])], nonterminal = 22),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [51, 52])])], nonterminal = 23),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [52, 53])])], nonterminal = 24),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [53, 54])])], nonterminal = 25),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [54, 55])])], nonterminal = 26),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [55, 56])])], nonterminal = 27),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [56, 57])])], nonterminal = 28),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [268, 288], rule_name = 'number'
+#)]), RegexCharacter(character_set = [57, 58])])], nonterminal = 29),
+#Grammar.Production(children = [RegexEmpty()], nonterminal = 30),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
+#'whitespace_opt')]), RegexCharacter(character_set = [9, 10])])], nonterminal = 31),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
+#'whitespace_opt')]), RegexCharacter(character_set = [10, 11])])], nonterminal = 32),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
+#'whitespace_opt')]), RegexCharacter(character_set = [11, 12])])], nonterminal = 33),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
+#'whitespace_opt')]), RegexCharacter(character_set = [12, 13])])], nonterminal = 34),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
+#'whitespace_opt')]), RegexCharacter(character_set = [13, 14])])], nonterminal = 35),
+#Grammar.Production(children = [RegexSequence(children = [RegexSequence(children
+#= [RegexEmpty(), RegexCharacterRule(character_set = [288, 295], rule_name =
+#'whitespace_opt')]), RegexCharacter(character_set = [32, 33])])], nonterminal = 36)
+#], n_terminals = 258)
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' grammar = {0:s}'.format(repr(grammar).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# lr1 = grammar.to_lr1()
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' lr1 = {0:s}'.format(repr(lr1).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# lr1.parse_text('(13 + 5 * 6) * 2', 0)
+# root = element.Element('root', text = '(13 + 5 * 6) * 2')
+# lr1.parse_yychunk(root, 0, 0, element.Element, iter([]))
+# xml.etree.ElementTree.dump(root)
+#
+# clr1 = lr1.to_clr1()
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' clr1 = {0:s}'.format(repr(clr1).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# clr1.parse_text('(13 + 5 * 6) * 2', 0)
+# root = element.Element('root', text = '(13 + 5 * 6) * 2')
+# clr1.parse_yychunk(root, 0, 0, element.Element, iter([]))
+# xml.etree.ElementTree.dump(root)
+#
+# lalr1 = lr1.to_lalr1()
+# #sys.stdout.write(
+# # wrap_repr(
+# # ' lalr1 = {0:s}'.format(repr(lalr1).replace('regex.', '')),
+# # 79
+# # )
+# #)
+#
+# lalr1.parse_text('(13 + 5 * 6) * 2', 0)
+# root = element.Element('root', text = '(13 + 5 * 6) * 2')
+# lalr1.parse_yychunk(root, 0, 0, element.Element, iter([]))
+# xml.etree.ElementTree.dump(root)
public / pilex.git / commitdiff